Builds on #16855 (@lsdsjy) which fixed DeepSeek v4 reasoning_content
replay via model_extra fallback + capturing tool_calls at method entry.
Kimi / Moonshot thinking mode enforces the same echo-back contract and
hits the same 400 when a tool-call turn is persisted without
reasoning_content.
- _build_assistant_message: pad branch now uses _needs_thinking_reasoning_pad()
(DeepSeek OR Kimi) instead of _needs_deepseek_tool_reasoning() alone.
- Extract _needs_thinking_reasoning_pad() and reuse it in
_copy_reasoning_content_for_api so both sites share one predicate.
- tests/run_agent/test_deepseek_reasoning_content_echo.py: add
TestBuildAssistantMessagePadsStrictProviders parametrized over DeepSeek
(attr=None, attr-absent), Kimi (attr=None), Moonshot (via base_url),
and an OpenRouter negative control that must NOT pad. Proven to fail
2/5 cases on Kimi/Moonshot without this change.
- scripts/release.py: add AUTHOR_MAP entries for lsdsjy and season179.
Refs #17400.
Co-authored-by: season179 <season.saw@gmail.com>
Alongside the existing 'least recently used' section, surface two more
rankings so users can see which of their agent-created skills actually
get exercised:
- 'most used (top 5)' — sorted by use_count descending. Hidden when every
skill has use_count=0 (noise suppression on fresh installs).
- 'least used (top 5)' — sorted by use_count ascending. Always shown
when the catalog is non-empty.
use_count started tracking real agent skill activation in PR #17932
(bump_use wired into skill_view tool + slash invocation + --skill
preload), so these rankings are now meaningful.
Tests: 3 new in tests/hermes_cli/test_curator_status.py — happy path
with mixed use_counts, zero-use suppression of the most-used section,
and the no-skills clean-empty case.
Treat skill views and edits as activity when curator reports and applies lifecycle transitions, so recently loaded or patched skills are not displayed or transitioned as never used.\n\nAdds regression tests for activity derivation, automatic transitions, and CLI status output.
restore_skill() in tools/skill_usage.py used archive_root.iterdir(), which
only walked the top level of .archive/. Skills archived under nested layouts
(e.g. .archive/openclaw-imports/<skill>/ from older archive paths or
external imports) were invisible to both the exact-match and prefix-match
candidate scans, surfacing as a misleading "skill '<name>' not found in
archive" error even though the directory existed on disk.
Switch both candidate scans to archive_root.rglob('*') so the lookup
descends into category subdirectories.
Fixes#17942
* fix(curator): split 'archived' into consolidated vs pruned in run reports
Users who watched a curator run saw skills like 'anthropic-api' listed
under 'Skills archived' and interpreted that as pruning — but the curator
had actually absorbed those skills into a new umbrella (e.g. 'llm-providers')
during the same run. The directory gets archived for safety (all removals
are recoverable), but the content still lives under a different name.
Users then 'restored' what they thought were deleted skills and ended up
with confusingly duplicated skillsets (old-name + absorbed-inside-umbrella).
Classify removed skills using this run's skill_manage tool calls:
- consolidated: content absorbed into a surviving/newly-created skill
(evidenced by a skill_manage write_file/patch/create/edit whose target
is a different skill AND whose file_path/content references the
removed skill's name)
- pruned: archived without consolidation evidence (truly stale)
REPORT.md now shows two distinct sections:
- 'Consolidated into umbrella skills' — with `removed → merged into umbrella`
- 'Pruned — archived for staleness' — pure staleness archives
run.json schema additions (backward compatible):
- counts.consolidated_this_run, counts.pruned_this_run
- consolidated: [{name, into, evidence}, ...]
- pruned: [names]
- archived: retained as the union for backward compat
Also: relabel the auto-transitions 'archived' counter to 'archived (no
LLM, pure time-based staleness)' so it's clearly distinct from LLM-pass
archives.
Tests: 9 new tests in test_curator_classification.py covering consolidation
evidence parsing (write_file/patch/create), hyphen/underscore name variants,
self-reference rejection, destination-must-exist, mixed runs, and
malformed-JSON fallback safety. Existing test_report_md_is_human_readable
updated to cover the new section names.
E2E: isolated HERMES_HOME, realistic 3-skill run, REPORT.md verified
end-to-end.
* feat(curator): hybrid model-declared + heuristic classification
Extend the consolidated-vs-pruned split with LLM-authored intent:
1. Curator prompt now requires a structured YAML block at the end of the
final response (consolidations / prunings with short rationale).
2. _parse_structured_summary() extracts it tolerantly — missing block,
malformed YAML, partial lists all fall back to heuristic cleanly.
3. _reconcile_classification() merges model intent with the tool-call
heuristic:
- Model wins on rationale when its umbrella exists post-run
- Model hallucination (umbrella doesn't exist) is downgraded to the
heuristic's finding, or pruned if there's no evidence either
- Heuristic catches model omission — consolidations the model
enumerated tools for but forgot to list get surfaced with a
'(detected via tool-call audit)' tag
4. REPORT.md now shows per-row rationale alongside 'removed → umbrella'
and flags audit-only rows so the user knows why no reason is shown.
Backward compat: run.json's 'archived' field (union) is preserved.
'pruned' is now a list of dicts with {name, source, reason};
'pruned_names' is the flat-name list for legacy consumers.
Tests: 15 new covering YAML parse edge cases (malformed, empty lists,
bare-string entries, missing fields), reconciler rules (model wins,
hallucination fallback, heuristic catches omission, prune with reason),
and an end-to-end report-render test with all four paths exercised.
Belt-and-suspenders on top of @briandevans' #17758 fix. The in-band
drain hand-off (await->create_task + session-guard preservation)
changed cleanup semantics in three places that the original PR
reasoned about but didn't test directly. Pin each invariant so a
future refactor can't silently regress them:
1. Normal single-message path still releases _active_sessions[sk] and
_session_tasks[sk] through end-of-finally. The #17758 follow-up
moved _release_session_guard under
if current_task is self._session_tasks.get(session_key)
For the 99%-common case current_task IS the stored task, so the
guard must still fire. Test would fail if the conditional were
ever tightened in a way that dropped the normal path.
2. Drain-task cancellation releases the session. If the drain task
spawned by the in-band hand-off is cancelled mid-handler (e.g.
/stop fired while draining a follow-up), its own finally must
fire _release_session_guard. Without this a cancel would leave
the session permanently pinned busy.
3. Late-arrival drain still spawns when no in-band drain preceded
it. Pre-existing path, but the #17758 follow-up added a
re-queue branch that only fires when ownership was already
handed off. When no handoff happened the else branch must still
spawn a fresh drain task — otherwise a message arriving during
stop_typing gets silently dropped.
All three tests pass against current main. Zero production code
changes.
The #1630 fix introduced a blanket ``agent_failed_early`` transcript skip
to prevent context-overflow sessions from looping. That guard also
triggers for unrelated transient failures (429 rate limits, read
timeouts, connection resets, provider 5xx) which have nothing to do with
session size — and it silently drops the user's message, so the agent
has no memory of the last turn on retry.
Split the failure classification in ``GatewayRunner._run_agent``:
* Context-overflow (``compression_exhausted`` flag, explicit
context-length phrases, or generic 400 with a long history) → keep
the existing skip, preserving the #1630/#9893 fix.
* Anything else that failed → persist just the user message so the
conversation survives a retry.
Use specific multi-word phrases (``context length``, ``token limit``,
``prompt is too long``, etc.) to match ``run_agent.py``'s own
classifier; bare ``exceed`` false-positively flagged "rate limit
exceeded" as context overflow.
Covered by new tests in ``tests/gateway/test_7100_transient_failure_transcript.py``
and the existing #1630 suite still passes.
Existing test_tar_pipe_commands asserted the literal substring
'tar xf - -C /' in ssh_str, which is no longer present after the
#17767 fix adds --no-overwrite-dir between 'tar xf -' and '-C /'.
Split the one substring check into three independent assertions for
the tar stdin mode, the new --no-overwrite-dir flag (regression guard
for #17767), and the extract target.
_set_nested unconditionally replaced any non-dict value with an empty
dict when walking the dotted path, which silently destroyed list-typed
config nodes the moment someone set a value with a numeric index
(e.g. 'hermes config set custom_providers.0.api_key NEW'). Any sibling
entries and any fields inside the targeted entry that the user didn't
write were lost.
Fix:
- _set_nested now detects list nodes and navigates by numeric index,
and preserves both dicts AND lists at intermediate positions (scalars
are still replaced so bare-scalar -> nested overrides keep working).
- set_config_value drops its duplicated navigation logic and calls
_set_nested instead -- single source of truth for the rules.
Regression tests (tests/hermes_cli/test_set_config_value.py):
- test_indexed_set_preserves_sibling_list_entries -- exact #17876 repro
- test_indexed_set_preserves_non_targeted_fields -- inner-dict fields survive
- test_deeper_nesting_through_list -- dict -> list -> dict -> scalar path
35/35 existing + new tests pass.
E2E-verified with the issue's repro against a real on-disk config.yaml --
list stays a list, entry 0 updated, entry 1 intact.
Closes#17876
Long-lived Gateway processes were sending duplicate tool names to
providers that enforce uniqueness:
- DeepSeek: 'Tool names must be unique.'
- Xiaomi MiMo: 'tools contains duplicate names: lcm_expand'
- Moonshot/Kimi: 'function name lcm_grep is duplicated'
TUI was unaffected because TUI runs with quiet_mode=False and skips the
cache entirely.
Root cause (two layered bugs)
- model_tools.get_tool_definitions(quiet_mode=True) memoizes its result
in _tool_defs_cache. The cache-hit path returned list(cached) (safe),
but the FIRST uncached call stored and returned the SAME object.
run_agent.py mutates self.tools (memory + LCM context-engine schemas)
in-place, so the very first agent init in a Gateway process
poisoned the cache, and every subsequent init appended LCM schemas
again on top of the already-polluted list.
- run_agent.py's context-engine injection (lcm_grep / lcm_describe /
lcm_expand) had no dedup, unlike the memory-tools injection right
above it which already skips already-present names.
Fix (defense in depth, per the issue's suggested fix)
- model_tools.get_tool_definitions: on the uncached branch, cache the
computed list but return list(result) to the caller. Same pattern as
the cache-hit path.
- run_agent.py: build _existing_tool_names from self.tools and skip
schemas whose names are already present, mirroring the memory-tools
block. This also defends against plugin paths that may register the
same schemas via ctx.register_tool().
Tests (tests/test_get_tool_definitions_cache_isolation.py)
- test_first_uncached_call_returns_fresh_list \u2014 pins the fix; without
it, first-call alias caused all the symptoms.
- test_cache_hit_returns_fresh_list \u2014 pre-existing behavior stays.
- test_caller_mutation_does_not_poison_cache \u2014 simulates run_agent
appending lcm_grep / lcm_expand to the returned list and asserts the
next call doesn't see them.
- test_repeated_caller_mutation_does_not_accumulate \u2014 reproduces the
long-lived Gateway accumulation pattern across 5 agent inits.
- test_non_quiet_mode_does_not_use_cache \u2014 sanity, explains why TUI
was fine.
5/5 pass on the new file; 23/23 still pass on tests/test_model_tools.py.
When a user sets model.context_length in config.yaml, the value was only
used for Hermes' internal compression decisions (context_compressor) but
NOT for Ollama's num_ctx parameter. Ollama auto-detects context from GGUF
metadata (often 256K+) and allocates that much VRAM regardless of the
user's config — causing OOM on smaller GPUs like the P100 (16GB).
Root cause: two separate context values existed independently:
- context_compressor.context_length = config value (e.g. 65536) ✓
- _ollama_num_ctx = GGUF metadata value (e.g. 256000) ✗ ignored config
Changes:
1. Cap Ollama num_ctx to config context_length (run_agent.py)
When model.context_length is explicitly set and no explicit
ollama_num_ctx override exists, cap the auto-detected GGUF value
to the user's context_length. This is the core fix — it prevents
Ollama from allocating more VRAM than the user budgeted.
2. Pass config_context_length through all secondary call sites
Several paths called get_model_context_length() without the config
override, falling through to the 256K default fallback:
- cli.py: @-reference expansion and /model switch display
- gateway/run.py: @-reference expansion and /model switch display
- tui_gateway/server.py: @-reference expansion
- hermes_cli/model_switch.py: resolve_display_context_length()
3. Normalize root-level context_length in config (hermes_cli/config.py)
_normalize_root_model_keys() now migrates root-level context_length
into the model section, matching existing behavior for provider and
base_url. Users who wrote `context_length: 65536` at the YAML root
instead of under `model:` had it silently ignored.
4. Fix misleading comments (agent/model_metadata.py)
DEFAULT_FALLBACK_CONTEXT is 256K (CONTEXT_PROBE_TIERS[0]), not 128K
as two comments stated.
Tests: 3 new tests for root-level context_length normalization.
All existing context_length tests pass (96 tests).
The busy-session handler (_handle_active_session_busy_message) bypassed the
authorization gate that the cold path enforces via _is_user_authorized(). In
shared-thread contexts (Slack threads, Telegram forum topics, Discord threads)
where thread_sessions_per_user=False (the default), all participants share one
session_key. An unauthorized user posting in the same thread as an authorized
user would hit the active-session branch, skip the auth check, and have their
text merged into _pending_messages or injected via agent.interrupt().
This commit adds the same _is_user_authorized() check at the top of the busy
handler, before any message queuing, steering, or interrupt logic. Unauthorized
messages are silently dropped (return True) with a warning log — matching the
cold-path behavior.
Affected platforms: Slack, Telegram, Discord, any adapter with shared-session
thread contexts.
Closes#17775
The `gemini` provider also serves Gemma (e.g. `gemma-4-31b-it`) and
historically other Google models like PaLM. Those reject
`extra_body.thinking_config` with HTTP 400:
Unknown name "thinking_config": Cannot find field
`_build_gemini_thinking_config()` was unconditionally producing a
config dict for any model on the `gemini` / `google-gemini-cli`
provider, which `ChatCompletionsTransport.build_kwargs` then dropped
into `extra_body["thinking_config"]`. The result: every chat turn for
Gemma users on the gemini provider blew up at the API edge.
The fix is the same shape Hermes already uses for the Gemini-2.5 vs
Gemini-3 family clamping: normalise the model id, strip an
`OpenRouter`-style `google/` prefix, and short-circuit early when the
result doesn't start with `gemini`. We return `None` rather than
`{"includeThoughts": False}`, because the API rejects the field name
itself — even the polite "off" form trips the same 400.
Three regression tests cover Gemma with reasoning enabled, Gemma with
reasoning disabled, and the `google/gemma-…` OpenRouter-style id; the
existing Gemini-2.5 / Gemini-3 / `google/gemini-…` cases keep passing
because the Gemini guard fires after the prefix strip.
Fixes#17426
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Ports PR #17888's send_multiple_images ABC to every gateway platform that
has a native multi-attachment API, so images arrive as a single bundled
message instead of N separate ones.
Native overrides:
- Telegram: send_media_group (10 photos per album, chunks over); animated
GIFs peeled off and routed through send_animation (albums don't support
animations)
- Discord: channel.send(files=[...]) (10 attachments per message, chunks
over); URL images downloaded into BytesIO so they render inline; forum
channels use create_thread with files=[...]
- Slack: files_upload_v2(file_uploads=[...]) (10 per call, chunks over);
respects thread_ts; records thread participation
- Mattermost: single post with file_ids list (5 per post — Mattermost cap,
chunks over)
- Email: single SMTP message with multiple MIME attachments (no chunk cap,
SMTP size governs); remote URLs remain linked in body (parity with
existing send_image)
All platforms fall back to the base per-image loop on any failure, so a
single bad image in a batch never loses the rest.
Matrix, WhatsApp, and single-attachment platforms (BlueBubbles, Feishu,
WeCom, WeChat, DingTalk) continue to use the base default loop — their
server APIs only accept one attachment per message anyway.
Tests: adds tests/gateway/test_send_multiple_images.py with 19 targeted
tests covering base default loop, chunking, animation peel-off, fallback
paths, and empty-batch no-ops across all five new overrides.
Co-authored-by: Maxence Groine <maxence@groine.fr>
Adds a new `send_multiple_images` method to the ``BasePlatformAdapter``
that implements the default "One image per message" loop and allows for
platform-specific overriding.
Implements such an override for the Signal adapter, batching images
and trying (best-effort) to work around rate-limits for voluminous
batches using a specific scheduler.
Also implements batching + rate-limit handling in the `send_message`
tool.
New tests added for the Signal adapter, its rate-limit scheduler and the
`send_message` tool
Merge resolved conflicts in web/src/{i18n/{en,zh,types}.ts,lib/api.ts}
by keeping both this branch's `profiles` additions and upstream's new
`models` page additions.
Copilot review feedback:
- Implement POST /api/profiles/{name}/open-terminal endpoint (already
present); align Windows branch to `cmd.exe /c start "" <cmd>` so it
matches the new test and spawns a fresh window instead of /k reusing
the parent console.
- Move backslash escaping out of the macOS AppleScript f-string
expression (Python <3.12 disallows backslashes inside f-string
expression parts).
- Patch `_get_wrapper_dir` via monkeypatch in
test_profiles_create_creates_wrapper_alias_when_safe so the test no
longer writes to the real `~/.local/bin`.
- Extend test_dashboard_browser_safe_imports to scan `.ts` files in
addition to `.tsx`.
- Switch upstream's new ModelsPage.tsx away from the `@nous-research/ui`
root barrel onto per-component subpaths to satisfy the stricter scan.
- Fix NouiTypography `leading-1.4` -> `leading-[1.4]` so Tailwind
actually emits the line-height for the `sm` variant.
- Guard ProfilesPage.openSoulEditor against out-of-order responses by
tracking the latest requested profile via a ref.
- Replace ProfilesPage's hand-rolled setup command with a fetch to
`/api/profiles/{name}/setup-command` so the copied command always
matches what the backend would actually run (handles wrapper-alias
collisions and reserved names correctly).
- Wire SOUL.md textarea label `htmlFor` -> textarea `id` so screen
readers and clicking the label work as expected.
The sandbox-side `_call()` in both the UDS and file-based transports was
not thread-safe, so scripts that call tools from multiple threads (e.g.
`ThreadPoolExecutor` over `terminal()`) inside a single `execute_code`
run could silently receive each other's responses.
Root cause:
* UDS transport — a single module-level `_sock` was shared across all
threads; the newline-framed protocol has no request-id; and the
server-side RPC loop handles one connection serially. With concurrent
callers, each thread would `sendall()` then race to `recv()` the next
newline-terminated response from the shared buffer, so responses got
delivered to the wrong caller.
* File transport — `_seq += 1` is a non-atomic read-modify-write, so
two threads could allocate the same sequence number and clobber each
other's request/response files.
Fix: guard `_call()` with a `threading.Lock` in the UDS case (covering
send+recv), and guard `_seq` allocation with a lock in the file case.
No protocol change.
Regression tests cover both the generated-source level (lock is present
and used) and an end-to-end concurrency test: running a sandboxed
ThreadPoolExecutor of 10 `terminal()` calls against a slow mock
dispatcher, asserting every caller sees its own tagged response. The
test fails without the fix (10/10 mismatched, matching real-world
repro) and passes with it.
The v11→v12 migrate_config step writes the API mode for every entry
under the new transport: field (per the v12+ schema in
_normalize_custom_provider_entry). _get_named_custom_provider
read the legacy api_mode: spelling only, so for every migrated
config the lookup returned None for the api mode.
Downstream, _resolve_named_custom_runtime then falls back through
custom_provider.get("api_mode") or _detect_api_mode_for_url(base_url)
or "chat_completions". For loopback URLs (proxies, local servers)
or unknown hostnames, the URL detector returns None and the resolver
silently downgrades the configured codex_responses /
anthropic_messages transport to chat_completions. Requests
get sent to /v1/chat/completions instead of /v1/responses or
/v1/messages and the provider 404s — or worse, returns a usable
chat_completions response while skipping the model's reasoning /
caching surface.
Fix: read both field names — entry.get("api_mode") or
entry.get("transport") — at the two match-by-key + match-by-name
branches in _get_named_custom_provider. The runtime normaliser
_normalize_custom_provider_entry already accepts both spellings;
this lifts the same compat into the direct-dict reader so v12+
configs work without going through the shim.
Adds three regression tests under
tests/hermes_cli/test_user_providers_model_switch.py:
- transport field is read on the match-by-key branch
- legacy api_mode spelling still works for hand-edited configs
- transport is read on the match-by-display-name branch
run_job() ignored the result's `failed=True` / `completed=False` flags
that agent.run_conversation populates on API exhaustion, mid-run
interrupts, and model aborts. Because final_response on those paths is
often a non-empty error string ("API call failed after 3 retries:
Request timed out."), the existing empty-response soft-fail in
_process_job did not trip either: the error text was delivered as if it
were the agent's reply and last_status was set to "ok" with no error
notification. Detect those flags right after the dict-shape guard and
raise so the existing except handler builds the proper failure tuple,
preserving the agent's error message via result["error"].
Adds a parametrized regression covering: API-retry-exhausted with error
text in final_response, completed=False with no final_response,
completed=False without an explicit failed flag, and the partial-reply
plus failed=True case. Plus a guard that a normal completed=True success
result is still treated as success.
Fixes#17855
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the in-band pending-message drain spawns a fresh task and
transfers ownership via _session_tasks[session_key] = drain_task,
the original task still unwinds through the finally block. The
drain task picks up the same interrupt_event in its own
_process_message_background entry, so an unconditional
_release_session_guard(session_key, guard=interrupt_event) at the
end of the finally matches and deletes _active_sessions[session_key]
while the drain task is still pending its first await.
A concurrent inbound message arriving in that handoff window passes
the Level-1 guard (no entry exists) and spawns a second
_process_message_background for the same session — two agents on
one session_key, duplicate responses, duplicate tool calls.
Fix: only call _release_session_guard when the current task still
owns _session_tasks[session_key]. When ownership has been
transferred to a drain task, leave _active_sessions populated; the
drain task's own lifecycle releases it. This mirrors the
late-arrival drain path in the same finally block, which already
leaves both entries alone after handing off.
Also reorder stdlib imports in the new regression test file to
match the gateway test convention (stdlib before third-party).
Regression test: capture _active_sessions[sk] identity at every
handler entry across a 2-step in-band drain chain and assert the
guard Event identity stays the same. Pre-fix, the original task's
finally deletes the entry, the drain task falls through to the
`or asyncio.Event()` branch, and a fresh Event is installed —
identity diverges. Post-fix, the entry is preserved and the drain
task reuses the original Event.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`_process_message_background` finished a turn, found a queued
follow-up, and drained it via `await
self._process_message_background(pending_event, session_key)`. Each
chained follow-up added a frame to the call stack instead of starting
fresh. Under sustained pending-queue activity (e.g. a user sending
follow-ups faster than the agent finishes turns) the C stack would
exhaust at ~2000 nested frames and SIGSEGV the process.
Mirror the late-arrival drain pattern that already exists in the same
function: spawn a new `asyncio.create_task(...)` for the pending event
and return so the current frame can unwind. The new task takes
ownership via `_session_tasks[session_key]`.
The late-arrival drain in `finally` could now race with the in-band
drain across the `await typing_task` / `await stop_typing` window, so
add a guard: if `_session_tasks[session_key]` is no longer the current
task, an in-band drain already spawned a follow-up task — re-queue the
late-arrival event so that task picks it up after its current event,
instead of spawning a second concurrent task for the same session_key.
Regression test (`test_pending_drain_no_recursion.py`) chains 12
follow-ups and asserts the recorded
`_process_message_background` stack depth stays bounded at handler
entry. Pre-fix: depths grow linearly `[1,2,3,…,12]`. Post-fix: all
depths are `1`.
`test_duplicate_reply_suppression::test_stale_response_suppressed_when_interrupted`
called `_process_message_background` directly and implicitly relied on
the old recursive `await` semantic — updated to wait for the spawned
drain task before checking the sent list.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Piper (OHF-Voice/piper1-gpl) is a fast, local neural TTS engine from the
Home Assistant project that supports 44 languages with zero API keys.
Adds it as a native built-in provider alongside edge/neutts/kittentts,
installable via 'hermes tools' with one keystroke.
What ships:
- New 'piper' built-in provider in tools/tts_tool.py
- Lazy import via _import_piper()
- Module-level voice cache keyed on (model_path, use_cuda) so switching
voices doesn't invalidate older cached voices
- _resolve_piper_voice_path() accepts either an absolute .onnx path or a
voice name (auto-downloaded on first use via 'python -m
piper.download_voices --download-dir <cache>')
- Voice cache at ~/.hermes/cache/piper-voices/ (profile-aware via
get_hermes_dir)
- Optional SynthesisConfig knobs: length_scale, noise_scale,
noise_w_scale, volume, normalize_audio, use_cuda — passed through
only when configured, so older piper-tts versions aren't broken
- WAV output then ffmpeg conversion path (same as neutts/kittentts) so
Telegram voice bubbles work when ffmpeg is present
- Piper added to BUILTIN_TTS_PROVIDERS so a user's
tts.providers.piper.command cannot shadow the native provider
(regression test included)
- 'hermes tools' wizard entry
- Piper appears under Voice and TTS as local free, with
'pip install piper-tts' auto-install via post_setup handler
- Prints voice-catalog URL and default-voice info after install
- config.yaml defaults
- tts.piper.voice defaults to en_US-lessac-medium
- Commented advanced knobs for discoverability
- Docs
- New 'Piper (local, 44 languages)' section in features/tts.md
explaining install path, voice switching, pre-downloaded voices,
and advanced knobs
- Piper listed in the ten-provider table and ffmpeg table
- Custom-command-providers section updated to drop the Piper example
(now native) and add a piper-custom example for users with their own
trained .onnx models
- overview.md bumps provider count to ten
- Tests (tests/tools/test_tts_piper.py, 16 tests)
- Registration (BUILTIN_TTS_PROVIDERS, PROVIDER_MAX_TEXT_LENGTH)
- _resolve_piper_voice_path across every branch: direct .onnx path,
cached voice name, fresh download with correct CLI args, download
failure, successful-exit-but-missing-files, empty voice to default
- _generate_piper_tts: loads voice once, reuses cache, voice-name
download wiring, advanced knobs flow through SynthesisConfig
- text_to_speech_tool end-to-end dispatch and missing-package error
- check_tts_requirements: piper availability toggles the return value
- Regression guard: piper cannot be shadowed by a command provider
with the same name
- Pre-existing test_tts_mistral test broadened to mock the new
piper/kittentts/command-provider checks (otherwise it false-passes
when piper is installed in the test venv)
E2E verification (live):
Actual pip install piper-tts, config piper + en_US-lessac-low,
text_to_speech_tool call, voice auto-downloaded from HuggingFace,
WAV synthesized, ffmpeg-converted to Ogg/Opus. Second call hits the
cache (~60ms). Cache dir populated with .onnx and .onnx.json.
This caught a real bug during development: the first pass used '-d' as
the download-dir flag; the actual piper.download_voices CLI wants
'--download-dir'. Fixed before PR opened.
Six tests in this file failed in CI (-n auto) after #17832 landed because
other tests on the same xdist worker reload hermes_cli.main:
tests/hermes_cli/test_env_loader.py:85-86
sys.modules.pop('hermes_cli.main', None)
importlib.import_module('hermes_cli.main')
tests/hermes_cli/test_skills_subparser.py:24-25
del sys.modules['hermes_cli.main']
When either ran first on a worker, our top-of-file
'from hermes_cli.main import _kill_stale_dashboard_processes' captured a
stale function object whose __globals__ points at the old module dict.
patch('hermes_cli.main._find_stale_dashboard_pids', ...) then patched the
new module, but the stale function resolved the dependency via its stale
__globals__, so every patch became a no-op: pids=[] → early return → no
signals, no output, assertions failed.
Fix: add an autouse fixture that rebinds the three module-level names to
whatever is currently live in sys.modules['hermes_cli.main'] before each
test runs. The pollutants in the other two files are load-bearing for
their own tests, so fixing it on the consumer side is correct.
Repro: pytest tests/hermes_cli/test_env_loader.py tests/hermes_cli/test_update_stale_dashboard.py
Voscko reported curator.auxiliary.provider/model was advertised in the
docs but ignored — the review fork read only model.provider/default. The
narrow fix would wire the one-off key through, but that leaves curator
as a parallel system: not in `hermes model` → auxiliary picker, not in
the dashboard Models tab, missing per-task base_url/api_key/timeout/
extra_body.
Unify curator with the rest of the aux task system so `hermes model`
and the dashboard configure it like every other aux task.
Four sources of truth updated:
- hermes_cli/config.py — add 'curator' slot to DEFAULT_CONFIG.auxiliary
(timeout=600 since reviews run long), drop the one-off curator.auxiliary
block from DEFAULT_CONFIG.curator.
- hermes_cli/main.py — add ('curator', 'Curator', 'skill-usage review pass')
to _AUX_TASKS so the CLI picker offers it.
- hermes_cli/web_server.py — add 'curator' to _AUX_TASK_SLOTS so the
dashboard REST endpoint accepts it.
- web/src/pages/ModelsPage.tsx — add Curator entry so the dashboard
Models tab renders the task.
agent/curator.py _resolve_review_model() now reads auxiliary.curator
first (canonical), falls back to legacy curator.auxiliary (with an info
log asking users to migrate), then falls back to the main chat model.
Pre-unification users keep working.
Docs updated: docs/user-guide/features/curator.md now points at
`hermes model` → auxiliary → Curator and the dashboard Models tab.
Tests: 6 unit tests on _resolve_review_model (auto default, canonical
slot honored, partial override fallback, legacy fallback with
deprecation log assertion, new-wins-over-legacy, empty-config safety)
plus a cross-registry test that curator is wired into all four sources
of truth. test_aux_tasks_keys_all_exist_in_default_config already
covers the DEFAULT_CONFIG ↔ _AUX_TASKS invariant.
Reported by Voscko on Discord.
UserMessageChunk and AgentMessageChunk do not have a message_id field
in the ACP schema. Passing it silently dropped the kwarg (pydantic
does not raise on unknown init kwargs here) and the subsequent test
assertions on .message_id raised AttributeError. Strip the dead
plumbing (uuid import, message_id= kwarg on both chunk types, unused
session_id/index parameters) and remove the matching .message_id
asserts from the test.
Adds a deterministic pre-check on top of htsh's exception-based fallback:
before calling /content/abstract or /content/overview on a non-pseudo URI,
probe /api/v1/fs/stat. If the server says the URI is a file, route straight
to /content/read instead of eating a failing 500 round-trip.
This is the same idea pty819 and chennest independently landed in PRs
#12757 and #12937 — merged here on top of htsh's broader fix so we keep
pseudo-URI normalization and v0.3.3 browse-shape handling while avoiding
the slow exception path on servers that return a raised 500 every time.
The exception fallback from #5886 stays in place for environments where
fs/stat is unavailable or returns an unfamiliar shape.
Also credits pty819, chennest, and htsh in AUTHOR_MAP so future release
notes attribute them correctly.
OpenViking returns 500 for /content/abstract and /content/overview when URI points to mem_*.md files.
Add resilient fallback to /content/read for non-pseudo summary file URIs while preserving pseudo summary normalization.
Also add regression tests for fallback behavior.
`hermes dashboard` is a long-lived foreground server that users often
start and forget about, sometimes in a shell they've since closed. We
didn't have a way to stop it — users had to find the PID manually.
Adds two lifecycle flags that reuse the same detection + termination
path the post-`hermes update` cleanup (PR #17832) uses:
hermes dashboard --status
List running hermes dashboard processes with PID + cmdline.
Exit 0, informational.
hermes dashboard --stop
Terminate all running dashboards (3s grace then force-kill survivors).
Exit 0 if none remain, 1 if any couldn't be stopped.
Windows uses `taskkill /F` as before.
Both flags short-circuit before any fastapi/uvicorn import so they work
even on installations where the dashboard extras aren't installed —
useful when you're cleaning up after uninstalling.
The kill helper gained an optional `reason=...` param so the output
reads "(requested via --stop)" instead of the post-update-specific
"running backend no longer matches the updated frontend" wording.
E2E: `hermes dashboard --status` with nothing running prints the
empty message; with a fake `hermes dashboard ...` cmdline spawned via
`exec -a`, `--status` lists it, `--stop` terminates it (exit -15),
and a follow-up `--status` returns empty.
Reshape of PR #17211 (@versun). Lets users wire any local or external
TTS CLI into Hermes without adding engine-specific Python code. Users
declare any number of named providers in config.yaml and switch between
them with tts.provider: <name>, alongside the built-ins (edge, openai,
elevenlabs, …).
Config shape:
tts:
provider: piper-en
providers:
piper-en:
type: command
command: 'piper -m ~/model.onnx -f {output_path} < {input_path}'
output_format: wav
Placeholders: {input_path}, {text_path}, {output_path}, {format},
{voice}, {model}, {speed}. Use {{ / }} for literal braces.
Key behavior:
- Built-in provider names always win — a tts.providers.openai entry
cannot shadow the native OpenAI provider.
- type: command is the default when command: is set.
- Placeholder values are shell-quote-aware (bare / single / double
context), so paths with spaces and shell metacharacters are safe.
- Default delivery is a regular audio attachment. voice_compatible: true
opts in to Telegram voice-bubble delivery via ffmpeg Opus conversion.
- Command failures (non-zero exit, timeout, empty output) surface to
the agent with stderr/stdout included so you can debug from chat.
- Process-tree kill on timeout (Unix killpg, Windows taskkill /T).
- max_text_length defaults to 5000 for command providers; override
under tts.providers.<name>.max_text_length.
Tests: tests/tools/test_tts_command_providers.py — 42 new tests cover
provider resolution, shell-quote context, placeholder rendering with
injection payloads, timeout, non-zero exit, empty output, voice_compatible
opt-in, and end-to-end dispatch through text_to_speech_tool. All 88
pre-existing TTS tests still pass.
Docs: new "Custom command providers" section in
website/docs/user-guide/features/tts.md with three worked examples
(Piper, VoxCPM, MLX-Kokoro), placeholder reference, optional keys,
behavior notes, and security caveat.
E2E-verified live: isolated HERMES_HOME, command provider declared in
config.yaml, text_to_speech_tool dispatches through the registered
shell command and the output file is produced as expected.
Co-authored-by: Versun <me+github7604@versun.org>
`hermes update` previously just printed a warning when it detected a
running `hermes dashboard` process from the previous version, telling
the user to kill and restart it themselves. In practice dashboards get
started and forgotten, so the warning was routinely ignored and users
ended up with a silent frontend/backend mismatch (new JS bundle served
against the old in-memory Python backend, e.g. new auth headers the old
code doesn't recognise → every API call 401s).
The dashboard has no service manager, no PID file, and we don't record
the original launch args (--host, --port, --insecure, --tui, --no-open)
so we can't auto-restart it. But we CAN stop it, which is what the
user wants — the failure mode when the stale process is left alive is
worse than the dashboard just being down.
- POSIX: SIGTERM, poll for ~3s, SIGKILL any survivors.
- Windows: `taskkill /PID <pid> /F`.
- Print each PID's outcome plus a one-line restart hint.
- Detection logic is unchanged (same ps / wmic scan, same guards
against the `pgrep -f` greedy-match trap from #16872 and the
#17049 wmic UnicodeDecodeError fix).
Also split the old monolithic `_warn_stale_dashboard_processes` into
`_find_stale_dashboard_pids` (scan) + `_kill_stale_dashboard_processes`
(kill), keeping the old name as an alias so any external callers still
work.
E2E verified: spawned a fake `hermes dashboard` cmdline via
`exec -a 'hermes dashboard …' sleep 300`, ran
`_kill_stale_dashboard_processes()`, confirmed SIGTERM exit (-15)
and that a post-scan returns an empty PID list.
Three narrow fixes targeting the remaining red checks after #17828:
1. ui-tui/src/app/slash/commands/ops.ts (Docker Build):
/reload-mcp's local params type annotated session_id: string
while ctx.sid is string | null. Widen to string | null —
matches every other rpc call site and the test harness which passes
{ session_id: null }. Fixes TS2322 on line 86. The rpc signature
itself is Record<string, unknown>, so this is purely a local
typing fix, no behavioral change.
2. tests/plugins/test_achievements_plugin.py (13 cascading test failures):
_install_fake_session_db did a raw sys.modules['hermes_state'] =
fake_module without restoration, leaking the fake across xdist
worker boundaries. Downstream tests doing from hermes_state import
SessionDB got a module whose SessionDB was lambda: fake_db
— 6 test_hermes_state.py tests failed with AttributeError: 'function'
object has no attribute '_sanitize_fts5_query' / _contains_cjk,
and 7 test_860_dedup.py tests failed with TypeError: got unexpected
keyword argument 'db_path' (real code calls SessionDB(db_path=...)).
Fix: stash monkeypatch on the plugin_api module object in the
fixture, and have the helper do monkeypatch.setitem(sys.modules,
'hermes_state', fake_module) for auto-restoration at test teardown.
3. tests/hermes_cli/test_web_server.py (WS race):
TestPtyWebSocket::test_pub_broadcasts_to_events_subscribers hit the
30s test timeout on CI. websocket_connect returns after
ws.accept() — but /api/events registers the subscriber in
_event_channels on the NEXT await (inside _event_lock). A
publish immediately after connect could race ahead of registration
and be dropped, and the subsequent receive_text() blocked until
SIGALRM killed the test. Fix: poll _event_channels after the
subscriber connects, before publishing.
Validation:
scripts/run_tests.sh tests/plugins/test_achievements_plugin.py
tests/run_agent/test_860_dedup.py
tests/test_hermes_state.py
tests/hermes_cli/test_web_server.py 338 passed
cd ui-tui && npm run type-check clean
cd ui-tui && npm run build clean
Remaining red checks are pure infra (Nix ubuntu hits
TwirpErrorResponse ResourceExhausted on the GH Actions cache API; Nix
macos bounces between npm build openssl-legacy and cache rate-limits)
and cannot be fixed in the codebase.
Extracted from PR #17211 (@versun) so it can land independently of the
local_command TTS provider redesign.
- Add should_send_media_as_audio(platform, ext, is_voice) in
gateway/platforms/base.py; single source of truth for audio routing.
- Add .flac to recognized audio extensions (MEDIA regex, weixin audio
set, send_message audio set).
- Telegram send_voice() now falls back to send_document for formats
Telegram's Bot API can't play natively (.wav, .flac, ...) instead of
raising; MP3/M4A still go to sendAudio, Opus/OGG still go to sendVoice.
- Route _send_telegram() in send_message_tool through a narrower
_TELEGRAM_SEND_AUDIO_EXTS = {.mp3, .m4a} set.
- cron.scheduler._send_media_via_adapter now delegates the audio
decision to should_send_media_as_audio so it matches the gateway.
- Update the cron live-adapter ogg test to flag [[audio_as_voice]] so
it still routes to sendVoice under the new Telegram-specific policy.
- Tests: unit coverage for should_send_media_as_audio across platforms,
end-to-end MEDIA routing via _process_message_background and
GatewayRunner._deliver_media_from_response, TelegramAdapter.send_voice
fallback for FLAC/WAV.
Co-authored-by: Versun <me+github7604@versun.org>
Fixes the xdist collision that broke CI on PR #17764, and structurally
prevents future plugin-adapter tests from reintroducing it.
Problem
-------
tests/gateway/test_teams.py (new in this PR) and tests/gateway/test_irc_adapter.py
(already on main) both followed the same anti-pattern:
sys.path.insert(0, str(_REPO_ROOT / 'plugins' / 'platforms' / '<name>'))
from adapter import <Adapter>
Every platform plugin ships its own adapter.py, so the bare
'from adapter import ...' races for sys.modules['adapter']. Whichever test
collected first in a given xdist worker won; the other crashed at
collection with ImportError, and the polluted sys.path cascaded into 19
unrelated test failures across tools/, hermes_cli/, and run_agent/ in the
same worker.
Fix
---
1. tests/gateway/_plugin_adapter_loader.py (new): shared helper
load_plugin_adapter('<name>') that imports plugins/platforms/<name>/adapter.py
via importlib.util under the unique module name plugin_adapter_<name>.
Zero sys.path mutation, no possibility of collision.
2. tests/gateway/test_irc_adapter.py and tests/gateway/test_teams.py:
migrated to the helper. All 'from adapter import ...' statements
(including the ones inside test methods) are replaced with module-level
attribute access on the loaded module.
3. tests/gateway/conftest.py: new pytest_configure guard that AST-scans
every test_*.py under tests/gateway/ at session start and fails the
run with a pointer to the helper if any test uses sys.path.insert into
plugins/platforms/ OR a bare 'import adapter' / 'from adapter import'.
Runs on the xdist controller only (skipped in workers). The next plugin
adapter test that tries to reintroduce this pattern gets rejected at
collection time with a clear remediation message.
4. scripts/release.py: add aamirjawaid@microsoft.com -> heyitsaamir to
AUTHOR_MAP so the check-attribution workflow passes.
Validation
----------
scripts/run_tests.sh tests/gateway/ 4194 passed
scripts/run_tests.sh tests/gateway/test_{teams,irc}* 72 passed (both orderings)
scripts/run_tests.sh <11 prev-failing test files> 398 passed
Guard triggers correctly on both Path-operator and string-literal forms
of the anti-pattern.
Hello! I am the maintainer of the microsoft-teams-apps Python SDK and
I built this Teams adapter to integrate Microsoft Teams into Hermes.
Adds a `plugins/platforms/teams` platform plugin using the new
PlatformRegistry system from #17751. The adapter self-registers via
`register(ctx)` — no hardcoding in run.py, toolsets.py, or any
other core file.
Key features:
- Supports personal DMs, group chats, and channel posts
- Adaptive Card approval prompts with in-place button replacement
(Allow Once / Allow Session / Always Allow / Deny)
- aiohttp webhook server bridged from the Teams SDK to avoid
the fastapi/uvicorn dependency
- ConversationReference caching for correct proactive sends in
non-DM chats
- `interactive_setup()` for `hermes gateway setup` integration
- `platform_hint` for LLM context (Teams markdown subset)
- 34 tests covering adapter init, send, message handling, and
plugin registration
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
PR #17660 landed a sweep of CI fixes but left three loose ends:
1. tests/cli/test_cli_loading_indicator.py::test_reload_mcp_sets_busy_state_
and_prints_status — /reload-mcp gained a prompt-cache-invalidation
confirmation (commit 4d7fc0f37) that was never wired into this test.
The test exercises the loading-indicator path, so pre-approve via
config and go straight into _reload_mcp().
2. tools/mcp_tool.py _make_tool_handler — the added
getattr(server, '_rpc_lock', None) + 'skip the lock if missing'
branch is inconsistent with four sibling call sites that still
direct-access server._rpc_lock. The lock is guaranteed by
MCPServerTask.__init__; falling through to an unlocked
session.call_tool would silently serialize-strip RPCs if the guard
ever triggered. Restore direct access.
3. tui_gateway/server.py _messages_as_conversation — the helper
existed only to catch 'TypeError: include_ancestors unexpected'
from mocked SessionDBs that don't actually exist. The real
SessionDB.get_messages_as_conversation has accepted
include_ancestors since introduction, and every test FakeDB in
the repo already declares the kwarg. Remove the shim, inline the
two call sites.
* feat(plugins): bundle hermes-achievements, scan full session history
Ships @PCinkusz's hermes-achievements dashboard plugin (https://github.com/PCinkusz/hermes-achievements) as a bundled plugin at plugins/hermes-achievements/ and fixes a bug in the scan path that made the plugin only see the first 200 sessions — making lifetime badges (50k tool calls, 75k errors, etc.) unreachable on long-running installs.
Changes:
- plugins/hermes-achievements/: vendor v0.3.1 verbatim (manifest, dist/, plugin_api.py, tests, docs, README).
- plugins/hermes-achievements/dashboard/plugin_api.py:
* scan_sessions(): limit=None now scans ALL sessions via SQLite LIMIT -1. Previously capped at 200, so users with 8000+ sessions saw ~2% of their history.
* evaluate_all(): first-ever scans run in a background thread so the dashboard request path never blocks. Stale snapshots serve immediately while a background refresh runs. force=True still blocks synchronously for manual /rescan.
* _build_pending_snapshot(), _start_background_scan(), _run_scan_and_update_cache(): supporting plumbing + idempotent thread spawn.
- tests/plugins/test_achievements_plugin.py: new tests covering the 200-cap regression, the background-scan first-run flow, stale-serve-plus-background-refresh, forced sync rescan, and scan-thread idempotency.
- website/docs/user-guide/features/built-in-plugins.md: lists hermes-achievements in the bundled-plugins table and documents API endpoints, state files, and performance characteristics.
E2E validated against a real 8564-session ~6.4GB state.db:
* Cold scan: 13m 19s (one-time, backgrounded — UI never blocks)
* Warm rescan: 1.47s (8563/8564 sessions reused from checkpoint cache)
* 57/60 achievements unlocked, 3 discovered — aggregates like total_tool_calls=259958, total_errors=164213, skill_events=368243 correctly surface lifetime badges that the 200-cap made unreachable.
Original credit: @PCinkusz (MIT-licensed). Upstream repo remains the staging ground for new badges; this bundle keeps the dashboard feature parity with Hermes core changes.
* feat(achievements): publish partial snapshots during cold scan
Previously a cold scan on a large session DB (13min on 8564 sessions)
showed zero badges for the entire duration, then every badge at once
when the scan completed. A dashboard refresh mid-scan was indistinguishable
from a fresh install with no history.
Now the scanner publishes a partial snapshot to _SNAPSHOT_CACHE every
250 sessions, so each refresh during a cold scan surfaces more badges
incrementally.
Mechanism:
- scan_sessions() takes an optional progress_callback fired every
progress_every sessions with (sessions_so_far, scanned, total).
- _compute_from_scan() is extracted from compute_all() and gains an
is_partial flag that skips writing to state.json — we don't want
to record unlocked_at based on a half-complete aggregate that a
later session might rebalance.
- _run_scan_and_update_cache() installs a publisher callback that
builds a partial snapshot, marks it mode='in_progress', and writes
it to the cache with age=0 so the UI keeps polling /scan-status
and picks up the final snapshot when the scan completes.
- Manual /rescan (force=True) disables partial publishing — the
caller is blocking on the final result anyway.
E2E against real 8564-session state.db (polled cache every 10s):
t=10s: cache empty
t=20s: 250/8564 scanned, 35 unlocked, 25 discovered
t=40s: 500/8564 scanned, 42 unlocked, 18 discovered
t=60s: 1000/8564 scanned, 49 unlocked, 11 discovered
...
Tests: 9/9 pass (2 new — partial snapshot publication + no-persist-on-partial).
Upstream unittest suite: 10/10 pass.
* feat(achievements): in-progress scan banner with live % progress
Previously the dashboard showed zero badges silently during long cold
scans (13min on 8564 sessions). The backend was publishing partial
snapshots every 250 sessions, but the bundled UI didn't surface any
indicator that a scan was running — it just rendered the main page
with whatever counts were currently published and no way for the user
to know more progress was coming.
UI changes (dist/index.js, dist/style.css):
- Added a scan-in-progress banner rendered between the hero and stats
when scan_meta.mode is 'pending' or 'in_progress'. Shows:
BUILDING ACHIEVEMENT PROFILE…
Scanned 1,750 of 8,564 sessions · 20%. Badges unlock as more history streams in.
with a pulsing teal indicator and a filling teal/cyan progress bar.
Disappears the moment the backend flips to 'full' or 'incremental'.
- Added an auto-poller via useEffect — while scanInFlight is true the
page re-fetches /achievements every 4s WITHOUT toggling the loading
skeleton, so unlock counts tick up visibly without the user refreshing.
The effect cleans itself up when the scan finishes.
- Added refresh() (re-fetch, no loading flip) alongside the existing
load() (full reload, used by the Rescan button).
Attribution preserved:
- Added a header comment to index.js crediting @PCinkusz
(https://github.com/PCinkusz/hermes-achievements, MIT) as the
original author, noting the banner is a layered addition on top
of the original dist bundle.
- Matching header comment in style.css, flagging the new
.ha-scan-banner* rules as the local addition.
Live-verified end to end:
- Spun up `hermes dashboard --port 9229 --no-open` against a fresh
HERMES_HOME symlinked to the real 8564-session state.db.
- Opened /achievements in a browser, confirmed the banner renders with
live progress: 'Scanned 1,000 of 8,564 sessions · 11%' → updates to
'1,250 ... · 14%' → '1,750 ... · 20%' without user interaction,
matching the backend's partial publications.
- Stats row simultaneously climbed from 35 → 49 → 53 unlocked as
more history streamed in.
- Vision analysis of the rendered page confirms the banner styling
matches the rest of the dashboard (dark card bg, teal accent, same
small-caps typography, pulsing indicator reusing ha-pulse keyframes).
The _CODEX_AUX_MODEL constant had already rotated twice in 6 weeks
(gpt-5.3-codex -> gpt-5.2-codex -> now broken again at gpt-5.2-codex)
because ChatGPT-account Codex gates which models it accepts via an
undocumented, shifting allow-list that OpenAI publishes no changelog
for. Any pinned default will keep going stale. Issue #17533 reports
the current breakage: every ChatGPT-account auxiliary fallback fails
with HTTP 400 "model is not supported" and the 60s pause loop degrades
long sessions.
Rather than reset the clock with another stale pin (PR #17544 proposes
gpt-5.2-codex -> gpt-5.4), remove the hardcoded second-order Codex
fallback entirely:
- Delete `_CODEX_AUX_MODEL`.
- Drop `_try_codex` from `_get_provider_chain()` (the auto chain now
ends at api-key providers; 4 rungs instead of 5).
- Rename `_try_codex() -> _build_codex_client(model)` and require an
explicit model from the caller. No more guessing.
- `resolve_provider_client("openai-codex", model=None)` now warns and
returns (None, None) instead of silently guessing a stale model ID.
- Remove `_try_codex` from the `provider="custom"` fallback ladder
(same stale-constant trap).
- `_resolve_strict_vision_backend("openai-codex")` routes through
`resolve_provider_client` so the caller's explicit model is honored.
Codex-main users are unaffected: Step 1 of `_resolve_auto` already
uses `main_provider` + `main_model` directly and passes the user's
configured Codex model through `resolve_provider_client`, which never
touched `_CODEX_AUX_MODEL`. Per-task overrides (`auxiliary.<task>.provider/model`)
continue to work and are the supported way to route specific aux tasks
through Codex.
Users whose main provider fails with a payment/connection error and
who have ONLY ChatGPT-account Codex auth will now see the 60s pause
without a stale-model-rejection noise line in between -- same outcome,
cleaner failure.
Closes#17533. Supersedes #17544 (which resets the clock on the
same stale-constant problem).
Keep context-1m-2025-08-07 in OAuth requests by default so 1M-capable
subscriptions retain full context. When Anthropic rejects a request with
400 'long context beta is not yet available for this subscription',
disable the beta for the rest of the session, rebuild the client, and
retry once.
Addresses #17680 (thanks @JayGwod for the clean reproduction) without
forcing every OAuth user off the 1M context window.
Changes:
- agent/error_classifier.py: new FailoverReason.oauth_long_context_beta_forbidden;
pattern matches 400 + 'long context beta' + 'not yet available'. Narrow
enough that the existing 429 tier-gate pattern keeps its own reason.
- agent/anthropic_adapter.py: _common_betas_for_base_url,
build_anthropic_client, build_anthropic_kwargs gain drop_context_1m_beta
kwarg. Default=False (1M stays). OAuth OAUTH_ONLY_BETAS unchanged.
- agent/transports/anthropic.py: build_kwargs forwards the flag.
- run_agent.py: self._oauth_1m_beta_disabled flag, retry-once guard,
recovery branch next to the image-shrink path. _rebuild_anthropic_client
honors the flag. The main build_kwargs call site threads it through for
fast-mode extra_headers.
- hermes_cli/doctor.py, hermes_cli/models.py: sibling OAuth /v1/models
probes get the same reactive retry — previously they'd falsely report
the Anthropic API as unreachable for affected subscriptions.
Tests: 2190 tests/agent/ + 94 adjacent integration tests pass. New unit
tests cover the classifier pattern (including the collision guard against
the 429 tier-gate) and the drop_context_1m_beta adapter behavior (default
keeps 1M, flag strips only 1M while preserving every other beta).
Platform plugins shipped in-repo under plugins/platforms/ should be
available out of the box — users shouldn't have to add 'irc-platform'
to plugins.enabled before they can pick IRC from the gateway setup menu.
Adds a new ``kind: platform`` plugin type that mirrors the existing
``kind: backend`` auto-load semantics:
- Bundled (shipped in the hermes-agent repo): auto-load unconditionally.
- User-installed (~/.hermes/plugins/): still opt-in via plugins.enabled
so untrusted code doesn't silently run.
Changes:
* hermes_cli/plugins.py: add 'platform' to _VALID_PLUGIN_KINDS, document
the new kind in the PluginManifest docstring, extend the bundled auto-
load rule from 'backend only' to 'backend or platform'.
* plugins/platforms/irc/plugin.yaml: declare kind: platform.
* hermes_cli/gateway.py: remove the now-redundant
_load_bundled_platform_plugins_for_enumeration() helper and the
_enable_plugin_for_platform() helper. The setup menu's _all_platforms()
just calls discover_plugins() and reads the registry — bundled
platforms are already loaded at that point. Drops the 'needs_enable'
flag and the 'plugin disabled — select to enable' status string.
* hermes_cli/setup.py: relax the "gateway is configured" detector used
during OpenClaw migration. Switching to _platform_status() in an
earlier commit tightened the check to require an exact "configured"
match, dropping platforms whose status is "enabled, not paired",
"partially configured", "configured + E2EE", etc. Now any non-"not
configured" status counts — the user has already started setup there
and we shouldn't force the section to rerun.
* tests/hermes_cli/test_setup_irc.py: drop the TestIRCPluginDisabledFlow
class and test_configure_platform_enables_disabled_plugin_first — the
no-longer-existent flow they were testing.
* tests/hermes_cli/test_setup_openclaw_migration.py: patch both
setup.get_env_value and gateway.get_env_value in the 4 gateway-section
tests that reach _platform_status() through the unified setup flow;
switch WHATSAPP_ENABLED to the literal "true" in the registry-parity
test so WhatsApp's value-shape validator matches.
Verified via fresh-install smoke (empty plugins.enabled, no env vars):
IRC plugin loads, Platform('irc') resolves, _all_platforms() lists IRC
with status 'not configured'. 160 targeted tests pass.
feat(gateway): refine Platform._missing_ and platform-connected dispatch
Restricts plugin-name acceptance to bundled plugin scan + registry
(no arbitrary string -> enum-pollution), pulls per-platform connectivity
checks into a _PLATFORM_CONNECTED_CHECKERS lambda map with a clean
_is_platform_connected method, and adds tests covering the checker map,
plugin platform interface, and IRC setup wizard.
Merge the two gateway setup paths (hermes setup gateway + hermes gateway
setup) to use a single _unified_platforms() list that merges built-in
_PLATFORMS with dynamically registered plugin entries from
platform_registry.
- Add setup_fn field to PlatformEntry for plugin setup flows
- _unified_platforms() merges built-ins with registry entries by key
- setup_gateway() now uses unified list instead of hardcoded
_GATEWAY_PLATFORMS tuple list
- gateway_setup() uses same unified list, plugin entries appear
alongside built-ins with no [plugin] suffix
- _platform_status() handles plugin platforms via registry check_fn
- Plugin platforms with setup_fn get called directly; plugins without
get a generic env-var display fallback
IRC and other plugin platforms now appear automatically in the setup
menu when registered via platform_registry.register().
feat(gateway): surface disabled platform plugins in setup and auto-enable on select
Platform plugins under plugins/platforms/* (IRC, etc.) were gated behind
plugins.enabled, so `hermes gateway setup` wouldn't list them until the
user ran `hermes plugins enable <name>` first. Now the setup menu always
surfaces them as "plugin disabled — select to enable", and picking one
adds it to plugins.enabled before running its setup flow.
Along the way, unify the two gateway setup flows so `hermes setup gateway`
and `hermes gateway setup` both read from the same platform list (built-in
_PLATFORMS + platform_registry entries), dispatch through a single
_configure_platform() helper, and share _platform_status(). Deletes the
dead bespoke wrappers in setup.py (_setup_whatsapp, _setup_weixin,
_setup_email, etc.) that duplicated logic now covered by the registry
path or _setup_standard_platform.
Also:
- PlatformEntry gains a plugin_name field so the registry knows which
plugin owns each entry (required for auto-enable).
- PluginContext.register_platform auto-stamps plugin_name from the
manifest so plugins don't have to pass it explicitly.
- PluginManager now scans plugins/platforms/* as its own category root,
one level below the bundled plugin scan.
- Fix IRC plugin discovery: rename PLUGIN.yaml → plugin.yaml (the
scanner is case-sensitive) and add the missing __init__.py that
_load_directory_module requires.
Extends the platform plugin interface from Phase 1 to cover every
touchpoint where built-in platforms have hardcoded behavior.
- allowed_users_env / allow_all_env: per-platform auth env vars
- max_message_length: smart-chunking for send_message tool
- pii_safe: session PII redaction flag
- emoji: CLI/gateway display
- allow_update_command: /update access control
send_message tool (tools/send_message_tool.py):
- Replaced hardcoded platform_map dict with Platform() call
- Added _send_via_adapter() for plugin platforms — routes through
live gateway adapter when available
- Registry-aware max message length for smart chunking
Cron delivery (cron/scheduler.py):
- Replaced hardcoded 15-entry platform_map with Platform() call
- Plugin platforms now work as cron delivery targets
User authorization (gateway/run.py _is_user_authorized):
- Registry fallback: checks PlatformEntry.allowed_users_env and
allow_all_env when platform not in hardcoded maps
- Plugin platforms get per-platform auth support
_UPDATE_ALLOWED_PLATFORMS: checks registry allow_update_command flag
Channel directory: includes plugin platforms in session enumeration
Orphaned config warning: descriptive message when plugin platform is
in config but no plugin registered it
Gateway weakref: _gateway_runner_ref for cross-module adapter access
hermes status: shows plugin platforms with (plugin) tag
hermes gateway setup: plugin platforms appear in menu with setup hints
hermes_cli/platforms.py: get_all_platforms() merges with registry,
platform_label() falls back to registry for plugin names
- 8 new tests (extended fields, cron resolution, platforms merge)
- Updated 3 tests for new Platform() based resolution
- 2829 passed, 24 pre-existing failures, zero new failures
Adds a platform adapter plugin interface so anyone can create new gateway
platforms (IRC, Viber, Line, etc.) as drop-in plugins without modifying
core gateway code.
- PlatformEntry dataclass: name, label, adapter_factory, check_fn,
validate_config, required_env, install_hint, source
- PlatformRegistry singleton with register/unregister/create_adapter
- _create_adapter() in gateway/run.py checks registry first, falls
through to existing if/elif chain for built-in platforms
- Platform._missing_() accepts unknown string values, creating cached
pseudo-members so Platform('irc') is Platform('irc') holds true
- GatewayConfig.from_dict() now parses plugin platform names from
config.yaml without rejecting them
- get_connected_platforms() delegates to registry for unknown platforms
- PluginContext.register_platform() for plugin authors
- Mirrors the existing register_tool() / register_hook() pattern
- Full async IRC adapter using stdlib asyncio (zero external deps)
- Connects via TLS, handles PING/PONG, nick collision, NickServ auth
- Channel messages require addressing (nick: msg), DMs always dispatch
- Markdown stripping for IRC-clean output, message splitting for
512-byte line limit
- Config via config.yaml extra dict or IRC_* env vars
- Platform enum dynamic members (identity stability, case normalization)
- PlatformRegistry (register, unregister, create, validation, factory)
- GatewayConfig integration (from_dict parsing, get_connected_platforms)
- IRC adapter (init, send, protocol parsing, markdown, requirements)
No existing platform adapters were migrated — the if/elif chain is
untouched. This is Phase 1: prove the interface with a real plugin.
Reloading MCP servers rebuilds the tool set for the active session, which
invalidates the provider prompt cache (tool schemas are baked into the
system prompt). The next message re-sends full input tokens — can be
expensive on long-context or high-reasoning models.
To surface that cost, /reload-mcp now routes through a new slash-confirm
primitive with three options: Approve Once / Always Approve / Cancel.
'Always Approve' persists approvals.mcp_reload_confirm: false so future
reloads run silently.
Coverage:
* Classic CLI (cli.py) — interactive numbered prompt.
* TUI (tui_gateway + Ink ops.ts) — text warning on first call; `now` /
`always` args skip the gate; `always` also persists the opt-out.
* Messenger gateway — button UI on Telegram (inline keyboard), Discord
(discord.ui.View), Slack (Block Kit actions); text fallback on every
other platform via /approve /always /cancel replies intercepted in
gateway/run.py _handle_message.
* Config key: approvals.mcp_reload_confirm (default true).
* Auto-reload paths (CLI file watcher, TUI config-sync mtime poll) pass
confirm=true so they do NOT prompt.
Implementation:
* tools/slash_confirm.py — module-level pending-state store used by all
adapters and by the CLI prompt. Thread-safe register/resolve/clear.
* gateway/platforms/base.py — send_slash_confirm hook (default 'Not
supported' → text fallback).
* gateway/run.py — _request_slash_confirm helper + text intercept in
_handle_message (yields to in-progress tool-exec approvals so
dangerous-command /approve still unblocks the tool thread first).
Tests:
* tests/tools/test_slash_confirm.py — primitive lifecycle + async
resolution + double-click atomicity (16 tests).
* tests/hermes_cli/test_mcp_reload_confirm_gate.py — default-config
shape + deep-merge preserves user opt-out (5 tests).
Targeted runs (hermetic): 89 passed (slash-confirm, config gate,
existing agent cache, existing telegram approval buttons).
PR #15027 (5 days ago) shipped TELEGRAM_GROUP_ALLOWED_USERS as a chat-ID
allowlist. #17686 correctly renames that to sender user IDs and moves
chat IDs to TELEGRAM_GROUP_ALLOWED_CHATS. Without a shim, any user on
PR #15027's guidance would silently start rejecting group traffic on
upgrade.
- gateway/run.py: in _is_user_authorized, if TELEGRAM_GROUP_ALLOWED_USERS
contains values starting with '-' (chat-ID-shaped), honor them as chat
IDs and log a one-shot deprecation warning pointing users at the new
TELEGRAM_GROUP_ALLOWED_CHATS var.
- tests/gateway/test_unauthorized_dm_behavior.py: three new tests cover
legacy chat-ID values authorizing the listed chat, not crossing to
other chats, and mixed sender/chat values in the same var.
- website/docs/user-guide/messaging/telegram.md: rewrite the Group
Allowlisting section to document the new user/chat split + migration
note. Remove stale '/thread_id' suffix claim (code never parsed it).
- website/docs/reference/environment-variables.md: document all three
Telegram allowlist env vars.
Salvage-follow-up to @shannonsands's /reload-skills PR. Trims the feature to
match the design: user-initiated rescan, no prompt-cache reset, no new
schema surface, no phantom user turn, and the next-turn note carries each
added/removed skill's 60-char description (not just its name).
Changes vs the original PR:
* Drop the in-process skills prompt-cache clear in reload_skills(). Skills
are invoked at runtime via /skill-name, skills_list, or skill_view —
they don't need to live in the system prompt for the model to use them.
Keeping the cache intact preserves prefix caching across the reload so
/reload-skills pays no cache-reset cost. (MCP has to break the cache
because tool schemas must be known at conversation start; skills do not.)
* Drop the skills_reload agent tool and SKILLS_RELOAD_SCHEMA from
tools/skills_tool.py, plus the four skills_reload enumerations in
toolsets.py. No new schema surface — agents can already see a freshly-
installed skill via skill_view / skills_list the moment it's on disk.
* Replace the phantom 'role: user' turn injection with a one-shot queued
note. CLI uses self._pending_skills_reload_note (same pattern as
_pending_model_switch_note, prepended to the next API call and cleared).
Gateway uses self._pending_skills_reload_notes[session_key]. The note
is prepended to the NEXT real user message in this session, so message
alternation stays intact and nothing out-of-band is persisted to the
transcript.
* reload_skills() now returns added/removed as
[{'name': str, 'description': str}, ...] (description truncated to 60
chars — matches the curator / gateway adapter budget). The injected
next-turn note formats each entry as 'name — description' so the model
can actually reason about which new skills to call without running
skills_list first.
* Only emit the note when the diff is non-empty. On empty diff, print
'No new skills detected' and do nothing else.
* Tests rewritten to cover the queue semantics, the description payload,
and a regression guard that the prompt-cache snapshot is preserved.
Adds a public reload path for the in-process skill caches so newly
installed (or removed) skills become visible mid-session without a
gateway restart. Mirrors the shape of /reload-mcp.
Three surfaces:
* /reload-skills slash command — CLI (cli.py) and gateway (gateway/run.py),
with /reload_skills alias for Telegram autocomplete and an explicit
Discord registration.
* skills_reload agent tool (tools/skills_tool.py) — lets agents/subagents
pick up freshly-installed skills via tool call.
* agent.skill_commands.reload_skills() — shared helper that clears
_skill_commands, _SKILLS_PROMPT_CACHE (in-process LRU), and the
on-disk .skills_prompt_snapshot.json, then returns an added/removed
diff plus the new total count.
Tested:
* tests/agent/test_skill_commands_reload.py (9 cases)
* tests/cli/test_cli_reload_skills.py (3 cases)
* tests/gateway/test_reload_skills_command.py (4 cases)
Use case: NemoClaw / OpenShell-style sandboxed orchestrators that drop
skills into ~/.hermes/skills mid-session, plus agentic flows where the
agent itself installs a skill via the shell tool and needs it bound
without a gateway restart. The Python helper
clear_skills_system_prompt_cache(clear_snapshot=True) already exists
internally — this PR just exposes it via slash command and tool.
Pull the top-level + chat parser construction out of main() into
hermes_cli/_parser.py so relaunch.py can introspect parser._actions to
discover which flags exist and whether they take values, instead of
maintaining a parallel hand-rolled (flag, takes_value) tuple list.
- _parser.py: build_top_level_parser() returns (parser, subparsers,
chat_parser); side-effect-free import.
- main.py: ~290 lines of inline parser construction collapsed to a
helper call. Other subparsers stay inline (dispatch is bound to
module-level cmd_* functions).
- _parser._inherited_flag(parser, ...): wraps parser.add_argument and
sets action.inherit_on_relaunch = True. Used in place of
parser.add_argument for the 25 flags (top-level + chat) that need to
carry over.
- _parser.PRE_ARGPARSE_INHERITED_FLAGS: holds --profile/-p, which
isn't on argparse (consumed earlier by main._apply_profile_override).
- relaunch.py: drops _CRITICAL_DESTS and _PRE_ARGPARSE_FLAGS; the table
builder now filters by getattr(action, 'inherit_on_relaunch', False).
- test_ignore_user_config_flags.py: brittle inspect.getsource grep
replaced with proper parser introspection.
- test_relaunch.py: introspection sanity tests added.
Salvaged from PR #17549; added top-level -t/--toolsets flag to
_parser.py so #17623 (fix(tui): honor launch toolsets) behavior is
preserved on current main.
Co-authored-by: ethernet <arilotter@gmail.com>
Extract all os.execvp('hermes', ...) calls into a utility so flags like
--tui, --dev, --profile, --model, --provider, et al. survive session
resume and post-setup relaunch.
- resolve_hermes_bin: prefers sys.argv[0] when callable, then PATH,
then falls back to '${sys.executable} -m hermes_cli.main' (fixes nix
run relaunches)
- build_relaunch_argv: allowlists critical flags so they carry over
- cmd_sessions browse now calls relaunch(['--resume', <id>])
- _apply_profile_override skips redundant work when HERMES_HOME is
already set (child inherits parent profile)
- setup.py replaces _resolve_hermes_chat_argv with relaunch_chat()
- added comprehensive tests for flag extraction and binary resolution
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
If a concurrent RPC mutates _sessions while session.delete is iterating
it (e.g. a parallel session.create on the thread pool), the bare except
swallowed the RuntimeError and let the delete proceed against a row
that may still be live. Snapshot via list(_sessions.values()) and
return an error when even that raises, instead of treating "couldn't
check" as "no active sessions."
Pressing `d` on the highlighted row in the resume picker prompts
`delete? y/n`; `y` deletes the session (DB row + on-disk transcript
files), anything else cancels. The active session is excluded from
deletion server-side.
Adds a new `session.delete` JSON-RPC handler that wraps
`SessionDB.delete_session`, forwarding the per-profile `sessions/`
directory so transcripts get cleaned up alongside the row.
CI Tests workflow has been red on main for 40+ consecutive runs. This
commit recovers every failure visible in run 25130722163 (most recent
completed run prior to this PR).
Root causes, by group:
Test-mock drift after product landed (fix: update mocks)
- test_mcp_structured_content / test_mcp_dynamic_discovery (6 tests):
product added _rpc_lock (#02ae15222) and _schedule_tools_refresh
(#1350d12b0) without updating sibling test files. Install a real
asyncio.Lock inside the fake run-loop and patch at _schedule_tools_refresh.
- test_session.py: renamed normalize_whatsapp_identifier → canonical_
whatsapp_identifier upstream; keep a local alias so the legacy tests
keep working.
- test_run_progress_topics Slack DM test: PR #8006 made Slack default
tool_progress=off; explicitly set it to 'all' in the test fixture so
the progress-callback path still runs. Also read tool_progress_callback
at call time rather than freezing it in FakeAgent.__init__ — production
assigns it AFTER construction.
- test_tui_gateway_server session-create/close race: session.create now
defers _start_agent_build behind a 50ms timer — wait for the build
thread to enter _make_agent before closing, otherwise the orphan-
cleanup path never runs.
- test_protocol session.resume: product get_messages_as_conversation now
takes include_ancestors kwarg; accept **_kwargs in the test stub.
- test_copilot_acp_client redaction: redactor is OFF by default (snapshots
HERMES_REDACT_SECRETS at import); patch agent.redact._REDACT_ENABLED=True
for the duration of the test.
- test_minimax_provider: after #17171, dots in non-Anthropic model names
stay dots even with preserve_dots=False. Assert the new invariant
rather than the old 'broken for MiniMax' behavior.
- test_update_autostash: updater now scans `ps -A` for dashboard PIDs;
the test's catch-all subprocess.run stub needed stdout/stderr fields.
- test_accretion_caps: read_timestamps dict is populated lazily when
os.path.getmtime succeeds. Use .get("read_timestamps", {}) to tolerate
CI filesystems where the stat races file creation.
Change-detector tests (fix: rewrite as structural invariants)
- test_credential_sources_registry_has_expected_steps: was a frozen set
comparison that broke when minimax-oauth was added. Rewrite as an
invariant check (every step has description, no dupes, core steps
present) per AGENTS.md 'don't write change-detector tests'.
xdist ordering / test pollution (fix: reset state, use module-local patches)
- test_setup vercel: sibling test saved VERCEL_PROJECT_ID='project' to
os.environ via save_env_value() and never cleared it. monkeypatch.delenv
the VERCEL_* vars in the link-file test.
- test_clipboard TestIsWsl: GitHub Actions is on Azure VMs whose real
/proc/version often contains 'microsoft'. Patching builtins.open with
mock_open didn't reliably intercept hermes_constants.is_wsl's call in
xdist workers that had already cached _wsl_detected=True from an
earlier test. Patch hermes_constants.open directly and add
teardown_method to reset the cache after each test.
Pytest-asyncio cancellation hangs (fix: bound product await with timeout)
- test_session_split_brain_11016 (3 params) + test_gateway_shutdown
cancel-inflight: under pytest-asyncio 1.3.0, 'await task' and
'asyncio.gather(cancelled_tasks)' can stall for 30s when the cancelled
task's finally block awaits typing-task cleanup. Bound both with
asyncio.wait_for(..., timeout=5.0) and asyncio.shield — the stragglers
are released from adapter tracking and allowed to finish unwinding in
the background. This is also a legitimate hardening: a wedged finally
shouldn't stall the caller's dispatch or a gateway shutdown.
Orphan UI config (fix: merge tiny tab into messaging category)
- test_web_server test_no_single_field_categories: the telegram.reactions
config field lived in its own 'telegram' schema category with no
siblings. Fold it under 'discord' via _CATEGORY_MERGE so the dashboard
doesn't render an orphan single-field tab.
Local verification: 38/38 originally-failing tests pass; 4044/4044
gateway tests pass; 684/684 targeted subset (all 16 touched test files)
passes.
Detect leaked SGR mouse-report fragments in CLI input, strip them, and reset terminal modes in-place so scroll and typing recover without reopening the tab. Add regression tests for escaped, visible, and bare leak forms.
* fix(tui): offload manual compaction RPC
Route TUI session compression through the existing long-handler pool so slow compaction does not block other gateway RPCs.
* fix(tui): show compaction progress immediately
Print a local status line before the compress RPC starts so slow manual compaction does not look like a no-op.
* feat(tui): rich /compress feedback parity with CLI
Show pre-compaction message count and rough token estimate immediately, emit a status update so the bottom bar reflects ongoing compaction, and report a multi-line summary (headline + token delta + optional note) using the shared summarize_manual_compression helper.
* fix(tui): show live compaction estimate in transcript
Mirror compression progress status into the transcript so users see the backend message count and token estimate while /compress is still running.
* fix(tui): single live compaction line with spinner glyph
Drop the redundant local "compressing context..." placeholder and prefix the live backend status line with a braille spinner glyph so /compress reads as a single in-progress row.
* fix(tui): address review nits on /compress feedback
Reuse the precomputed token estimate inside _compress_session_history so the gateway does not redo the O(n) work while holding history_lock, keep the status bar pinned during long manual compactions instead of auto-restoring after 4s, and drop the redundant noop bullet that doubled with the system role glyph.
* fix(tui): release history_lock during compaction LLM call
Move the snapshot/commit pattern into _compress_session_history so the lock is held only across the in-memory bookkeeping, not during agent._compress_context. Also emit a final neutral status update from session.compress so the pinned compressing indicator clears even on errors.
* fix(tui): rebuild prompt cleanly + sync session_key after compress
Pass system_message=None so AIAgent._compress_context rebuilds the system prompt without nesting the cached identity block. Reuse the handler's pre-snapshotted history inside _compress_session_history to avoid a second O(n) copy under the lock. After compaction, when AIAgent._compress_context rotates session_id, sync the gateway session_key, migrate approval notify + yolo state, restart the slash worker, and clear the stale pending title. Mirrors HermesCLI._manual_compress.
* Avoid /compress lock re-entry in slash side effects.
Stop pre-locking history before _compress_session_history in slash command mirroring, keep session-key sync parity with manual compression, and add a regression test that asserts /compress is invoked without holding history_lock.
* fix(tui): honor launch toolsets
Carry chat --toolsets through the TUI launcher so TUI sessions use the same per-session tool scope as the classic CLI.
* fix(tui): parse top-level toolsets flag
Allow top-level hermes --tui --toolsets to reach the implicit chat session, matching chat subcommand behavior.
* fix(tui): validate launch toolsets
Filter invalid HERMES_TUI_TOOLSETS entries and fall back to configured CLI toolsets when the override contains no valid toolsets.
* fix(tui): avoid config load for builtin toolsets
Honor built-in HERMES_TUI_TOOLSETS values before loading config and treat all/* as the all-toolsets sentinel.
* fix(cli): honor toolsets in oneshot mode
Forward top-level --toolsets into oneshot agent construction so the flag is not silently ignored outside the TUI path.
* fix(cli): validate oneshot toolsets
Reject invalid-only oneshot toolset overrides before output redirection and clarify TUI fallback warnings.
* fix(cli): preserve all-toolsets sentinel
Map explicit all/* oneshot toolset overrides to the all-toolsets sentinel and replace locals() checks in TUI toolset loading.
* fix(cli): warn on extra all-toolset entries
Warn when all/* toolset overrides include additional ignored entries so typos are still visible.
* fix(tui): honor plugin toolset overrides
Discover plugin toolsets before rejecting unresolved explicit toolset overrides and read raw config for MCP name validation.
* fix(tui): reuse toolset argument normalizer
Share top-level TUI toolset argument parsing with the oneshot path to avoid duplicate normalization logic.
* fix(cli): reject disabled mcp toolsets
Validate explicit toolset overrides against enabled MCP servers only and clarify top-level toolset flag help.
* fix(cli): distinguish disabled mcp from unknown toolsets
Report disabled MCP servers separately from unknown toolset entries and stub plugin discovery in invalid-name tests for determinism.
shutil.copytree from default ~/.hermes duplicated ~/.hermes/profiles into
the new profile, causing nested profiles/.../profiles/... and huge disk use.
Match export behavior (_DEFAULT_EXPORT_EXCLUDE_ROOT) by ignoring the sibling
profiles tree at the source root.
Made-with: Cursor
The skip_pre_tool_call_hook flag was added to prevent double-firing of
pre_tool_call when run_agent._invoke_tool pre-checks for a block
directive and then dispatches via handle_function_call. But the
implementation added an else: branch that fired invoke_hook again for
'observers', without noticing that get_pre_tool_call_block_message() in
hermes_cli.plugins already fires invoke_hook('pre_tool_call', ...) as
part of its block-directive poll.
Result: every tool call ran through the run_agent loop fired the hook
twice — reported by community users whose observer / audit plugins
logged each tool invocation twice with identical timestamps.
Fix: delete the else: branch. The single-fire contract is now:
- skip=False (direct handle_function_call): hook fires once inside
get_pre_tool_call_block_message().
- skip=True (run_agent._invoke_tool path): caller fires the hook
once via get_pre_tool_call_block_message(); handle_function_call
must not fire it again.
Tightened the existing skip-flag test (renamed to
test_skip_flag_prevents_double_fire) to assert pre_tool_call fires
zero times when skip=True, and added
test_run_agent_pattern_fires_pre_tool_call_exactly_once to lock in
end-to-end that the full block-check + dispatch sequence fires the
hook exactly once.
Extend curator's pin flag from 'skip auto-transitions' to 'no agent
edits at all'. All five skill_manage mutation actions (edit, patch,
delete, write_file, remove_file) now refuse pinned skills with a
message pointing the user at `hermes curator unpin <name>`.
Motivation: pin used to only stop the curator's own maintenance pass
from touching a skill. Nothing prevented the main agent from editing
or deleting a pinned skill via skill_manage in-session. This gives
users a hard fence against unwanted agent edits — same semantics as
curator pinning, extended to the write tool.
Create is unaffected (you can't pin a name that doesn't exist yet,
and name collisions already error out). Broken sidecars fail open
rather than lock the agent out.
The schema description advertises the new refusal so models know
not to route around it with rename/recreate tricks.
compute_next_run() ignored the last_run_at parameter for cron-type
schedules, always computing from _hermes_now() instead. This was
inconsistent with interval jobs which DO use last_run_at as the anchor.
After a crash or restart, cron jobs would compute next_run_at from
the arbitrary restart time rather than the actual last execution time.
While the stale detection in get_due_jobs() catches most cases, using
last_run_at as the croniter base eliminates edge cases and makes the
behavior consistent across schedule types.
Salvaged from #9014 (authored by @beenherebefore) onto current main.
The original PR branch was 2+ weeks stale and would have reverted
substantial unrelated work (jobs_file_lock, workdir/context_from/
enabled_toolsets, issue #16265 state=error recovery). Kept just the
7-line substantive fix and the regression test.
Bare `float(os.getenv("HERMES_CRON_TIMEOUT", 600))` in `run_job()` raises
a `ValueError` when the env var is set to a non-numeric string (e.g. "abc").
Replace it with the same defensive try/except pattern already used by
`_get_script_timeout()` for `HERMES_CRON_SCRIPT_TIMEOUT`: log a warning
and fall back to the 600 s default instead of crashing.
Also update the existing env-var tests to exercise the new code path and
add two new tests — one for an invalid value, one for an empty string.
Fixes#11319
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Closes#4759, closes#4381.
Mutating actions (patch, edit, write_file, remove_file, delete) used to
refuse skills that lived under `skills.external_dirs` with 'Skill X is in
an external directory and cannot be modified. Copy it to your local skills
directory first.' Faced with that error, the agent would fall back to
action='create', which always writes under ~/.hermes/skills/ — producing
a silent duplicate of the external skill in the local store.
Fix: drop the read-only gate. `skills.external_dirs` is configured by the
user; if they pointed it at a directory, they already said 'these are my
skills, treat them the same.' Filesystem permissions handle the genuine
read-only case (write fails, agent sees the error).
- New _containing_skills_root() resolves whichever dir actually contains
the skill; _delete_skill uses it to bound empty-category cleanup so an
external root is never rmdir'd.
- _create_skill behavior is unchanged: new skills still land in local
SKILLS_DIR only. Fewer moving parts.
- Seven new TestExternalSkillMutations tests covering patch/edit/write_file/
remove_file/delete/create against a mocked two-root layout + a category
rmdir-safety check.
When a user authenticates a built-in provider via env var (e.g. DASHSCOPE_API_KEY
triggers the built-in 'alibaba' row) AND defines a custom_providers entry
pointing at the same endpoint, the picker previously emitted two rows for one
endpoint. The built-in row already carries the canonical slug, curated model
list, and correct auth wiring, so the shadow custom entry is redundant.
Adds a _builtin_endpoints set populated as sections 1/2/2b emit rows. Each
entry is the provider's effective base URL (env override via base_url_env_var
wins over the static inference_base_url, so DASHSCOPE_BASE_URL-overridden
endpoints dedup correctly). Section 4 skips any grouped custom entry whose
base_url matches.
Intentionally does NOT repurpose model_catalog.enabled as a 'hide built-ins'
flag. That config controls the remote curated-manifest fetch (documented on
the model-catalog reference page) and overloading it would silently change
behavior for users who disable it for network/privacy reasons.
Three new tests:
- shadow dedup fires when endpoint matches static inference_base_url
- dedup does NOT hide custom entries on genuinely distinct endpoints
- dedup honors the base_url_env_var override path
Covers the #16748 fix:
- unsigned thinking blocks synthesised from reasoning_content survive replay
- non-latest assistant turns keep their thinking (DeepSeek validates every turn)
- signed Anthropic blocks are stripped (DeepSeek can't validate them)
- cache_control is stripped from thinking blocks
- OpenAI-compat base (api.deepseek.com without /anthropic) is NOT matched
- non-DeepSeek third parties (minimax) keep the generic strip-all behaviour
Follow-up to the cherry-picked PR #17447. The original flush spawned a
bare threading.Thread for the buffer-flush path, overwriting
self._sync_thread — which is aliased to the long-lived writer thread.
Two consequences:
1. No serialization with the writer queue. If old-session retains were
still queued in _retain_queue, the flush ran concurrently with the
writer and both threads could call aretain_batch against the same
document_id.
2. The pre-spawn 'self._sync_thread.join(timeout=5.0)' tried to join the
long-lived writer, which never exits, so the join was a no-op that
just timed out — never actually serialized anything.
Fix: enqueue the flush closure on _retain_queue via _ensure_writer +
put(). Natural FIFO ordering behind any pending retains, no new thread,
no broken join. Shutdown-aware so it doesn't enqueue after teardown.
Tests updated to drain via _retain_queue.join() instead of the stale
_sync_thread.join(). Added regression guard
test_flush_serializes_behind_pending_retains_via_writer_queue that
blocks the writer mid-retain to prove the flush waits in FIFO behind
the old retain.
Also seeds _retain_queue / _shutting_down / stubbed _ensure_writer on
the bare-object test helper in test_memory_session_switch.py so that
path doesn't blow up under the new queue-enqueue.
tests/plugins/memory/test_hindsight_provider.py + tests/agent/test_memory_session_switch.py: 103/103 passing.
Two data-loss / leak gaps in HindsightMemoryProvider.on_session_switch
introduced by #17409.
1. Buffered turns silently lost when retain_every_n_turns > 1.
on_session_switch unconditionally cleared _session_turns without
flushing. Users who batched every N>1 turns and switched mid-batch
(/reset, /new, /resume, /branch, or context compression) had those
buffered turns disappear. Same data-loss class as the shutdown race,
different lifecycle event.
Note commit_memory_session() -> on_session_end() runs *before*
on_session_switch on /reset, but Hindsight doesn't implement
on_session_end so the buffer survives that step and dies at clear
time. /resume, /branch, and compression skip commit_memory_session
entirely so an on_session_end impl wouldn't help them anyway.
Fix: snapshot the old _session_id, _document_id, _parent_session_id,
_turn_index, and _session_turns; spawn one final retain that lands
under the OLD document_id; then rotate state. Metadata is built
synchronously against the old self._* so session_id / lineage tags
on the flushed item all reference the prior session consistently.
2. Stale _prefetch_result leaks across switch.
If queue_prefetch ran in the old session and the result hadn't been
consumed by prefetch() yet, on_session_switch left the cached recall
text in place. The next session's first prefetch() call would return
text mined from the prior session's bank/query.
Fix: join any in-flight _prefetch_thread (3s bounded — matches
shutdown()), then clear _prefetch_result under _prefetch_lock before
rotating session_id.
Tests
-----
- tests/plugins/memory/test_hindsight_provider.py (TestSessionSwitchBufferFlush):
- buffered turns flushed under OLD document_id with OLD lineage tags
- empty buffer => no spurious retain
- _prefetch_result cleared on switch
- in-flight prefetch thread is awaited before clear (no race)
- tests/agent/test_memory_session_switch.py: factory extended to seed the
attrs the new flush path reads (_retain_source, _platform, _bank_id,
prefetch state, etc.) and stub _run_hindsight_operation so existing
switch-state assertions keep passing without network setup.
The ~/.openclaw/ detection banner (#16327) had two problems flagged in #16629:
1. It only pitched 'hermes claw cleanup' (destructive archive) and never
mentioned 'hermes claw migrate' — the actual non-destructive path that
ports config/memory/skills into Hermes.
2. The copy anthropomorphized the bug ('the agent can still get confused',
'dutifully reads') and framed OpenClaw as a competitor to eliminate
('instead of Hermes's').
Rewrite so migrate leads, cleanup is a clearly-labelled follow-up with a
warning that archiving breaks OpenClaw for users still running it.
Closes#16629
Address Copilot review on PR #16666:
1. **Duplicate event on every tool start** — both ``tool_progress_callback``
and ``tool_start_callback`` fire side-by-side in ``run_agent.py``, so
wiring both into chat completions emitted *two* ``hermes.tool.progress``
events per real tool call. Drop the legacy ``_on_tool_progress`` emit
entirely; ``_on_tool_start`` now produces a single unified event that
carries the legacy ``tool``/``emoji``/``label`` fields plus the new
``toolCallId``/``status`` correlation fields. Label is computed inline
via ``build_tool_preview`` so callers do not need to pre-format it.
2. **Weak per-event correlation in the regression test** — the previous
assertion checked that a ``toolCallId`` appeared *somewhere* in the
aggregate, which would have passed even if ``running`` lacked the id.
Collect ``(status, toolCallId)`` per event and assert each event
carries the correct pair, plus exactly two events on the wire (no
silent duplication regression).
The two existing chat-completions tool-progress tests are updated to fire
``tool_start_callback`` instead of ``tool_progress_callback``, matching
production reality where ``run_agent`` always pairs them.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds Vercel Sandbox as a supported Hermes terminal backend alongside
existing providers (Local, Docker, Modal, SSH, Daytona, Singularity).
Uses the Vercel Python SDK to create/manage cloud microVMs, supports
snapshot-based filesystem persistence keyed by task_id, and integrates
with the existing BaseEnvironment shell contract and FileSyncManager
for credential/skill syncing.
Based on #17127 by @scotttrinh, cherry-picked onto current main.
Adds two API server endpoints for external UIs and orchestrators:
- GET /v1/capabilities — machine-readable feature discovery so clients
can detect which Runs API / SSE / auth features this Hermes version
supports before depending on them.
- GET /v1/runs/{run_id} — pollable run status so dashboards can check
queued/running/completed/failed/cancelled/stopping state without
holding an SSE connection open.
Also moves request validation ahead of run allocation so invalid
payloads no longer leave orphaned entries in _run_streams waiting for
the TTL sweep.
task_id is intentionally kept as "default" for the Runs API to
preserve the shared-sandbox model used by CLI, gateway, and the
existing _run_agent_with_callbacks path. session_id is surfaced in
run status for external-UI correlation only.
Salvage of PR #17085 by @Magaav.
The guard that drops Anthropic's `thinking` kwarg for Kimi endpoints was
matched on `https://api.kimi.com/coding` only. Users configuring a
custom Kimi-compatible gateway (or an official Moonshot host) with
`api_mode: anthropic_messages` fall through to the generic third-party
path, which strips thinking blocks AND still sends
`thinking={enabled,...}` → upstream rejects with HTTP 400
"reasoning_content is missing in assistant tool call message at index N"
on the next request after a tool call.
Replace `_is_kimi_coding_endpoint` callers (history replay + thinking
kwarg gate) with `_is_kimi_family_endpoint(base_url, model)` that also
matches the `api.kimi.com` / `moonshot.ai` / `moonshot.cn` hosts and
Kimi/Moonshot family model names (`kimi-`, `moonshot-`, `k1.`, `k2.`,
…) for custom / proxied endpoints. Keeps the UA-header check in
`build_anthropic_client` URL-only — the `claude-code/0.1.0` header is
an official-Kimi contract.
Plumbs optional `model` through `convert_messages_to_anthropic` so
the unsigned reasoning_content→thinking block synthesised for Kimi's
history validation survives the third-party signature-stripping pass
on custom hosts too.
Closes#17057.
The cron schema contracts deliver as a string ("local", "origin",
"telegram", "telegram:chat_id[:thread_id]", or comma-separated combos),
but MCP clients and scripts sometimes pass an array like ['telegram'].
Before this change, the list was written to jobs.json verbatim, and
the scheduler's str(deliver).split(',') then tried to resolve the
literal string "['telegram']" as a platform — returning None and
logging 'no delivery target resolved for deliver=[\'telegram\']'.
Fix on both ends:
- tools/cronjob_tools.py: normalize deliver at the API boundary on
create and update, so storage is always a string.
- cron/scheduler.py: normalize deliver in _resolve_delivery_targets,
so existing jobs.json entries with list-form deliver are handled
gracefully without requiring users to edit the file.
Closes#17139
The plugin used to spawn one daemon thread per sync_turn() to do the
aretain_batch network write. On CLI exit, that pattern raced interpreter
shutdown — the last retain could reach aiohttp after asyncio's
"cannot schedule new futures" guard had fired, producing noisy logs and
silently losing the final unsaved turn:
WARNING ... Hindsight sync failed: cannot schedule new futures after
interpreter shutdown
ERROR asyncio: Unclosed client session
client_session: <aiohttp.client.ClientSession object at 0x...>
Switch to a single-writer model: each provider owns one long-lived
writer thread plus a queue. sync_turn() snapshots state and enqueues a
job; the writer drains sequentially. Once shutdown() is called:
- new sync_turn() / queue_prefetch() calls are dropped, not enqueued
- a sentinel wakes the writer so it finishes in-flight work
- shutdown joins the writer (10s) before nulling the client
Also register an idempotent atexit hook from the first sync_turn(), so
exit paths that don't go through MemoryManager.shutdown_all() (Ctrl-C,
abrupt exit) still get a chance to drain.
Tests: keep _sync_thread as a legacy alias to the writer, swap join()
calls to _retain_queue.join() (canonical wait-for-drain), add a new
TestShutdownRace suite covering single-writer reuse, post-shutdown drop,
queue draining, and shutdown idempotency.
Two fix-ups for #17123:
1. Reword the inline comment in `_warn_stale_dashboard_processes` to
accurately describe the failure mode (locale-dependent decoder, not a
"default UTF-8 decoder") and identify `errors="ignore"` as the
load-bearing protection. Per Copilot's review.
2. Switch `TestWindowsWmicEncoding` from `patch("hermes_cli.main.sys")`
to `monkeypatch.setattr(sys, "platform", "win32")` — the codebase's
canonical pattern (e.g. `tests/hermes_cli/test_auth_ssl_macos.py`).
The MagicMock-replacement approach passed locally on Python 3.12 but
the platform-equality check failed under CI's xdist+Python 3.11,
leaving both new tests red despite the fix being present.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`hermes update` calls `_warn_stale_dashboard_processes()` to warn about
dashboard processes still running the pre-update Python backend. On
Windows, that scan shells out to `wmic process get ProcessId,CommandLine
/FORMAT:LIST` with `text=True` and no explicit encoding.
`wmic` emits text in the system code page (e.g. cp936 on zh-CN locales),
not UTF-8. Without an explicit `encoding=`, Python's default UTF-8
decoder crashes the subprocess reader thread with
`UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd0 ...`. In
Python 3.11 that crash is silently absorbed: `subprocess.run()` returns
a `CompletedProcess` with `result.stdout = None`, the next line calls
`result.stdout.split("\n")`, and `hermes update` aborts with the
exact `AttributeError: 'NoneType' object has no attribute 'split'`
trace reported in #17049.
Fix: pass `encoding="utf-8", errors="ignore"` so undecodable bytes
cannot take down the reader thread (the parsing only matches the ASCII
prefixes `CommandLine=` and `ProcessId=`, so dropping non-UTF-8 bytes
is safe), and short-circuit when `result.stdout is None` as a defensive
guard for environments where the reader thread still fails for other
reasons.
This is the same root cause as #17074 (which patches
`hermes_cli/gateway._scan_gateway_pids` for the `hermes setup` path).
That PR does not touch `_warn_stale_dashboard_processes`, so
`hermes update` remains broken on the same locales until this lands.
Regression test in `tests/hermes_cli/test_update_stale_dashboard.py`:
- `test_wmic_invoked_with_utf8_ignore_errors` asserts the explicit
encoding/errors kwargs reach `subprocess.run`.
- `test_wmic_returns_none_stdout_does_not_crash` simulates the
reader-thread-crashed `result.stdout=None` aftermath and asserts the
function returns silently instead of raising AttributeError.
Both new tests fail against clean origin/main (7d4648461) reproducing
the original AttributeError; both pass with this patch. The remaining
3 failures in `tests/hermes_cli/test_cmd_update.py` and
`test_update_autostash.py` are pre-existing baselines on origin/main —
they reproduce identically without this change and are unrelated to
the wmic scan.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Widen #17163 to the sibling file tools/transcription_tools.py, which had
the same class of bug. STT provider call sites and the _get_provider
selection gate called os.getenv(...) directly and missed keys that only
lived in ~/.hermes/.env.
Same pattern as tts_tool.py: one guarded top-level import of
get_env_value (falls back to os.getenv on ImportError), then every
API-key and paired-base-URL lookup swapped over.
Call sites migrated:
- _transcribe_groq — GROQ_API_KEY
- _transcribe_mistral — MISTRAL_API_KEY
- _transcribe_xai — XAI_API_KEY, XAI_STT_BASE_URL
- _get_provider — GROQ/MISTRAL/XAI_API_KEY in explicit + auto branches
Module-level defaults (DEFAULT_STT_MODEL, GROQ_BASE_URL, etc.) stay on
os.getenv — they're import-time constants, not runtime config, and the
dotenv fallback would add no value there.
New regression tests in tests/tools/test_transcription_dotenv_fallback.py
(8 cases) mirror briandevans' TTS tests: per-provider dotenv-key
forwarding, selection-gate dotenv visibility, and an end-to-end probe
that patches hermes_cli.config.load_env to simulate ~/.hermes/.env
carrying the key while os.environ does not.
Wrap the new top-level `from hermes_cli.config import get_env_value`
in try/except ImportError and fall back to a thin os.getenv shim, so
importing tools.tts_tool keeps working in environments where
hermes_cli.config is unavailable. This matches the existing tolerance
in `_load_tts_config()` (tools/tts_tool.py) and the same
import-fallback pattern in tools/tool_backend_helpers.py::fal_key_is_configured.
Also update the TestDotenvFallbackPerProvider docstring to accurately
describe the mocking strategy: per-provider tests patch
`tools.tts_tool.get_env_value` directly, while the regression-guard
tests cover the lower-level `hermes_cli.config.load_env` integration.
Addresses Copilot review on #17163.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
TTS provider tools (elevenlabs, xai, minimax, mistral, gemini) called
os.getenv("X_API_KEY") directly, which bypassed Hermes's dotenv bridge in
hermes_cli.config. Users who keep their TTS keys only in ~/.hermes/.env saw
"X_API_KEY not set" errors even though the rest of the stack
(agent/credential_pool, hermes_cli/auth) already resolves keys through
get_env_value() — same class of bug as #15914 fixed for those modules.
Switch every TTS env-var lookup (API keys, base URLs, and
check_tts_requirements gates) to get_env_value, which checks os.environ
first and then ~/.hermes/.env. Behaviour for users with keys exported in
the shell is unchanged; users with dotenv-only keys now succeed. The two
diagnostics prints in __main__ are migrated for consistency.
Regression test (tests/tools/test_tts_dotenv_fallback.py):
- per-provider: each backend reads the dotenv key when only
~/.hermes/.env carries it (5 providers).
- end-to-end: with hermes_cli.config.load_env returning the key and
os.environ empty, _generate_minimax_tts and check_tts_requirements
both succeed; reverting tools/tts_tool.py back to os.getenv makes all
7 tests fail with "MINIMAX_API_KEY not set" / similar.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs(anthropic): correct OAuth scope to Max plan + extra usage credits only
The previous docs pass (#17399) overstated what Anthropic OAuth works
with. In practice Hermes can only route against a Claude Max plan that
has purchased extra usage credits — the base Max allowance is not
consumed, and Claude Pro is not supported at all. Without Max + extra
credits, users must fall back to an ANTHROPIC_API_KEY (pay-per-token).
Updates the four pages touched in #17399:
- integrations/providers.md
- user-guide/features/credential-pools.md
- reference/environment-variables.md
- getting-started/quickstart.md
* fix(aux): skip kimi-coding in vision auto-detect (closes#17076)
Kimi Coding Plan's /coding endpoint (Anthropic Messages wire) has no
image_in capability — Kimi's own docs confirm and suggest switching to
a vision-capable model. Vision lives on the separate Kimi Platform
(api.moonshot.ai, OpenAI-wire, pay-as-you-go). When the user has
kimi-coding as main provider and auxiliary.vision.provider=auto,
resolve_vision_provider_client was handing back an AnthropicAuxiliaryClient
wrapped around /coding which 404'd on every vision request.
Add a _PROVIDERS_WITHOUT_VISION frozenset ({kimi-coding, kimi-coding-cn})
and gate the main-provider vision branch on membership. On a skip the
auto-detect falls through to OpenRouter → Nous like any other
main-provider-unavailable case.
Explicit per-task overrides (auxiliary.vision.provider=kimi-coding) are
unaffected — the skip only applies when the caller is in auto mode.
Tests: 4 new targeted tests in TestVisionAutoSkipsKimiCoding covering
the skip path, CN variant, explicit-override passthrough, and a guard
against accidental skip-list widening.
Regression test for the ret=-2 / errmsg='unknown error' disambiguation:
- ret=-2 or errcode=-2 with 'unknown error' → stale session (True)
- ret=-2 with 'freq limit' or other errmsg → rate limit (False)
- ret=-14 → not matched here (handled by SESSION_EXPIRED_ERRCODE path)
- Success codes and missing errmsg → False
_run_async() bridges sync tool handlers to async code. When the handler
is invoked from inside a running event loop (gateway / nested async),
it spawns a worker thread and blocks on future.result(timeout=300).
Before this change, a coroutine that ran past 300s leaked its worker
thread:
- future.cancel() is a no-op on a running ThreadPoolExecutor future
(cancel only works on not-yet-started work).
- pool.shutdown(wait=False, cancel_futures=True) let the caller
proceed but the worker kept running the coroutine until it
returned on its own.
Every tool timeout leaked one thread. In long-lived gateway / RL
sessions this is cumulative.
The fix replaces bare asyncio.run() with a worker wrapper that
creates its own event loop. On timeout, _run_async schedules
task.cancel() on that loop via call_soon_threadsafe, then shuts the
pool down with wait=False so the caller returns immediately. The
coroutine observes CancelledError at its next await and the worker
thread exits cleanly.
Also switches logger.error() to logger.exception() in the top-level
handle_function_call() except block so tool failures produce full
stack traces in errors.log instead of just the message.
Related: #17420 (contributor flagged the leak; the original fix used
pool.shutdown(wait=True) which would have converted the leak into a
hang — caller blocks forever on the same stuck coroutine). Credit
for identifying the leak goes to the contributor.
Co-authored-by: 0z! <162235745+0z1-ghb@users.noreply.github.com>
Wrap each adapter.connect() in asyncio.wait_for() so one platform hanging
during startup or reconnect cannot block the others. Telegram's 8-retry
connect loop (~140s worst case) previously prevented Feishu from ever
starting when Telegram was network-restricted — common for users in
regions where Telegram is blocked.
Default timeout is 30s; override via HERMES_GATEWAY_PLATFORM_CONNECT_TIMEOUT
(0 disables). Applied to both startup and the reconnect watcher so a
platform that hangs mid-retry also does not stall retries for others.
Fixes#17242
When a background terminal process spawns a descendant daemon that
inherits the stdout pipe (e.g. 'hermes update' triggering a gateway
systemctl restart), the reader thread's stdout.read() never returns EOF
and its finally: block never runs. session.exited stays False forever,
so process(action='poll') returns 'running' indefinitely even though
the direct child exited long ago.
Issue #17327: Feishu user polled 74 times over 7 minutes before killing
the gateway manually.
Fix: add _reconcile_local_exit() that checks the direct Popen.poll()
before trusting session.exited. If the direct child has exited, drain
any immediately-readable bytes non-blocking and flip session.exited.
Called from poll() and wait(). The stuck reader thread remains blocked
but is a daemon thread and gets reaped with the process.
Safe no-op for env/PTY sessions, already-exited sessions, and live
children (returns None from Popen.poll()).
Fixes#6672
Memory providers now receive on_session_switch() whenever AIAgent.session_id
rotates mid-process — /resume, /branch, /reset, /new, and context
compression. Before this, providers that cached per-session state in
initialize() (Hindsight's _session_id, _document_id, accumulated
_session_turns, _turn_counter) kept writing into the old session's
record after the agent had moved on.
MemoryProvider ABC
------------------
- New optional hook on_session_switch(new_session_id, *,
parent_session_id='', reset=False, **kwargs) with no-op default for
backward compat. reset=True signals /reset or /new — providers should
flush accumulated per-session buffers. reset=False for /resume,
/branch, compression where the logical conversation continues.
MemoryManager
-------------
- on_session_switch() fans the hook out to every registered provider.
Isolated try/except per provider — one bad provider can't block others.
- Empty/None new_session_id is a no-op to avoid corrupting provider state
during shutdown paths.
run_agent.py
------------
- _sync_external_memory_for_turn now passes session_id=self.session_id
into sync_all() and queue_prefetch_all(). Providers with defensive
session_id updates in sync_turn (Hindsight already had this at
plugins/memory/hindsight/__init__.py:1199) now actually receive the
current id.
- Compression block at ~L8884 already notified the context engine of
the rollover; now also calls
_memory_manager.on_session_switch(reason='compression').
cli.py
------
- new_session() fires reset=True, reason='new_session' so providers
flush buffers.
- _handle_resume_command fires reset=False, reason='resume' with the
previous session as parent_session_id.
- _handle_branch_command fires reset=False, reason='branch' with the
parent session_id already captured for the DB parent link.
gateway/run.py
--------------
- _handle_resume_command now evicts the cached AIAgent, mirroring
/branch and /reset. The next message rebuilds a fresh agent whose
memory provider initialize() runs with the correct session_id —
matches the pattern the gateway already uses for provider state
cross-session transitions.
Hindsight reference implementation
----------------------------------
- plugins/memory/hindsight/__init__.py adds on_session_switch that:
updates _session_id, mints a fresh _document_id (prevents
vectorize-io/hindsight#1303 overwrite), and clears _session_turns /
_turn_counter / _turn_index so in-flight batches don't flush under
the new document id. parent_session_id only overwritten when provided
(avoids clobbering on a bare switch).
Tests
-----
- tests/agent/test_memory_session_switch.py: new dedicated file. ABC
default no-op, manager fan-out, failure isolation, empty-id no-op,
session_id propagation through sync_all/queue_prefetch_all, Hindsight
state transitions for every reset/non-reset case, parent preservation.
- tests/cli/test_branch_command.py: new test verifying /branch fires
the hook with correct parent_session_id + reset=False + reason.
- tests/gateway/test_resume_command.py: new test verifying /resume
evicts the cached agent.
- tests/run_agent/test_memory_sync_interrupted.py: updated existing
assertions to account for the session_id kwarg on sync_all and
queue_prefetch_all.
E2E verified (real imports, tmp HERMES_HOME):
- /resume: session_id updates, doc_id fresh, buffers cleared, parent set
- /branch: session_id forks, parent links to original
- /new: reset=True clears accumulated state
- compression: reason='compression' propagated, lineage preserved
- Empty id: no-op, state preserved
- Legacy provider without on_session_switch: no crash
Reported by @nicoloboschi (Hindsight maintainer); related scope-widening
comment by @kidonng extending coverage to compression.
MiniMax's /anthropic endpoint documents cache_control support (0.1x read
pricing, 5-min TTL) for MiniMax-M2.7, M2.5, M2.1, M2. PR #12846 gated
third-party Anthropic-wire caching on 'claude' in model name, which left
MiniMax's own model family re-paying full input tokens every turn.
Opt in explicitly via provider id (minimax / minimax-cn) or host match
(api.minimax.io / api.minimaxi.com). Narrow allowlist mirroring the
existing Qwen/Alibaba branch below; leaves room for a capability-based
surface (ProviderConfig.supports_anthropic_cache) if a third provider
needs it.
Closes#17332
Three Signal adapter improvements that depend on the no-edit-mode
plumbing from the previous commit.
1. Native formatting (markdown -> Signal bodyRanges)
Signal renders markdown as literal characters (**bold**, `code`, #
heading), which looks broken. Added _markdown_to_signal(text) that
strips markdown syntax and emits Signal-native bodyRanges as
start:length:STYLE entries. Offsets are computed in UTF-16 code
units so non-BMP emoji stay aligned. Supports BOLD, ITALIC, STRIKE,
MONO, and headings mapped to BOLD. Fenced code and inline code are
handled; link syntax is unwrapped to visible text + URL.
Includes edge-case fixes reported previously:
- Bullet lists ("* item") no longer misidentified as italics
- URLs containing underscores no longer italicized around the dot
2. Reply-quote context
Parses dataMessage.quote on inbound messages and populates
MessageEvent.raw_message with sender + timestamp_ms. This lets the
gateway's existing [Replying to: "..."] injector (gateway/run.py)
work on Signal, matching Telegram/Matrix behavior.
3. Processing reactions
Overrides on_processing_start -> hourglass and on_processing_complete
-> checkmark via the sendReaction JSON-RPC using targetAuthor and
targetTimestamp pulled from raw_message. Uses the ProcessingOutcome
enum introduced in the previous commit.
Also sets SUPPORTS_MESSAGE_EDITING = False on SignalAdapter so the
no-edit streaming path activates.
Tests: 40+ new tests in tests/gateway/test_signal_format.py covering
markdown conversion, UTF-16 offset correctness with non-BMP emoji,
bullet-list and URL false-positive regressions, reply-quote extraction,
and reaction payload shape. Regression extensions to test_signal.py.
Every curator pass now emits a dated report directory under
`~/.hermes/logs/curator/{YYYYMMDD-HHMMSS}/` with two files:
- `run.json` — machine-readable full record (before/after snapshot,
state transitions, all tool calls, model/provider, timing, full LLM
final response untruncated, error if any)
- `REPORT.md` — human-readable markdown: model + duration header,
auto-transition counts, LLM consolidation stats, archived-this-run
list, new-skills-this-run list, state transitions, the full LLM
final summary, and a recovery footer pointing at the archive + the
`hermes curator restore` command
Reports live under `logs/curator/`, not inside `skills/` — they're
operational telemetry, not user-authored skill data, and belong
alongside `agent.log` / `gateway.log`.
Internals:
- `_run_llm_review()` now returns a dict (final, summary, model,
provider, tool_calls, error) instead of a bare truncated string so
the reporter has full fidelity
- Report writer is fully best-effort — any failure logs at DEBUG and
never breaks the curator itself. Same-second rerun gets a numeric
suffix so reports can't clobber each other
- Report path stamped into `.curator_state` as `last_report_path`
- `hermes curator status` surfaces a "last report:" line so users
can immediately open the latest run
Tests (all green):
- 7 new tests in tests/agent/test_curator_reports.py covering: report
location (logs not skills), both files written, run.json shape and
diff accuracy, markdown structure, error path still writes, state
transitions captured, same-second runs get unique dirs
- Existing test_run_review_synchronous_invokes_llm_stub updated to
stub the new dict-returning _run_llm_review signature
Live E2E: ran a synchronous pass against a 1-skill test collection
with a stubbed LLM; report written correctly, state stamped with
last_report_path, markdown human-readable, run.json machine-parseable.
Add opt-in terminal.docker_run_as_host_user config flag that passes
--user $(id -u):$(id -g) to the Docker backend so files written into
bind-mounted directories (/workspace, /root, docker_volumes entries) are
owned by the host user instead of root.
When enabled on POSIX platforms, also drops SETUID/SETGID caps since the
container no longer needs gosu/su to switch users. Falls back cleanly on
platforms without os.getuid (e.g. native Windows Docker) with a warning.
Wired through all three config.yaml -> TERMINAL_* env-var bridges:
- cli.py env_mappings (CLI + TUI startup)
- gateway/run.py _terminal_env_map (gateway / messaging platforms)
- hermes_cli/config.py _config_to_env_sync (`hermes config set`)
Also fixes docker_mount_cwd_to_workspace silently failing in gateway
mode -- it was missing from gateway/run.py's _terminal_env_map.
Adds tests/tools/test_terminal_config_env_sync.py to guard against
future drift between the three bridges (same bug class shipped twice
in one month).
Bundled Hermes image won't work with this flag since its entrypoint
expects to start as root for the usermod/gosu hermes flow; works with
the default nikolaik/python-nodejs image and plain Debian/Ubuntu.
Copy profile dashboard changes onto a fresh branch under the vincez-hms-coder account.
Includes:
- Profiles dashboard route and sidebar entry
- Profile lifecycle REST endpoints
- SOUL.md read/write support
- i18n labels and helper text updates
- Targeted profile API tests
Test plan:
- pytest tests/hermes_cli/test_web_server.py -k profile -q
- cd web && npm run build
Based on three live test runs against 346 agent-created skills on the
author's own setup (~6.5 min, opus-4.7, 86 API calls), the curator
prompt needed three sharpenings before it consistently produced real
umbrella consolidation instead of passive audit output:
**Umbrella-first framing.** The original 'decide keep/patch/archive/
consolidate' framing lets opus default to 'keep' whenever two skills
aren't byte-identical. The new prompt explicitly tells the reviewer
that pairwise distinctness is the wrong bar — the right question is
'would a human maintainer write this as N separate skills, or one
skill with N labeled subsections?' Expect 10-25 prefix clusters; merge
each into an umbrella via one of three methods.
**Three concrete consolidation methods.** (a) Merge into an existing
umbrella (patch the broadest skill, archive siblings); (b) Create a
new umbrella SKILL.md (skill_manage action=create); (c) Demote
session-specific detail into references/, templates/, or scripts/
under the umbrella via skill_manage action=write_file, then archive
the narrow sibling. This matches the support-file vocabulary the
review-prompt side already uses (PR #17213).
**Two observed bailouts pre-empted:** 'usage counters are zero so I
can't judge' (rule 4: judge on content, not use_count) and 'each has
a distinct trigger' (rule 5: pairwise distinctness is the wrong bar).
**Config-aware parent inheritance.** _run_llm_review() was building
AIAgent() without explicit provider/model, hitting an auto-resolve
path that returned empty credentials → HTTP 400 'No models provided'
against OpenRouter. Fork now inherits the user's main provider and
model (via load_config + resolve_runtime_provider) before spawning —
runs on whatever the user is currently on, OAuth-backed or
pool-backed included.
**Unbounded iteration ceiling.** max_iterations=8 was way too low for
an umbrella-build pass over hundreds of skills. A live pass takes
50-100 API calls (scanning, clustering, skill_view'ing candidates,
patching umbrellas, mv'ing siblings). Raised to 9999 — the natural
stopping criterion is 'no more clusters worth processing', not an
arbitrary tool-call budget.
**Tests updated:** test_curator_review_prompt_has_invariants accepts
DO NOT / MUST NOT and drops 'keep' from the required-verb set (the
umbrella-first prompt correctly deemphasizes 'keep' as a first-class
decision label since passive keep-everything is the failure mode
being prevented). Added test_curator_review_prompt_is_umbrella_first
asserting the umbrella framing, class-level thinking, references/
+ templates/ + scripts/ support-file mentions, and the 'use_count
is not evidence of value' pre-emption. Added
test_curator_review_prompt_offers_support_file_actions asserting
skill_manage action=create and action=write_file are both named.
**Live validation on author's setup:**
- Run 1 (old prompt): 3 archives, stopped after surveying — typical passive outcome
- Run 2 (consolidation prompt): 44 archives, 3 patches, surfaced the 50-skill mlops reorg duplicate bug but didn't umbrella
- Run 3 (this prompt): 249 archives + 18 new class-level umbrellas created, reducing agent-created skills from 346 → 118 with every archived skill's content preserved as references/ under its umbrella. Pinned skill untouched. Full report in PR description.
Weekly is closer to how skill churn actually works — most agent-created
skills don't change multiple times per day, so a daily review is pure
cost without benefit. Bumping the default to 7 days reduces aux-model
spend while still catching drift and staleness on the timescales that
matter (30d stale, 90d archive).
Changes:
- DEFAULT_INTERVAL_HOURS: 24 -> 168 (7 days)
- config.yaml default: interval_hours: 24 -> 24 * 7
- CLI status line renders as '7d' when interval is a whole-day multiple
- Test `test_old_run_eligible` decoupled from the exact default: it now
uses 2 * get_interval_hours() so future tweaks don't break it
Previous invariants only gated the primary entry points
(apply_automatic_transitions, archive_skill, CLI pin). Several paths
were unprotected:
- bump_view / bump_use / bump_patch / set_state / set_pinned wrote
usage records unconditionally, which is confusing noise in
.usage.json even though the review list filtered them out
- restore_skill did not check whether a bundled skill now shadows
the archived name
- CLI unpin was asymmetric with CLI pin — it had no gate
Fixes:
- _mutate() (the shared counter / state writer) now drops silently
when the skill is not agent-created. .usage.json never gains a
record for a bundled or hub-installed skill.
- restore_skill() refuses to restore under a name that is now
bundled or hub-installed (would shadow upstream).
- CLI unpin gate matches CLI pin.
New tests:
- 5 provenance-guard tests on skill_usage (one per mutator)
- 1 end-to-end test that hammers every mutator at a bundled skill
and a hub skill, asserts both are untouched on disk, and asserts
the sidecar stays clean
- 2 CLI tests proving pin/unpin refuse bundled skills symmetrically
64/64 tests passing (29 skill_usage + 27 curator + 8 new guards).
The LLM review prompt mentioned bespoke `archive_skill` and `pin_skill`
tools that are not registered as model tools. Swap the prompt to rely
on the real surface:
- skill_manage action=patch — for patching and consolidation
- terminal — to `mv` skill dirs into .archive/
Also drop `pin` from the model's decision list — pinning is a user
opt-out for `hermes curator pin <skill>`, not something the model
should do autonomously.
Decision list is now: keep / patch / consolidate / archive.
Tests updated: prompt-invariant test now asserts the existing tools
are referenced and that bespoke tool names do NOT appear. New test
prevents `pin` from being re-added as a model decision.
Adds the Curator — an auxiliary-model background task that periodically
reviews AGENT-CREATED skills and keeps the collection tidy: tracks usage,
transitions unused skills through active → stale → archived, and spawns
a forked AIAgent to consolidate overlaps and patch drift.
Default: enabled, inactivity-triggered (no cron daemon). Runs on CLI
startup and gateway boot when the last run is older than interval_hours
(default 24) AND the agent has been idle for min_idle_hours (default 2).
Invariants (all load-bearing):
- Never touches bundled or hub-installed skills (.bundled_manifest +
.hub/lock.json double-filter)
- Never auto-deletes — archive only. Archives are recoverable
via `hermes curator restore <skill>`
- Pinned skills bypass all auto-transitions
- Uses the aux client; never touches the main session's prompt cache
New files:
- tools/skill_usage.py — sidecar .usage.json telemetry, atomic writes,
provenance filter
- agent/curator.py — orchestrator: config, idle gating, state-machine
transitions (pure, no LLM), forked-agent review prompt
- hermes_cli/curator.py — `hermes curator {status,run,pause,resume,
pin,unpin,restore}` subcommand
- tests/tools/test_skill_usage.py — 29 tests
- tests/agent/test_curator.py — 25 tests
Modified files (surgical patches):
- tools/skills_tool.py — bump view_count on successful skill_view
- tools/skill_manager_tool.py — bump patch_count on skill_manage
patch/edit/write_file/remove_file; forget record on delete
- hermes_cli/config.py — add curator: section to DEFAULT_CONFIG
- hermes_cli/commands.py — add /curator CommandDef with subcommands
- hermes_cli/main.py — register `hermes curator` subparser via
register_cli() from hermes_cli.curator
- cli.py — /curator slash-command dispatch + startup hook
- gateway/run.py — gateway-boot hook (mirrors CLI)
Validation:
- 54 new tests across skill_usage + curator, all passing in 3s
- 346 tests across all touched files' neighbors green
- 2783 tests across hermes_cli/ + gateway/test_run_progress_topics.py green
- CLI smoke: `hermes curator status/pause/resume` work end-to-end
Companion to PR #16026 (class-first skill review prompt) — together
they form a loop: the review prompt stops near-duplicate skill creation
at the source, and the curator prunes/consolidates what still accumulates.
Refs #7816.
Commit 3c42064e made config.yaml the single source of truth for
TERMINAL_CWD, but the config bridge passes cwd values verbatim to
os.environ. When a user sets terminal.cwd: ~/ in config.yaml, the
literal string '~/'' reaches subprocess.Popen, which the kernel
rejects because it does not expand shell tilde syntax.
This patch adds three defensive layers:
1. gateway/run.py — expanduser at config bridge time so TERMINAL_CWD
is always an absolute path.
2. tools/terminal_tool.py — expanduser when reading TERMINAL_CWD in
_get_env_config(), guarding against stale or manually-set env vars.
3. tools/environments/local.py — expanduser in LocalEnvironment before
passing cwd to subprocess.Popen, the final safety net.
Includes regression tests in test_config_cwd_bridge.py for nested
terminal.cwd, top-level cwd alias, and precedence ordering.
Refs: 3c42064e
The known-key splitter in `_sanitize_env_lines` used substring matching
to find concatenated KEY=VALUE pairs. When a registered key was a suffix
of another (LM_API_KEY is a suffix of GLM_API_KEY), the shorter key's
needle would match inside the longer one, causing the sanitizer to
rewrite `GLM_API_KEY=...` as `G\nLM_API_KEY=...` and silently break
Z.AI/GLM auth (and similarly `GLM_BASE_URL` -> `G\nLM_BASE_URL`).
Drop matches whose needle range is fully contained within a longer
overlapping match. Two regression tests cover the suffix-collision case
and confirm a real concatenation that happens to start with the longer
key still splits where it should.
Fixes#17138
Classic CLI exposes ``/reload`` (re-reads ~/.hermes/.env into
``os.environ`` via ``hermes_cli.config.reload_env``) so newly added API
keys take effect without restarting the session. The TUI was missing
the parity command, so users had to Ctrl+C out and ``hermes --tui``
again whenever they added or rotated a credential.
Three small wires:
* New ``reload.env`` JSON-RPC method in ``tui_gateway/server.py`` that
delegates to ``hermes_cli.config.reload_env`` and returns the count
of vars updated.
* New ``/reload`` slash command in ``ui-tui/src/app/slash/commands/ops.ts``
matching the existing ``/reload-mcp`` pattern (native RPC, no slash
worker).
* Drop ``cli_only=True`` from the ``reload`` ``CommandDef`` in
``hermes_cli/commands.py`` so help/menus surface it in the TUI too.
``reload_env`` itself is environment-agnostic.
Same caveat as classic CLI: the *currently constructed* agent's
credential pool / provider routing does not auto-rebuild. Users who
want a brand-new credential resolution should follow with ``/new``.
Tests:
* New ``test_reload_env_rpc_calls_hermes_cli_reload_env`` confirms
RPC delegates and reports the count.
* New ``test_reload_env_rpc_surfaces_errors`` confirms exceptions are
rendered as JSON-RPC errors.
* ``createSlashHandler.test.ts`` slash-parity matrix extended with
``['/reload', 'reload.env', {}]`` so we can't regress the routing.
Validation:
scripts/run_tests.sh tests/test_tui_gateway_server.py — 92/92.
scripts/run_tests.sh tests/hermes_cli/test_commands.py — 128/128.
cd ui-tui && npm run type-check — clean; npm test --run — 390/390.
After PR #7885 (97b0cd51e) added content-side segment breaks for
natural mid-turn assistant messages, the tool-progress task in
gateway/run.py was not updated to match. progress_msg_id and
progress_lines persisted for the whole run, so after a tool batch
produced bubble B1 followed by content bubble C1, the next tool.started
kept editing the OLD bubble B1 above C1 — making the chat appear out
of order on Telegram, Discord, and Slack.
Add on_new_message callback to GatewayStreamConsumer, fired at the
four sites where a fresh content bubble lands on the platform:
- _send_or_edit first-send branch (NOT edits)
- _send_commentary
- _send_new_chunk (overflow split)
- each successful chunk of _send_fallback_final
Gateway supplies a lambda that enqueues ('__reset__',) into the
progress_queue. send_progress_messages() handles the marker in both
the main loop and the CancelledError drain path, clearing
progress_msg_id, progress_lines, and the dedup state so the next
tool.started opens a fresh bubble below the new content.
Result: each tool batch appears in chronological order below the
preceding content. When no content appears between tool batches,
tools still group in one bubble (CLI-style compactness).
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
init_session() runs a login shell bootstrap that sources profile scripts
(.bashrc, .bash_profile, etc.) before capturing pwd. If any profile
script changes the working directory, the captured cwd overwrites the
configured terminal.cwd value — so terminal commands run in the wrong
directory despite the TUI banner showing the configured path.
Add an explicit 'builtin cd' to the configured cwd in the bootstrap
script, after profile sourcing but before pwd capture, ensuring the
configured terminal.cwd is always what gets recorded.
Fixes#14044
* Reject unsupported schemes (anything outside http/https/ws/wss) in
cli.py /browser connect before probing or persisting, matching the
gateway's existing 4015 path.
* Defend gateway browser.manage against `{"url": null}` and
non-string urls: empty/null falls back to DEFAULT_BROWSER_CDP_URL,
non-string returns a 4015 instead of slipping into the generic
5031 catch via TypeError on `"://" in url`.
* Add regression tests for both null-url fallback and non-string
rejection.
* Gate `browser.progress` emit on truthy `session_id`. The TUI
prints `messages` from the response when there's no session, so
emitting events too would double-render. Now: with a session →
events stream live; without one → bundled messages only.
* Resolve `system = platform.system()` once in `_browser_connect`
and thread it through `try_launch_chrome_debug` and
`_failure_messages` → `manual_chrome_debug_command`, so the
generated hint is consistent (and tests are deterministic) on
any host.
* Add `test_browser_manage_connect_no_session_skips_progress_events`
to lock in the gating behavior.
Fixes from Copilot's two passes on PR #17238:
* Validate parsed URL once: reject missing host, invalid port, and
unsupported scheme up front so malformed inputs (e.g. http://:9222
or http://localhost:abc) don't fall through to a generic 5031.
* Tighten _is_default_local_cdp to require a discovery-style path so
ws://127.0.0.1:9222/devtools/browser/<id> is not collapsed to bare
http://127.0.0.1:9222 (which would lose the path and break the
connect).
* Move browser.manage into _LONG_HANDLERS so the up-to-10s
launch-and-retry loop runs on the RPC pool instead of blocking the
main dispatcher.
* try_launch_chrome_debug uses Windows-appropriate detach kwargs
(creationflags=DETACHED_PROCESS|CREATE_NEW_PROCESS_GROUP) instead
of POSIX-only start_new_session=True.
* manual_chrome_debug_command uses subprocess.list2cmdline on
Windows so the printed instruction is cmd.exe-compatible.
* Mirror host/port validation in cli.py /browser connect so the
classic CLI never persists an invalid BROWSER_CDP_URL.
Emit browser.progress JSON-RPC notifications during the connect work and render them in the TUI as system transcript lines, so users see the same step-by-step status the base CLI prints instead of nothing for ~1m followed by a final result.
Return CLI-style browser connect status messages from the gateway and render them in the TUI so local Chrome launch attempts are visible instead of ending in a silent delayed failure.
Detect an actual Chrome/Chromium executable before printing a manual CDP launch command, including common WSL-mounted Windows browser paths, so /browser connect does not suggest google-chrome when it is unavailable.
Share Chrome CDP launch helpers between the classic CLI and TUI so default /browser connect uses loopback consistently, retries local Chrome launch, and reports a copyable manual-start command instead of claiming a dead connection.
The background skill-review prompts (_SKILL_REVIEW_PROMPT and the **Skills**
half of _COMBINED_REVIEW_PROMPT) steered the reviewer toward passive
behavior — most passes concluded 'Nothing to save.' even when the session
produced real lessons. User-preference corrections (style, format,
legibility, verbosity) were especially lost: they were read as memory
signals only, so skills never carried the fix.
This rewrite changes the stance:
- **Active-update bias.** The reviewer now treats inaction as a missed
learning opportunity. 'Nothing to save.' remains an explicit escape
but is no longer framed as the most-common outcome.
- **User-preference corrections are first-class skill signals.** Style,
tone, format, legibility, verbosity complaints — and the actual
phrasings users use ('stop doing X', 'this is too verbose', 'I hate
when you Y', 'remember this') — now warrant patching the skill that
governs the task, not just writing to memory.
- **Loaded-skill-first preference order.** When a skill was loaded via
/skill-name or skill_view during the session, the reviewer patches
THAT one first. It was in play; it's the right place.
- **Four-step ladder: patch-loaded → patch-umbrella → support-file →
create.** Support files are explicitly enumerated as three kinds:
* references/<topic>.md — session-specific detail OR condensed
knowledge banks (quoted research, API docs excerpts, domain notes)
* templates/<name>.<ext> — starter files to copy and modify
* scripts/<name>.<ext> — statically re-runnable actions
- **Name-veto for CREATE.** New skill names MUST be class-level — no PR
numbers, error strings, codenames, library-alone names, or session
artifacts ('fix-X / debug-Y / audit-Z-today'). If the proposed name
only fits today's task, fall back to one of the patch/support-file
options.
- **Memory scope clarified.** 'who the user is and what the current
situation and state of your operations are' — MEMORY.md is
situational/state, USER.md is identity/preferences.
- **Curator handoff.** Reviewer flags overlap; the background curator
handles consolidation at scale. Single-session reviewer doesn't
attempt umbrella-rebalancing.
Tests: tests/run_agent/test_review_prompt_class_first.py upgraded to
assert the new behavioral contracts (active bias, user-correction
signals, loaded-skill-first, support-file kinds, name-veto, memory
framing, curator handoff). 17 tests, all pass.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
TUI session readiness was still laggy after the gateway-ready fixes. Profiling
session.create -> session.info showed the slow phase is background AIAgent
construction (~1.1s). A cProfile run of tui_gateway.server::_make_agent showed
model_tools/tool discovery importing tools.code_execution_tool, whose
module-level EXECUTE_CODE_SCHEMA calls _get_execution_mode(), which imported
cli.CLI_CONFIG.
That pulled the classic interactive CLI stack (prompt_toolkit/Rich and REPL
setup) into every agent startup path, including hermes --tui where it is not
used. Replace that with hermes_cli.config.read_raw_config(), which is cached and
reads only the raw code_execution section. Existing defaults still apply when
the key is absent.
Measurements on macOS Terminal.app:
- import run_agent: ~466ms -> ~347ms
- model_tools import: ~418ms -> ~272ms
- _make_agent: ~1452ms -> ~1239ms
- session.create -> session.info: ~1167ms -> ~999ms
- full hermes --tui ready p50: ~1655ms -> ~1537ms
Tests:
- scripts/run_tests.sh tests/tools/test_code_execution_modes.py tests/tools/test_code_execution.py
Validate configured providers against both Hermes runtime provider ids and
catalog-normalized provider ids. This keeps providers like ai-gateway from
being rejected after catalog resolution maps them to models.dev ids.
Keep credential checks and vendor-slug warnings anchored to the runtime id
so doctor reports actionable provider names in follow-up diagnostics.
Two amplifying optimizations to per-turn overhead in the gateway:
1. get_tool_definitions() memoization (model_tools.py)
Keyed on (frozenset(enabled), frozenset(disabled),
registry._generation, config.yaml mtime+size). Only active when
quiet_mode=True (which is every hot-path caller — gateway,
AIAgent.__init__); quiet_mode=False keeps the existing print side
effects. Cached path returns a shallow-copy list sharing read-only
schema dicts.
Measured: 7.5 ms → 0.01 ms per call (~750× speedup). Gateway
constructs fresh AIAgent per message, so this saves ~7 ms/turn before
any LLM work.
2. check_fn() TTL cache (tools/registry.py)
check_fn callables like check_terminal_requirements probe external
state (Docker daemon, Modal SDK, playwright binary). For a long-lived
process, hitting them on every get_definitions() pass was pure waste
— external state changes on human timescales. 30 s TTL so env-var
flips (hermes tools enable X) propagate within a turn or two without
explicit invalidation.
Measured: first call 7.5ms → 1.6ms (check_fn probes now dominate);
subsequent calls ~0.01ms via the upstream memoization.
Invalidation surface:
- registry._generation bumps on register/deregister/register_toolset_alias,
invalidating the memoized definitions automatically.
- config.yaml mtime in the cache key captures user-visible config edits
affecting dynamic schemas (execute_code mode, discord allowlist).
- invalidate_check_fn_cache() exposed for explicit flushes (e.g. after
hermes tools enable/disable).
- tests/conftest.py autouse fixture clears both caches before every test
so env-var monkeypatches don't see stale results.
Also fixes a regression from PR #17046 that I missed:
- tools/web_tools.py — Firecrawl was removed from module scope by the
lazy import, breaking 8 tests that patch 'tools.web_tools.Firecrawl'.
Applied the same _FirecrawlProxy pattern used in auxiliary_client/
run_agent for OpenAI (module-level proxy that looks like the class
but imports the SDK on first call/isinstance; patch() replaces the
attribute as usual).
Verified:
- 49/49 tests/tools/test_web_tools_config.py pass (was 8 failing on main)
- 68/68 tests/tools/test_homeassistant_tool.py pass (was 1 failing in
the full suite due to check_fn TTL cross-test pollution; fixed by
the autouse fixture)
- 3887/3895 tests/tools/ (8 pre-existing fails: 2 delegate, 1 mcp
dynamic discovery, 5 mcp structured content — all confirmed on main)
- 2973/2976 tests/agent/ + tests/run_agent/ (3 pre-existing fails)
- 868/868 tests/run_agent/ (excluding test_run_agent.py which has
pre-existing suite-level issues)
- Live smoke: 2 turns + /model switch + tool calls, zero errors in
agent.log session window.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
* fix(tui): honor documented mouse_tracking config key
The TUI runtime was reading display.tui_mouse while docs and user-facing
examples pointed users at display.mouse_tracking. That made persistent
mouse-disable config look like a no-op for users trying to restore native
terminal selection/copy behavior on Linux/SSH/tmux terminals.
Use display.mouse_tracking as the canonical key, keep display.tui_mouse as
a legacy fallback, and have /mouse write the documented key. Both gateway
config.get and client-side config sync now share the same precedence: the
canonical key wins, then the legacy key, then default on.
* review(copilot): align mouse tracking config coercion
- Load gateway config once before deriving display.mouse_tracking state.
- Use key-presence precedence on the TUI client too, so canonical
mouse_tracking wins over legacy tui_mouse even when the value is null.
- Treat numeric 0 as disabled on both gateway and client, matching the
existing string "0" handling.
- Widen ConfigDisplayConfig mouse fields because config.get full returns raw
YAML, not normalized booleans.
This PR groups the TUI fixes that restore macOS Terminal usability and clean up the theme/composer regressions:
- copy transcript selections on macOS drag-release so Terminal.app users can copy while mouse tracking is enabled
- copy composer selections on macOS drag-release; composer selection is internal to TextInput and does not use the global Ink selection bus
- keep IDE Cmd+C forwarding setup macOS-only, and make keybinding conflict checks respect simple when-clause overlap/negation
- force truecolor before chalk initializes (unless NO_COLOR / FORCE_COLOR / HERMES_TUI_TRUECOLOR opt-outs apply) so the default banner keeps its gold/amber/bronze gradient in Terminal.app
- move TUI surfaces onto semantic theme tokens and preserve skin prompt symbols as bare tokens with renderer-owned spacing
- render focused placeholders as dim hint text in TTY mode instead of inverse/selected-looking synthetic cursor text
* feat(tui): pluggable busy-indicator styles (kaomoji/emoji/unicode/ascii)
The status-bar `FaceTicker` rotated through wide-and-variable kaomoji
glyphs (`(｡•́︿•̀｡)`, `( ͡° ͜ʖ ͡°)`, …) every 2.5s. Real display widths range
from ~5 to ~16 columns, so the rest of the bar (cwd, ctx %, voice,
bg counter) shifted on every cycle. Padding the verb alone (#17116)
helped but didn't address the dominant jitter source — the glyph
itself.
Add four indicator styles, configurable + hot-swappable:
* `kaomoji` (default — preserves the existing vibe; verb is now
pad-stable so the only width churn left is the kaomoji itself).
* `emoji` — single 2-col emoji frame (`⚕ 🌀🤔✨🍵🔮`).
* `unicode` — `unicode-animations` braille spinner (1-col, smooth).
* `ascii` — `| / - \` (1-col, max compat).
Wires:
* `display.tui_status_indicator` in `DEFAULT_CONFIG` (default
`kaomoji`).
* New JSON-RPC `config.set/get indicator` keys, narrow allow-list.
* `applyDisplay` reads the field and patches `UiState.indicatorStyle`,
so the existing `mtime` poll picks up `~/.hermes/config.yaml` edits
within ~5s without a TUI restart.
* `/indicator [style]` slash command (alias `/indicator-style`,
subcommand completion `kaomoji|emoji|unicode|ascii`). Bare form
shows the current style; setter fires `config.set` and
optimistically `patchUiState({ indicatorStyle })` so the live TUI
swaps immediately, matching the `/skin` UX.
* `CommandDef("indicator", ..., subcommands=...)` so classic CLI
autocomplete + TUI `complete.slash` both surface it.
* `FaceTicker` decouples spinner cadence from verb cadence — the
glyph runs at the spinner's authored interval (or `FACE_TICK_MS`
for kaomoji), the verb stays on the original 2.5s cycle, and both
re-arm cleanly when style changes.
Tests:
* `normalizeIndicatorStyle` rejects unknown / non-string input.
* `applyDisplay → tui_status_indicator` covers fan-out + fallback.
* `/indicator <style>` hot-swaps `UiState.indicatorStyle` after a
successful `config.set`.
* `/indicator sparkle` rejects with the usage hint and never hits
the gateway.
* Slash-parity matrix gets `'/indicator'` → `config.get`.
Validation:
cd ui-tui && npm run type-check — clean; npm test --run — 398/398.
scripts/run_tests.sh tests/test_tui_gateway_server.py
tests/hermes_cli/test_commands.py — 220/220.
* chore(tui): drop /indicator-style alias to declutter autocomplete
* fix(tui): drop verb-width pad — /indicator handles glyph jitter directly
* fix(tui): unicode indicator style hides the verb (cleanest option)
* refactor(tui): single source of truth for INDICATOR_STYLES; cleaner error format
Round 1 Copilot review on PR #17150:
- Exported `INDICATOR_STYLES` const tuple from `interfaces.ts`;
`IndicatorStyle` union type is derived from it. `useConfigSync`
builds its validation Set from the tuple, and `session.ts` uses it
for both the usage hint and the runtime allow-list — adding/removing
a style now touches one line.
- Backend `config.set indicator` error message: switched
`sorted(allowed)` list repr to `pick one of ascii|emoji|kaomoji|unicode`
(matches the TUI usage hint), and reports the normalized `raw`
instead of the original `value`. Backend allowed tuple now has a
comment pointing back at `INDICATOR_STYLES` so the two stay aligned.
Note: kept the verb portion unpadded per design intent — fixed-width
padding was the exact UX the `/indicator` command was added to remove.
Stable width comes from the glyph; verbs cycling is part of the kawaii
aesthetic. Reply on the verb thread will explain.
* fix(tui): drop type collapse + gate verb timer + DEFAULT_INDICATOR_STYLE
Round 2 Copilot review on PR #17150:
- `tui_status_indicator?: 'ascii' | ... | string` collapses to `string`
in TS — consumers got no narrowing. Documented as plain `string` with
a comment about runtime validation via `normalizeIndicatorStyle`.
- `FaceTicker` always started a 2.5s verb interval, even for the
`unicode` style which hides the verb entirely. Now gated on
`showVerb` from `renderIndicator` — `unicode` stays calm.
Pre-emptive self-review (avoid round 3):
- Three call sites duplicated the literal `'kaomoji'` default
(uiStore, normalizeIndicatorStyle, slash command). Added
`DEFAULT_INDICATOR_STYLE` to interfaces.ts and threaded it through
so changing the default touches one line.
* fix(tui-gateway): normalize config.get indicator output to match TUI render
Round 4 Copilot review on PR #17150: `config.get` for `indicator`
returned the raw `display.tui_status_indicator` value without
validation, so a hand-edited config.yaml with stray casing or an
unknown style would leave `/indicator` printing one thing while
the TUI rendered the kaomoji default (frontend's
`normalizeIndicatorStyle` does this normalization on receive).
Lifted the allow-list to module scope as `_INDICATOR_STYLES` /
`_INDICATOR_DEFAULT`, reused by both `config.set` and `config.get`.
Comment notes the alignment with `INDICATOR_STYLES` /
`DEFAULT_INDICATOR_STYLE` in interfaces.ts so adding/removing a
style is a one-line change on each end.
Tests cover: known value verbatim, casing/whitespace normalize,
unknown→default, unset→default.
* fix(tui-gateway): preserve falsy-input diagnostics in config.set indicator error
Round 5 Copilot review on PR #17150: `raw = str(value or "").strip().lower()`
collapsed any falsy non-string (`0`, `False`, `[]`) to empty string,
so the error message read `unknown indicator: ` with nothing after —
losing the original input.
Switched to `("" if value is None else str(value)).strip().lower()`
so only `None` (the genuine 'no value' case) becomes blank. Used
`{raw!r}` in the error so the diagnostic is unambiguous (`'0'` vs `0`).
Tests:
- known-value happy path (`'EMOJI'` → `'emoji'`)
- falsy non-string inputs (`0` / `False` / `[]`) surface meaningfully
- `None` keeps the blank-repr error
* fix(tui-gateway): harden stdio transport against half-closed pipes + SIGTERM races
`tui_gateway` reports `tui_gateway_crash.log` traces where the main
thread sits in `sys.stdin` while a worker holds `_stdout_lock` mid-
flush, and SIGTERM then calls `sys.exit(0)` while the lock is still
held — the interpreter shutdown stalls behind the wedged write.
Two narrowly scoped hardenings:
**`tui_gateway/transport.py`**
* Move JSON serialisation outside the lock — long messages no longer
block sibling writers while we serialise.
* Treat `BrokenPipeError`, `ValueError` ("I/O on closed file") and
generic `OSError` from both `write` and `flush` as "peer is gone":
return `False` instead of bubbling, matching what `write_json`'s
callers in `entry.py` already expect.
* Split `flush` into its own try block so a stuck flush never strands
a partial write or holds the lock indefinitely on its way out.
* Optional `HERMES_TUI_GATEWAY_NO_FLUSH=1` env knob to skip explicit
`flush()` entirely on environments where a half-closed read pipe
produces an indefinite kernel-level block. Default unchanged.
**`tui_gateway/entry.py`**
* `_log_signal` now spawns a 1-second daemon timer that calls
`os._exit(0)` if the orderly `sys.exit(0)` path is itself stuck
behind a wedged worker. Atexit handlers run inside the grace
window when they can; the timer is the safety net so a deadlocked
flush no longer strands the gateway process.
Tests:
* `test_write_json_closed_stream_returns_false` — ValueError path.
* `test_write_json_oserror_on_flush_returns_false` — OSError on flush
must not strand the lock; the write portion still landed before the
flush failure.
* `test_write_json_no_flush_env_skips_flush` — env knob bypass.
Validation: `scripts/run_tests.sh tests/tui_gateway/test_protocol.py`
(42/42 pass; one pre-existing failure on
`test_session_resume_returns_hydrated_messages` is unrelated to this
change — same `include_ancestors` mock kwarg issue tracked elsewhere).
`scripts/run_tests.sh tests/test_tui_gateway_server.py` 90/90 pass.
* review(copilot): tighten transport hardening comments + test cleanup
* review(copilot): narrow exception capture, configurable grace, simpler no-flush test
* fix(tui-gateway): narrow ValueError to closed-stream; surface UnicodeEncodeError
Copilot review on PR #17118: `UnicodeEncodeError` is a ValueError
subclass, so a non-UTF-8 stdout (mismatched PYTHONIOENCODING / locale)
would have been silently swallowed as 'peer gone' under
`except ValueError`. That hides a real environment bug.
Now:
- UnicodeEncodeError → log with exc_info (warning) and drop the frame
- ValueError where str(e) contains 'closed file' → peer gone, return False
- Any other ValueError → log loudly, drop frame (defensive, but visible)
Same shape applied to flush. Adds two regression tests.
* fix(tui-gateway): reserve write() False for peer-gone; re-raise programming errors
Round 2 Copilot review on PR #17118: `Transport.write()` returning
`False` is documented as 'peer is gone', and `entry.py` reacts by
calling `sys.exit(0)`. But the implementation also returned False
for non-IO conditions (non-JSON-safe payloads, UnicodeEncodeError,
unrelated ValueErrors), so a programming error or local env bug would
present as a clean disconnect — exactly the diagnosis pain we wanted
to eliminate.
Now:
- `json.dumps` failure → re-raises (TypeError/ValueError surfaces in crash log)
- `BrokenPipeError` → False (peer gone)
- `ValueError('...closed file...')` → False (peer gone)
- `UnicodeEncodeError` and any other ValueError → re-raise
- `OSError` → False (existing IO-failure semantics, debug-logged)
Tests updated to assert the re-raise behaviour and added a
non-serializable-payload regression test.
* fix(tui-gateway): narrow OSError to peer-gone errnos; honest test naming
Round 3 Copilot review on PR #17118:
- Docstring claimed False = peer gone, but generic OSError on write/flush
also returned False — meaning ENOSPC/EACCES/EIO would silently exit.
Added `_PEER_GONE_ERRNOS = {EPIPE, ECONNRESET, EBADF, ESHUTDOWN, +WSA}`
and narrowed the OSError handlers; non-peer-gone errnos re-raise.
Docstring now lists OSError as peer-gone branch with the errno set.
- The `_DISABLE_FLUSH` test was named after the env var but actually
patched the module constant. Renamed it to reflect the contract being
tested (skips flush when constant is true) AND added a real
end-to-end test that sets the env var, reloads transport.py, and
asserts the constant flips. Cleanup reload restores defaults so
parallel tests stay isolated.
Self-review (avoid round 4):
- Verified TeeTransport's secondary-swallow stays intentional.
- _log_signal grace path already covered by separate tests.
* fix(tui): make /browser connect actually take effect on the live agent
Reports were that `/browser connect <url>` (and "changes to CDP url
don't get picked up") didn't propagate to the live agent in `--tui`,
forcing users to fall back to setting `browser.cdp_url` in
`config.yaml` and restarting. Tracing the path on current main shows
the protocol wiring is already correct — `/browser` is registered in
`ui-tui/src/app/slash/commands/ops.ts` and dispatches `browser.manage`
through the gateway RPC, NOT the slash worker (covered by the
`browser.manage` row in `slashParity.test.ts`). But three real gaps
left the experience flaky:
1. `cleanup_all_browsers()` ran AFTER `os.environ["BROWSER_CDP_URL"]`
was rewritten. `_ensure_cdp_supervisor(...)` reads the env to
resolve its target URL, so a tool call landing in that brief window
could re-attach the supervisor to the OLD CDP endpoint just before
we reaped sessions, leaving the agent talking to a dead URL.
Reorder to clean first, swap env, clean again so the supervisor
for the default task is definitively closed.
2. `browser.manage status` reported only the env var, ignoring
`browser.cdp_url` from config.yaml. `_get_cdp_override()` (the
resolver the agent itself uses) consults both — match it so
`/browser status` answers the same question the next
`browser_navigate` will see. Closes a stealth bug where users
saw "browser not connected" while their CDP URL was perfectly
set in config.yaml.
3. `/browser disconnect` only cleared `BROWSER_CDP_URL` and reaped
once, leaving the same swap window as connect. Symmetrical
double-cleanup here too.
Frontend (`ops.ts`):
* Echo "next browser tool call will use this CDP endpoint" on success
so users see immediate confirmation that the gateway accepted the
swap, even before any tool runs.
* Mention `browser.cdp_url` in `config.yaml` in the usage hint and
the not-connected status line. Persistent config is the correct
fix for some terminal-multiplexer / sub-agent flows where env
inheritance is unreliable; surfacing it makes that workaround
discoverable.
Tests (4 new, all hermetic):
* `status` returns the resolved URL when only `browser.cdp_url` is
set in config.yaml.
* `connect` writes env AND cleans before/after, in that order.
* `connect` against an unreachable endpoint does NOT mutate env or
reap.
* `disconnect` removes env and cleans twice.
Validation:
scripts/run_tests.sh tests/test_tui_gateway_server.py — 94/94 pass.
cd ui-tui && npm run type-check — clean; npm test --run — 389/389.
* review(copilot): always defer to _get_cdp_override; normalize bare host:port
* review(copilot): collapse discovery-style CDP paths so /json/version isn't duplicated
* fix(tui): /browser status must not perform CDP discovery I/O
Copilot review on PR #17120: previous version routed through
`tools.browser_tool._get_cdp_override`, which calls
`_resolve_cdp_override` and performs an HTTP probe to /json/version
with a multi-second timeout for discovery-style URLs. That blocks
the TUI on `/browser status` whenever the configured host is slow
or unreachable.
Status now reads env-then-config directly with no network I/O. The
WS normalization still happens in `browser_navigate` for actual
tool calls, so behaviour-on-call is unchanged.
* fix(tui): skip /json/version probe for concrete ws://devtools/browser endpoints
Round 2 Copilot review on PR #17120: hosted CDP providers (Browserbase,
browserless, etc.) return concrete `ws[s]://.../devtools/browser/<id>`
URLs which are already directly connectable but don't serve the HTTP
discovery path. The previous `/json/version` probe rejected these
valid endpoints with 'could not reach browser CDP'.
For `ws[s]://...` URLs whose path starts with `/devtools/browser/` we
now do a TCP-level reachability check (`socket.create_connection`)
instead of the HTTP probe. The actual CDP handshake happens on the
next `browser_navigate` call, so we still surface unreachable hosts
as 5031 errors — just without the false negatives.
Discovery-style URLs (`http://host:port[/json[/version]]`) keep the
HTTP probe path unchanged. Updated existing test + added two new
ones (TCP-only success, TCP unreachable → 5031).
* feat(tui): opt-in auto-resume of the most recent session
`hermes --tui` always forges a fresh session at startup unless the user
sets `HERMES_TUI_RESUME=<id>`. Disconnects, terminal-window crashes,
and accidental Ctrl+D therefore lose every piece of in-flight context
even though `state.db` still has the full history a `/resume` away.
Add an opt-in path that mirrors classic CLI's `hermes -c` muscle
memory: when `display.tui_auto_resume_recent: true` is set in
`~/.hermes/config.yaml`, the TUI looks up the most recent human-facing
session and resumes it instead of starting fresh. Default off so
existing users aren't surprised; explicit `HERMES_TUI_RESUME` always
wins.
Wires:
* New `session.most_recent` JSON-RPC in `tui_gateway/server.py` that
returns the first non-`tool` row from `list_sessions_rich`, or
`{"session_id": null}` when none. Uses the same deny-list as
`session.list` so sub-agent rows can't sneak in.
* `createGatewayEventHandler.handleReady` re-ordered: explicit
`STARTUP_RESUME_ID` first (unchanged), then conditional auto-resume
via `config.get full → display.tui_auto_resume_recent`, then the
legacy `newSession()` fallback. Failures of either RPC fall back
to `newSession()` so the path is always finite.
* Default `display.tui_auto_resume_recent: False` added to
`DEFAULT_CONFIG` in `hermes_cli/config.py` (no `_config_version`
bump per AGENTS.md — deep-merge handles the additive key).
Tests:
* 4 new vitest cases in `createGatewayEventHandler.test.ts` cover
every gate-and-fallback combination (env wins, config off, config
on with hit, config on with miss).
* 3 new pytest cases for `session.most_recent` (denied row skip,
tool-only → null, db-unavailable → null).
Validation:
scripts/run_tests.sh tests/test_tui_gateway_server.py — 93/93.
cd ui-tui && npm run type-check — clean; npm test --run — 393/393.
* review(copilot): fold session.most_recent errors into null + extend ConfigDisplayConfig
* review(copilot): cover RPC-rejection fallbacks in auto-resume tests
- Remove dead _lmstudio_loaded_context attribute from run_agent.py (set
but never read — the loaded context is pushed to context_compressor.update_model
which is the actual consumer)
- Cache empty reasoning options with 60s TTL to avoid per-turn HTTP probe
for non-reasoning LM Studio models. Non-empty results cached permanently.
- Extract _lmstudio_server_root(), _lmstudio_request_headers(), and
_lmstudio_fetch_raw_models() shared helpers in models.py — eliminates
URL-strip + auth-header + HTTP-call duplication across probe_lmstudio_models,
ensure_lmstudio_model_loaded, and lmstudio_model_reasoning_options
- Revert runtime_provider.py base_url precedence change: preserve the
established contract (saved config.base_url > env var > default) for all
api_key providers
- Remove unnecessary config version bump 22→23
- Fix TUI test: relax target_model assertion to avoid module-cache flake
- AUTHOR_MAP: added rugved@lmstudio.ai → rugvedS07
CopilotACPClient communicates via subprocess stdio and returns a plain
SimpleNamespace from _create_chat_completion(). The streaming path tries
to iterate this as a stream, crashing with:
TypeError: 'types.SimpleNamespace' object is not iterable
Mirror the existing ACP exclusion pattern (used for Responses API upgrade)
to disable streaming when provider is copilot-acp or base_url starts with
acp:// or acp+tcp://.
Based on PR #9428 by @ningfangbin and issue #16271 by @Joseph19820124.
Fixes#16271
Previously, check_browser_requirements() only checked for the agent-browser
CLI, not the Chromium binary it drives. When the CLI was present but
Chromium wasn't (common in Docker images predating the playwright install
step), the browser tool was advertised to the agent, every call hung for
the full command timeout (~30s each, ~220s for a chained navigate), and
the agent eventually gave up with no useful error — users saw 'browser
not working' with empty errors.log.
Changes:
- tools/browser_tool.py: add _chromium_installed() checking
PLAYWRIGHT_BROWSERS_PATH + default Playwright cache paths for
chromium-* / chromium_headless_shell-* dirs; wire into
check_browser_requirements() for local mode (cloud providers
unaffected). _run_browser_command fails fast with an actionable
Docker vs. host message instead of hanging. _running_in_docker()
checks /.dockerenv and /proc/1/cgroup.
- hermes_cli/tools_config.py: post_setup for 'Local Browser' now runs
'agent-browser install --with-deps' after npm install to actually
download Chromium. In Docker, points user at the updated image pull
instead of trying to install into a read-only layer. Cloud-provider
post_setup (browserbase) skips Chromium install entirely.
- tests/tools/test_browser_chromium_check.py: new tests covering
search roots, install detection, requirements branches (local/cloud/
camofox), and the fast-fail guard in docker/non-docker contexts.
- tests/tools/test_browser_homebrew_paths.py: 5 existing subprocess-path
tests now mock _chromium_installed=True since they exercise the
post-guard subprocess path.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
Auxiliary tasks (title_generation, vision, compression, web_extract,
session_search) now pick the correct wire protocol based on the
endpoint, not just on which resolve_provider_client branch built the
client. Fixes 404s on Kimi Coding Plan and any other named provider
whose endpoint speaks Anthropic Messages.
Root cause: the 'api_key' branch of resolve_provider_client (and the
Step 2 fallback chain inside _resolve_auto) always built a plain
OpenAI client regardless of what the endpoint actually spoke. For
provider=kimi-coding + model=kimi-for-coding, that meant:
POST https://api.kimi.com/coding/v1/chat/completions
{ "model": "kimi-for-coding", ... }
→ 404 resource_not_found_error
The /coding route only accepts the Anthropic Messages shape (the main
agent already uses api_mode=anthropic_messages for it). Earlier fixes
(#16819, #22ddac4b1) patched the anonymous-custom, named-custom, and
external-process branches — but the named api_key branch (kimi-coding,
minimax, zai, future /anthropic providers) was the fourth sibling and
never got the same treatment.
Fix: one module-level helper _maybe_wrap_anthropic() that rewraps a
plain OpenAI client in AnthropicAuxiliaryClient when:
- api_mode is explicitly 'anthropic_messages', OR
- the URL ends in '/anthropic', OR
- the host is api.kimi.com + path contains '/coding', OR
- the host is api.anthropic.com.
Wired into _wrap_if_needed (covers all resolve_provider_client
branches that already go through it) and into the Step 2 api_key
fallback chain inside _resolve_auto. Explicit api_mode still wins:
passing api_mode='chat_completions' forces OpenAI wire, and already-
wrapped specialized adapters (Codex, Gemini native, CopilotACP) pass
through unchanged.
E2E verified:
- resolve_provider_client('kimi-coding', 'kimi-for-coding')
→ AnthropicAuxiliaryClient (was plain OpenAI, which 404'd)
- _resolve_auto Step 1 for kimi-coding runtime → AnthropicAuxiliaryClient
- resolve_provider_client('openrouter', ...) → plain OpenAI (no regression)
- api_mode='chat_completions' override → plain OpenAI (explicit wins)
Tests:
- tests/agent/test_auxiliary_transport_autodetect.py (new): 21 tests
covering URL detection, wrap decisions, and integration.
- 204/205 existing auxiliary tests pass (1 pre-existing failure on
main, unrelated to this change).
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
Append a compact 'model · 68% · ~/projects/hermes' footer to the FINAL
message of each turn, disabled by default (display.runtime_footer.enabled).
Answers the Telegram-side parity ask: runtime context that the CLI status
bar already shows is now available in messaging replies when enabled.
Wiring:
- gateway/runtime_footer.py: resolve_footer_config + format_runtime_footer +
build_footer_line. Pure-function renderer; per-platform overrides under
display.platforms.<platform>.runtime_footer.
- gateway/run.py: appends footer to response right after reasoning prepend
so it lands only on the final message (never tool progress or streaming
chunks). When streaming already delivered the body (already_sent), the
footer is sent as a small trailing message instead.
- agent_result now exposes context_length alongside last_prompt_tokens so
the footer can compute the pct; both gateway return paths updated.
- /footer [on|off|status] slash command, wired in CLI (cli.py) and gateway
(gateway/run.py both running-agent bypass and main dispatch). Global
toggle only; per-platform overrides via config.yaml.
Graceful degradation:
- Missing context_length (unknown model) → pct field silently dropped
(no '?%' artifact).
- Empty final_response → no footer appended.
- Unknown field names in config → silently ignored.
Tests: 25-case unit suite (tests/gateway/test_runtime_footer.py) plus E2E
harness covering streaming vs non-streaming branches, per-platform override,
and the exact argument contract gateway/run.py uses.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
The contributor's PR (#16750) scoped the fix to run_setup_wizard() and
explicitly punted the two sibling sites. Both have the identical
[ -e /dev/tty ] pattern followed by a < /dev/tty redirect and crash in
Docker the same way:
- scripts/install.sh:732 install_system_packages() -- apt sudo prompt
fallback. sudo ... < /dev/tty dies with the same ENXIO.
- scripts/install.sh:1395 maybe_start_gateway() -- gateway-install gate,
same function path as the wizard reproducer.
Fix both with the same (: </dev/tty) 2>/dev/null probe, and parametrize
the regression test over all three gated functions so any future
regression is caught regardless of which site breaks.
Address the three Copilot inline findings on the regression test:
- Switch _extract_run_setup_wizard() from str.index() with hard-coded
markers (which raises ValueError if `maybe_start_gateway()` is renamed
or the marker leaks into a comment) to an anchored regex on the
function-definition + closing-brace boundaries.
- Match `[ -e /dev/tty ]` with surrounding whitespace, optional quoting,
and the `test -e /dev/tty` form so the regression guard catches every
spelling of the existence-only check, not just the exact substring.
- Replace the literal `(: </dev/tty)` substring assertion with a
higher-level invariant — the gate must be an `if`/`if !` whose test
redirects stdin from /dev/tty — so equivalent open-based probes
(`exec 3</dev/tty` + close, brace-grouped variants, etc.) keep the
test green while the bare existence check stays caught.
Verified guard: both tests still pass on the fix and both fail on
`origin/main` with the documented messages.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
In Docker builds the `/dev/tty` device node is present in the mount
namespace, so `[ -e /dev/tty ]` returns true — but opening it fails
with `ENXIO: No such device or address`. Under the old gate the
"no terminal available" skip never triggered, the setup wizard ran,
and the build aborted a few lines later when bash tried `< /dev/tty`:
/tmp/install.sh: line 1347: /dev/tty: No such device or address
Replace the existence check with `(: </dev/tty) 2>/dev/null`, which
actually attempts to open /dev/tty in a subshell. The probe succeeds
when piped from `curl | bash` on a real terminal (the wizard's intended
use case) and fails cleanly in Docker build / CI contexts so the skip
kicks in before the redirect can crash.
Add a regression test that statically asserts run_setup_wizard does not
gate on the bare existence check and that the open-based probe is in
place.
Fixes#16746.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The gateway caches one AIAgent per session to preserve prompt-cache hits,
keyed by _agent_config_signature(). The signature previously only
fingerprinted model/credentials/toolsets/ephemeral-prompt — NOT the
compression or context_length config. As a result, users who edited
model.context_length or compression.threshold in config.yaml on a
long-lived gateway saw no effect until they triggered an unrelated
cache eviction (/model switch, /reset, gateway restart).
Add a new cache_keys parameter to _agent_config_signature and a
_CACHE_BUSTING_CONFIG_KEYS registry listing config values the agent
bakes in at construction time. Call sites read the current config and
pass it through — next gateway message with an edited config
rebuilds the agent.
Keys registered:
- model.context_length
- compression.enabled
- compression.threshold
- compression.target_ratio
- compression.protect_last_n
Reported by @OP (Apr 26 feedback bundle).
## Changes
- gateway/run.py: new _CACHE_BUSTING_CONFIG_KEYS tuple,
_extract_cache_busting_config classmethod, cache_keys kwarg on
_agent_config_signature, call site passes the extracted dict
- tests/gateway/test_agent_cache.py: 11 new tests
(5 on _agent_config_signature behavior, 6 on _extract_cache_busting_config)
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
Network errors through proxies (e.g. sing-box) can leave httpx
connections in a half-closed state occupying pool slots. After enough
reconnect cycles the 256-connection default fills up entirely, causing
Pool timeout: All connections in the connection pool are occupied.
Fix: cycle only the getUpdates request object (_request[0]) via
shut-down + re-initialize before restarting polling. This drains stale
connections without touching the general request (_request[1]) that
concurrent send_message / edit_message calls rely on.
The drain is applied to both _handle_polling_network_error and
_handle_polling_conflict reconnect paths via a shared
_drain_polling_connections() helper. Failures in the drain are
swallowed so reconnect always proceeds.
Based on #16466 by @Mirac1eSky.
Auxiliary callers that configure reasoning via
auxiliary.<task>.extra_body.reasoning were having that config silently
dropped by the Codex Responses adapter — it only forwarded
messages/model/tools through to responses.stream(), never translating
chat.completions-shaped reasoning hints into the Responses API's
top-level reasoning + include fields.
Mirror the main-agent translation from agent/transports/codex.py:
- extra_body.reasoning.effort → resp_kwargs.reasoning.{effort, summary:"auto"}
- 'minimal' → 'low' clamp (Codex backend rejects 'minimal')
- Always include ['reasoning.encrypted_content'] when reasoning is enabled
- {'enabled': False} → omit reasoning and include entirely
- Non-dict reasoning values are ignored defensively
Reported by @OP (Apr 26 feedback bundle).
## Changes
- agent/auxiliary_client.py: _CodexCompletionsAdapter.create() now reads
and translates extra_body.reasoning before calling responses.stream()
- tests/agent/test_auxiliary_client.py: 9 new tests covering all effort
levels, the minimal→low clamp, the disabled path, the no-op paths,
and defensive handling of wrong-shape inputs
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
The gateway session-hygiene pre-compression safety valve had a hardcoded
400-message threshold. On long-lived sessions with short turns this was
either too high (users with aggressive compression preferences) or too
low (users with very large context models who want to keep more history
in-flight).
Add compression.hygiene_hard_message_limit (default 400) so it can be
tuned without forking the gateway.
Reported by @OP (Apr 26 feedback bundle).
## Changes
- hermes_cli/config.py: new DEFAULT_CONFIG key with 400 default
- gateway/run.py: read compression.hygiene_hard_message_limit at
hygiene-time, fall back to 400 if missing/invalid
- tests/gateway/test_session_hygiene.py: two tests — override fires at
the configured limit, default does not fire below 400
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
When openai-codex tokens expire or the ChatGPT account hits a 429
window, the pool entry gets marked STATUS_EXHAUSTED with
last_error_reset_at many hours in the future. If the user then runs
`hermes model` / `hermes auth openai-codex` to reauth, fresh tokens
land in ~/.hermes/auth.json but the pool entry stayed frozen behind
its reset_at — every request kept failing with 'credential pool: no
available entries (all exhausted or empty)' until the original window
elapsed.
_available_entries() already had auth.json/credentials-file resync
branches for anthropic/claude_code and nous/device_code; openai-codex
was missing. Added _sync_codex_entry_from_auth_store() mirroring the
nous version (reads state["tokens"][{access,refresh}_token] +
state["last_refresh"]) and wired it into the exhausted-entry resync
loop.
Also softens the 'codex CLI not found' doctor warning — native
device-code OAuth does not require the Codex binary, only
importing existing Codex CLI tokens does. Downgraded to an info line.
Reported on Discord by p1aceho1der: Codex stalled indefinitely after
a rate-limit reset, reauth didn't help, and doctor falsely warned
that the codex CLI was required.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
Gemini 3 Flash documents low/medium/high as the accepted thinkingLevel
values. The salvaged bridge was forwarding Hermes' "minimal" effort to
Flash verbatim, which is not a documented Gemini level and risks a 400
from the native adapter.
Clamp minimal->low on Flash (matching how Pro already clamps minimal+low
down), and funnel anything outside {low, medium, high} into medium to
keep the request valid by construction. No behaviour change for the
documented effort levels.
Add tests/test_cli_manual_compress.py verifying _manual_compress passes
None (not the cached system prompt) to _compress_context, forwards the
/compress <topic> focus string, rotates CLI session_id to the new child
session, and clears the pending title.
Co-authored-by: revar <revar@users.noreply.github.com>
Follow-up to PR #16802 (BeliefanX). The original fix read
`agent_history[-1].get("timestamp")` for the tool-tail freshness gate,
but `gateway/run.py` strips the `timestamp` field off all tool/tool_call
rows when building `agent_history` from the raw transcript (see
`clean_msg = {k: v for k, v in msg.items() if k != "timestamp"}`). At
runtime the tool-tail branch always saw `None` and silently took the
legacy-fresh path — the stale-guard never fired for the tool-tail case
it was supposed to cover.
Changes:
- Read the freshness signal from the RAW `history` list (via new
`_last_transcript_timestamp()` helper) BEFORE the strip. Both the
resume_pending branch and the tool-tail branch use this single signal,
replacing the two divergent ones.
- Default window bumped 15 min → 1 hour via new
`_AUTO_CONTINUE_FRESHNESS_SECS_DEFAULT`. The 15-minute default was
shorter than the default `gateway_timeout` of 30 min, so a legitimate
long-running turn interrupted near its timeout boundary and resumed
shortly after would have been misclassified as stale.
- Configurable via `config.yaml` `agent.gateway_auto_continue_freshness`
(bridged to `HERMES_AUTO_CONTINUE_FRESHNESS` at gateway startup — same
pattern as `gateway_timeout`). Set to 0 to disable the gate.
- `_coerce_gateway_timestamp` now explicitly rejects bool (which is a
subclass of int and would otherwise coerce to 0.0/1.0).
- Tests rewritten to exercise the real production data shape: raw
`history` → `_build_agent_history` strip → freshness decision. A
regression guard (`test_stale_tool_tail_with_production_data_shape`)
asserts `agent_history` tool rows carry NO timestamp, protecting
against someone "fixing" the original bug by re-adding the stripped
field (which would break the OpenAI tool-result message contract).
Add BeliefanX to scripts/release.py AUTHOR_MAP.
E2E verified: config.yaml → env var bridge → helper returns configured
value; default 1h window; malformed/empty env var falls back to default;
ISO-Z timestamps parse; ms-epoch coerced; bool rejected.
Extract the islink/realpath guard from the 16743 fix into a single
atomic_replace() helper in utils.py, then migrate every os.replace()
call site in the codebase to use it.
The original PR #16777 correctly identified and fixed the bug, but
only patched 9 of ~24 call sites. The same bug class (managed
deployments that symlink state files silently losing the link on
every write) still existed at auth.json, sessions file, gateway
config, env_loader, webhook subscriptions, debug store, model
catalog, pairing, google OAuth, nous rate guard, and more.
Rather than add another 10+ copies of the same three-line guard,
consolidate into atomic_replace(tmp, target) which:
- resolves symlinks via os.path.realpath before os.replace
- returns the resolved real path so callers can re-apply permissions
- is a drop-in replacement for os.replace at the use sites
Changes:
- utils.py: new atomic_replace() helper + atomic_json_write /
atomic_yaml_write now call it instead of inlining the guard
- 16 files: all os.replace() call sites migrated to atomic_replace()
- agent/{google_oauth, nous_rate_guard, shell_hooks}.py
- cron/jobs.py
- gateway/{pairing, session, platforms/telegram}.py
- hermes_cli/{auth, config, debug, env_loader, model_catalog, webhook}.py
- tools/{memory_tool, skill_manager_tool, skills_sync}.py
Tests: tests/test_atomic_replace_symlinks.py pins the invariant for
atomic_replace + atomic_json_write + atomic_yaml_write, covers plain
files, first-time creates, broken symlinks, and permission preservation.
Refs #16743
Builds on #16777 by @vominh1919.
Real OpenClaw configs key agents.defaults.models by full provider/model
API ID with an 'alias' field on the value (e.g.
{'anthropic/claude-opus-4-6': {'alias': 'Claude Opus 4.6'}}). Add
regression tests for issue #16745 covering:
- reverse-lookup of alias against real schema (keyed by API ID)
- alias resolution when model is a bare string vs {'primary': ...}
- passthrough when the value is already a provider/model API ID
- passthrough when the alias has no catalog match
- string-valued catalog entries (belt-and-suspenders)
- no catalog at all
25 new tests (all Bedrock API calls mocked, no real AWS creds needed):
tests/hermes_cli/test_bedrock_model_picker.py (20 tests):
- provider_model_ids("bedrock") uses live discovery, returns regional
model IDs, falls back gracefully on empty/exception, resolves all
bedrock aliases (aws, aws-bedrock, amazon-bedrock) to live discovery
- list_authenticated_providers() section 2: bedrock appears with AWS
creds, model list from discover_bedrock_models(), total_models
matches, is_current flag works, absent creds hides bedrock, discovery
failure does not crash, no duplicate entries
- Region routing: botocore profile eu-central-1 yields eu.* model IDs
end-to-end; env var takes priority over botocore profile
- providers.py overlay: exists with correct transport/auth_type, label
is non-empty, all aliases normalize to bedrock
tests/agent/test_bedrock_adapter.py (5 tests):
- resolve_bedrock_region() botocore profile fallback, botocore failure
fallback, us-east-1 hard fallback (with botocore mocked)
* fix(anthropic): remove Claude Code fingerprinting from OAuth Messages API path
OAuth requests now identify as Hermes on the wire. Removed:
- "You are Claude Code, Anthropic's official CLI for Claude." system
prompt prepend
- Hermes Agent → Claude Code / Nous Research → Anthropic
system-prompt substitutions
- mcp_ tool-name prefix on outgoing tool schemas + message history
- Matching mcp_ strip on inbound tool_use blocks (strip_tool_prefix path
removed from AnthropicTransport.normalize_response, + all 5 call
sites in run_agent.py and auxiliary_client.py)
- user-agent: claude-cli/<v> (external, cli) and x-app: cli headers on
the Messages API client
Added:
- OAuth path strips context-1m-2025-08-07 — Anthropic rejects OAuth
requests carrying it with HTTP 400 'This authentication style is
incompatible with the long context beta header.'
Kept (auth plumbing, not identity spoofing):
- _is_oauth_token classifier and is_oauth flag threading
- Bearer vs x-api-key auth routing
- _OAUTH_ONLY_BETAS (claude-code-20250219, oauth-2025-04-20) — backend
requires these on the OAuth-gated Messages endpoint
- _OAUTH_CLIENT_ID (Claude Code's) — Anthropic doesn't issue OAuth
creds to third parties; this is the only way the login flow works
- claude-cli/<v> User-Agent on the OAuth token exchange + refresh
endpoints at platform.claude.com/v1/oauth/token — bare requests get
Cloudflare 1010 blocked
Verified live against api.anthropic.com with a fresh sk-ant-oat01-*
token:
- claude-haiku-4-5 simple message: HTTP 200, 'OK' response
- claude-haiku-4-5 tool call: HTTP 200, stop_reason=tool_use, tool
named 'terminal' (no mcp_ prefix) round-tripped correctly
- Outgoing wire: no user-agent, no x-app, real Hermes identity in
system prompt, real tool name in schema
Closes/supersedes #16820 (mcp_ PascalCase normalization patch — no longer
needed since the mcp_ round-trip is gone).
* fix(anthropic): resolve_anthropic_token() reads credential pool first
Close the gap where ~/.hermes/auth.json → credential_pool.anthropic
(where hermes login + dashboard PKCE flow write OAuth tokens) was not
in resolve_anthropic_token()'s source list.
Before: users who authed via hermes login got the token written into
the pool, but legacy fallback code paths (auxiliary_client, models
catalog fetch, explicit-runtime path) that call resolve_anthropic_token()
saw None and raised 'No Anthropic credentials found' — even though the
token was sitting in auth.json.
New priority 1: pool.select() with env-sourced entries skipped. Skipping
env:* entries preserves the existing env-var priority logic further
down the chain (static env OAuth → refreshable Claude Code upgrade via
_prefer_refreshable_claude_code_token).
Surfaced while writing the hermes-agent-dev skill playbook for
'finding a live OAuth token for an E2E test'.
---------
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
Adds a pre-call sanitizer that detects assistant messages containing only
reasoning (reasoning / reasoning_content, no visible content, no
tool_calls) and drops them from the API copy. Adjacent user messages
left behind are merged so role alternation is preserved for the
provider.
Mirrors Claude Code's approach in src/utils/messages.ts
(filterOrphanedThinkingOnlyMessages + mergeAdjacentUserMessages). We
drop the whole turn rather than fabricate stub text (the '.' /
'(continued)' pattern from contributor PRs #11098, #13010, #16842 that
were rejected because they put words in the model's mouth).
The stored conversation history (self.messages) is never mutated — only
the per-call api_messages copy. Users still see the reasoning block in
the CLI/gateway transcript; only the wire copy is cleaned. Session
persistence keeps the full trace.
Two call sites covered:
- Main agent loop, after _sanitize_api_messages (catches every turn).
- Iteration-limit-summary fallback path.
Tests: tests/run_agent/test_thinking_only_sanitizer.py — 25 cases
covering detection (string/list content, whitespace-only, tool_calls,
reasoning_details list form), drop behavior, adjacent-user merge
(string+string, list+list, mixed), non-mutation of input dicts, and
system-message handling.
E2E live-tested against 5 providers with a poisoned history (empty
assistant message + reasoning_content): OpenRouter→Anthropic/OpenAI/
DeepSeek-R1/Qwen, native Gemini. All 5 accepted the cleaned request.
Happy-path regression (5/5) confirms the sanitizer is a noop when no
thinking-only turn exists.
Related: #16823 (wontfix — stub-text approach rejected).
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
Registers tencent-tokenhub (https://tokenhub.tencentmaas.com/v1) as a
new API-key provider with model tencent/hy3-preview (256K context).
- PROVIDER_REGISTRY entry + TOKENHUB_API_KEY / TOKENHUB_BASE_URL env vars
- Aliases: tencent, tokenhub, tencent-cloud, tencentmaas
- openai_chat transport with is_tokenhub branch for top-level
reasoning_effort (Hy3 is a reasoning model)
- tencent/hy3-preview:free added to OpenRouter curated list
- 60+ tests (provider registry, aliases, runtime resolution,
credentials, model catalog, URL mapping, context length)
- Docs: integrations/providers.md, environment-variables.md,
model-catalog.json
Author: simonweng <simonweng@tencent.com>
Salvaged from PR #16860 onto current main (resolved conflicts with
#16935 Azure Anthropic env-var hint tests and the --provider choices=
list removal in chat_parser).
Three related fixes around custom env-var-name hints for provider entries.
1. Azure Anthropic path: previously hardcoded to look up AZURE_ANTHROPIC_KEY
then ANTHROPIC_API_KEY with no way to override. If a user wrote
model:
provider: anthropic
base_url: https://my-resource.services.ai.azure.com/anthropic
key_env: MY_CUSTOM_KEY
the key_env hint was silently ignored and the resolver raised
'No Azure Anthropic API key found' even when MY_CUSTOM_KEY was set
in the environment. The runtime now checks, in order:
(1) os.getenv(model_cfg.key_env)
(2) os.getenv(model_cfg.api_key_env) # docs alias
(3) model_cfg.api_key # inline value
(4) AZURE_ANTHROPIC_KEY # historical default
(5) ANTHROPIC_API_KEY # historical default
Error message updated to mention key_env as an option.
2. Provider entry normalizer (_normalize_custom_provider_entry): accept
'api_key_env' as a snake_case alias for 'key_env', and 'apiKeyEnv' as a
camelCase alias. Adds both to the _KNOWN_KEYS set so the 'unknown
config keys ignored' warning doesn't fire on valid configs.
3. _VALID_CUSTOM_PROVIDER_FIELDS: add 'key_env'. That set documents
supported custom_providers entry fields; it was drifting from reality
since key_env has been read at runtime in auxiliary_client.py,
runtime_provider.py, and main.py for a while.
Docs: website/docs/guides/azure-foundry.md now uses the canonical key_env
field and notes that api_key_env / keyEnv / apiKeyEnv are accepted as
aliases.
Validation: 12 new tests in test_runtime_provider_resolution.py covering
all 5 Azure Anthropic resolution paths + 4 normalizer-alias tests. Pass
rate across related suites (165 + 46 tests): 100%.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
* feat(claw-migrate): harden OpenClaw import with plan-first apply, redaction, and pre-migration backup
Adopts four design patterns from OpenClaw's reciprocal migrate-hermes
importer so both migration paths have the same safety posture.
- **Refuse-on-conflict apply.** 'hermes claw migrate' now refuses to
execute when the plan has any conflict items, unless --overwrite is
set. Previously the user could say 'yes, proceed' and end up with a
silent partial migration that skipped every conflicting item.
- **Engine-level secret redaction.** The report.json and summary.md
written to disk (and --json stdout) run through a redactor that
matches OpenClaw's key-name markers and value-shape patterns
(sk-*, ghp_*, xox*-, AIza*, Bearer *). Prevents accidental API key
leakage in bug reports and support channels.
- **Pre-migration tarball snapshot.** Apply creates one timestamped
restore-point archive of ~/.hermes/ at ~/.hermes/migration/pre-migration-backups/
before any mutation, excluding regenerable directories
(sessions, logs, cache). Opt out with --no-backup.
- **Blocked-by-earlier-conflict sequencing.** If a config.yaml write
hits conflict/error mid-apply, subsequent config-mutating options
are marked skipped with reason 'blocked by earlier apply conflict'
rather than attempting partial writes.
- **Structured warnings[] and next_steps[] on the report** — actionable
guidance surfaces in both JSON output and summary.md.
- **--json output mode** — emits the redacted report on stdout for CI.
Also flips --preset full to NOT auto-enable --migrate-secrets. Users
now have to opt in to secret import explicitly, mirroring OpenClaw's
two-phase posture.
Status/kind/action constants are defined (STATUS_MIGRATED etc) with
values that match the existing strings the script emits, so the
report schema is backward-compatible. ItemResult gains a 'sensitive'
bool field that redaction and consumers can key off.
Validation: 26 new unit tests + 1 updated test in tests/skills/
test_openclaw_migration_hardening.py and test_claw.py cover redaction
(key markers, value patterns, recursion, on-disk), warnings/next_steps,
blocked-by-earlier sequencing, --json mode, and the preset-flip.
Manual E2E against a fake $HERMES_HOME with real-shaped secrets
confirmed: (1) secrets never appear in stdout or on disk,
(2) _cmd_migrate refuses apply when plan has conflicts,
(3) --overwrite proceeds past the guard and the backup tarball is
created, (4) --no-backup skips the archive.
Related docs: website/docs/guides/migrate-from-openclaw.md and
website/docs/reference/cli-commands.md updated to reflect the
preset-flip and new --no-backup flag.
* refactor(claw-migrate): reuse hermes backup system for pre-migration snapshot
Drops the inline tarball in hermes_cli/claw.py in favor of
hermes_cli.backup.create_pre_migration_backup(), which shares an
implementation with create_pre_update_backup via a new
_write_full_zip_backup helper. Benefits:
- Consistent exclusion rules with hermes backup (_EXCLUDED_DIRS,
_EXCLUDED_SUFFIXES, _EXCLUDED_NAMES — single source of truth).
- SQLite safe-copy via _safe_copy_db (state.db restores cleanly).
- Zip format restorable with 'hermes import <archive>'.
- Lives under ~/.hermes/backups/pre-migration-*.zip alongside
pre-update-*.zip — one place for all snapshot archives.
- Auto-prune rotation with separate keep counters (pre-migration
keeps 5, pre-update keeps 5, they don't touch each other's files).
7 new tests in tests/hermes_cli/test_backup.py lock the contract:
directory location, shared exclusion rules, _validate_backup_zip
acceptance (i.e. restorable with 'hermes import'), non-recursive
into prior backups, rotation, missing-home handling, and the
invariant that pre-migration rotation never touches pre-update
backups.
Help text and docs updated — the restore hint now says
'hermes import <name>' instead of 'tar -xzf <archive> -C ~/'.
* chore(claw-migrate): use backup._format_size and drop duplicate output line
Minor polish using another existing primitive from hermes_cli.backup:
- Show backup archive size with _format_size (e.g. '(245 B)' or '(2.4 MB)')
matching the format hermes backup already uses.
- Drop the duplicate 'Pre-migration backup saved' line after Migration
Results — the earlier 'Pre-migration backup: <path> (<size>)' line
already surfaces the path before apply runs.
---------
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
Follow-up to #15328's vision-unsupported retry branch in run_agent.py.
_strip_images_from_messages() previously deleted any message whose content
was entirely images. That's fine for synthetic user messages injected for
attachment delivery, but it breaks providers for tool-role messages — the
paired tool_call_id on the preceding assistant message ends up unmatched,
which OpenAI-compatible APIs reject with HTTP 400.
Fix: tool-role messages whose content becomes empty are replaced with a
plaintext placeholder that preserves the tool_call_id linkage. Only
non-tool messages are dropped. Added 10 tests covering the role-alternation
invariants + image-type coverage.
Image-rejection detector: expanded phrase list (image content not
supported / multimodal input / vision input / model does not support
image) and gated on 4xx status so transient 5xx errors never get
misinterpreted as 'server said no to images'. Detection is documented as
best-effort English phrase matching.
AUTHOR_MAP: mapped 3820588+ddupont808@users.noreply.github.com to
ddupont808 so release notes attribute the salvage correctly.
Background macOS desktop control via cua-driver MCP — does NOT steal the
user's cursor or keyboard focus, works with any tool-capable model.
Replaces the Anthropic-native `computer_20251124` approach from the
abandoned #4562 with a generic OpenAI function-calling schema plus SOM
(set-of-mark) captures so Claude, GPT, Gemini, and open models can all
drive the desktop via numbered element indices.
- `tools/computer_use/` package — swappable ComputerUseBackend ABC +
CuaDriverBackend (stdio MCP client to trycua/cua's cua-driver binary).
- Universal `computer_use` tool with one schema for all providers.
Actions: capture (som/vision/ax), click, double_click, right_click,
middle_click, drag, scroll, type, key, wait, list_apps, focus_app.
- Multimodal tool-result envelope (`_multimodal=True`, OpenAI-style
`content: [text, image_url]` parts) that flows through
handle_function_call into the tool message. Anthropic adapter converts
into native `tool_result` image blocks; OpenAI-compatible providers
get the parts list directly.
- Image eviction in convert_messages_to_anthropic: only the 3 most
recent screenshots carry real image data; older ones become text
placeholders to cap per-turn token cost.
- Context compressor image pruning: old multimodal tool results have
their image parts stripped instead of being skipped.
- Image-aware token estimation: each image counts as a flat 1500 tokens
instead of its base64 char length (~1MB would have registered as
~250K tokens before).
- COMPUTER_USE_GUIDANCE system-prompt block — injected when the toolset
is active.
- Session DB persistence strips base64 from multimodal tool messages.
- Trajectory saver normalises multimodal messages to text-only.
- `hermes tools` post-setup installs cua-driver via the upstream script
and prints permission-grant instructions.
- CLI approval callback wired so destructive computer_use actions go
through the same prompt_toolkit approval dialog as terminal commands.
- Hard safety guards at the tool level: blocked type patterns
(curl|bash, sudo rm -rf, fork bomb), blocked key combos (empty trash,
force delete, lock screen, log out).
- Skill `apple/macos-computer-use/SKILL.md` — universal (model-agnostic)
workflow guide.
- Docs: `user-guide/features/computer-use.md` plus reference catalog
entries.
44 new tests in tests/tools/test_computer_use.py covering schema
shape (universal, not Anthropic-native), dispatch routing, safety
guards, multimodal envelope, Anthropic adapter conversion, screenshot
eviction, context compressor pruning, image-aware token estimation,
run_agent helpers, and universality guarantees.
469/469 pass across tests/tools/test_computer_use.py + the affected
agent/ test suites.
- `model_tools.py` provider-gating: the tool is available to every
provider. Providers without multi-part tool message support will see
text-only tool results (graceful degradation via `text_summary`).
- Anthropic server-side `clear_tool_uses_20250919` — deferred;
client-side eviction + compressor pruning cover the same cost ceiling
without a beta header.
- macOS only. cua-driver uses private SkyLight SPIs
(SLEventPostToPid, SLPSPostEventRecordTo,
_AXObserverAddNotificationAndCheckRemote) that can break on any macOS
update. Pin with HERMES_CUA_DRIVER_VERSION.
- Requires Accessibility + Screen Recording permissions — the post-setup
prints the Settings path.
Supersedes PR #4562 (pyautogui/Quartz foreground backend, Anthropic-
native schema). Credit @0xbyt4 for the original #3816 groundwork whose
context/eviction/token design is preserved here in generic form.
Opt-in Langfuse tracing for Hermes conversations — LLM calls, tool
usage, usage/cost breakdown per span. Hooks into pre/post_api_request,
pre/post_llm_call, pre/post_tool_call. SDK is optional; missing SDK or
credentials renders the plugin inert.
Salvaged from PR #16845 by @kshitijk4poor, who wrote the plugin
(~875 LOC, 6 hooks, Langfuse usage-details/cost-details normalization,
read_file payload summarization).
Salvage scope (why this isn't PR #16845 as-authored):
- Lives at plugins/observability/langfuse/ (standalone kind, opt-in via
plugins.enabled) instead of a new parallel optional-plugins/
directory. Standalone bundled plugins are already opt-in — only their
plugin.yaml is scanned at startup; the Python module is not imported
unless the user enables it. The premise of optional-plugins/ (avoid
import cost for users who don't want it) is already solved by the
existing plugin system.
- Dropped the triple activation gate (plugins.enabled +
plugins.langfuse.enabled + HERMES_LANGFUSE_ENABLED). The Hermes plugin
system's own enable/disable is authoritative; runtime credentials
gate whether the hook actually traces.
- Rewrote _is_enabled() → cached _get_langfuse() with an _INIT_FAILED
sentinel. The original called hermes_cli.config.load_config() from
every hook invocation (full yaml parse + deep merge + env expansion
on every pre/post_tool_call, potentially 100+ times per turn). The
cached version reads env once and returns the cached client or None
on every subsequent call with zero further work.
- hermes tools → Langfuse Observability post-setup adds
observability/langfuse to plugins.enabled directly (via
_save_enabled_set) instead of going through an install-copy flow.
Enable:
hermes tools # interactive
hermes plugins enable observability/langfuse # manual
Required env (set by `hermes tools` or in ~/.hermes/.env):
HERMES_LANGFUSE_PUBLIC_KEY
HERMES_LANGFUSE_SECRET_KEY
HERMES_LANGFUSE_BASE_URL # optional
Co-authored-by: kshitijk4poor <kshitijk4poor@gmail.com>
Narrow plaintext shortcut that rewrites a tiny set of admin phrases
("restart gateway", "restart the gateway", "restart hermes") into the
/restart slash command, but only in DMs. Scope is intentionally tight:
- DM text messages only — group chats keep natural-language semantics
- Exact restart-style phrases only
- Skips anything already starting with "/"
Without this, the LLM can receive "restart gateway" as a user turn and
try to satisfy it via the terminal tool (systemctl restart ...). That
kills the gateway while the originating agent is still running, which
leaves systemd in "draining" state waiting on a process it's about to
kill. Routing the phrase to the slash-command dispatcher bypasses the
agent loop and uses the existing restart machinery (request_restart).
Called once, at the adapter level in BasePlatformAdapter.handle_message,
so every platform gets it for free and pending-message reinjection is
covered by the same call site.
Adds 2 Telegram-parametrized e2e tests: DM routes to request_restart,
group chats fall through to the normal agent path.
Runtime already supports list-form fallback_model (run_agent.py:1459
iterates fallback_chain; fallback_cmd.py migrates legacy single-dict
configs to list format). The config validator and save_config comment
gate still assumed single-dict form and flagged list-form configs as
errors. Fix both:
- validate_config_structure: when fallback_model is a list, validate
each entry has provider+model; keep the existing single-dict path.
- save_config: suppress the "add fallback_model" comment when any list
entry is well-formed.
Adds 4 list-form validator tests.
PR #16858's session-scoped interactive sudo password cache falls back to
a thread-identity scope when no HERMES_SESSION_KEY is bound. ACP never
set that contextvar, so two ACP sessions landing on the same reused
ThreadPoolExecutor thread still shared the cache — the exact scenario
the PR headlined.
acp_adapter/server.py now:
- binds HERMES_SESSION_KEY=<session_id> via gateway.session_context
inside _run_agent() (and clears on exit)
- wraps the loop.run_in_executor(_executor, _run_agent) call in a fresh
contextvars.copy_context() so concurrent ACP sessions don't stomp on
each other's ContextVar writes (executor pool threads would otherwise
share a context).
Adds tests/acp/test_approval_isolation.py::
test_sudo_password_cache_isolated_across_acp_sessions_on_same_pool_thread
which drives two back-to-back sessions through a 1-worker ThreadPoolExecutor
and asserts B does not observe A's cached password.
Follow-up on top of the cherry-picked contributor commit for #16751:
1. Delete triggers: the original PR switched FTS5 from external to inline
content mode and concatenated content || tool_name || tool_calls in
the insert/update triggers, but left the delete triggers passing
old.content to the FTS5 delete-command. FTS5 inline delete requires
the content to match what was stored, so every DELETE on messages
raised 'SQL logic error'. Replaced with plain DELETE FROM ... WHERE
rowid = old.id on all four delete paths (normal + trigram, delete +
update-delete).
2. v11 migration: existing DBs have the old external-content FTS tables
and triggers. Because CREATE VIRTUAL TABLE IF NOT EXISTS / CREATE
TRIGGER IF NOT EXISTS skip when the objects already exist, upgraders
would have kept the broken behavior forever. Bumped SCHEMA_VERSION
to 11 and added a migration that drops both FTS tables + all 6 old
triggers, recreates them via FTS_SQL / FTS_TRIGRAM_SQL, and backfills
from messages using the same concatenation expression.
3. Regression tests: 6 new tests cover INSERT / UPDATE / DELETE paths
for tool_name + tool_calls indexing plus the full v10 -> v11 upgrade
path on a hand-built legacy DB.
FTS5 default tokenizer splits 'sp_new1' into tokens 'sp' and 'new1'.
Without quoting, a search for 'sp_new' becomes an AND query
('sp AND new') that fails to match rows indexed as 'sp_new1'.
Fix: add underscore to the character class in Step 5 regex
([.-] -> [._-]) so underscored terms are wrapped in double quotes.
Also adds test_sanitize_fts5_quotes_underscored_terms.
Both keys are documented in cli-config.yaml.example and read at runtime by
hermes_cli/timeouts.py (get_provider_request_timeout and get_provider_stale_timeout),
but the provider-entry validator in config.py flagged them as unknown, producing
noisy warnings on every CLI invocation for users who followed the documented config.
Fixes#16779
Previously, agent.disabled_toolsets in config.yaml only worked for CLI
mode (run_agent.py --disabled_toolsets). The gateway always passed
enabled_toolsets to AIAgent, and get_tool_definitions() ignored
disabled_toolsets when enabled_toolsets was set.
Fix: _get_platform_tools() now reads agent.disabled_toolsets from config
and excludes those toolsets from the returned set. This runs last so it
overrides everything above.
Added 3 tests covering cross-platform suppression, explicit platform
config override, and empty/missing config no-op behavior.
Streaming-only providers (glm, MiniMax, gpt-5.x via aigw, Anthropic via
openai-compat shims) emit reasoning through delta.reasoning_content
chunks that get accumulated into the local reasoning_text string — but
never land on the assistant message object as a top-level attribute. The
prior guard at _build_assistant_message only wrote reasoning_content
when the SDK exposed hasattr(msg, 'reasoning_content'), so these
providers persisted the chain-of-thought under the internal 'reasoning'
key and omitted the protocol-standard field.
The poison was silent until the user later switched to a DeepSeek-v4 or
Kimi thinking model, at which point replay failed with HTTP 400:
'The reasoning_content in the thinking mode must be passed back to the
API.' One reported session store accumulated 4,031 poisoned messages
across 1,101 files (#16844).
Fix: add an additive fallback that promotes the already-sanitized
reasoning_text to reasoning_content when no earlier branch wrote it AND
reasoning text was actually captured. Layered on top of the existing
SDK-attr branch and DeepSeek ''-pad (#15250) rather than replacing them,
so every existing behavior is preserved:
- SDK-exposed reasoning_content (OpenAI/Moonshot/DeepSeek SDK) still
wins.
- DeepSeek tool-call ''-pad still fires when the SDK exposes the attr
but the value is None.
- Non-thinking turns with no reasoning leave the field absent, so
_copy_reasoning_content_for_api's cross-provider leak guard (#15748),
promote-from-'reasoning' tier, and thinking-pad tier remain live at
replay time.
- No empty '' gets eagerly written on every assistant turn (which would
have bypassed the read-side ladder and triggered empty thinking-block
insertion in the Anthropic adapter).
Tests: three new TestBuildAssistantMessage cases covering the streaming
promotion path, SDK precedence, and field-absent-when-no-reasoning
invariant.
Credit @Sanjays2402 for the original diagnosis and patch in #16884;
this is a scoped rework that preserves the existing read-side
compensation code as defense in depth.
Refs #16844, #16884, #15250, #15353, #15748.
Address Copilot review on #16868:
1. Tighten pool iteration. ``validate_copilot_token`` only rejects empty
strings and classic PATs (``ghp_*``); a malformed/unsupported ``gho_*``
token at ``credential_pool.copilot[0]`` would pass the gate and short-
circuit the loop, hiding a later valid entry. Switch to calling
``exchange_copilot_token`` directly: only entries that actually exchange
into a live Copilot API token are returned. Bad/expired entries fall
through to the next, and an exhausted pool returns ``""`` so the picker
falls back to the curated list (existing behaviour).
2. Reword the docstring + test module docstring to describe the pool seed
path accurately — ``hermes auth add copilot`` adds an api-key-typed
credential whose ``access_token`` field stores the pasted token, and
``_seed_from_env`` mirrors ``COPILOT_GITHUB_TOKEN`` from
``~/.hermes/.env`` into the pool. The previous wording implied
``auth add copilot`` itself ran the device-code flow, which it does
not (the device-code flow lives in ``hermes model``).
Two new tests cover the iteration change:
- ``test_skips_pool_entry_that_fails_to_exchange`` — pool[0] raises,
pool[1] succeeds, picker uses pool[1].
- ``test_all_pool_entries_fail_exchange_returns_empty`` — every entry
raises, return ``""``.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Users whose only Copilot credential is the OAuth `access_token` saved by
`hermes auth add copilot` (device-code flow) saw the `/model` picker drop
back to a stale hardcoded list. Reason: `_resolve_copilot_catalog_api_key`
only consulted env vars (`COPILOT_GITHUB_TOKEN` / `GH_TOKEN` /
`GITHUB_TOKEN`) and the `gh auth token` CLI fallback, never the credential
pool that Hermes's own login flow writes into `auth.json`. With no token,
the live catalog fetch silently 401s and the picker hides current models
(claude-opus-4.7, claude-sonnet-4.6, gpt-5.5, grok-code-fast-1) — even
though `/model <id>` works fine because runtime inference reads the pool
through a different code path.
Mirror the Codex catalog resolver pattern: env-var first (unchanged), then
walk `read_credential_pool("copilot")` for the first entry with a
supported `access_token` (`gho_*` / `github_pat_*` / `ghu_*`). Run it
through `get_copilot_api_token()` so the catalog request uses the same
exchanged token the runtime path uses. Classic PATs (`ghp_*`) are still
rejected up-front via `validate_copilot_token` since the Copilot API
doesn't accept them.
Strictly additive: env still wins, and a missing/locked auth.json (or any
exception during pool read) still returns "" so the caller falls through
to the curated catalog.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`/new` after `/model <custom-provider>:<model>` silently reverted to a
native provider whose static catalog happened to contain the same model
name (e.g. `deepseek-v4-pro` → native `deepseek` → 401).
Root cause at the `/model` writeback site: `HERMES_INFERENCE_PROVIDER`
was set unconditionally but `HERMES_TUI_PROVIDER` was only mirrored when
it was already set. On sessions launched without `--provider`,
`HERMES_TUI_PROVIDER` stayed unset, so `_resolve_startup_runtime()` on
`/new` skipped the explicit-provider early return and fell through to
`detect_static_provider_for_model()`.
Fix: set `HERMES_TUI_PROVIDER` unconditionally alongside
`HERMES_INFERENCE_PROVIDER` when `/model` lands. Keeps #15755's
invariant intact — `HERMES_TUI_PROVIDER` remains the canonical
"explicit this process" carrier, `HERMES_INFERENCE_PROVIDER` remains
ambient and does not short-circuit startup resolution.
Bug report and diagnosis: @Bartok9 in #16857 / #16873.
Fixes#16857
Replace the Linux/macOS pgrep regex ("hermes.*dashboard") with a ps
scan + the same explicit patterns list already used on the Windows
branch and in hermes_cli.gateway._scan_gateway_pids:
hermes dashboard
hermes_cli.main dashboard
hermes_cli/main.py dashboard
The old greedy regex would match any cmdline containing both words —
e.g. a chat session whose argv mentions "dashboard" or an unrelated
grafana/dashboard-server process. Added regression tests for both.
Follow-up tightening on #16881.
The dashboard is a long-lived server process users start and forget.
When hermes update replaces files on disk, the running process holds
the old Python backend in memory while the JS bundle gets updated,
producing a silent frontend/backend mismatch (e.g. v0.11.0 changed
the session token header -- old backends reject every API call).
Scan for running dashboard processes after a successful update (both
git and ZIP paths) and print a warning with their PIDs and restart
instructions. Mirrors the existing pattern for gateway processes.
Fixes#16872
PR #16888 swaps the opencode-zen/go resolver so that api_mode is always
re-derived from the effective model before the persisted api_mode is
consulted. That's the point of the fix — a stale anthropic_messages
from a previous minimax default must not survive a /model switch to a
chat_completions target (or vice versa) and strip /v1 from base_url.
The prior test asserted the opposite precedence — that a persisted
api_mode won over model-derived mode — and was added in #4508 to lock
in escape-hatch behavior. Under the new precedence that escape hatch
no longer exists for opencode (only for providers that genuinely
support both modes at a single endpoint — and for opencode the model
name is the unambiguous signal). Rename + invert the assertion to
document the intentional behavior change.
Refs #16878.
Switch _PRIORITY_PROCESSING_MODELS and _ANTHROPIC_FAST_MODE_MODELS from
hardcoded frozensets to prefix-based matching. Any gpt-*, o1*, o3*, o4*
(OpenAI) and any claude-* (Anthropic) now exposes /fast.
Fixes the case where gpt-5.5 and other post-catalog models silently
skipped Priority Processing because they weren't in the frozenset.
Future OpenAI/Anthropic releases will work without a catalog bump.
Safety:
- Codex-series (*codex*) still excluded — they route through the Codex
Responses API which doesn't take service_tier.
- Anthropic adapter already gates speed=fast on native endpoints only
(_is_third_party_anthropic_endpoint), so claude-sonnet-4.6 on
OpenRouter/Bedrock/opencode-zen won't leak the unknown beta.
- service_tier=priority is silently dropped by non-OpenAI proxies, so
false positives are harmless.
OpenClaw users who started before the rebrand (when the project was
clawd/clawdbot) often have a custom workspace directory configured via
agents.defaults.workspace in openclaw.json (e.g. ~/clawd/ instead of
~/.openclaw/workspace/).
The migration tool only checked hardcoded relative paths (workspace/,
workspace-main/, workspace-assistant/) inside the source root, so files
like MEMORY.md, skills, and daily memory in custom workspaces were
silently skipped.
This change:
- Reads agents.defaults.workspace from openclaw.json at init time
- Uses it as a final fallback in source_candidate() when files aren't
found in the standard locations
- Standard workspace paths are still preferred (custom is fallback only)
- Custom workspace is only used when it's outside the source_root tree
(avoids double-matching when workspace/ is the default)
Adds two tests:
- Custom workspace files are discovered and migrated
- Standard workspace location is preferred over custom
Flips security.redact_secrets from true to false in DEFAULT_CONFIG, and
the HERMES_REDACT_SECRETS env-var fallback in agent/redact.py now
requires explicit opt-in ("1"/"true"/"yes"/"on") to enable.
New installs and users without a security.redact_secrets key get pass-
through tool output. Existing users whose config.yaml explicitly sets
redact_secrets: true keep redaction on — the config-yaml -> env-var
bridges in hermes_cli/main.py and gateway/run.py still honor their
setting.
Also updates the inline config comments, website docs, and the
hermes-agent skill so /hermes config set security.redact_secrets true
is now the documented way to turn it on.
MatrixAdapter._is_self_sender returns True defensively when _user_id is empty
(whoami not yet resolved) to prevent echo loops — see #15763. The reaction
approval test must therefore initialize a user_id so _on_reaction does not
drop the inbound test event before reaching the approval handler.
Self-contained docker-compose harness that exercises the new bootstrap
branch against a real Continuwuity homeserver. Three tests:
1. fresh bot → bootstrap fires, /keys/query returns master + ssk
with UNPADDED base64 keyids, current device is signed by the
new SSK
2. second startup with same crypto store → bootstrap is skipped
3. MATRIX_RECOVERY_KEY set → existing verify_with_recovery_key path
takes precedence, no new bootstrap
Run via:
docker compose -f tests/e2e/matrix_xsign_bootstrap/docker-compose.yml up -d
python tests/e2e/matrix_xsign_bootstrap/test_bootstrap.py
docker compose -f tests/e2e/matrix_xsign_bootstrap/docker-compose.yml down -v
The test mirrors the bootstrap snippet from matrix.py inline so it can
run without importing the full hermes gateway and its deps. Skipped
automatically when mautrix isn't installed or the homeserver is
unreachable.
All three pass against ghcr.io/continuwuity/continuwuity:latest
(Continuwuity 0.5.7). The unpadded-keyid assertion is the load-bearing
one — it's exactly the property the PR's bootstrap path provides that
the hand-rolled `base64.b64encode().decode()` scripts get wrong.
* Port from Kilo-Org/kilocode#9448: roll up subagent costs into parent session total
Child subagents built by delegate_task() each track their own
session_estimated_cost_usd, but the parent agent's total never folded
those numbers in. On runs where the parent mostly delegates and the
children do the expensive work, the footer/UI was reporting a fraction
of the actual spend — sometimes $0.00 when the parent itself made no
billed calls.
Fix:
- Capture each child's session_estimated_cost_usd into _child_cost_usd
on the result entry (before child.close() drops the counter).
- After the existing subagent_stop hook loop, sum the children's costs
and add the total to parent.session_estimated_cost_usd.
- Promote session_cost_source from 'none' -> 'subagent' when the parent
had no direct spend but children did, so the UI doesn't label the
total as having unknown provenance. Real sources (openrouter,
anthropic, etc.) are preserved.
Nested orchestrator -> worker trees roll up naturally: each layer's own
delegate_task() folds its direct children in, and when the orchestrator
itself returns, its parent folds the orchestrator's now-inflated total
on top.
Internal fields (_child_cost_usd, _child_role) are stripped from the
results dict before it's serialised back to the model — same contract
as _child_role already followed.
Tests: TestSubagentCostRollup (5 cases) covers single-child, batch,
zero-cost-children, preserved-source, and legacy-fixture paths.
Source: https://github.com/Kilo-Org/kilocode/pull/9448
* fix(web): scope dashboard config Reset button to the current tab
Reported by @ykmfb001 via X: clicking 'Restore Defaults' (恢复默认值) on
the Auxiliary page wiped the entire config.yaml to defaults, not just
the auxiliary section. The button sits next to the category tabs and
users reasonably assumed 'reset this tab', not 'reset everything'.
Changes:
- handleReset now scopes to the fields in the current view:
active category's fields (form mode) or search-matched fields
(search mode). Only those keys are copied from defaults; the rest
of the config is left alone.
- Added a window.confirm() with the scope name before applying.
- Button is hidden in YAML mode (scoping doesn't apply there).
- Tooltip/aria-label now name the scope, e.g. 'Reset Auxiliary to
defaults'.
- i18n: new resetScopeTooltip / confirmResetScope / resetScopeToast
strings in en + zh; resetDefaults key preserved for compat.
On AWS Bedrock (and Azure AI Foundry), Claude Opus 4.6/4.7 and Sonnet 4.6
are capped at 200K context unless the request carries the
`context-1m-2025-08-07` beta header. On native Anthropic (api.anthropic.com)
1M went GA so the header is a harmless no-op, but Bedrock/Azure still gate
it as beta as of 2026-04.
Hermes was advertising 1M in model_metadata.py (`claude-opus-4-7: 1000000`)
while silently sending a request without the beta — so Bedrock users saw
a 200K ceiling with no error message, and no config knob unblocked it.
Claude Code sends this header by default, which is why the same Bedrock
credentials worked there.
- Add `context-1m-2025-08-07` to `_COMMON_BETAS` (alongside interleaved
thinking and fine-grained tool streaming).
- Strip it in `_common_betas_for_base_url` for MiniMax bearer-auth
endpoints — they host their own models, not Claude, so Anthropic beta
headers are irrelevant and could risk rejection.
- Attach `_COMMON_BETAS` as `default_headers` on the AnthropicBedrock
client. Previously that constructor passed no betas at all, so native
Anthropic had the 1M unlock via default_headers but Bedrock didn't.
- Fast-mode per-request `extra_headers` already rebuilds from
`_common_betas_for_base_url`, so it picks up the 1M beta automatically.
Reported by user 'Rodmar' on Discord: Bedrock Opus 4.7 stuck at 200K while
same credentials worked in Claude Code.
Anyone who ran hermes between Apr 15 (42aeb4ec) and Apr 22 (a7d78d3b)
has schema_version=7 from the pre-renumber api_call_count migration.
When a7d78d3b inserted reasoning_content as the new v7 and pushed
api_call_count to v8, the 'if current_version < 7' gate was already
false for those users, so reasoning_content was never created —
sqlite3.OperationalError: no such column: reasoning_content on any
/continue or /resume touching assistant replays.
Replaces the version-gated ADD COLUMN chain with _reconcile_columns():
on every startup, parse SCHEMA_SQL via an in-memory SQLite and diff
against PRAGMA table_info; ALTER TABLE ADD COLUMN for anything missing.
Follows the Beets / sqlite-utils pattern — SCHEMA_SQL becomes the single
source of truth for declared columns. Self-healing and idempotent.
v10 trigram FTS backfill is retained in a version-gated block — that
migration isn't a column add, it inserts existing message rows into
the new FTS virtual table, so reconciliation can't express it.
schema_version is also kept for future row-data migrations.
Salvaged from #14097 (@kshitijk4poor) onto current main; v10 trigram
preservation and the v9 codex_message_items column (stale-missed by
the original branch) are covered automatically by reconciliation.
Tests:
- Regression: DB at old v7 with api_call_count but no reasoning_content
gets the column on open
- Idempotency: reopening the same DB is a no-op
- Structural invariant: every SCHEMA_SQL column is in the live DB
- Existing v2 migration test still passes
- E2E verified against fresh / v1 / old-v7 / v9 DBs, plus v10 trigram
backfill preserved
Plugins can now observe dangerous-command approval events in real time,
on both the CLI-interactive path and the async gateway path. This is the
missing hook surface external tools need to build approval notifiers
(macOS menu-bar allow/deny, Slack alerts, audit logs, etc.) without
forking Hermes or running a parallel gateway adapter.
Changes:
- hermes_cli/plugins.py: add two entries to VALID_HOOKS
- tools/approval.py: fire both hooks from check_all_command_guards --
around prompt_dangerous_approval (CLI surface) and around the
notify_cb + blocking event.wait loop (gateway surface)
- website/docs/user-guide/features/hooks.md: document both hooks with
a macOS-notification example
- tests/tools/test_approval_plugin_hooks.py: 5 tests covering CLI once,
CLI deny, plugin-crash resilience, gateway approve, gateway timeout
Hooks are observer-only: return values are ignored, so plugins cannot
veto or pre-answer an approval (use pre_tool_call for that). A crashing
plugin cannot break the approval flow -- invoke_hook swallows per-
callback errors, and the wrapper logs and swallows dispatch-layer
errors too.
Surface kwarg distinguishes "cli" from "gateway"; post hook reports
choice as one of once/session/always/deny/timeout.
A misconfigured auxiliary.compression.model is a user-fixable problem that silent recovery would hide. The previous retry-on-main logic transparently swallowed aux-model failures whenever the fallback succeeded, leaving the user's broken config in place and racking up future failures.
Track the aux-model failure on the compressor alongside the existing fallback-placeholder fields:
- _last_aux_model_failure_model: str | None
- _last_aux_model_failure_error: str | None
Both are set at the moment the aux model errors (captured before summary_model is cleared for retry), regardless of whether the retry succeeds. Cleared at compress() start and on on_session_reset() so a clean run doesn't leak stale warnings.
Surface at three places:
- gateway hygiene auto-compress: ℹ note to the platform adapter (thread_id preserved)
- gateway /compress command: ℹ line appended to the reply
- CLI via _emit_warning: deduped on (model, error) so repeat compactions don't spam
Distinct from the existing ⚠️ dropped-turns warning — different severity, different emoji, explicit 'context is intact' reassurance.
The existing retry-on-main path in _generate_summary only fires for errors that match the _is_model_not_found heuristic (404/503, 'model_not_found', 'does not exist', 'no available channel'). Other misconfiguration errors — 400s from aggregators, provider-specific 'no route' strings, opaque rejections — fall straight through to the transient-cooldown branch, which drops N turns of context and inserts a static placeholder.
Losing context is almost always worse than one extra summary attempt. Add a best-effort retry-on-main for the unknown-error branch, guarded by the same invariants as the existing fast-path retry: only when summary_model differs from main, and only once per compressor (_summary_model_fallen_back).
Tests cover: 404 fast-path fallback still works, unknown 400 now falls back, same-model aux skips retry (no infinite loop), and a double-failure (aux + main) stops at 2 calls.
PR #16333 added a warning to the manual /compress reply when the
auxiliary summariser fails and the static fallback placeholder is
used, but only the gateway-hygiene path had a test
(test_session_hygiene_warns_user_when_summary_generation_fails).
The /compress branch in _handle_compress_command was uncovered.
New test test_compress_command_appends_warning_when_summary_generation_fails
mocks the compressor's _last_summary_fallback_used /
_last_summary_dropped_count / _last_summary_error fields and
verifies the /compress reply contains the ⚠️ marker, the underlying
error string, the dropped message count, and the 'historical
message(s) were removed' wording — i.e. the same contract the
hygiene-path test enforces.
Address review feedback on PR #16333:
1. The hygiene-path warning send was missing metadata=_hyg_meta. On
Telegram topics / Slack threads / Discord threads the warning would
land in the main channel instead of the originating thread. Now
reuses the same _hyg_meta dict already computed for the hygiene
compaction itself.
2. New gateway-level test
test_session_hygiene_warns_user_when_summary_generation_fails
verifies end-to-end:
- When the compressor's _last_summary_fallback_used flag is True,
the gateway invokes adapter.send() exactly once.
- The warning message includes the dropped count and the underlying
error string.
- metadata={'thread_id': ...} is propagated so the warning lands
in the originating topic/thread.
Tests: 20 gateway hygiene + 54 context_compressor — all pass.
When auxiliary compression's summary LLM call fails (e.g. model 404,
auxiliary model misconfigured), the compressor still drops the selected
turns and inserts a static fallback placeholder — the dropped context
is unrecoverable.
Previously the only signal of this was a WARNING in agent.log. Gateway
users (Telegram/Discord/etc.) had no way to know context was lost
because the existing _emit_warning path requires a status_callback,
and the gateway hygiene path uses a temporary _hyg_agent with
quiet_mode=True and no callback wired up.
Changes:
- ContextCompressor: track _last_summary_fallback_used and
_last_summary_dropped_count on each compress() call. Cleared at the
start of compress() and on session reset.
- gateway/run.py hygiene: after auto-compress, inspect the temp
agent's compressor; if fallback was used, send a visible ⚠️ warning
to the user via the platform adapter (TG/Discord/etc.) including
dropped count and the underlying error.
- gateway/run.py /compress: append the same warning to the manual
compress reply so users running /compress see the failure too.
Acceptance:
- Summary success: no user-visible warning (unchanged).
- Summary failure on gateway hygiene: user receives a TG/Discord
message with dropped count + error + remediation hint.
- Summary failure on /compress: warning appended to the command reply.
- CLI status_callback / _emit_warning path is untouched.
- Test coverage: two new tests verify the tracking fields are set on
failure and cleared on subsequent success.
The typing-indicator refresh loop in BasePlatformAdapter._keep_typing
awaited each send_typing call unconditionally. Each call is an HTTP
round-trip to the platform API (Telegram/Discord), normally ~100ms. When
the same network instability that causes upstream provider timeouts
(e.g. Anthropic capacity blips slowing first-token latency past the
120s stream-read timeout) also slows the platform typing API to
multi-second response times, the refresh loop stalls inside the await.
Platform-side typing expires at ~5s, so the bubble dies and stays dead
until the stuck send_typing call returns — right when the user most
needs the 'still working' signal and instead sees a bot that looks
dead, then asks 'wtf are you doing' which itself interrupts the
eventually-recovering turn.
Bound each send_typing with asyncio.wait_for (1.5s cap, derived from
interval so it's always below the 2s cadence). Slow calls get abandoned
so the next scheduled tick fires a fresh send_typing on schedule. As
long as any one of them reaches the platform within its ~5s
typing-expiry window, the bubble stays visible across the stall.
Also catches non-timeout send_typing exceptions (transient HTTP errors)
so one bad tick doesn't terminate the whole loop.
Tests: 4 new in tests/gateway/test_keep_typing_timeout.py covering
slow-send non-blocking, fast-send still-awaited, exception resilience,
and paused-chat regression guard.
* feat(tui): auto copy-on-select for transcript text
Drag in the transcript already highlighted but you had to press Cmd+C to
land it on the clipboard, and the highlight cleared on copy — most users
never realised selection existed. Now drag-release fires copySelectionNoClear
so the text is on the clipboard immediately while the highlight stays put,
matching iTerm2's "Copy to pasteboard on selection" default. Esc clears.
Behaviour:
- Single click in the input still positions the cursor (TextInput onClick).
- Single click in the transcript still does nothing destructive.
- Double / triple click select word / line, then drag extends.
- /copyselect [on|off|toggle] (alias /cos) flips the setting at runtime,
HERMES_TUI_DISABLE_COPY_ON_SELECT=1 disables at startup, persists via
display.tui_copy_on_select in config.yaml.
Help overlay now lists drag-select, multi-click, and click-to-position
so the gestures are discoverable.
Made-with: Cursor
* fix(tui): support prompt text selection gestures
Add mouse drag selection and Shift+Arrow/Home/End extension inside the TUI composer so prompt text behaves like a normal editable field while keeping click-to-position and right-click paste intact.
Made-with: Cursor
* Revert "feat(tui): auto copy-on-select for transcript text"
This reverts commit 6701288fe07a53af873e1ef53855a9618d733327.
* fix(tui): allow composer selection from prompt whitespace
Give the composer a one-cell mouse capture pad before the editable text. The prompt glyph/gutter still does not become selectable, but dragging from the edge now anchors at input offset 0 so users do not need to hit the first character precisely.
Made-with: Cursor
* fix(tui): clear selections from blank composer space
Clicking blank space in the transcript or composer now clears active TUI/input selections like a normal text surface. TextInput clicks stop bubbling so cursor placement and selection gestures keep their local behavior.
Made-with: Cursor
* fix(tui): delegate prompt gutter drags to composer text
The prompt gutter is now an input gesture region, not selectable content. Dragging from the whitespace or prompt area anchors the composer selection at offset 0, while selection highlight/copy remains limited to actual input text.
Made-with: Cursor
* fix(tui): move composer cursor to end on selection clear
External clear actions now collapse the composer selection to the end of the input, matching normal text-field behavior after dismissing a selection.
Made-with: Cursor
* fix(tui): capture composer padding before prompt
Add an explicit mouse capture cell over the left padding before the prompt glyph. Drags starting there now delegate to the composer input at offset 0 instead of starting terminal-level selection over the prompt chrome.
Made-with: Cursor
* fix(tui): avoid npm install on lockfile mtime churn
Compare package-lock.json against npm's hidden node_modules lock by content instead of mtimes. Git checkouts and npm lock rewrites can make the root lockfile newer even when installed dependencies already match, causing hermes --tui to print Installing TUI dependencies on every launch.
Made-with: Cursor
* fix(tui): include prompt leading cell in gesture region
Use the prompt box's real layout region to cover the leading whitespace cell before the glyph. The cell now participates in mouse hit testing and delegates to composer selection instead of starting terminal-level selection.
Made-with: Cursor
* fix(tui): widen prompt-side gesture capture band
Capture a wider left-side band around the composer prompt row so drags starting in terminal gutter/padding cells are consumed and delegated to input selection, instead of triggering terminal-level selection chrome.
Made-with: Cursor
* fix(tui): make pre-prompt spacer non-selectable content
Replace the sticky-prompt fallback `Text(' ')` with an empty spacer box so the visual gap remains but no literal space character is rendered/copyable before the composer prompt.
Made-with: Cursor
* fix(tui): capture pre-prompt spacer without shifting prompt layout
Revert the widened negative-margin prompt capture band and instead capture drags on the dedicated spacer row above the prompt. This keeps prompt/text alignment stable while still delegating whitespace-start drags to composer selection.
Made-with: Cursor
* fix(tui): align prompt with status bar and capture full input row
Drop the leading prompt column from 3 to 2 so the input first character lines up with the status bar text. Wrap the prompt+input row in a single mouse-capture box and stop event propagation from TextInput's own handlers so any drag in that row delegates to composer selection without leaking to terminal-level selection.
Made-with: Cursor
* fix(tui): anchor hardware cursor during composer selection
When a composer selection covers a row exactly the column width, the rendered text fills the row and the terminal auto-wraps the hardware cursor to col 0 of the next row, leaving a ghost block beneath the prompt. Park the cursor at the start of the input box during selection so it can't escape the input region.
Made-with: Cursor
* fix(tui): hide hardware cursor during composer selection
Stop fighting auto-wrap by hiding the hardware cursor outright while the
composer has an active selection. This prevents both the ghost block under
the prompt (cursor wrapping past the last cell) and the parked-cursor block
on the first selected character. The cursor restores as soon as the
selection clears or focus changes.
Made-with: Cursor
* chore(tui): /clean — drop dead capture-pad path, dedupe gutter handlers
- TextInput: remove unused leftCaptureColumns prop and capture-pad math, drop
unused mouseApi.startAt, fold mouse offset into a single offsetAt helper,
share a MouseEventLite type across the four handlers.
- appLayout: hoist a GutterMouseEvent type and an endInputDrag callback so the
spacer/prompt/input rows share one shape.
- _tui_need_npm_install: lift the runtime-only key set to a module constant,
collapse nested isinstance checks, and document the mtime fallback.
Made-with: Cursor
* fix(tui): address copilot review on PR #16732
- Split InputSelection.clear() into clear() (cursor-preserving) and
collapseToEnd() (clear + jump to end). Cmd+C copy paths keep using
clear() so the cursor stays put; the blank-area click in useMainApp
switches to collapseToEnd() to match the requested UX.
- Spacer-row drags now force row=0 when forwarding into the input,
since the spacer's vertical origin doesn't align with the input box
and Ink mouse-capture keeps dispatching motion to the original
target. Prompt+input row drag keeps localRow because origins match.
Made-with: Cursor
* fix(tui): give TextInput Box an explicit width
After the /clean pass dropped the unused capture-pad math, the wrapping
Box also lost its explicit width and started sizing to its rendered
content. Clicks past the last character missed TextInput and fell
through to the parent prompt-row Box, which collapsed the cursor to
offset 0. Pin the Box back to `columns` so the input owns its full
column span regardless of value length.
Made-with: Cursor
* feat(tui): double-click select-all + hide cursor on terminal blur
- Track click time/offset in TextInput so a quick second click on the
same offset triggers select-all. Ink's screen-level multi-click is
bypassed once our onMouseDown captures, so the gesture has to be
detected locally.
- Extend the cursor-hide effect to also fire when the terminal loses
focus, so the hollow-rect ghost most terminals draw at the parked
cursor position disappears too.
Made-with: Cursor
* chore(tui): /clean — extract isMultiClickAt helper
Pull the click-recurrence math out of TextInput's onMouseDown into a
small isMultiClickAt(offset) helper so the handler reads as the gesture
list it actually is (multi-click → select-all, otherwise start).
Drop the redundant length>0 guard now that selectAll() already noops on
an empty value.
Made-with: Cursor
* docs(tui): explain _tui_need_npm_install content-vs-mtime comparison
Expand the docstring so future readers understand why we parse the
lockfiles instead of comparing mtimes, what the optional/peer skip
covers, how stale hidden-lock entries are handled, and when we fall
back to mtime.
Same layering concern as the persisted-assistant scrub already removed:
_emit_interim_assistant_message and the final_response return path were
mutating model output broadly. Streaming scrubber covers real leaks
delta-by-delta; these post-stream scrubs were redundant.
Reviewer pushback on the original boundary-hardening commits — three
overreach points pulled plugin-specific policy into shared core paths:
1. gateway/run.py hardcoded a '## Honcho Context' literal split for
vision-LLM output. Plugin-format heading in framework code; could
truncate legitimate output naturally containing that header.
Drop the literal split; keep generic sanitize_context (the wrapper
strip is plugin-agnostic). Plugin-specific cleanup belongs at the
provider boundary, not the shared gateway path.
2. run_agent.run_conversation scrubbed user_message and
persist_user_message before the conversation loop. User text is
sacred — if a user types a literal <memory-context> tag we must
not silently delete it. The producer (build_memory_context_block)
is the only legitimate emitter; user input should never need the
reverse op.
3. _build_assistant_message scrubbed model output before persistence.
Same hazard: would silently mutate legitimate documentation/code
the model emits containing the literal markers. The streaming
scrubber catches real leaks delta-by-delta before content is
concatenated; persist-time scrub was redundant belt-and-suspenders.
4. _fire_stream_delta stripped leading newlines from every delta unless
a paragraph break flag was set. Mid-stream '\n' is legitimate
markdown — lists, code fences, paragraph breaks — and chunk
boundaries are arbitrary. Narrow lstrip to the very first delta
of the stream only (so stale provider preamble still gets cleaned
on turn start, but mid-stream formatting survives).
Plus: build_memory_context_block now logs a warning when its defensive
sanitize_context strips something — surfaces buggy providers returning
pre-wrapped text instead of silently double-fencing.
Net architectural change: scrub surface collapses from 8 sites to 3
(StreamingContextScrubber on output deltas, plugin→backend send,
build_memory_context_block input-validation). Plugin-specific strings
stay out of shared runtime paths. User input and persisted assistant
output are no longer mutated.
Tests: rescoped TestMemoryContextSanitization (helper-correctness only,
no source-inspection of removed call sites), updated vision tests to
drop '## Honcho Context' literal-split assertions, updated
_build_assistant_message persistence test to assert preservation.
Added: cross-turn scrubber reset, build_memory_context_block warn-on-
violation, mid-stream newline preservation (plain + code fence).
Closed PR #5137 addressed the retrieval path (peer cards via get_card()
instead of the session-scoped lookup that returned empty for per-session
messaging flows) — that architectural fix is already in main as
_fetch_peer_card / _fetch_peer_context.
What never got fixed is the user-visible side: honcho_profile returning
a flat 'No profile facts available yet.' leaves the model to guess at
why. The model then often surfaces it to the user as a cryptic error.
Adds a diagnostic hint next to the existing 'result' message, enumerating
the likely causes in rough order of frequency:
1. Observation disabled for this peer (user_observe_me/others off)
2. Peer card hasn't accumulated yet (fresh peer / dialectic cadence
hasn't fired enough turns — cards build over time)
3. Generic fallback: self-hosted Honcho < 3.x lacks peer cards
The hint also suggests alternative tools (honcho_reasoning / honcho_search)
so the model can route around the empty card rather than giving up.
Schema description updated so the model knows the hint field exists and
that an empty card is NOT an error state.
7 tests cover the hint paths: warmup, observation-disabled for user + ai,
generic fallback, populated card still returns plain result (no hint),
alternative-tool suggestion present.
The scheme-validation commit (e77a3f2c) was too strict: a user with
legacy ''baseUrl: localhost:8000'' (no ''http://'' prefix) in their
''~/.honcho/config.json'' would get ''No API key configured'' from the
CLI after that change, even though their setup worked before.
urlparse on a schemeless host:port treats the host segment as the
scheme and leaves netloc empty, so the http/https check rejected it.
Falls back to a lenient check for schemeless strings that look like
hosts: contain '.' or ':', aren't a boolean/null literal, aren't pure
digits. The SDK still rejects truly malformed URLs at connect time
with a clearer error than ours.
Three new tests: legacy schemeless hosts accepted; obvious garbage
literals (''true'', ''null'', ''12345'') still rejected. Reviewer
noted concern #1: schemeless regression for self-hosters with old
configs.
Two small follow-ups to the PR review:
- Hoist hashlib import from _enforce_session_id_limit() to module top.
stdlib imports are free after first cache, but keeping all imports at
module top matches the rest of the codebase.
- _resolve_api_key now URL-parses baseUrl and requires http/https +
non-empty netloc before returning the 'local' sentinel. A typo like
baseUrl: 'true' (or bare 'localhost') no longer silently passes the
credential guard; the CLI correctly reports 'not configured'.
Three new tests cover the new validation (garbage strings, non-http
schemes, valid https).
fixes#5719
The auxiliary vision LLM called by gateway._enrich_message_with_vision
can echo its injected Honcho system prompt back into the image
description. That description gets embedded verbatim into the enriched
user message, so recalled memory (personal facts, dialectic output)
surfaces into a user-visible bubble.
Strips both forms of leak before embedding:
- <memory-context>...</memory-context> fenced blocks (sanitize_context)
- trailing '## Honcho Context' sections (header + everything after)
Plus regression tests:
- tests/agent/test_streaming_context_scrubber.py — 13 tests on the
stateful scrubber (whole block, split tags, false-positive partial
tags, unterminated span, reset, case-insensitivity)
- tests/run_agent/test_run_agent_codex_responses.py — 2 new tests on
_fire_stream_delta covering the realistic 7-chunk leak scenario and
the cross-turn scrubber reset
- tests/gateway/test_vision_memory_leak.py — 4 tests covering the
vision auto-analysis boundary (clean pass-through, '## Honcho Context'
header, fenced block, both patterns together)
When no explicit timeout is configured (HonchoClientConfig.timeout,
honcho.timeout / requestTimeout, or HONCHO_TIMEOUT), get_honcho_client
previously constructed the SDK with no timeout kwarg, letting the
underlying httpx client hang indefinitely if the Honcho backend
became unreachable mid-request.
This is a silent-failure hazard on the post-response path of
run_conversation: the memory_manager.sync_all() / queue_prefetch_all()
calls fire after the agent has already generated its final reply, so
a stalled Honcho request blocks run_conversation from returning.
The gateway never logs "response ready" and never delivers the
response to the platform (Telegram, etc.), even though the text is
already saved to the session file.
Repro: unplug the network or block app.honcho.dev mid-turn after
the model has produced its final message. Without this change,
_run_agent never returns. With it, the call aborts after 30s,
run_conversation returns, and the gateway delivers the response
(Honcho sync failure is logged and swallowed as before).
The default applies only when nothing is configured, so any
deployment that has explicitly set timeout / HONCHO_TIMEOUT /
honcho.timeout / honcho.requestTimeout keeps its existing value.
Self-hosted deployments that genuinely need a longer ceiling can
still override via any of those knobs.
_resolve_api_key() only checks for apiKey / HONCHO_API_KEY, so all
CLI subcommands (identity --show, status, migrate, etc.) bail with
"No API key configured" on self-hosted instances that use baseUrl
without an API key.
Return "local" when baseUrl or HONCHO_BASE_URL is set, matching the
client.py behavior that already handles this case for the SDK.
Tested on: macOS, self-hosted Honcho (Docker, localhost:8000).
Gateway session keys (Matrix "!room:server" + thread event IDs, Telegram
supergroup reply chains, Slack thread IDs with long workspace prefixes) can
exceed Honcho's 100-character session ID limit after sanitization. Every
Honcho API call for those sessions then 400s with "session_id too long".
Add a helper that enforces the 100-char limit after sanitization:
short keys (the common case) short-circuit unchanged; over-limit keys
keep a prefix and append a deterministic `-<8 hex>` SHA-256 suffix over
the original key so two long keys sharing a leading segment can't
collide onto the same truncated ID.
Adds 7 regression tests in tests/honcho_plugin/test_client.py covering
short / exact-limit / long / deterministic / collision-resistant /
allowlist-preserving / hash-suffix-present cases.
When a gateway drives Hermes (Telegram, Discord, Slack, ...), it passes the
platform-native user ID as ``runtime_user_peer_name`` into the Honcho
session manager. That ID wins over ``peer_name`` in ``honcho.json``, so a
single user who connects over three platforms ends up as three separate
Honcho peers — one per platform — with fragmented memory and no cross-
platform context continuity.
For multi-user bots this is correct (and must not change): each user gets
their own peer scope. For the vast majority of personal Hermes deployments
the configured ``peer_name`` is an unambiguous identity, though, so the
reporter asked for an opt-in knob that pins the user peer to that value.
Fix: new ``pinPeerName`` boolean on the host config, default ``false``.
When ``true`` AND ``peerName`` is set, the configured peer_name beats the
gateway's runtime identity; every other resolution case is unchanged.
honcho.json:
{
"peerName": "Igor",
"hosts": {
"hermes": { "pinPeerName": true }
}
}
session.py (resolution order, pinned case):
runtime_user_peer_name → skipped (opt-in flag active)
config.peer_name → WINS "Igor"
session-key fallback → unreached
Parsing follows the same host-block-overrides-root pattern as every other
flag in HonchoClientConfig.from_global_config (``_resolve_bool`` helper).
Tests (tests/honcho_plugin/test_pin_peer_name.py — 13 cases, 5 groups):
- Config parsing: default, root true, host-block true, host overrides
root, explicit false.
- Peer resolution: runtime wins by default (regression guard for multi-
user bots), config wins when pinned, pin-without-peer_name is a no-op
(prevents silent peer-id collapse to session-key fallback), CLI path
where runtime is absent, deepest fallback intact, assistant peer
untouched by the flag.
- Cross-platform unification: Telegram UID + Discord snowflake collapse
to one peer when pinned; negative control confirms two distinct
runtime IDs still produce two peers when unpinned.
244 honcho_plugin tests pass, 3 pre-existing skips, zero regressions.
Defensive detail: session.py uses ``getattr(self._config, "pin_peer_name",
False)`` so callers building partial config objects (several test fixtures
across the codebase do this) don't break if they haven't updated yet.
Runtime cost: one attr lookup per new session.
Closes#14984
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: bypass FTS5 for CJK queries in session_search
FTS5 default tokenizer splits CJK characters into individual tokens,
so multi-character queries like "大别山项目" become AND of single chars.
This produces few/no results compared to LIKE substring search.
For CJK queries, skip FTS5 entirely and use LIKE for accurate
phrase matching.
Fixes NousResearch/hermes-agent#15500
* fix: cache _contains_cjk, escape LIKE wildcards, add regression tests
On top of the CJK FTS5 bypass from #15509:
- Cache _contains_cjk() result in a local var to avoid redundant O(n)
scans on every CJK query
- Escape %, _ in LIKE queries so literal wildcards in user input are
not treated as SQL wildcards (consistent with other LIKE queries in
hermes_state.py that use ESCAPE '\')
- Fix misleading comment ('or CJK fallback' → accurate description)
- Add 3 regression tests:
- test_cjk_partial_fts5_results_supplemented_by_like (#15500 / #14829)
- test_cjk_like_dedup_no_duplicates
- test_cjk_like_escapes_wildcards (new wildcard escaping)
* feat: trigram FTS5 index for CJK search, replace LIKE fallback
Replace the LIKE '%query%' full-table-scan fallback for CJK queries with
a proper trigram FTS5 index (messages_fts_trigram). The trigram tokenizer
creates overlapping 3-byte sequences so substring matching works natively
for any script — CJK, Thai, etc.
For queries with 3+ CJK characters: uses the trigram FTS5 table with
proper ranking, snippets, and indexed lookups. For shorter queries
(1-2 CJK chars): falls back to LIKE since the trigram tokenizer needs
≥9 UTF-8 bytes (3 CJK chars) minimum.
Schema v10 migration creates the trigram table and backfills existing
messages. Triggers keep the index in sync on INSERT/UPDATE/DELETE.
Builds on top of #16276 (bypass FTS5 for CJK, escape LIKE wildcards).
---------
Co-authored-by: vominh1919 <vominh1919@gmail.com>
- config.py: remove dead ENV_VARS_BY_VERSION[17] entry (current _config_version
is 22, so all users are past version 17 and would never be prompted for
GMI_API_KEY on upgrade — consistent with how arcee was added)
- auxiliary_client.py: use google/gemini-3.1-flash-lite-preview as GMI aux
model instead of anthropic/claude-opus-4.6 (matches cheap fast-model pattern
used by all other providers: zai→glm-4.5-flash, kimi→kimi-k2-turbo-preview,
stepfun→step-3.5-flash, kilocode→google/gemini-3-flash-preview)
- test_gmi_provider.py: fix malformed write_text() call in doctor test
(was: write_text("GMI_API_KEY=*** encoding="utf-8") → missing closing quote,
wrote literal string 'GMI_API_KEY=*** encoding=' to .env file)
- test_gmi_provider.py + test_auxiliary_client.py: update aux model assertions
to match new cheaper default
- docs/integrations/providers.md: add 'gmi' to inline 'Supported providers'
fallback list (was only in the table, not the inline list at line ~1181)
- docs/reference/cli-commands.md: add 'gmi' to --provider choices list
Distinguish missing model from unsupported model before enabling fast mode and cover both cases so config and live agent state remain untouched on invalid fast toggles.
Match classic CLI parity by refusing to enable fast mode when the active model cannot produce fast request overrides, avoiding a misleading fast status with no runtime effect.
Make `config.set fast status` read-only and keep live agent request overrides in sync with fast-mode toggles so runtime API kwargs match the selected mode.
Harden busy mode config reads against invalid display config shapes and align /fast help+usage text with accepted aliases, with regression coverage for non-dict display values.
Route /browser, /reload-mcp, /rollback, /stop, /fast, and /busy through direct TUI RPC handlers so state changes hit the live gateway session instead of slash-worker fallback. Add TUI session finalize/reset parity hooks (memory commit + plugin boundaries) and parity matrix tests to keep mutating commands off fallback.
Handle queued-title ValueError cleanup during session init, harden Discord message source building for test stubs, and fix the Dockerfile contract test syntax error. Also refresh the TUI lockfile and Nix build flags so nix ubuntu-latest no longer fails on npm lock/peer resolution drift.
Retry queued pending titles even when the DB already has a non-empty title so explicit user title intents are not silently lost (for example after auto-title). Includes regression coverage.
Tighten pending-title flush during session init and treat row lookup failures during title-set no-op detection as RPC errors instead of silently queueing.
Handle session.title read failures without crashing, distinguish no-op title writes from missing session rows, and use a distinct empty-title error code with regression coverage.
- create HERMES_TUI_ACTIVE_SESSION_FILE with mkstemp instead of a predictable tmp path and always cleanup in finally
- add assertions that launch wiring uses a randomized session file path and removes it on exit
- use a grouped last_active join in search_sessions to avoid per-row correlated max lookups
- always close SessionDB in _resolve_last_session via finally and add regression coverage for search failure cleanup
- order session listing by computed last_active in SessionDB so callers get MRU rows directly
- keep _resolve_last_session as a single-row lookup and add regression coverage for >20 session sampling
Route TUI /title through session.title RPC and queue titles when the session DB row is still initializing, so renamed sessions reliably appear in /resume and browse flows.
Thread a vision-request flag through auxiliary provider resolution so Copilot clients can include Copilot-Vision-Request only for vision tasks. This preserves normal text requests while ensuring Copilot vision payloads reach the vision-capable route.
Add regression coverage for Copilot vision routing and keep cached text and vision clients separate so a text client without the header is not reused for vision.
Co-authored-by: dhabibi <9087935+dhabibi@users.noreply.github.com>
* fix: clean gateway auxiliary client caches on teardown
* fix(gateway): recover from stale pid files and close cron agents
Two issues were keeping the gateway from surviving long runs:
1. `_cleanup_invalid_pid_path` delegated to `remove_pid_file`, which
refuses to unlink when the file's pid differs from our own. That
safety check exists for the --replace atexit handoff, but it also
applied to stale-record cleanup, so after a crashy exit the pid
file was orphaned: `write_pid_file()`'s O_EXCL create then failed
with `FileExistsError`, and systemd looped on "PID file race lost
to another gateway instance". Unlink unconditionally from this
helper since the caller has already verified the record is dead.
2. The cron scheduler never closed the ephemeral `AIAgent` it creates
per tick, and never swept the process-global auxiliary-client
cache. Over days of 10-minute ticks this leaked subprocesses and
async httpx transports until the gateway hit EMFILE. Release the
agent and call `cleanup_stale_async_clients()` in `run_job`'s
outer `finally`, matching the gateway's own per-turn cleanup.
* chore(release): map bloodcarter@gmail.com -> bloodcarter
---------
Co-authored-by: bloodcarter <bloodcarter@gmail.com>
The backup takes a consistent snapshot of each .db via sqlite3.backup(),
so shipping the live .db-wal / .db-shm / .db-journal alongside pairs the
fresh snapshot with stale sidecar state and produces a torn restore on
first open. Sidecars are transient and SQLite regenerates them on next
connection anyway.
This also trims multi-MB of junk from every zip — state.db-wal alone was
~9 MB here, doubled by the fact the WAL is the live write-ahead log, not
data.
PR #13734 fixed the concurrent-tool-executor vector (ThreadPoolExecutor
workers didn't inherit the CLI's TLS approval callback). Two vectors
remained that could still land in the deadlocking input() fallback:
1. _spawn_background_review spawns a raw threading.Thread with no
approval callback installed, so any dangerous-command guard the
review agent trips falls back to input() -> deadlock against the
parent's prompt_toolkit TUI (same class as delegate_task subagents,
fixed in 023b1bff1 / #15491). Install a _bg_review_auto_deny
callback at thread start, clear on finally.
2. prompt_dangerous_approval's fallback unconditionally spawned a
daemon thread calling input() when approval_callback was None.
That fallback can never succeed under prompt_toolkit because the
user's Enter goes to pt's raw-mode stdin capture. Detect an active
pt Application via get_app_or_none() and fail closed (deny + log)
instead, so future threads that forget to install a callback
degrade gracefully instead of hanging 60s invisibly.
Regression guards:
- tests/run_agent/test_background_review.py verifies the review
worker thread sees a callable auto-deny callback mid-run and that
the slot is cleared in the finally block.
- tests/tools/test_approval.py TestFailClosedUnderPromptToolkit
verifies prompt_dangerous_approval returns 'deny' fast under a
mocked pt Application, and that a real callback still wins over
the guard.
The background skill/memory review agent was created without toolset
restrictions, inheriting the full default tool set. This allowed it to
use terminal, send_message, delegate_task, and other tools outside its
intended scope, potentially performing unrelated side effects after
skill creation.
Restrict the review agent to only memory and skills toolsets by passing
enabled_toolsets=['memory', 'skills'] during AIAgent construction.
Fixes#15204
The gateway fix in the previous commit forwards _session_messages on
gateway session teardown. The CLI exit cleanup path had the same bug:
it read getattr(agent, 'conversation_history', None) or [] — but AIAgent
has no conversation_history attribute, so providers always received [].
Switch to _session_messages (same attribute the gateway now uses),
guarded by isinstance(..., list) to preserve the no-arg fallback for
MagicMock-based CLI test stubs.
Adds tests/cli/test_cli_shutdown_memory_messages.py (4 cases mirroring
the gateway suite).
``_cleanup_agent_resources`` previously invoked
``agent.shutdown_memory_provider()`` with no arguments, so every memory
provider's ``on_session_end`` hook received an empty list. Providers
with an early-return guard on empty input (Holographic, Hindsight) never
extracted facts from the conversation, and users hit
"抱歉，找不到相關的對話記錄" on the first turn after any gateway
restart, session reset, or idle expiry.
Forward ``agent._session_messages`` — the transcript the agent itself
maintains and refreshes every turn via ``_persist_session`` — so
providers see the actual conversation. Falls back to the legacy no-arg
call whenever the attribute is absent or not a list (test stubs built
via ``object.__new__`` or ``MagicMock``) to preserve backward
compatibility with existing suites. ``AIAgent.shutdown_memory_provider``
already accepts ``messages: list = None`` (run_agent.py:4126), so this
is a pure caller-side fix.
Paths that use ``skip_memory=True`` temporary agents (memory flush,
hygiene auto-compress, ``/compress``) are no-ops inside
``shutdown_memory_provider`` because ``self._memory_manager`` is None —
no behaviour change for them.
Covers Part A of the bug report. Part B (adding ``on_session_end`` to
the Hindsight plugin) is a separate concern that would benefit from
this fix landing first.
Regression test added at
``tests/gateway/test_shutdown_memory_provider_messages.py`` covering:
populated messages forwarded, empty list still forwarded, attribute
missing falls back, non-list (MagicMock) falls back, provider
exceptions don't block ``close()``, None agent no-op, and agent
without ``shutdown_memory_provider`` tolerated.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Session-local trajectory cache — keyed by session hash, regenerated
per-session, won't port to another machine anyway. On a large install
this was multiple GB of pure noise in every zip.
Also adds a regression test for the pre-existing backups/ exclusion
so the two machine-local dirs share coverage.
The zip backup could add minutes to every 'hermes update' on large
HERMES_HOME directories. Flip the default to off and add a --backup
flag for one-off opt-in runs.
- updates.pre_update_backup default: True -> False
- hermes update: new --backup flag (opposite of existing --no-backup)
- Silent no-op when disabled (no message spam on every update)
- Existing --no-backup still works and wins over --backup
- Users who explicitly set pre_update_backup: true keep the old behavior
- Tests updated to cover default-off, --backup opt-in, and config-enabled paths
* feat(image-input): native multimodal routing based on model vision capability
Attach user-sent images as OpenAI-style content parts on the user turn when
the active model supports native vision, so vision-capable models see real
pixels instead of a lossy text description from vision_analyze.
Routing decision (agent/image_routing.py::decide_image_input_mode):
agent.image_input_mode = auto | native | text (default: auto)
In auto mode:
- If auxiliary.vision.provider/model is explicitly configured, keep the
text pipeline (user paid for a dedicated vision backend).
- Else if models.dev reports supports_vision=True for the active
provider/model, attach natively.
- Else fall back to text (current behaviour).
Call sites updated: gateway/run.py (all messaging platforms), tui_gateway
(dashboard/Ink), cli.py (interactive /attach + drag-drop).
run_agent.py changes:
- _prepare_anthropic_messages_for_api now passes image parts through
unchanged when the model supports vision — the Anthropic adapter
translates them to native image blocks. Previous behaviour
(vision_analyze → text) only runs for non-vision Anthropic models.
- New _prepare_messages_for_non_vision_model mirrors the same contract
for chat.completions and codex_responses paths, so non-vision models
on any provider get text-fallback instead of failing at the provider.
- New _model_supports_vision() helper reads models.dev caps.
vision_analyze description rewritten: positions it as a tool for images
NOT already visible in the conversation (URLs, tool output, deeper
inspection). Prevents the model from redundantly calling it on images
already attached natively.
Config default: agent.image_input_mode = auto.
Tests: 35 new (test_image_routing.py + test_vision_aware_preprocessing.py),
all existing tests that reference _prepare_anthropic_messages_for_api
still pass (198 targeted + new tests green).
* feat(image-input): size-cap + resize oversized images, charge image tokens in compressor
Two follow-ups that make the native image routing safer for long / heavy
sessions:
1) Oversize handling in build_native_content_parts:
- 20 MB ceiling per image (matches vision_tools._MAX_BASE64_BYTES,
the most restrictive provider — Gemini inline data).
- Delegates to vision_tools._resize_image_for_vision (Pillow-based,
already battle-tested) to downscale to 5 MB first-try.
- If Pillow is missing or resize still overshoots, the image is
dropped and reported back in skipped[]; caller falls back to text
enrichment for that image.
2) Image-token accounting in context_compressor:
- New _IMAGE_TOKEN_ESTIMATE = 1600 (matches Claude Code's constant;
within the realistic range for Anthropic/GPT-4o/Gemini billing).
- _content_length_for_budget() helper: sums text-part lengths and
charges _IMAGE_CHAR_EQUIVALENT (1600 * 4 chars) per image/image_url/
input_image part. Base64 payload inside image_url is NOT counted
as chars — dimensions don't matter, only image-presence.
- Both tail-cut sites (_prune_old_tool_results L527 and
_find_tail_cut_by_tokens L1126) now call the helper so multi-image
conversations don't slip past compression budget.
Tests: 9 new in test_image_routing.py (oversize triggers resize,
resize-fails-returns-None, oversize-skipped-reported), 11 new in
test_compressor_image_tokens.py (flat charge per image, multiple images,
Responses-API / Anthropic-native / OpenAI-chat shapes, no-inflation on
raw base64, bounds-check on the constant, integration test that an
image-heavy tail actually gets trimmed).
* fix(image-input): replace blanket 20MB ceiling with empirically-verified per-provider limits
The previous commit imposed a hardcoded 20 MB base64 ceiling on all
providers, triggering auto-resize on anything larger. This was wrong in
both directions:
* Too loose for Anthropic — actual limit is 5 MB (returns HTTP 400
'image exceeds 5 MB maximum' above that).
* Too strict for OpenAI / Codex / OpenRouter — accept 49 MB+ without
complaint (empirically verified April 2026 with progressive PNG
sizes).
New behaviour:
* _PROVIDER_BASE64_CEILING table: only anthropic and bedrock have a
ceiling (5 MB, since bedrock-on-Claude shares Anthropic's decoder).
* Providers NOT in the table get no ceiling — images attach at native
size and we trust the provider to return its own error if it
disagrees. A provider-specific 400 message is clearer than us
guessing wrong and silently degrading image quality.
* build_native_content_parts() gains a keyword-only provider arg;
gateway/CLI/TUI pass the active provider so Anthropic users get
auto-resize protection while OpenAI users don't pay it.
* Resize target dropped from 5 MB to 4 MB to slide safely under
Anthropic's boundary with header overhead.
Empirical measurements (direct API, no Hermes in the loop):
image b64 anthropic openrouter/gpt5.5 codex-oauth/gpt5.5
0.19 MB ✓ ✓ ✓
12.37 MB ✗ 400 5MB ✓ ✓
23.85 MB ✗ 400 5MB ✓ ✓
49.46 MB ✗ 413 ✓ ✓
Tests: rewrote TestOversizeHandling (5 tests): no-ceiling pass-through,
Anthropic resize fires, Anthropic skip on resize-fail, build_native_parts
routes ceiling by provider, unknown provider gets no ceiling. All 52
targeted tests pass.
* refactor(image-input): attempt native, shrink-and-retry on provider reject
Replace proactive per-provider size ceilings with a reactive shrink path
on the provider's actual rejection. All providers now attempt native
full-size attachment first; if the provider returns an image-too-large
error, the agent silently shrinks and retries once.
Why the previous design was wrong: hardcoding provider ceilings
(anthropic=5MB, others=unlimited) meant OpenAI users on a 10MB image
paid no tax, but Anthropic users lost quality on anything >5MB even
though the empirical behaviour at provider-reject time is the same
(shrink + retry). Baking the table into the routing layer also
requires updating Hermes every time a provider's limit changes.
Reactive design:
- image_routing.py: _file_to_data_url encodes native size, no ceiling.
build_native_content_parts drops its provider kwarg.
- error_classifier.py: new FailoverReason.image_too_large + pattern
match ("image exceeds", "image too large", etc.) checked BEFORE
context_overflow so Anthropic's 5MB rejection lands in the right
bucket.
- run_agent.py: new _try_shrink_image_parts_in_messages walks api
messages in-place, re-encodes oversized data: URL image parts
through vision_tools._resize_image_for_vision to fit under 4MB,
handles both chat.completions (dict image_url) and Responses
(string image_url) shapes, ignores http URLs (provider-fetched).
New image_shrink_retry_attempted flag in the retry loop fires the
shrink exactly once per turn after credential-pool recovery but
before auth retries.
E2E verified live against Anthropic claude-sonnet-4-6:
- 17.9MB PNG (23.9MB b64) attached at native size
- Anthropic returns 400 "image exceeds 5 MB maximum"
- Agent logs '📐 Image(s) exceeded provider size limit — shrank and
retrying...'
- Retry succeeds, correct response delivered in 6.8s total.
Tests: 12 new (8 shrink-helper shapes + 4 classifier signals),
replaces 5 proactive-ceiling tests with 3 simpler 'native attach works'
tests. 181 targeted tests pass. test_enum_members_exist in
test_error_classifier.py updated for the new enum value.
* feat(plugins): google_meet — bundled plugin for join+transcribe Meet calls
v1 shipping transcribe-only. Spawns headless Chromium via Playwright,
joins an explicit https://meet.google.com/ URL, enables live captions,
and scrapes them into a transcript file the agent can read across turns.
The agent then has the meeting content in context and can do followup
work (send recap, file issues, schedule followups) with its regular tools.
Surface:
- Tools: meet_join, meet_status, meet_transcript, meet_leave, meet_say
(meet_say is a v1 stub — returns not-implemented; v2 will wire
realtime duplex audio via OpenAI Realtime / Gemini Live +
BlackHole / PulseAudio null-sink.)
- CLI: hermes meet setup | auth | join | status | transcript | stop
- Lifecycle: on_session_end auto-leaves any still-running bot.
Safety:
- URL regex rejects anything that isn't https://meet.google.com/...
- No calendar scanning, no auto-dial, no auto-consent announcement.
- Single active meeting per install; a second meet_join leaves the first.
- Platform-gated to Linux + macOS (Windows audio routing for v2 untested).
- Opt-in: standalone plugin, user must add 'google_meet' to
plugins.enabled in config.yaml.
Zero core changes. Plugin uses existing register_tool /
register_cli_command / register_hook surfaces. 21 new unit tests cover the
URL safety gate, transcript dedup + status round-trip, process-manager
refusals/start/stop paths, tool-handler JSON shape under each branch,
session-end cleanup, and platform-gated register().
* feat(plugins/google_meet): v2 realtime audio + v3 remote node host
v2 \u2014 agent speaks in-meeting
audio_bridge.py: PulseAudio null-sink (Linux) + BlackHole probe (macOS).
On Linux we load pactl module-null-sink + module-virtual-source, track
module ids for teardown; Chrome gets PULSE_SOURCE=<virt src> env so its
fake mic reads what we write to the sink. macOS just probes BlackHole
2ch and returns its device name \u2014 the plugin refuses to switch the
user's default audio input (that would surprise them).
realtime/openai_client.py: sync WebSocket client for the OpenAI Realtime
API. RealtimeSession.speak(text) sends conversation.item.create +
response.create, accumulates response.audio.delta PCM bytes, appends
them to a file. RealtimeSpeaker runs a JSONL-queue loop consuming
meet_say calls. 'websockets' is an optional dep imported lazily.
meet_bot.py: when HERMES_MEET_MODE=realtime, provisions AudioBridge,
starts RealtimeSession + speaker thread, spawns paplay to pump PCM
into the null-sink, then cleans everything up on SIGTERM. If any
realtime setup step fails, falls back cleanly to transcribe mode
with an error flagged in status.json.
process_manager.enqueue_say(): writes a JSONL line to say_queue.jsonl;
refuses when no active meeting or active meeting is transcribe-only.
tools.meet_say: real implementation; requires active mode='realtime'.
meet_join: adds mode='transcribe'|'realtime' param.
v3 \u2014 remote node host
node/protocol.py: JSON envelope (type, id, token, payload) + validate.
node/registry.py: $HERMES_HOME/workspace/meetings/nodes.json, with
resolve() auto-selecting the sole registered node when name is None.
node/server.py: NodeServer \u2014 websockets.serve, bearer-token auth,
dispatches start_bot/stop/status/transcript/say/ping onto the local
process_manager. Token auto-generated + persisted on first run.
node/client.py: NodeClient \u2014 short-lived sync WS per RPC, raises
RuntimeError on error envelopes, clean API matching the server.
node/cli.py: 'hermes meet node {run,list,approve,remove,status,ping}'
subtree; wired into the main meet CLI by cli.py so 'hermes meet node'
Just Works.
tools.py: every meet_* tool accepts node='<name>'|'auto'; when set,
routes through NodeClient to the remote bot instead of running
locally. Unknown node \u2192 clear 'no registered meet node matches ...'
error.
cli.py: 'hermes meet join --node my-mac --mode realtime' and
'hermes meet say "..." --node my-mac' route to the node; 'hermes
meet node approve <name> <url> <token>' registers one.
Tests
21 v1 tests updated (meet_say is no longer a stub; active-record now
carries mode).
20 new audio_bridge + realtime tests.
42 new node tests (protocol/registry/server/client/cli).
17 new v1/v2/v3 integration tests at the plugin level covering
enqueue_say edge cases, env var passthrough, mode validation, node
routing (known/unknown/auto/ambiguous), and argparse wiring for
`hermes meet say` + `hermes meet node` + --mode/--node flags.
Total: 100 plugin tests + 58 plugin-system tests = 158 passing.
E2E verified on Linux with fresh HERMES_HOME: plugin loads, 5 tools
register, on_session_end hook wires, 'hermes meet' CLI tree wires
including the node subtree, NodeRegistry round-trips, meet_join routes
correctly to NodeClient under node='my-mac' with mode='realtime',
enqueue_say accepts realtime/rejects transcribe, argparse parses every
new flag cleanly.
Zero changes to core. All new code lives under plugins/google_meet/.
* feat(plugins/google_meet): auto-install, admission detect, mac PCM pump, barge-in, richer status
Ready-for-live-test follow-up on PR #16364. Five additions that matter for
the first live run on a real Meet, in priority order:
1. hermes meet install [--realtime] [--yes]
pip install playwright websockets + python -m playwright install chromium
--realtime: installs platform audio deps (pulseaudio-utils on Linux via
sudo apt, blackhole-2ch + ffmpeg on macOS via brew). Prompts before
sudo/brew unless --yes. Refuses on Windows. Refuses to auto-flip the
macOS default input — user still selects BlackHole in System Settings
(deliberate; surprise audio rerouting is worse than a manual step).
2. Admission detection
_detect_admission(page): Leave-button visible OR caption region
attached OR participants list present → we're in-call.
_detect_denied(page): 'You can\'t join this video call' / 'You were
removed' / 'No one responded to your request' → bail out.
HERMES_MEET_LOBBY_TIMEOUT (default 300s) caps how long we sit in
the lobby before giving up. in_call stays False until admitted.
Status surfaces leaveReason: duration_expired | lobby_timeout |
denied | page_closed.
3. macOS PCM pump
ffmpeg reads speaker.pcm (24kHz s16le mono) and writes to the
BlackHole AVFoundation output via -f audiotoolbox
-audio_device_index <N>. _mac_audio_device_index() probes
ffmpeg -f avfoundation -list_devices true to resolve 'BlackHole 2ch'
→ numeric index. Falls back to index 0 on probe failure. Linux
paplay pump unchanged.
4. Richer status dict
_BotState now tracks realtime, realtimeReady, realtimeDevice,
audioBytesOut, lastAudioOutAt, lastBargeInAt, joinAttemptedAt,
leaveReason. RealtimeSession.audio_bytes_out / last_audio_out_at
counters fold into the status file once a second so meet_status()
can show the agent's voice activity in near-real-time.
5. Barge-in
RealtimeSession.cancel_response() sends type='response.cancel' over
the same WS (lock-guarded so it's safe to call from the caption
thread while speak() is reading frames). Handles response.cancelled
as a terminal frame type. _looks_like_human_speaker() gates triggers
so the bot's own name, 'You', 'Unknown', and blanks don't self-cancel.
Called from the caption drain loop: when a new caption arrives
attributed to a real participant while rt.session exists, we fire
cancel_response() and stamp lastBargeInAt.
Tests: 20 new unit tests across _BotState telemetry, barge-in gating,
admission/denied probe error handling, cancel_response with and without
a connected WS, and `hermes meet install` CLI wiring (flag parsing +
end-to-end subprocess.run verification + Linux-already-installed fast
path). Total 171 passing across all google_meet test files + the
plugin-system regression suite.
E2E verified on Linux: plugin loads, all 5 tools register,
`hermes meet install --realtime --yes` parses, fresh-bot status.json
has every new telemetry key, cancel_response on a disconnected session
returns False without raising, barge-in helper gates the bot's own
name correctly.
Still out of scope (for a future PR, not blocking live test):
mic → Realtime duplex (the agent listening to meeting audio via
WebRTC), node-host TLS/pairing UX, Windows audio, Meet create+Twilio.
Docs updated: SKILL.md now lists the installer subcommand, lobby
timeout, barge-in caveat, and the full status-dict reference table.
README.md quick-start uses hermes meet install.
Every 'hermes update' now runs a full backup of ~/.hermes/ first, so
users can always roll back to the exact state they had before the
update if anything goes wrong (corrupted sessions.db, broken skills,
config migrations that don't round-trip, etc.).
Changes:
- hermes_cli/backup.py: new create_pre_update_backup() helper. Writes
to <HERMES_HOME>/backups/pre-update-<stamp>.zip using the same
exclusion rules and SQLite safe-copy as 'hermes backup'. Auto-rotates
(keep last N, pre-update-*.zip only — hand-dropped zips in backups/
are untouched). Adds 'backups' to _EXCLUDED_DIRS so subsequent backups
don't nest prior ones.
- hermes_cli/main.py: _run_pre_update_backup() wired into
_cmd_update_impl before any git operation. Prints save path, restore
command, and how to disable. Swallows failures so a broken backup
never blocks the update itself. New --no-backup flag on 'hermes
update' for one-off override.
- hermes_cli/config.py: new 'updates' section in DEFAULT_CONFIG with
pre_update_backup (default true) and backup_keep (default 5).
Auto-surfaces in the dashboard config UI.
- tests/hermes_cli/test_backup.py: +11 tests covering backup location,
content parity with 'hermes backup', no-recursion, rotation, manual
file preservation, config gate, --no-backup flag, flag-wins-over-config.
The CLI renders through prompt_toolkit in non-full-screen mode, so every
repaint uses the renderer's tracked _cursor_pos.y to cursor_up() + erase
before drawing the new frame. Any time that tracked position drifts from
terminal reality, redraws stack on top of stale content instead of
overwriting it. Four user-visible bugs share this root cause.
Fixes:
- #5474 (SIGWINCH ghosts): the resize wrapper previously only handled
column-shrink reflow. Generalize it to force a full screen-clear
(erase_screen + cursor_goto(0,0)) and renderer.reset() on every resize
— covers widen, row-shrink, and multiplexer SIGWINCH-less redraws.
- #8688 (cmux/tmux tab switch): no SIGWINCH fires on focus regain, so
prompt_toolkit has no signal to recover. Add a _force_full_redraw()
helper, bound to Ctrl+L (standard bash/zsh/vim convention) and exposed
as /redraw. Users can manually clear drift without restarting Hermes.
- #14692 (DSR response leaks — ^[[53;1R): resize storms make
prompt_toolkit's CSI 6n queries race past the input parser; the
terminal's reply ends up as literal input text. Add a sibling of the
bracketed-paste sanitizer that strips \x1b[<row>;<col>R and the
caret-escape visible form from paste text, buffer text-filter, and
the input-processing loop.
The idle-redraw removal (#12641) is in the preceding commit from
@foxion37 — keeping them as separate commits preserves attribution.
On provider switches mid-session (e.g. MiniMax -> DeepSeek), the source
assistant turn carries a 'reasoning' field written by the prior provider
but no 'reasoning_content' key. _copy_reasoning_content_for_api would
promote that foreign 'reasoning' to 'reasoning_content' on the outbound
DeepSeek request, leaking a cross-provider chain of thought and in
practice causing HTTP 400.
DeepSeek's own _build_assistant_message always pins reasoning_content=''
at creation time for tool-call turns, so the shape (reasoning set,
reasoning_content absent, tool_calls present) is unreachable from
same-provider DeepSeek history — it can only come from a prior provider.
Pad with '' in that case instead of promoting.
Healthy same-provider 'reasoning' promotion (no tool_calls, or on
providers that do not require the empty-string pin) is unchanged.
Defensive: when the generator encounters a fenced code block containing
Unicode box-drawing characters, wrap it in `<!-- ascii-guard-ignore -->`
markers so the docs-site-checks lint (which scans inside code fences)
can't reject the page for a skill's own diagram.
Plain bash/python code blocks stay uncluttered — only blocks with box
chars get wrapped. Skill authors no longer have to remember to add the
ignore markers in every SKILL.md with ASCII art.
Fixes#15305.
Quick state snapshot now includes pairing JSONs (generic + legacy +
Feishu comment pairing), and `hermes update` takes a pre-update
snapshot labeled `pre-update` before pulling.
Pairing data lives outside state.db in platform-specific JSONs under
~/.hermes/pairing/, ~/.hermes/platforms/pairing/, and
~/.hermes/feishu_comment_pairing.json. The update command already
couldn't touch $HERMES_HOME, but #15733 reports lost pairing after
an update — this gives users something to restore from via
`/snapshot list` / `/snapshot restore <id>` if anything clobbers
the approved-user lists.
- Extend _QUICK_STATE_FILES with pairing paths (files + dirs)
- Snapshot walks directories recursively and records each file in the
manifest individually so restore logic is unchanged
- _cmd_update_impl calls create_quick_snapshot(label='pre-update')
after 'Found N new commits' and before 'Pulling updates'
- Snapshot failures are logged at debug and never block the update
Refs #15733.
read_file's dedup path returned a lightweight stub on re-reads of an
unchanged file, then returned early — so the consecutive-read loop
guard (hard block at count>=4) at the bottom of read_file_tool never
ran for stub-looped calls. Weaker tool-following models (local Qwen3.6
variants in the reported case) ignore the passive 'refer to earlier
result' hint and hammer the same read_file call until iteration budget
runs out.
Track per-key stub returns in task_data['dedup_hits'] and, on the
second stub for the same (path, offset, limit), return a hard BLOCKED
error mirroring the wording the real-read path already uses. A real
read, an intervening non-read tool call (notify_other_tool_call), or
reset_file_dedup (on context compression) all clear the counter so
the guard never stays engaged longer than the actual loop.
Closes#15759
Telegram groups emit a single bot_command entity covering the whole
/cmd@botname span with no accompanying mention entity, so the existing
mention gate in _message_mentions_bot dropped slash commands sent via
the bot-menu autocomplete whenever require_mention is enabled.
Recognise bot_command entities whose @botname suffix matches the bot
username (case-insensitive) as a direct mention, and keep rejecting
commands addressed at other bots. Fixes#15415.
When 'hermes model' runs against a providers: (keyed-schema) entry that
relies only on key_env, the picker resolves the env var for the live
/models request and then wrote a synthesized 'api_key: ${KEY_ENV}' back
to the providers.<key> entry. That's redundant — the runtime already
resolves from key_env directly — and it clutters configs that
intentionally keep credentials out of config.yaml.
Only persist provider_entry['api_key'] when the user originally had an
inline value (literal secret or ${VAR} template). Entries that declared
only key_env stay clean on save.
Fixes#15803.
Harden the Matrix adapter's sender-drop guards so bot-self events and
appservice/bridge identities never reach the gateway's pairing flow or
the agent loop.
Two filters, applied as early as possible in _on_room_message (and
_on_reaction for the self-filter):
1. _is_self_sender(sender) — case-insensitive + whitespace-trimmed
equality with self._user_id. When self._user_id is still empty
(whoami has not resolved, or login failed), returns True
defensively: an unidentified bot dropping its own events is always
preferable to falling into an echo loop. The previous byte-for-byte
equality check let differently-cased copies of the bot's MXID slip
through, and an unresolved self-ID silently disabled the guard.
2. _is_system_or_bridge_sender(sender) — drops appservice namespace
puppets (conventional @_bridge_...:server form) and malformed
senders with an empty localpart. These identities used to fall
through to the gateway's unauthorized-user path, trigger a pairing
code, and — once an operator approved the bridge — every outbound
message the bridge relayed would loop back as an authorized user
message. This was the root of the 'hall of mirrors' symptom.
Fixes#15763
Test plan
---------
scripts/run_tests.sh tests/gateway/test_matrix.py
scripts/run_tests.sh tests/gateway/test_matrix_mention.py tests/gateway/test_matrix_voice.py
All 182 tests pass. 14 new regression tests cover exact / case-insensitive
/ whitespace / unresolved-self-id matches, bridge prefix detection, empty
sender, and the full _on_room_message drop path.
Closes#15775.
Title generation swallowed exceptions at debug level and returned None,
so a depleted auxiliary provider (e.g. OpenRouter 402) silently left
sessions with NULL titles. Reporter observed 45 untitled sessions
accumulated over 19 days with no user-visible indication.
- agent/title_generator.py: accept optional failure_callback, bump log
to WARNING, invoke callback on call_llm exception (swallowing callback
errors so nothing can crash the fire-and-forget worker thread).
- cli.py, gateway/run.py: pass agent._emit_auxiliary_failure as the
callback so failures route through the existing user-visible warning
channel.
- tests: cover callback fires / errors are swallowed / no-callback
legacy behavior / maybe_auto_title forwards kwarg to worker.
raw_content from message["content"] can be a list that contains bare
strings, not only dicts. The previous `p.get("text", "")` call raised
AttributeError on string items, crashing context compression for any
session that had a message with mixed content.
Guard with isinstance checks: dict → .get("text"), str → len(p),
fallback → len(str(p)). Adds a regression test covering the bare-string
case that would have AttributeError'd on the pre-fix code.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
_find_tail_cut_by_tokens called len(content) to estimate message tokens.
When content is a list of blocks (multimodal: text + image_url), len()
returns block count (e.g. 2) rather than character count, so a message
with 500 chars of text was counted as ~10 tokens instead of ~135.
This caused the backward walk to exhaust all messages before hitting the
budget ceiling; the head_end safeguard then forced cut = n - min_tail,
shrinking the protected tail to the bare minimum and preventing effective
compression of long multimodal conversations.
Fix mirrors the existing pattern in _prune_old_tool_results (line 487):
sum(len(p.get("text", "")) for p in raw_content)
if isinstance(raw_content, list) else len(raw_content)
Tests: 3 new cases in TestTokenBudgetTailProtection — regression guard
(confirms the test fails with the bug), plain-string regression guard,
and image-only block edge case.
Fixes#16087.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
If the gateway's Python env loses access to 'croniter' between when a
cron job was created and when mark_job_run() fires, compute_next_run()
returns None for cron schedules. mark_job_run() treated that as terminal
completion and wrote enabled=false, state=completed — turning a missing
runtime dep into a silent, permanent job-off.
That behaviour is safe for one-shot jobs but wrong for recurring ones. A
missing dep should surface as an error the user can see, not as successful
completion of a job that is about to stop firing.
mark_job_run() now only disables the job on next_run_at=None when the
schedule is one-shot. For recurring (cron/interval) schedules it keeps
enabled=true, sets state=error, and records last_error so the user can
see why the job isn't advancing. compute_next_run() also logs a warning
the first time cron+no-croniter hits, so the underlying cause is visible
in the gateway log.
Tests cover:
- recurring cron job stays enabled with state=error when HAS_CRONITER=False
- recurring interval stays enabled when compute_next_run returns None
- one-shot jobs still flip to enabled=false, state=completed (no regression)
Fixes#16265
Azure Foundry deploys GPT-5.x, codex-*, and o1/o3/o4 reasoning models as
Responses-API-only. Calling /chat/completions against these deployments
returns 400 'The requested operation is unsupported.', which broke any
user who ran 'hermes model' on Azure, picked a gpt-5/codex deployment,
and kept the default api_mode: chat_completions. Verified in a user
debug bundle on 2026-04-26: gpt-5.3-codex failed on synopsisse.openai.azure.com
with that exact payload while gpt-4o-pure on the same endpoint worked.
Adds azure_foundry_model_api_mode(model_name) that returns
codex_responses when the model name starts with gpt-5, codex, o1, o3,
or o4 — otherwise None so chat_completions / anthropic_messages stay
untouched for gpt-4o, Llama, Claude-via-Anthropic, etc.
Resolver (both the direct Azure Foundry path and the pool-entry path)
consults it and upgrades api_mode unless the user explicitly picked
anthropic_messages. target_model (from /model mid-session switch)
takes precedence over the persisted default so switching from gpt-4o
to gpt-5.3-codex routes correctly before the next request.
Docs: correct the azure-foundry guide which previously claimed Azure
keeps gpt-5.x on chat completions — that was only true for early Azure
OpenAI, not Azure Foundry codex/o-series deployments.
Tests: 14 unit tests for azure_foundry_model_api_mode + 6 integration
tests in TestAzureFoundryResolution covering Bob's exact scenario,
target_model override, anthropic_messages guard, and o3-mini.
Parse scope from the raw callback URL before stripping the auth code so Flow.fetch_token matches user-granted scopes. Add regression test for dual-scope callbacks.
Made-with: Cursor
Two related fixes for OpenClaw-residue problems after an OpenClaw→Hermes
migration (especially migrations done via OpenClaw's own tool, which
doesn't archive the source directory).
1. optional-skills/migration/openclaw-migration/scripts/openclaw_to_hermes.py:
rebrand_text() was rewriting ~/.openclaw/config.yaml → ~/.Hermes/config.yaml
(capital H — a directory that doesn't exist). Now case-preserving:
"OpenClaw" → "Hermes" (prose), but "openclaw" → "hermes" (so filesystem
paths land on the real Hermes home). Regex logic unchanged — replacement
function now checks if the matched text was all-lowercase and emits the
replacement in the matching case.
2. agent/onboarding.py + cli.py: one-time startup banner the first time
Hermes launches and finds ~/.openclaw/. Tells the user to run
`hermes claw cleanup` to archive it, gated on the existing onboarding
seen-flag framework (onboarding.seen.openclaw_residue_cleanup in
config.yaml). Fires once per install; re-running requires wiping that
flag or running cleanup directly.
Tests:
- 4 new TestDetectOpenclawResidue tests (present / absent / file-instead-
of-dir / default-home smoke)
- 2 TestOpenclawResidueHint tests (content check)
- 2 TestOpenclawResidueSeenFlag tests (flag isolation + round-trip)
- test_rebrand_text_preserves_filesystem_path_casing regression test
with 4 scenarios including the exact ~/.openclaw/config.yaml case
- Existing test_rebrand_text_* tests updated to the new case-preserving
contract (lowercase input → lowercase output)
Co-authored-by: teknium1 <teknium@noreply.github.com>
* feat(skills): install skills from a direct HTTP(S) URL
Adds UrlSource adapter so `hermes skills install <url-to-SKILL.md>` and
`/skills install <url>` work as first-class operations — no more
improvising with curl + patch + cp.
- Claims identifiers that start with http(s):// and end in .md
- Skips /.well-known/skills/ URLs (WellKnownSkillSource handles those)
- Skill name from YAML frontmatter, URL-slug fallback
- Single-file SKILL.md only (v1 scope — multi-file skills need a manifest)
- Trust level 'community'; full security scan still runs
- Lock file stores the URL as identifier so `hermes skills update`
re-fetches from the same URL cleanly
Scope matches real user need from @versun's docx feedback where
`https://sharethis.chat/SKILL.md` had no first-class install path.
* feat(skills): interactive name/category for URL installs + --name override
Follow-up to the UrlSource adapter. The previous commit fell back to weak
heuristics when frontmatter had no ``name:`` and could produce garbage names
like ``SKILL`` or ``unnamed-skill``. Now:
tools/skills_hub.py
- ``UrlSource._is_valid_skill_name()`` — strict identifier check
(``^[a-z][a-z0-9_-]*$``), rejects sentinel values (``SKILL``, ``README``,
``INDEX``, ``unnamed-skill``, empty, non-strings).
- ``_resolve_skill_name()`` returns ``Optional[str]`` — ``None`` when
nothing valid is resolvable. Also ignores unsafe frontmatter names
(``../evil``) and falls through to URL slug instead of returning None
immediately, so a URL with a bad frontmatter but a good path still
works.
- ``fetch()``/``inspect()`` carry an ``awaiting_name=True`` marker in
metadata/extra when resolution fails, letting ``do_install`` decide
whether to prompt, apply an override, or error out.
hermes_cli/skills_hub.py
- ``do_install`` gains a ``name_override`` parameter.
- On URL-sourced bundles with ``awaiting_name=True``:
1. If ``name_override`` is valid → use it.
2. If ``name_override`` is invalid → refuse with a clear error.
3. Else if ``skip_confirm=True`` (non-interactive: slash / TUI /
gateway / scripts) → refuse with an actionable retry hint pointing
at ``--name <your-name>`` on both CLI and slash forms.
4. Else (interactive TTY) → prompt for the name.
- Interactive TTY also prompts for a category when none is given for a
URL-sourced install, hinting existing category buckets so users can
reuse ``productivity``, ``devops``, etc. Empty input → flat install.
- ``_existing_categories()`` scans ``~/.hermes/skills/`` for subdirs that
look like category buckets (contain nested SKILL.md files); skips
top-level skills and hidden dirs.
- ``_prompt_for_skill_name()`` / ``_prompt_for_category()`` helpers
(EOF/Ctrl-C-safe, match the existing ``Confirm [y/N]`` prompt style).
hermes_cli/main.py
- ``hermes skills install`` argparse gains ``--name <name>``.
hermes_cli/skills_hub.py (slash)
- ``/skills install <url> --name <x>`` parsing added.
Tests
- tests/tools/test_skills_hub.py: updated ``UrlSource`` tests to assert
the new ``awaiting_name`` metadata; added 4 new tests for
``_is_valid_skill_name`` rejection sets and the awaiting-name marker.
- tests/hermes_cli/test_skills_hub.py: 8 new tests covering --name
override accept/reject, non-interactive error, interactive name prompt,
interactive category prompt, cancel-aborts-install, and
``_existing_categories`` scan behavior (buckets vs flat skills).
- E2E verified all four paths (no-name/no-override → error;
--name override → install; frontmatter name → install;
invalid --name → rejection).
---------
Co-authored-by: teknium1 <teknium@noreply.github.com>
`_resolve_effective_accept()` used `return bool(cfg_val)` for the
`hooks_auto_accept` config key. In Python, `bool("false")` is `True`,
so a user setting `hooks_auto_accept: "false"` (quoted YAML string)
in `config.yaml` would silently enable auto-approval of every shell
hook, bypassing the consent prompt entirely.
Replace the coercion with the same type-aware parsing already used for
the HERMES_ACCEPT_HOOKS env var three lines above: bool passthrough,
strings checked against {1,true,yes,on} case-insensitively, everything
else (including "false", None, 0, ints) rejected.
Add TestHooksAutoAcceptParsing guarding the regression across all four
value shapes (bool, string-truthy, string-falsy, missing/None).
Reported by @sprmn24 in #16244.
- remove the temporary -c MRU logic and companion test from this branch so PR #15926 stays focused on TUI perf work
- keep the resume-ordering change isolated in the dedicated follow-up PR
CPU profiling showed the built TUI loading React development modules unless NODE_ENV was set. Default CLI and dashboard TUI children to production while preserving explicit user overrides.
When _compress_context rotates session_id (compression split), fire
on_session_start(new_sid, boundary_reason="compression",
old_session_id=<old>) on the active context engine. Plugin engines
(e.g. hermes-lcm) use this to preserve DAG lineage across the rollover
instead of re-initializing fresh per-session state.
Built-in ContextCompressor.on_session_start accepts **kwargs and ignores
them — no behavior change for default users.
Closes hermes-lcm#68 symptom: after Hermes compressed and minted a new
physical session, LCM was treating the split as a fresh /new and losing
continuity (compression_count: 1, store_messages: 0, dag_nodes: 0).
Credit: @Tosko4 (PR #13370) — minimized scope to the boundary_reason
signal only; the broader session-lifecycle refactor will be taken in
separate PRs if justified by concrete plugin need.
Every working dir hermes ever touches gets its own shadow git repo under
~/.hermes/checkpoints/{sha256(abs_dir)[:16]}/. The per-repo _prune is a
no-op (comment in CheckpointManager._prune says so), so abandoned repos
from deleted/moved projects or one-off tmp dirs pile up forever. Field
reports put the typical offender at 1000+ repos / ~12 GB on active
contributor machines.
Adds an opt-in startup sweep that mirrors the sessions.auto_prune
pattern from #13861 / #16286:
- tools/checkpoint_manager.py: new prune_checkpoints() and
maybe_auto_prune_checkpoints() helpers. Deletes shadow repos that
are orphan (HERMES_WORKDIR marker points to a path that no longer
exists) or stale (newest in-repo mtime older than retention_days).
Idempotent via a CHECKPOINT_BASE/.last_prune marker file so it only
runs once per min_interval_hours regardless of how many hermes
processes start up.
- hermes_cli/config.py: new checkpoints.auto_prune /
retention_days / delete_orphans / min_interval_hours knobs.
Default auto_prune: false so users who rely on /rollback against
long-ago sessions never lose data silently.
- cli.py / gateway/run.py: startup hooks gated on checkpoints.auto_prune,
called right next to the existing state.db maintenance block.
- Docs updated with the new config knobs.
- 11 regression tests: orphan/stale deletion, precedence, byte-freed
tracking, non-shadow dir skip, interval gating, corrupt marker
recovery.
Refs #3015 (session-file disk growth was fixed in #16286; this covers
the checkpoint side noted out-of-scope there).
The write_file guard added in #16223 used strict equality against the
internal dedup status message. In practice, the model sometimes
prepends a short note or appends a trailing comment before calling
write_file, which slipped past the strict check.
Broaden the heuristic: reject writes whose stripped content equals
the status message OR contains it and is <=2x its length. Short,
status-dominated writes are always corruption; legitimate docs that
quote the message verbatim are always much longer.
Adds two tests: one for the small-wrapper corruption shape, one
confirming large legitimate files that quote the status still write.
write_file_tool and patch_tool both call _update_read_timestamp to
refresh the staleness tracker after writing, but they never invalidate
the dedup cache entries for the written path. The dedup cache keys are
(resolved_path, offset, limit) → mtime tuples populated by read_file_tool.
On filesystems where a read and write land in the same mtime second (or
when mtime granularity is 1s), the cached and current mtime are equal,
so the dedup check incorrectly returns a 'File unchanged since last
read' stub — even though the file was just overwritten.
The agent then sees stale content (or a stale 'File not found' error)
and enters expensive error-recovery loops, burning API calls.
Fix: add _invalidate_dedup_for_path(filepath, task_id) that removes all
dedup entries whose resolved path matches the written file. Called from
_update_read_timestamp so both write_file_tool and patch_tool benefit
automatically. Scoped to the writing task_id — other tasks' caches are
not affected.
6 regression tests added covering:
- read→write→read within same mtime second (core #13144 scenario)
- invalidation across all offset/limit combinations
- isolation: writing file A does not invalidate file B's cache
- isolation: writing in task A does not invalidate task B's cache
- _invalidate_dedup_for_path safety on missing task / empty dedup
All 25 tests pass (19 existing + 6 new).
Fixes#13144
Four independent session-UX bugs reported by an external user (#16294).
/save wrote hermes_conversation_<ts>.json to CWD — invisible to
'hermes sessions browse' and easy to lose. Snapshots now write under
~/.hermes/sessions/saved/ and the command prints the absolute path plus
a 'hermes --resume <id>' hint for the live DB-indexed session.
'hermes sessions browse' default --limit raised from 50 to 500. With the
old ceiling, users with moderately long histories saw only the most
recent 50 rows and assumed older sessions had been lost.
TUI session.list (`/resume` picker) switched from a hardcoded allow-list
of 13 gateway source names to a deny-list of just { 'tool' }. Sessions
tagged acp / webhook / user-defined HERMES_SESSION_SOURCE values and
any newly-added platform now surface. Default limit 20 → 200.
ollama-cloud provider setup passes force_refresh=True to
fetch_ollama_cloud_models() so a user entering their API key sees the
fresh catalog (e.g. deepseek v4 flash, kimi k2.6) immediately instead
of waiting up to an hour for the disk cache TTL to expire.
Closes#16294.
_web_ui_build_needed() in PR #14914 checked web_dir/"dist" as the
sentinel, but vite.config.ts sets outDir: "../hermes_cli/web_dist" so
the build output lands in hermes_cli/web_dist/, never in web/dist/.
The sentinel was therefore always missing → _web_ui_build_needed always
returned True → npm install + Vite build ran on every startup → OOM on
low-memory VPS persisted unchanged.
Fix: derive dist_dir as web_dir.parent / "hermes_cli" / "web_dist" so
the sentinel points to the actual build output directory.
Fixes#14898
When the gateway intercepts a pending /update prompt and the user sends
a recognized slash command (/new, /help, ...), the command now dispatches
normally AND the detached update subprocess is unblocked by writing a
blank .update_response. _gateway_prompt reads '' → strips → returns the
prompt's default (typically a safe 'n' / skip), so the update process
exits cleanly instead of blocking on stdin until the 30-minute watcher
timeout.
Also clears _update_prompt_pending[session_key] on this path so stray
future input for the same session isn't re-intercepted.
Extends PR #15849 with tests for the new cancel-write + a regression
test pinning the legacy behavior of unrecognized /foo slash commands
still being consumed as the response.
Slack Bolt posts are not editable like CLI spinners; medium-tier new still emitted a permanent line per tool start (issue #14663).
- Built-in slack default: off; other tier-2 platforms unchanged.
- Adjust /verbose isolation test for off to new cycle.
- Migration tests: read/write config.yaml as UTF-8 (Windows locale).
- TestAutoMaintenance gains 3 tests: auto-prune deletes transcript files
when sessions_dir is passed, preserves them when it isn't (backward-
compat), and never touches active-session files during prune.
- FakeDB helpers in test_sessions_delete.py accept **kwargs so they
don't break when delete_session signature gains sessions_dir.
Extends the existing channel_skill_bindings mechanism (previously
Discord-only) to Slack, so a channel or DM can auto-load one or more
skills at session start without relying on the model's skill selector
for every short reply.
Motivation: Mats's German flashcards DM pushes a cron-driven card
5x/day; he responds with one-word guesses like 'work'. Previously each
reply required the main agent to decide whether to load german-flashcards
(full opus turn just to pick a skill). With the binding configured per
Slack channel, the skill is injected at session start and grading runs
directly.
Changes:
- Extract resolve_channel_skills() from DiscordAdapter._resolve_channel_skills
into gateway.platforms.base (now shared across adapters).
- DiscordAdapter._resolve_channel_skills delegates to the shared helper
(behavior preserved — existing test suite still passes unchanged).
- SlackAdapter: resolve channel_skill_bindings on each message and attach
auto_skill to MessageEvent. gateway/run.py already handles auto-skill
injection on new sessions; this just wires Slack through it.
- gateway/config.py: accept channel_skill_bindings in slack: block of
config.yaml (was Discord-only).
- Tests: new tests/gateway/test_slack_channel_skills.py with 11 cases
covering DM/thread/parent resolution, single-vs-list skills, dedup,
malformed entries. Discord suite unchanged.
- Docs: add 'Per-Channel Skill Bindings' section to Slack user guide.
Config example:
slack:
channel_skill_bindings:
- id: "D0ATH9TQ0G6"
skills: ["german-flashcards"]
Enter while the agent is busy can now inject the typed text via /steer —
arriving at the agent after the next tool call — instead of interrupting
(current default) or queueing for the next turn.
Changes:
- cli.py: keybinding honors busy_input_mode='steer' by calling
agent.steer(text) on the UI thread (thread-safe), with automatic
fallback to 'queue' when the agent is missing, steer() is unavailable,
images are attached, or steer() rejects the payload. /busy accepts
'steer' as a fourth argument alongside queue/interrupt/status.
- gateway/run.py: busy-message handler and the PRIORITY running-agent
path both route through running_agent.steer() when the mode is 'steer',
with the same fallback-to-queue safety net. Ack wording tells users
their message was steered into the current run. Restart-drain queueing
now also activates for 'steer' so messages aren't lost across restarts.
- agent/onboarding.py: first-touch hint has a steer branch for both
CLI and gateway.
- hermes_cli/commands.py: /busy args_hint updated to include steer,
and 'steer' is registered as a subcommand (completions).
- hermes_cli/web_server.py: dashboard select widget offers steer.
- hermes_cli/config.py, cli-config.yaml.example, hermes_cli/tips.py:
inline docs updated.
- website/docs/user-guide/cli.md + messaging/index.md: documented.
- Tests: steer set/status path for /busy; onboarding hints;
_load_busy_input_mode accepts steer; busy-session ack exercises
steer success + two fallback-to-queue branches.
Requested on X by @CodingAcct.
Default is unchanged (interrupt).
MCP stdio servers are spawned via the SDK's stdio_client, which on
Linux uses start_new_session=True (setsid). When a cron job is
cancelled mid-way (timeout, agent finish, exception), the subprocess
often escapes the SDK's teardown and survives as a session leader.
Because setsid() detaches the child from the gateway's process group
/ cgroup tree, systemd does not reap it on service restart either —
so every cron tick that touches an MCP tool leaks a dangling server
process.
Fix:
* tools/mcp_tool.py — _run_stdio now wraps the whole stdio+session
context in try/finally. On any exit path (clean, exception,
cancellation), PIDs still alive are moved from the active
_stdio_pids set into a new _orphan_stdio_pids set. Orphan
detection is done via os.kill(pid, 0) — a cheap liveness probe
that never signals the target.
* tools/mcp_tool.py — _kill_orphaned_mcp_children gains an
include_active=False flag. Default behaviour now only reaps the
orphan set so concurrent sessions (other parallel cron jobs or
live user chats) are never disrupted. The existing shutdown path
passes include_active=True to keep the previous "kill everything"
semantics after the MCP loop is stopped.
* cron/scheduler.py — the cleanup hook is moved from run_job()'s
finally (which would race with parallel siblings after #13021)
into tick() after the ThreadPoolExecutor has joined every future.
At that point there are no in-flight sessions from this tick, so
sweeping the orphan set is always safe.
Net effect: zero regression for healthy sessions, and orphan MCP
servers no longer accumulate between gateway restarts.
Made-with: Cursor
Multiple overlapping Slack attachment improvements:
1. Upload retry with backoff on transient errors (429, 5xx, connection
reset, rate_limited, service unavailable). New _is_retryable_upload_error
helper covers three upload paths: _upload_file, send_video,
send_document. Up to 3 attempts with 1.5s * attempt backoff.
2. Thread participation tracking: successful file uploads now add the
thread_ts to _bot_message_ts, mirroring how text replies are tracked.
This lets follow-up thread messages auto-trigger the bot (same
engagement rules as replied threads).
3. Thread metadata preservation in the image redirect-guard fallback
(send_image → send text fallback) and in two gateway.run.py send
paths (image + document fallback calls).
4. HTML response rejection in _download_slack_file_bytes. Parallels
the existing check in _download_slack_file. Guards against Slack
returning a sign-in / redirect page as document bytes when scopes
are missing, so the agent doesn't get HTML-as-a-PDF.
5. File lifecycle event acks (file_shared / file_created / file_change).
These events arrive around snippet uploads. Acking them silences the
slack_bolt 'Unhandled request' 404 warnings without changing behavior.
6. Post-loop message type classification so a mixed image+document upload
classifies as PHOTO (or VOICE if no image), falling back to DOCUMENT.
Previously, the per-file classification in the inbound loop could be
overwritten unpredictably.
7. Expanded text-inject whitelist in inbound document handling to cover
.csv, .json, .xml, .yaml, .yml, .toml, .ini, .cfg (up to 100KB) so
snippets and config files are directly visible to the agent, not just
cached as opaque uploads. Paired with new MIME entries in
SUPPORTED_DOCUMENT_TYPES in base.py.
Squashed from two commits in #11819 so the single commit carries the
contributor's GitHub attribution (the original commits were authored
under a local dev hostname).
Ports openclaw/openclaw#72038 to hermes-agent.
Telegram's `editMessageText` preserves the original message timestamp,
so a long-running streamed reply (reasoning models that take 60+ seconds
to finish) would keep the first-token timestamp even after completion.
Users can't tell how long a task actually took.
When a preview message has been visible for >= 60s (configurable via
`streaming.fresh_final_after_seconds`), finalize by sending a fresh
message instead of editing in place, then best-effort delete the stale
preview. Short previews still edit in place (the existing fast path).
Implementation notes adapted from OpenClaw's TypeScript original:
- `StreamConsumerConfig` gains `fresh_final_after_seconds` (default 0 =
legacy edit-in-place). Gateway-level `StreamingConfig` defaults to 60.
- `GatewayStreamConsumer` tracks `_message_created_ts` at first-send and
checks it in `_send_or_edit` on `finalize=True`. New helpers
`_should_send_fresh_final` + `_try_fresh_final`.
- `BasePlatformAdapter` gains optional `delete_message(chat_id, message_id)`
returning False by default. `TelegramAdapter` implements it via
`_bot.delete_message`.
- `gateway/run.py` only enables fresh-final for `Platform.TELEGRAM`;
other platforms ignore the setting (they don't have the stale-edit
timestamp problem or edit-then-read works cheaply).
- Fallback to normal edit on any fresh-send failure — no user-visible
regression if Telegram rate-limits a send or the message is gone.
Tests: 15 new cases in tests/gateway/test_stream_consumer_fresh_final.py
covering short/long previews, config plumbing, delete-support absent,
send-failure fallback, __no_edit__ sentinel safety, and StreamingConfig
round-trip.
Co-authored-by: Hermes Agent <agent@nousresearch.com>
Slack's modern composer sends messages with a 'blocks' array that
contains rich_text elements. When a user forwards or quotes another
message, the quoted content shows up in the rich_text_quote children
of that array — and is NOT included in the plain 'text' field. The
agent saw only the lossy plain text and was blind to forwarded /
quoted content. Same story for link unfurl previews (Notion, docs,
GitHub, etc.) which Slack puts in the 'attachments' array.
Two fixes in the inbound handler:
1. _extract_text_from_slack_blocks walks rich_text / rich_text_quote /
rich_text_list / rich_text_preformatted trees and renders readable
text ('> quoted', '• bullet', code fences), dedupes against the
plain text field, and appends the extracted content so the agent
sees everything.
2. Link unfurl / attachment preview extraction reads title, url,
body, and footer from the 'attachments' array and appends a
'📎 [title](url)\n body\n _footer_' section per preview.
Skips is_msg_unfurl to avoid echoing our own Slack replies back.
Routing is careful not to trust augmented text: mention gating
(is_mentioned) and slash-command detection both run against the
original 'text' field, so forwarded content containing '<@bot>' or
'/deploy' in a quote can't trick the bot into responding in a
channel it shouldn't or classifying a normal message as a command.
Adjustment from original PR: dropped _serialize_slack_blocks_for_agent,
which inlined a redacted JSON dump of non-rich_text blocks (section,
accessory, actions, etc.) — the agent would see the raw Block Kit
structure for UI-heavy alerts. It added up to 6000 characters to the
prompt context on every qualifying message with no opt-out. The
rich_text extraction and attachment unfurls cover the common bug-fix
case (quoted/forwarded content + link previews) without the prefill
tax. If a user needs block inspection later, it can return as a
config opt-in.
Also updates the Slack platform notes in session.py to accurately
describe what the gateway inlines.
After #14798 made cron honor per-platform `hermes tools` config, the
`_DEFAULT_OFF_TOOLSETS` filter silently stripped `homeassistant` from
cron jobs for users who'd been relying on the previous blanket toolset.
Norbert's HA cron reports regressed as a result.
The HA toolset is already runtime-gated by its `check_fn` (requires
HASS_TOKEN to register any tools). When HASS_TOKEN is set the user has
explicitly opted in — `_DEFAULT_OFF_TOOLSETS` adds nothing in that case,
so stop double-gating and restore HA for cron / cli / other platforms
without an explicit saved toolset list.
moa and rl stay off by default (original #14798 goal preserved).
Fixes HA cron regression reported by Norbert.
HindsightEmbedded.close() delegates to its sync client.close(). When Hermes
created/used that client on the shared async loop, closing it from the main
thread raises 'attached to a different loop' before aiohttp releases the
session — so the ClientSession / TCPConnector leak past provider teardown.
Close the embedded inner async client on the shared loop first via
_run_sync(inner_client.aclose()), then let the wrapper's sync close()
do its daemon/UI bookkeeping.
Salvage of #14605: test placement rebased — appended TestShutdown class
after TestSharedEventLoopLifecycle (which landed on main after the PR was
written). Original author attribution preserved.
Translate Slack attachment failures into actionable user-facing notices
instead of generic download errors. When a scope/auth/permission issue
breaks attachment processing, the user sees:
[Slack attachment notice]
- Slack attachment access failed for photo.jpg. Missing scope:
files:read. Update the Slack app scopes/settings and reinstall
the app to the workspace.
Two helpers do the translation:
_describe_slack_api_error — handles SlackApiError responses
(missing_scope, invalid_auth, file_not_found, access_denied, etc.)
_describe_slack_download_failure — handles httpx.HTTPStatusError
(401/403/404) and Slack-returns-HTML-sign-in fallbacks
Wired into three existing call sites:
- the Slack Connect files.info path (PR #11111) so scope errors
surface instead of being logged as generic "files.info failed"
- the image, audio, and document download paths so 401/403 and
HTML-body responses translate into actionable notices
Adjustment from original PR: dropped _probe_slack_file_access_issue,
the proactive pre-download files.info probe. It added one extra
Slack API call per attachment even on healthy ones, and overlapped
with the existing files.info call from PR #11111. The post-failure
translation path covers the same user-facing diagnostic value
without the per-message tax.
Also documents files:read scope more prominently in the Slack setup
guide and troubleshooting table.
Contributed back from https://github.com/xinbenlv/zn-hermes-agent.
Closes#7015.
Co-authored-by: xinbenlv <zzn+pa@zzn.im>
Background review fork now inherits session_id, credential_pool, and
status_callback from the parent (added in #16099 after this PR was
written). Extend the bare-agent helper so the regression test keeps
reaching the cleanup assertions instead of failing in the runtime
resolver.
Signed-off-by: Teknium <8425893+teknium1@users.noreply.github.com>
Temporary background review agents can initialize Hindsight-backed memory clients, but close() alone skips provider teardown. Shut the memory provider down before closing so aiohttp sessions do not leak at process exit.
Made-with: Cursor
The Slack thread-context fetcher used to drop every message with a
bot_id, which silently erased the thread parent whenever a cron job (or
any other bot) had posted it. As a result, replies to a cron-posted
summary lost all context and the agent answered as if from a blank
thread.
Changes:
1. gateway/platforms/slack.py::_fetch_thread_context
- Keep the thread parent even when it was posted by a bot
(e.g. cron summaries, third-party integrations).
- Only skip *our own* prior bot replies to avoid circular context,
matching the per-workspace bot user id via _team_bot_user_ids so
multi-workspace deployments stay correct.
- Keep non-self bot children (useful third-party context).
2. gateway/platforms/slack.py::_handle_slack_message
- Populate MessageEvent.reply_to_text for thread replies (parity
with Telegram/Discord/Feishu/WeCom). gateway.run uses this field
to inject a [Replying to: "..."] prefix when the parent is not
already in the session history, which is exactly the scenario
triggered by cron-generated thread parents.
- New helper _fetch_thread_parent_text reuses the existing thread-
context cache (and its 60s TTL) to avoid duplicate
conversations.replies calls; falls back to a cheap limit=1 fetch
when the cache is cold.
Tests:
- Updated TestSlackThreadContext::test_skips_bot_messages to reflect
the new behaviour (self-bot child dropped, third-party bot kept).
- Added:
* test_fetch_thread_context_includes_bot_parent
* test_fetch_thread_context_excludes_self_bot_replies
* test_fetch_thread_context_multi_workspace
* test_fetch_thread_context_current_ts_excluded (regression guard)
* test_fetch_thread_parent_text_from_cache
* test_slack_reply_to_text_set_on_thread_reply
* test_slack_reply_to_text_none_for_top_level_message
Full Slack suite: 176 passed (was 169).
Slack's chat.postMessage API rejects user IDs (U...) and workspace
IDs (W...) — they are not valid conversation IDs. Posting to them
fails because the API requires a channel ID (C/G/D). To DM a user,
the sender must first call conversations.open to obtain a D... ID.
Tighten _SLACK_TARGET_RE from [CGDUW] to [CGD] so the send path rejects
U/W values as explicit targets and instead falls through to channel-
name resolution (where they'll fail with a clear 'could not resolve'
error rather than silently getting stuck in a retry loop on the API).
Flip the corresponding regression test to assert U/W values are not
explicit. Matches the narrower regex briandevans proposed in #15939.
Co-authored-by: briandevans <brian@bde.io>
send_message(target='slack:<channel_id>') failed with "Could not
resolve" because _parse_target_ref had no Slack branch — Slack's
uppercase alphanumeric IDs fell through to channel-name resolution,
which only matched by name. As a fallback, the agent would retry with
bare target='slack' and post to the home channel instead.
Three fixes:
- _parse_target_ref recognizes Slack IDs (C/G/D/U/W prefix) as
explicit targets so the name-resolver is bypassed entirely.
- resolve_channel_name tries a case-sensitive raw-ID match before
the existing name match, so any platform's IDs resolve cleanly.
- _build_slack now actually calls users.conversations against each
workspace's AsyncWebClient (paginated), instead of only returning
session-history entries. This populates the directory with public
and private channels the bot has joined, so action='list' shows
them and they can also be addressed by name. Errors from one
workspace don't block others.
build_channel_directory becomes async (Slack web calls require it).
The two async-context callers in gateway/run.py are awaited; the
cron ticker thread call bridges via asyncio.run_coroutine_threadsafe.
Slack bot needs channels:read and groups:read scopes for full
enumeration; missing scopes degrade gracefully per-workspace.
addressing #15927
load_gateway_config() has a side effect: when config.yaml contains
platform-gating keys (slack.require_mention, slack.strict_mention,
slack.free_response_channels, slack.allow_bots, slack.reactions, plus
analogous keys for discord/telegram/whatsapp/dingtalk/matrix), it calls
os.environ[KEY] = ... to bridge them to env-var form.
monkeypatch.delenv doesn't track direct os.environ mutations made
inside the test body, so tests that call load_gateway_config() leak
those env vars into later tests on the same xdist worker. The failure
mode is flaky seed-dependent: test_top_level_message_requires_mention_
even_with_session (and siblings in TestThreadReplyHandling) pass when
SLACK_REQUIRE_MENTION is unset but fail when a leaked value of 'false'
is present.
Add the gating env vars to _HERMES_BEHAVIORAL_VARS so the hermetic
autouse fixture blanks them on every test setup, closing the leak
regardless of which test sets them.
Extends the strict_mention feature so an @mention in strict mode no
longer persistently tags the thread as 'mentioned'. Without this, the
thread's first mention would permanently auto-trigger the bot on every
subsequent message — which is exactly what strict_mention is designed
to prevent. Closes the agent-to-agent ack loop hole hhhonzik identified
in #14117.
Co-authored-by: hhhonzik <me@janstepanovsky.cz>
Adds a strict_mention config option that, when enabled, requires an
explicit @-mention on every message in channel threads. Disables the
'once mentioned, forever in the thread' and session-presence auto-triggers.
- New _slack_strict_mention() helper (config.extra + SLACK_STRICT_MENTION env)
- Bridged top-level slack.strict_mention yaml to SLACK_STRICT_MENTION env,
matching require_mention/allow_bots bridging
- Unit tests for the helper + config bridge
Top-level channel messages arrive at _resolve_thread_ts with
metadata.thread_id set to the message's own ts, because the inbound
handler in _handle_message_event uses 'event.ts' as a session-keying
fallback when event.thread_ts is absent. That made metadata alone
insufficient to distinguish a real thread reply from a top-level
message, so reply_in_thread=false only took effect in DMs.
Use reply_to (== incoming message_id == ts for top-level messages) as
the tiebreaker: when metadata.thread_id == reply_to the 'thread' is the
synthetic session-keying fallback, not a real parent, so we reply
directly in the channel. Real thread replies (reply_to != thread_id)
still resolve to the parent thread and preserve conversation context.
Closes#9268.
Parameterize the test helpers in test_status_command.py to accept a
Platform and add two regression tests ensuring the first-run home-channel
onboarding uses '/hermes sethome' on Slack and '/sethome' everywhere else.
Co-authored-by: sgaofen <135070653+sgaofen@users.noreply.github.com>
Repeated /queue commands now each produce a full agent turn, in order,
with no merging. Previously the second /queue overwrote the first
because the handler wrote directly into the adapter's single-slot
_pending_messages dict.
- GatewayRunner grows a _queued_events overflow buffer (dict of list).
- /queue puts new items in the adapter's next-up slot when free,
otherwise appends to the overflow. After each run's drain consumes
the slot, the next overflow item is promoted so the recursive run
picks it up.
- /new and /reset clear the overflow.
- /status now reports queue depth when non-zero.
- Ack message shows the depth once it exceeds 1.
Helpers (_enqueue_fifo, _promote_queued_event, _queue_depth) use the
getattr default-fallback pattern so existing tests that build bare
GatewayRunner instances via object.__new__ keep working.
Before: delegate_task children each allocated their own terminal
sandbox keyed by child task_id. Starting extra containers (or Modal
sandboxes / Daytona workspaces) is expensive, and the subagent's work
is invisible to the parent — files written by the child in its
container don't exist in the parent's when the subagent returns.
After: a single `_resolve_container_task_id` helper maps any
tool-call task_id to "default" UNLESS an env override is registered
for it. The parent agent and all delegate_task children therefore
share one long-lived sandbox — installed packages, cwd, /workspace
files, and /tmp scratch carry over freely between them.
RL and benchmark environments (TerminalBench2, HermesSweEnv, ...)
opt in to isolation via `register_task_env_overrides(task_id, {...})`;
those task_ids survive the collapse and get their own sandbox,
preserving the per-task Docker image behavior these benchmarks rely on.
file_state / active-subagents registry / TUI events still key off the
original child task_id, so the 'subagent wrote a file the parent read'
warning and UI per-subagent panels keep working.
Tradeoff: parallel delegate_task children (tasks=[...]) now share one
bash/container. Concurrent cd, env-var mutations, and writes to the
same path will collide. If that bites a specific workflow, the
subagent can opt back into isolation via register_task_env_overrides.
Applied at four lookup sites:
- tools/terminal_tool.py terminal_tool() and get_active_env()
- tools/file_tools.py _get_file_ops() and _get_live_tracking_cwd()
- tools/code_execution_tool.py _get_or_create_environment()
Docs: website/docs/user-guide/configuration.md updated to reflect the
shared-container reality and document the RL/benchmark carve-out.
Tests: tests/tools/test_shared_container_task_id.py (9 cases).
Every command in COMMAND_REGISTRY (/btw, /stop, /model, /help, /new,
/bg, /reset, ...) is now a first-class Slack slash command instead of
a /hermes <subcommand>. Users get the same autocomplete-driven slash
picker experience Slack users expect and that Discord and Telegram
already provide.
Previously Slack registered ONE native slash (/hermes) and split on
the first word, so typing /btw in Slack's composer got 'couldn't find
an app for /btw' because the workspace manifest never declared it.
Changes
- hermes_cli/commands.py: slack_native_slashes() + slack_app_manifest()
generate a Slack manifest from the registry (canonical names +
aliases + plugin commands), clamped to Slack's 50-slash cap with
/hermes reserved as the catch-all.
- gateway/platforms/slack.py: single regex matcher dispatches every
registered slash to _handle_slash_command, which dispatches on
command['command']. Legacy /hermes <subcommand> keeps working for
backward compat with older workspace manifests.
- hermes_cli/slack_cli.py + hermes_cli/main.py: new 'hermes slack
manifest' command prints/writes a full manifest (display info,
OAuth scopes, event subs, socket mode, slash commands) ready to
paste into 'Create from manifest' or Features → App Manifest.
- hermes_cli/setup.py: _setup_slack() now writes the manifest up-front
and points users at the 'From an app manifest' flow; also offers
to refresh the manifest on reconfigure for picking up new commands.
- Tests: 14 new tests covering native-slash dispatch (/btw, /stop,
/model), legacy /hermes <sub> compat, manifest structure, and
telegram<->slack parity (every Telegram command must also register
as a Slack slash). Existing /hermes-registration test updated to
assert the new regex matches /hermes, /btw, /stop, /model, /help.
- Docs: slack.md gains a 'Slash Commands' section + Option A manifest
flow in Step 1; cli-commands.md documents 'hermes slack manifest'.
Users pick up the new slashes by running 'hermes slack manifest --write'
and pasting into Features → App Manifest → Edit in their Slack app
config, then Save (Slack prompts for reinstall if scopes changed).
* fix(tui): call maybe_auto_title for TUI sessions (#15961)
The maybe_auto_title() helper is called from cli.py and gateway/run.py
but was never wired into tui_gateway/server.py, so every session started
via 'hermes --tui' landed in state.db with an empty title. Evidence from
the issue reporter: 0/154 TUI sessions titled vs 91/383 CLI.
Mirror the CLI/Gateway pattern: after emitting message.complete, when the
turn finished cleanly, fire-and-forget title generation using the session
key, user prompt, agent response, and current history.
Fixes#15949.
Co-authored-by: math0r-be <math0r-be@github.com>
* chore(release): map math0r-be placeholder email in AUTHOR_MAP
---------
Co-authored-by: math0r-be <math0r-be@github.com>
* fix(/branch): redirect session_log_file and expose branch sessions in list
Two bugs when using /branch:
1. cli.py _handle_branch_command updated agent.session_id but not
agent.session_log_file, so all messages written after branching
landed in the original session's JSON file and the branch never
got its own session_{id}.json on disk.
Fix: mirror the compression-split path (run_agent.py:7579) and
update session_log_file immediately after changing session_id.
2. hermes_state.py list_sessions_rich filtered out every session
with parent_session_id IS NOT NULL to hide sub-agent runs and
compression continuations. Branch sessions share this column, so
they became invisible to `hermes sessions list` and `sessions browse`.
Fix: also include branch children — those whose parent ended with
end_reason='branched' AND whose started_at >= parent.ended_at
(the same timing condition that get_compression_tip uses to
distinguish continuations from live-spawned subagents).
Fixes#14854
Co-Authored-By: Octopus <liyuan851277048@icloud.com>
* chore(release): map octo-patch placeholder email in AUTHOR_MAP
---------
Co-authored-by: octo-patch <octo-patch@github.com>
Co-authored-by: Octopus <liyuan851277048@icloud.com>
When a cloud browser provider (Browserbase / Browser-Use / Firecrawl) is
configured, browser_navigate now transparently spawns a local Chromium
sidecar for URLs whose host resolves to a private/loopback/LAN address
(localhost, 127.0.0.1, 192.168.x.x, 10.x.x.x, *.local, *.lan, *.internal,
::1, 169.254.x.x). Public URLs continue to use the cloud provider in the
same conversation.
Previously, setting BROWSERBASE_API_KEY / cloud_provider: browserbase
pinned the whole tool to cloud for the process — localhost URLs were
either SSRF-blocked (default) or sent to Browserbase (where they 404'd
because the cloud can't reach your LAN). Users who wanted 'cloud for
public, local for localhost' had no way to express it short of toggling
providers mid-session.
Implementation uses a composite session key scheme: the bare task_id
serves the cloud session, and a '{task_id}::local' sidecar serves the
local Chromium. _last_active_session_key[task_id] tracks which of the
two served the most recent nav so snapshot/click/fill/etc. hit the
correct one. cleanup_browser(bare_task_id) reaps both.
Feature is on by default. Opt out via:
browser:
auto_local_for_private_urls: false
The cloud provider never sees private URLs. Post-redirect SSRF guard
is preserved: redirects from public onto private addresses still block.
'hermes skills list' now shows every skill's enabled/disabled status
and accepts --enabled-only to filter down to what will actually load
for the active profile:
hermes -p dario skills list --enabled-only
Previously the command was a flat catalog — it did not apply
skills.disabled from config.yaml, so there was no way to see the
live skill set for a profile without reading config by hand.
Profile switching already works via -p (swaps HERMES_HOME); this
just surfaces the result visibly.
Changes:
- hermes_cli/skills_hub.py: do_list adds a Status column and an
enabled_only filter; summary reports enabled/disabled split
- hermes_cli/main.py: --enabled-only flag on 'skills list'
- /skills list slash command accepts --enabled-only too
- tests: 4 new (status column, disabled marking, enabled-only
hiding, no platform leakage into get_disabled_skill_names);
existing fixtures updated to accept skip_disabled kwarg
Reported by @mochizukimr on X.
Address Copilot review findings:
1. Gate _last_activity_desc on interrupt_depth == 0 alongside _last_activity_ts.
Both fields are semantically paired — desc describes the activity *at* ts.
Updating desc without ts made get_activity_summary() report "starting new
turn (cached)" for 20+ minutes while the timestamp showed the true stale
duration, producing misleading diagnostic output.
2. Monkeypatch gateway.run.time.time to a fixed epoch in tests that assert
on _last_activity_ts values. Real time.time() comparisons were latently
flaky under slow CI or NTP adjustments. _FAKE_NOW = 10_000.0 is used
as the reference; assertions are now exact equality rather than >=.
3. Add test_fresh_turn_resets_desc and test_interrupt_turn_preserves_desc to
directly cover the gated desc behaviour introduced by (1).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
_last_activity_ts was unconditionally reset to time.time() on every
_agent_cache hit. For interrupt-recursive _run_agent calls
(_interrupt_depth > 0) this silently reset the inactivity watchdog's
idle clock on each re-entry, preventing the 30-min timeout from ever
firing when a turn got stuck in an interrupt loop. A stuck session
would emit "Still working... iteration 0/60, starting new turn (cached)"
heartbeats indefinitely instead of timing out.
Gate the reset on _interrupt_depth == 0 only. Fresh external turns
still receive the reset so a session idle for 29 min doesn't trip the
watchdog before the new turn makes its first API call (#9051).
The per-turn reset logic is extracted into a static helper
_init_cached_agent_for_turn() to make it directly testable.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Follow-up to cherry-picked PR #15920:
- agent/credential_pool.py: hoist 'from hermes_cli.config import get_env_value'
to module top instead of inline try/except in each seed site (3 sites).
No import cycle — hermes_cli/config.py doesn't depend on agent.credential_pool.
- hermes_cli/auth.py: same hoist for the _resolve_api_key_provider_secret loop.
- tests/tools/test_credential_pool_env_fallback.py: replace smoke-only tests
with real .env file I/O. Each test writes a temp ~/.hermes/.env, verifies
_seed_from_env / _resolve_api_key_provider_secret read from it, and asserts
the full priority chain: os.environ > .env > credential_pool. Uses
'deepseek' as the test provider since 'openai' isn't in PROVIDER_REGISTRY
and _seed_from_env's generic path requires a real pconfig lookup.
New `hermes kanban` CLI subcommand + `/kanban` slash command + skills for
worker and orchestrator profiles. SQLite-backed task board
(~/.hermes/kanban.db) shared across all profiles on the host. Zero
changes to run_agent.py, no new core tools, no tool-schema bloat.
Motivation: delegate_task is a function call — sync fork/join, anonymous
subagent, no resumability, no human-in-the-loop. Kanban is the durable
shape needed for research triage, scheduled ops, digital twins,
engineering pipelines, and fleet work. They coexist (workers may call
delegate_task internally).
What this adds
- hermes_cli/kanban_db.py — schema, CAS claim, dependency resolution,
dispatcher, workspace resolution, worker-context builder.
- hermes_cli/kanban.py — 15-verb CLI surface and shared run_slash()
entry point used by both CLI and gateway.
- skills/devops/kanban-worker — how a profile should work a claimed task.
- skills/devops/kanban-orchestrator — "you are a dispatcher, not a
worker" template with anti-temptation rules.
- /kanban slash command wired into cli.py and gateway/run.py. Bypasses
the running-agent guard (board writes don't touch agent state), so
/kanban unblock can free a stuck worker mid-conversation.
- Design spec at docs/hermes-kanban-v1-spec.pdf — comparative analysis
vs Cline Kanban, Paperclip, NanoClaw, Gemini Enterprise; 8 patterns;
4 user stories; implementation plan; concurrency correctness.
- Docs: website/docs/user-guide/features/kanban.md, CLI reference
updated, sidebar entry added.
Architecture highlights
- Three planes: control (user + gateway), state (board + dispatcher),
execution (pool of profile processes).
- Every worker is a full OS process, spawned as `hermes -p <profile>`.
No in-process subagent swarms — solves NanoClaw's SDK-lifecycle
failure class.
- Atomic claim via SQLite CAS in a BEGIN IMMEDIATE transaction; stale
claims reclaimed 15 min after their TTL expires.
- Tenant namespacing via one nullable column — one specialist fleet
can serve many businesses with data isolation by workspace path.
Tests: 60 targeted tests (schema, CAS atomicity, dependency resolution,
dispatcher, workspace kinds, tenancy, CLI + slash surface). All pass
hermetic via scripts/run_tests.sh.
Follow-up to PR #16053 (/btw as /background alias). Cleans up the
plumbing added exclusively for the old ephemeral /btw handler and
repairs a broken btw bypass that landed between my refactor and this
follow-up.
run_agent.py:
- Remove persist_session kwarg, instance attr, and _persist_session
short-circuit. Only /btw ever passed persist_session=False; with
/btw gone the default (always persist) is the only behavior anyone
ever wanted.
gateway/run.py:
- Remove the unreachable 'if _cmd_def_inner.name == "btw"' block
(PR #16059). Canonical name for a /btw message is 'background' after
alias resolution — the comparison could never be true, and it called
_handle_btw_command which no longer exists. The /background branch
above it already dispatches /btw correctly.
tests/gateway/test_running_agent_session_toggles.py:
- Fix test_btw_dispatches_mid_run to mock _handle_background_command
(the real dispatch target for /btw) instead of the deleted
_handle_btw_command.
/btw spawns a parallel ephemeral side-question task (self-guarded against
concurrent /btw on the same chat) — exactly like /background. But it was
missing from the running-agent bypass list in _handle_message(), so it
fell through to the catch-all and returned:
⏳ Agent is running — /btw can't run mid-turn. Wait for the current
response or /stop first.
That's the opposite of what /btw is for — asking a side question while
the main turn is still working. Add the bypass next to /background and a
regression test covering the mid-turn dispatch path.
Reported by @IuriiTiunov on Telegram.
PR #16046 added /busy and /verbose hints to the classic CLI and the
gateway runner but skipped the Ink TUI (and therefore the dashboard
/chat page, which embeds the TUI via PTY). This extends the same
latch to the TUI with TUI-native wording.
The TUI's busy-input model is not the /busy knob from the CLI —
single Enter while busy auto-queues, double Enter on an empty line
interrupts. The new busy-input hint teaches THAT gesture instead of
telling the user to flip a config that does not apply.
Changes:
- agent/onboarding.py — add busy_input_hint_tui() + tool_progress_hint_tui()
- tui_gateway/server.py — onboarding.claim JSON-RPC (Ink triggers busy
hint on enqueue) + _maybe_emit_onboarding_hint helper hooked into
_on_tool_complete for the 30s/tool_progress=all path. Same
config.yaml latch so each hint fires at most once per install across
CLI, gateway, and TUI combined.
- ui-tui/src/gatewayTypes.ts — OnboardingClaimResponse + onboarding.hint event
- ui-tui/src/app/createGatewayEventHandler.ts — render the hint event as sys()
- ui-tui/src/app/useSubmission.ts — claim busy_input_prompt on first
busy enqueue
- tests/agent/test_onboarding.py — +3 cases for TUI hint shape
- tests/tui_gateway/test_protocol.py — +4 cases for onboarding.claim
- website/docs/user-guide/tui.md — new 'Interrupting and queueing'
section explaining the TUI's double-Enter model and the hints
Validation:
scripts/run_tests.sh tests/agent/test_onboarding.py \
tests/tui_gateway/test_protocol.py \
tests/gateway/test_busy_session_ack.py
-> 66 passed
npm --prefix ui-tui run type-check -> clean
npm --prefix ui-tui run lint -> clean
npm --prefix ui-tui run build -> clean
Manage the fallback_providers chain from the CLI instead of hand-editing
config.yaml. The picker reuses select_provider_and_model() from 'hermes
model' — same provider list, same credential prompts, same model picker.
hermes fallback [list] Show the current chain (primary + fallbacks)
hermes fallback add Run the model picker, append selection to chain
hermes fallback remove Pick an entry to delete (arrow-key menu)
hermes fallback clear Remove all entries (with confirmation)
'add' snapshots config['model'] before calling the picker, extracts the
user's selection from the post-picker state, then restores the primary
and appends {provider, model, base_url?, api_mode?} to fallback_providers.
Auth store's active_provider is snapshot/restored too so OAuth-provider
fallbacks don't silently deactivate the user's primary. Duplicates and
self-as-fallback are rejected. Legacy single-dict 'fallback_model' entries
are auto-migrated to the list format on first write.
Instead of a blocking first-run questionnaire, show a one-time hint the first
time the user hits each behavior fork:
1. First message while the agent is working — appends a hint to the busy-ack
explaining the /busy queue vs /busy interrupt knob, phrased to match the
mode that was just applied (don't tell a queue-mode user to switch to
queue).
2. First tool that runs for >= 30s in the noisiest progress mode
(tool_progress: all) — prints a hint about /verbose to cycle display
modes (all -> new -> off -> verbose). Gated on /verbose actually being
usable on the surface: always shown on CLI; on gateway only shown when
display.tool_progress_command is enabled.
Each hint is latched in config.yaml under onboarding.seen.<flag>, so it
fires exactly once per install across CLI, gateway, and cron, then never
again. Users can wipe the section to re-see hints.
New:
- agent/onboarding.py — is_seen / mark_seen / hint strings, shared by
both CLI and gateway.
- onboarding.seen in DEFAULT_CONFIG (hermes_cli/config.py) and in
load_cli_config defaults (cli.py). No _config_version bump — deep
merge handles new keys.
Wired:
- gateway/run.py: _handle_active_session_busy_message appends the hint
after building the ack. progress_callback tracks tool.completed
duration and queues the tool-progress hint into the progress bubble.
- cli.py: CLI input loop appends the busy-input hint on the first busy
Enter; _on_tool_progress appends the tool-progress hint on the first
>=30s tool completion. In-memory CLI_CONFIG is also updated so
subsequent fires in the same process are suppressed immediately.
All writes go through atomic_yaml_write and are wrapped in try/except
so onboarding can never break the input/busy-ack paths.
The base adapter's auto-TTS path fired on any voice message unless the
chat had explicitly run /voice off — it never read voice.auto_tts from
config.yaml, so users who set auto_tts: false still got audio replies.
Gate the base adapter on a three-layer decision instead:
1. chat in _auto_tts_enabled_chats (explicit /voice on|tts) → fire
2. chat in _auto_tts_disabled_chats (explicit /voice off) → suppress
3. else → voice.auto_tts global default
Runner now pushes voice.auto_tts onto the adapter as _auto_tts_default
and mirrors /voice on|tts chats into _auto_tts_enabled_chats via the
existing _sync_voice_mode_state_to_adapter path. /voice off still wins.
Closes#16007.
When the LLM response carries N parallel tool calls, the agent fires
N tool.started events back-to-back before its interrupt check runs.
A user sending /stop mid-batch would see the '⚡ Interrupting current
task' ack followed by a trail of 🔍 web_search bubbles for the remaining
events in the batch — making the interrupt feel ignored.
progress_callback and the drain loop in send_progress_messages now
check agent.is_interrupted (via agent_holder[0], the existing
cross-scope handle). Events that arrive after interrupt are dropped
at both the queueing and rendering stages. The '⚡ Interrupting'
message is sent through a separate adapter path and is unaffected.
OpenRouter and Nous Portal curated picker lists now resolve via a JSON
manifest served by the docs site, falling back to the in-repo snapshot
when unreachable. Lets us update model lists without shipping a release.
Live URL: https://hermes-agent.nousresearch.com/docs/api/model-catalog.json
(source at website/static/api/model-catalog.json; auto-deploys via the
existing deploy-site.yml GitHub Pages pipeline on every merge to main).
Schema (v1) carries id + optional description + free-form metadata at
manifest, provider, and model levels. Pricing and context length stay
live-fetched via existing machinery (/v1/models endpoints, models.dev).
Config (new model_catalog section, default enabled):
model_catalog.url master manifest URL
model_catalog.ttl_hours disk cache TTL (default 24h)
model_catalog.providers.<name>.url optional per-provider override
Fetch pipeline: in-process cache -> disk cache (fresh < TTL) -> HTTP
fetch -> disk-cache-on-failure fallback -> in-repo snapshot as last
resort. Never raises to callers; at worst returns the bundled list.
Changes:
- website/static/api/model-catalog.json initial manifest (35 OR + 31 Nous)
- scripts/build_model_catalog.py regenerator from in-repo lists
- hermes_cli/model_catalog.py fetch + validate + cache module
- hermes_cli/models.py fetch_openrouter_models() +
new get_curated_nous_model_ids()
- hermes_cli/main.py, hermes_cli/auth.py Nous flows use the helper
- hermes_cli/config.py model_catalog defaults
- website/docs/reference/model-catalog.md + sidebars.ts
- tests/hermes_cli/test_model_catalog.py 21 tests (validation, fetch
success/failure, accessors,
disabled, overrides, integration)
Stop pre-stripping the path from the configured MCP server URL before
constructing OAuthClientProvider. The MCP SDK strips the path itself via
OAuthContext.get_authorization_base_url() for authorization-server
discovery, but uses the full server_url through
resource_url_from_server_url() + check_resource_allowed() to validate
against the server's RFC 9728 Protected Resource Metadata.
For servers whose PRM advertises a path-scoped resource (e.g. Notion's
https://mcp.notion.com/mcp), our _parse_base_url() collapsed the URL to
the origin, so check_resource_allowed() saw requested='/' vs
configured='/mcp/' and refused the token. Fixes OAuth against Notion MCP
(and any other path-scoped resource).
Closes#16015.
`_apply_model_switch_result` (the interactive `/model` picker's
confirmation path) printed `ModelInfo.context_window` straight from
models.dev, which reports the vendor-wide value (1.05M for gpt-5.5 on
openai). ChatGPT Codex OAuth caps the same slug at 272K, so the picker
showed 1M while the runtime (compressor, gateway `/model`, typed
`/model <name>`) correctly used 272K — the classic 'sometimes 1M,
sometimes 272K' mismatch on a single model.
Both display paths now go through `resolve_display_context_length()`,
matching the fix that `_handle_model_switch` received earlier.
Also bump the stale last-resort fallback in DEFAULT_CONTEXT_LENGTHS
(`gpt-5.5: 400000 -> 1050000`) to match the real OpenAI API value; the
272K Codex cap is already enforced via the Codex-OAuth branch, so the
fallback now reflects what every non-Codex probe-miss should see.
Tests: adds `test_apply_model_switch_result_context.py` with three
scenarios (Codex cap wins, OpenRouter shows 1.05M, resolver-empty falls
back to ModelInfo). Updates the existing non-Codex fallback test to
assert 1.05M (the correct value).
## Validation
| path | before | after |
|-------------------------------|-----------|-----------|
| picker -> gpt-5.5 on Codex | 1,050,000 | 272,000 |
| picker -> gpt-5.5 on OpenAI | 1,050,000 | 1,050,000 |
| picker -> gpt-5.5 on OpenRouter | 1,050,000 | 1,050,000 |
| typed /model gpt-5.5 on Codex | 272,000 | 272,000 |
#14934 added deepseek-v4-pro / deepseek-v4-flash to the DeepSeek native
provider but the context-window lookup still falls back to the existing
"deepseek" substring entry (128K). DeepSeek V4 ships with a 1M context
window, so any caller relying on get_model_context_length() for
pre-flight token budgeting (compression, context warnings) under-counts
by ~8x.
Add explicit lowercase entries for the four DeepSeek model ids that
ship 1M context:
- deepseek-v4-pro
- deepseek-v4-flash
- deepseek-chat (legacy alias, server-side maps to v4-flash non-thinking)
- deepseek-reasoner (legacy alias, server-side maps to v4-flash thinking)
Longest-key-first substring matching means these explicit entries also
cover the vendor-prefixed forms (deepseek/deepseek-v4-pro on OpenRouter
and Nous Portal) without regressing the existing 128K fallback for
older / unknown DeepSeek model ids on custom endpoints.
Source: https://api-docs.deepseek.com/zh-cn/quick_start/pricing
The background skill-review prompt (spawned after N user turns) now instructs
the reviewer to SURVEY existing skills first, identify the CLASS of task, and
PREFER updating/generalizing an existing skill over creating a new narrow one.
This reduces near-duplicate skill accumulation at the source. Catches the
common failure mode where repeated tasks of the same class each spawn their
own specific skill ("fix-my-tauri-error", "fix-my-electron-error") instead
of a single class-level skill ("desktop-app-build-troubleshooting").
Applied to both _SKILL_REVIEW_PROMPT and the **Skills** half of
_COMBINED_REVIEW_PROMPT. Memory-only review prompt unchanged.
Groundwork for the Curator feature (issue #7816) — the creation-side fix.
Curator handles the retirement/consolidation side in a follow-up PR.
Tests assert the behavioral instructions are present (survey, class, update-
over-create, overlap-flagging, opt-out clause) rather than snapshotting the
full prompt text.
Nous Portal multiplexes multiple upstream providers (DeepSeek, Kimi,
MiMo, Hermes) behind one endpoint. Before this fix, any 429 on any of
those models recorded a cross-session file breaker that blocked EVERY
model on Nous for the cooldown window -- even though the caller's
own RPM/RPH/TPM/TPH buckets were healthy. Users hit a DeepSeek V4 Pro
capacity error, restarted, switched to Kimi 2.6, and still got
'Nous Portal rate limit active -- resets in 46m 53s'.
Nous already emits the full x-ratelimit-* header suite on every
response (captured by rate_limit_tracker into agent._rate_limit_state).
We now gate the breaker on that data: trip it only when either the
429's own headers or the last-known-good state show a bucket with
remaining == 0 AND a reset window >= 60s. Upstream-capacity 429s
(healthy buckets everywhere, but upstream out of capacity) fall
through to normal retry/fallback and the breaker is never written.
Note: the in-memory 'restart TUI/gateway to clear' workaround
circulated in Discord does NOT work -- the breaker is file-backed at
~/.hermes/rate_limits/nous.json. The workaround for users still
affected by a bad state file is to delete it.
Reported in Discord by CrazyDok1 and KYSIV (Apr 2026).
Plugin hooks fired after a tool dispatch now receive an integer
duration_ms kwarg measuring how long the tool's registry.dispatch()
call took (time.monotonic() before/after). Inspired by Claude Code
2.1.119 which added the same field to PostToolUse hook inputs.
Wire points:
- model_tools.py: measure dispatch latency, pass duration_ms to
invoke_hook("post_tool_call", ...) and invoke_hook("transform_tool_result", ...)
- hermes_cli/hooks.py: include duration_ms in the synthetic payload
used by 'hermes hooks test' and 'hermes hooks doctor' so shell-hook
authors see the same shape at development time as runtime
- shell hooks (agent/shell_hooks.py): no code change needed;
_serialize_payload already surfaces non-top-level kwargs under
payload['extra'], so duration_ms lands at extra.duration_ms for
shell-hook scripts
Plugin authors can now build latency dashboards, per-tool SLO alerts,
and regression canaries without having to wrap every tool manually.
Test: tests/test_model_tools.py::test_post_tool_call_receives_non_negative_integer_duration_ms
E2E: real PluginManager + dispatch monkey-patched with a 50ms sleep,
hook callback observes duration_ms=50 (int).
Refs: https://code.claude.com/docs/en/changelog (2.1.119, Apr 23 2026)
Adds a floor below --yolo: a tiny set of commands so catastrophic they
should never run via the agent, regardless of --yolo, gateway /yolo,
approvals.mode=off, or cron approve mode. Opting into yolo is trusting
the agent with your files and services — not trusting it to wipe the
disk or power the box off.
The list is deliberately small (12 patterns), covering only
unrecoverable ops:
- rm -rf targeting /, /home, /etc, /usr, /var, /boot, /bin, /sbin,
/lib, ~, $HOME
- mkfs (any variant)
- dd + redirection to raw block devices (/dev/sd*, /dev/nvme*, etc.)
- fork bomb
- kill -1 / kill -9 -1
- shutdown, reboot, halt, poweroff, init 0/6, telinit 0/6,
systemctl poweroff/reboot/halt/kexec
Recoverable-but-costly commands (git reset --hard, rm -rf /tmp/x,
chmod -R 777, curl | sh) stay in DANGEROUS_PATTERNS where yolo can
still pass them through — that's what yolo is for.
Container backends (docker/singularity/modal/daytona) continue to
bypass both hardline and dangerous checks, since nothing they do can
touch the host.
Inspired by Mercury Agent's permission-hardened blocklist.
Bare `hermes setup` on a returning user now drops straight into the
full reconfigure wizard — every prompt shows the current value as its
default, press Enter to keep or type a new value to change it. The
returning-user menu is gone.
Behavior:
- First-time user: first-time wizard (unchanged)
- Returning user, bare command: full reconfigure wizard (new default)
- Returning user, `--quick`: only prompt for missing/unset items
- Returning user, one section: `hermes setup model|terminal|gateway|tools|agent`
- `--reconfigure`: preserved as backwards-compat alias (no-op since it's now default)
The section functions already used current values as prompt defaults —
this change just removes the extra click to get to them.
The 'Quick Setup - configure missing items only' menu option is now
exposed as the explicit `--quick` flag; it's the narrow case of
filling in missing config (e.g. after a partial OpenClaw migration or
when a required API key got cleared).
Inspired by Mercury Agent's `mercury doctor` UX.
Also removes:
- RETURNING_USER_MENU_SECTION_KEYS (orphaned constant)
- Two returning-user menu tests in test_setup_noninteractive.py
(guarding behavior that no longer exists — covered by
test_setup_reconfigure.py instead)
The azure-foundry wizard now probes the endpoint before asking the user
to pick anything by hand:
1. URL path sniff — endpoints ending in /anthropic are Azure Foundry
Claude routes and skip to anthropic_messages.
2. GET <base>/models probe — if the endpoint returns an OpenAI-shaped
model list, we switch to chat_completions and prefill the picker
with the returned deployment/model IDs.
3. Anthropic Messages probe — fallback for endpoints that don't expose
/models but do speak the Anthropic Messages shape.
4. Manual fallback — private endpoints / custom routes still work;
the user picks API mode + types a deployment name.
Context length for the selected model is resolved through the existing
agent.model_metadata.get_model_context_length chain (models.dev,
provider metadata, hardcoded family fallbacks) and stored in
model.context_length when a non-default value is found.
Also refactors runtime_provider so Azure Foundry resolution is reused
between the explicit-credentials path and the default top-level path —
previously the /v1 strip for Anthropic-style Azure only ran when the
caller passed explicit_* args, which meant config-driven sessions
hit a double-/v1 URL.
New module hermes_cli/azure_detect.py with 19 unit tests covering:
- path sniff, model ID extraction, probe fallbacks
- HTTP error handling (URLError, HTTPError)
- context-length lookup passthrough
- DEFAULT_FALLBACK_CONTEXT rejection
New runtime tests cover:
- OpenAI-style Azure Foundry
- Anthropic-style Azure Foundry with /v1 stripping
- Missing base_url / API key raising AuthError
Rationale: Microsoft confirms there's no pure-API-key endpoint to list
Azure deployments (that requires ARM management auth). The v1 Azure
OpenAI endpoint does expose /models with the resource's available
model catalog, which is good enough for picker prefill in the common
case. Users on private/gated endpoints fall through to manual entry.
Azure OpenAI exposes an OpenAI-compatible endpoint at
`{resource}.openai.azure.com/openai/v1` that accepts the standard
`openai` Python client. Two issues prevented gpt-5.x models from working:
1. `_max_tokens_param()` only sent `max_completion_tokens` for
`api.openai.com` URLs. Azure also requires `max_completion_tokens`
for gpt-5.x models.
2. The `codex_responses` upgrade gate unconditionally upgraded gpt-5.x
to Responses API. Azure does NOT support the Responses API — it serves
gpt-5.x on the regular `/chat/completions` path, causing a 404.
Fix: add `_is_azure_openai_url()` that matches `openai.azure.com` URLs.
- `_max_tokens_param()` now returns `max_completion_tokens` for Azure.
- The `codex_responses` upgrade gate skips Azure so gpt-5.x stays on
`chat_completions` where Azure actually serves it.
- The fallback-provider api_mode picker also recognises Azure and stays
on chat_completions.
- Tests cover max_tokens routing, api_mode behaviour, and URL detection.
gpt-4.x models on Azure are unaffected (already used chat_completions +
max_tokens, which Azure accepts for those models).
Salvage of PR #10086 — rewritten against current main where the
codex_responses upgrade gate gained copilot-acp / explicit-api_mode
exclusions.
Fixes#15779. Custom-provider per-model context_length (`custom_providers[].models.<id>.context_length`) is now honored across every resolution path, not just agent startup. Also adds 256K as the top probe tier and default fallback.
## What changed
New helper `hermes_cli.config.get_custom_provider_context_length()` — single source of truth for the per-model override lookup, with trailing-slash-insensitive base-url matching.
`agent.model_metadata.get_model_context_length()` gains an optional `custom_providers=` kwarg (step 0b — runs after explicit `config_context_length` but before every other probe).
Wired through five call sites that previously either duplicated the lookup or ignored it entirely:
- `run_agent.py` startup — refactored to use the new helper (dedups legacy inline loop, keeps invalid-value warning)
- `AIAgent.switch_model()` — re-reads custom_providers from live config on every /model switch
- `hermes_cli.model_switch.resolve_display_context_length()` — new `custom_providers=` kwarg
- `gateway/run.py` /model confirmation (picker callback + text path)
- `gateway/run.py` `_format_session_info` (/info)
## Context probe tiers
`CONTEXT_PROBE_TIERS = [256_000, 128_000, 64_000, 32_000, 16_000, 8_000]` — was `[128_000, ...]`. `DEFAULT_FALLBACK_CONTEXT` follows tier[0], so unknown models now default to 256K. The stale `128000` literal in the OpenRouter metadata-miss path is replaced with `DEFAULT_FALLBACK_CONTEXT` for consistency.
## Repro (from #15779)
```yaml
custom_providers:
- name: my-custom-endpoint
base_url: https://example.invalid/v1
model: gpt-5.5
models:
gpt-5.5:
context_length: 1050000
```
`/model gpt-5.5 --provider custom:my-custom-endpoint` → previously "Context: 128,000", now "Context: 1,050,000".
## Tests
- `tests/hermes_cli/test_custom_provider_context_length.py` — new file, 19 tests covering the helper, step-0b integration, and the 256K tier invariants
- `tests/hermes_cli/test_model_switch_context_display.py` — added regression tests for #15779 through the display resolver
- `tests/gateway/test_session_info.py` — updated default-fallback assertion (128K → 256K)
- `tests/agent/test_model_metadata.py` — updated tier assertions for the new top tier
Add ability to interrupt a running agent via the runs API. Previously
/v1/runs could start a run and subscribe to events, but there was no
way to cancel it. The new endpoint stores agent and task references
during execution, calls agent.interrupt() to stop LLM calls, then
cancels the asyncio task.
Includes 15 tests covering start, events, and stop scenarios.
When the user interrupts a long-running task, prompt_toolkit tries to
flush stdout during emergency shutdown. If stdout is in a broken state
(redirected to /dev/null, pipe closed, terminal gone), the flush raises
`OSError: [Errno 5] Input/output error` which propagates unhandled and
crashes the CLI.
Two defense layers:
1. `_suppress_closed_loop_errors`: add `OSError` with `errno.EIO` to
the asyncio exception handler, matching the existing pattern for
`RuntimeError("Event loop is closed")` and `KeyError("is not
registered")`.
2. Outer `except (KeyError, OSError)` block: add `errno.EIO` check
before the existing string-match guards, silently suppressing the
error instead of printing a misleading stdin-related message.
Fixes#13710.
The raw-template lookup added in PR #15817 went through
`get_compatible_custom_providers(read_raw_config())`, which calls
`_normalize_custom_provider_entry` → `urlparse(base_url)`. Any
entry whose `base_url` is itself an env-ref (`${NEURALWATT_API_BASE}`)
was dropped as 'not a valid URL', so `api_key_ref` stayed empty and the
resolved secret was still written to `model.api_key` — the exact case
the original Discord report described.
Replace the normalizer-gated lookup with a direct read of
`raw['custom_providers']` and `raw['providers']`, indexed by name
(case-insensitive, optionally qualified by model) so the loaded
(expanded) entry can be matched regardless of how `base_url` is
written.
Add an integration regression test driving the real
`select_provider_and_model` entry point with the Discord-reported
NeuralWatt config (`${VAR}` in both `base_url` and `api_key`).
This test fails on the PR-only fix and passes with the broadened
lookup.
Previously _copy_reasoning_content_for_api only padded reasoning_content
when the assistant message had tool_calls. DeepSeek V4 thinking mode
requires the field on every assistant turn, including plain text replies
without tool_calls.
- Remove the 'source_msg.get("tool_calls") and' guard
- Update test: plain assistant turns now get padded for DeepSeek/Kimi
Fixes#15213
- expand short model aliases like sonnet/opus via static catalogs during startup runtime resolution
- keep startup alias resolution network-free and add regression tests in models and tui gateway suites
The Codex Responses API rejects input_text inside assistant messages —
only output_text and refusal are valid content types for assistant role.
_chat_content_to_responses_parts() previously hardcoded all text content
to input_text regardless of the message role. When an assistant message
had list-format content (multimodal or structured), this produced invalid
input_text parts that the API rejected with:
Invalid value: 'input_text'. Supported values are: 'output_text' and 'refusal'.
Fix: add a role parameter to _chat_content_to_responses_parts() that
selects output_text for assistant messages and input_text for user
messages. Thread this through _chat_messages_to_responses_input() and
_preflight_codex_input_items().
Fixes#15687
When a user sends /stop during a streaming API call, the outer poll loop
detects _interrupt_requested and closes the HTTP connection. However, the
inner _call() thread catches the connection error and enters its retry
loop — opening a FRESH connection without checking the interrupt flag.
On slow providers like ollama-cloud, each retry attempt blocks for the
full stream-read timeout (120s+). With 3 retry attempts this caused
510+ second delays between /stop and actual response — the agent appeared
completely unresponsive despite the stop being acknowledged.
Fix: add an _interrupt_requested check at the top of the streaming retry
loop so the agent exits immediately instead of retrying.
Also fix log truncation: all session key logging in gateway/run.py used
[:20] or [:30] slices, which truncated 'agent:main:telegram:dm:5690190437'
(33 chars) to 'agent:main:telegram:' — losing the identifying chat type
and user ID. Replace with full keys to make logs debuggable.
Reported by user Sidharth Pulipaka via Telegram on ollama-cloud provider.
The AIAgent.flush_memories pre-compression save, the gateway
_flush_memories_for_session, and everything feeding them are
obsolete now that the background memory/skill review handles
persistent memory extraction.
Problems with flush_memories:
- Pre-dates the background review loop. It was the only memory-save
path when introduced; the background review now fires every 10 user
turns on CLI and gateway alike, which is far more frequent than
compression or session reset ever triggered flush.
- Blocking and synchronous. Pre-compression flush ran on the live agent
before compression, blocking the user-visible response.
- Cache-breaking. Flush built a temporary conversation prefix
(system prompt + memory-only tool list) that diverged from the live
conversation's cached prefix, invalidating prompt caching. The
gateway variant spawned a fresh AIAgent with its own clean prompt
for each finalized session — still cache-breaking, just in a
different process.
- Redundant. Background review runs in the live conversation's
session context, gets the same content, writes to the same memory
store, and doesn't break the cache. Everything flush_memories
claimed to preserve is already covered.
What this removes:
- AIAgent.flush_memories() method (~248 LOC in run_agent.py)
- Pre-compression flush call in _compress_context
- flush_memories call sites in cli.py (/new + exit)
- GatewayRunner._flush_memories_for_session + _async_flush_memories
(and the 3 call sites: session expiry watcher, /new, /resume)
- 'flush_memories' entry from DEFAULT_CONFIG auxiliary tasks,
hermes tools UI task list, auxiliary_client docstrings
- _memory_flush_min_turns config + init
- #15631's headroom-deduction math in
_check_compression_model_feasibility (headroom was only needed
because flush dragged the full main-agent system prompt along;
the compression summariser sends a single user-role prompt so
new_threshold = aux_context is safe again)
- The dedicated test files and assertions that exercised
flush-specific paths
What this renames (with read-time backcompat on sessions.json):
- SessionEntry.memory_flushed -> SessionEntry.expiry_finalized.
The session-expiry watcher still uses the flag to avoid re-running
finalize/eviction on the same expired session; the new name
reflects what it now actually gates. from_dict() reads
'expiry_finalized' first, falls back to the legacy 'memory_flushed'
key so existing sessions.json files upgrade seamlessly.
Supersedes #15631 and #15638.
Tested: 383 targeted tests pass across run_agent/, agent/, cli/,
and gateway/ session-boundary suites. No behavior regressions —
background memory review continues to handle persistent memory
extraction on both CLI and gateway.
_check_compression_model_feasibility calls get_model_context_length
without provider=, so Codex OAuth users get 1,050,000 (from models.dev
for 'openai') instead of the actual 272,000 limit. This happens because
_infer_provider_from_url maps chatgpt.com → 'openai' (not 'openai-codex'),
skipping the Codex-specific resolution branch entirely.
Result: compression threshold set at 85% of 1.05M = 892K — conversations
never trigger compression, the context grows unbounded, and when gateway
hygiene eventually forces compression, the Codex endpoint drops the
oversized streaming request ('peer closed connection without sending
complete message body').
Fix: forward self.provider to get_model_context_length so provider-
specific resolution branches (Codex OAuth 272K, Copilot live /models,
Nous suffix-match) fire correctly.
Reported by user on GPT 5.5 via Codex OAuth Pro (paste.rs/vsra3).
* fix(terminal): three-layer defense against watch_patterns notification spam
Background processes that stack notify_on_complete=True with watch_patterns
can flood the user with duplicate, delayed notifications — matches deliver
asynchronously via the completion queue and continue arriving minutes after
the process has exited. The docstring warning against this (PR #12113) has
proven insufficient; agents still misuse the combination.
Three layered defenses, each sufficient on its own:
1. Mutual exclusion (terminal_tool.py): When both flags are set on a
background process, drop watch_patterns with a warning. notify_on_complete
wins because 'let me know when it's done' is the more useful signal and
fires exactly once. Extracted as _resolve_notification_flag_conflict() so
the rule is testable in isolation.
2. Suppress-after-exit (process_registry.py): _check_watch_patterns() now
bails the moment session.exited is True. Post-exit chunks (buffered reads
draining after the process is gone) no longer produce notifications. This
is the fix flagged as future work in session 20260418_020302_79881c.
3. Global circuit breaker (process_registry.py): Per-session rate limits don't
catch the sibling-flood case — N concurrent processes can each stay under
8/10s and still collectively spam. New WATCH_GLOBAL_MAX_PER_WINDOW=15 cap
trips a 30-second cooldown across ALL sessions, emits a single
watch_overflow_tripped event, silently counts dropped events, and emits a
watch_overflow_released summary when the cooldown ends.
Also updates the tool schema + docstring to document the new behavior.
Tests: 8 new tests covering all three fixes (suppress-after-exit x2,
mutual-exclusion resolver x4, global breaker trip/cooldown/release x2).
All 60 tests across test_watch_patterns.py, test_notify_on_complete.py,
test_terminal_tool.py pass.
Real-world trigger: self-inflicted in session 20260425_051924 — three
concurrent hermes-sweeper review subprocesses each set watch_patterns=
['failed validation', 'errored'] AND notify_on_complete=True, then iterated
over multiple items, producing enough matches per process to defeat the
per-session cap while staying under the global cap that didn't yet exist.
* fix(terminal): aggressive 1-per-15s watch_patterns rate limit + strike-3 promotion
Per Teknium's direction, the watch_patterns rate limit is now much more
aggressive and self-healing.
## New rule — per session
- HARD cap: 1 watch-match notification per 15 seconds per process.
- Any match arriving inside the cooldown window is dropped and counts as
ONE strike for that window (many drops in the same window still = 1 strike).
- After 3 consecutive strike windows, watch_patterns is permanently disabled
for the session and the session is auto-promoted to notify_on_complete
semantics — exactly one notification when the process actually exits.
- A cooldown window that expires with zero drops resets the consecutive
strike counter — healthy cadence is forgiven.
## Schema + docstring rewritten
The tool schema description now gives the model explicit guidance:
- notify_on_complete is 'the right choice for almost every long-running task'
- watch_patterns is for RARE one-shot signals on LONG-LIVED processes
- Do NOT use watch_patterns with loops/batch jobs — error patterns fire every
iteration and will hit the strike limit fast
- Mutual exclusion is stated on both parameter descriptions
- 1/15s cooldown and 3-strike promotion are stated in the watch_patterns
description so the model sees the contract every turn
## Removed
- WATCH_MAX_PER_WINDOW (8/10s) and WATCH_OVERLOAD_KILL_SECONDS (45) — the
new 1/15s limit subsumes both; keeping them would double-count.
- _watch_window_hits / _watch_window_start / _watch_overload_since fields
on ProcessSession. Replaced by _watch_last_emit_at / _watch_cooldown_until
/ _watch_strike_candidate / _watch_consecutive_strikes.
## Kept
- Global circuit breaker across all sessions (15/10s → 30s cooldown) as a
secondary safety net for concurrent siblings. Still valuable when 20
short-lived processes each fire once — none individually violates the
per-session limit.
- Suppress-after-exit guard.
- Mutual exclusion resolver at the tool entry point.
## Tests
- 6 new tests in TestPerSessionRateLimit covering: first match delivers,
second in cooldown suppressed, multi-drop = single strike, 3 strikes
disables + promotes, clean window resets counter, suppressed count
carried to next emit.
- Global circuit breaker tests rewritten to use fresh sessions instead of
hacking removed per-window fields.
- 50/50 watch_patterns + notify_on_complete tests pass.
- 60/60 including test_terminal_tool.py pass.
* feat(dashboard): page-scoped plugin slots for built-in pages
Dashboard plugins can now inject components into specific built-in
pages (Sessions, Analytics, Logs, Cron, Skills, Config, Env, Docs,
Chat) without overriding the whole route.
Previously, plugins could only:
1. Add new tabs (tab.path)
2. Replace whole built-in pages (tab.override)
3. Inject into global shell slots (header-*, footer-*, pre-main, ...)
None of those let a plugin add a banner, card, or widget to an
existing page. The new <page>:top / <page>:bottom slots close that
gap, reusing the existing registerSlot() API.
Changes
- web/src/plugins/slots.ts: 18 new KNOWN_SLOT_NAMES entries
(sessions:top, sessions:bottom, analytics:top, ..., chat:bottom),
grouped under "Shell-wide" vs "Page-scoped" in the docblock
- web/src/pages/*: each built-in page now renders
<PluginSlot name="<page>:top" />
as the first child of its outer wrapper and
<PluginSlot name="<page>:bottom" />
as the last child -- zero visual cost when no plugin registers
- plugins/example-dashboard: registers a demo banner into
sessions:top via registerSlot(), with matching slots entry in
the manifest -- so freshly-setup users can see what page-scoped
slots look like without writing any plugin code
- website/docs: new "Page-scoped slots" table in the plugin
authoring guide, with a worked example
- tests/hermes_cli/test_web_server.py: round-trip test for
colon-bearing slot names (sessions:top, analytics:bottom, ...)
Validation
- npm run build: clean (tsc -b + vite build, 2761 modules)
- scripts/run_tests.sh tests/hermes_cli/test_web_server.py::TestDashboardPluginManifestExtensions: 5/5 pass
* fix(terminal): three-layer defense against watch_patterns notification spam
Background processes that stack notify_on_complete=True with watch_patterns
can flood the user with duplicate, delayed notifications — matches deliver
asynchronously via the completion queue and continue arriving minutes after
the process has exited. The docstring warning against this (PR #12113) has
proven insufficient; agents still misuse the combination.
Three layered defenses, each sufficient on its own:
1. Mutual exclusion (terminal_tool.py): When both flags are set on a
background process, drop watch_patterns with a warning. notify_on_complete
wins because 'let me know when it's done' is the more useful signal and
fires exactly once. Extracted as _resolve_notification_flag_conflict() so
the rule is testable in isolation.
2. Suppress-after-exit (process_registry.py): _check_watch_patterns() now
bails the moment session.exited is True. Post-exit chunks (buffered reads
draining after the process is gone) no longer produce notifications. This
is the fix flagged as future work in session 20260418_020302_79881c.
3. Global circuit breaker (process_registry.py): Per-session rate limits don't
catch the sibling-flood case — N concurrent processes can each stay under
8/10s and still collectively spam. New WATCH_GLOBAL_MAX_PER_WINDOW=15 cap
trips a 30-second cooldown across ALL sessions, emits a single
watch_overflow_tripped event, silently counts dropped events, and emits a
watch_overflow_released summary when the cooldown ends.
Also updates the tool schema + docstring to document the new behavior.
Tests: 8 new tests covering all three fixes (suppress-after-exit x2,
mutual-exclusion resolver x4, global breaker trip/cooldown/release x2).
All 60 tests across test_watch_patterns.py, test_notify_on_complete.py,
test_terminal_tool.py pass.
Real-world trigger: self-inflicted in session 20260425_051924 — three
concurrent hermes-sweeper review subprocesses each set watch_patterns=
['failed validation', 'errored'] AND notify_on_complete=True, then iterated
over multiple items, producing enough matches per process to defeat the
per-session cap while staying under the global cap that didn't yet exist.
* fix(terminal): aggressive 1-per-15s watch_patterns rate limit + strike-3 promotion
Per Teknium's direction, the watch_patterns rate limit is now much more
aggressive and self-healing.
## New rule — per session
- HARD cap: 1 watch-match notification per 15 seconds per process.
- Any match arriving inside the cooldown window is dropped and counts as
ONE strike for that window (many drops in the same window still = 1 strike).
- After 3 consecutive strike windows, watch_patterns is permanently disabled
for the session and the session is auto-promoted to notify_on_complete
semantics — exactly one notification when the process actually exits.
- A cooldown window that expires with zero drops resets the consecutive
strike counter — healthy cadence is forgiven.
## Schema + docstring rewritten
The tool schema description now gives the model explicit guidance:
- notify_on_complete is 'the right choice for almost every long-running task'
- watch_patterns is for RARE one-shot signals on LONG-LIVED processes
- Do NOT use watch_patterns with loops/batch jobs — error patterns fire every
iteration and will hit the strike limit fast
- Mutual exclusion is stated on both parameter descriptions
- 1/15s cooldown and 3-strike promotion are stated in the watch_patterns
description so the model sees the contract every turn
## Removed
- WATCH_MAX_PER_WINDOW (8/10s) and WATCH_OVERLOAD_KILL_SECONDS (45) — the
new 1/15s limit subsumes both; keeping them would double-count.
- _watch_window_hits / _watch_window_start / _watch_overload_since fields
on ProcessSession. Replaced by _watch_last_emit_at / _watch_cooldown_until
/ _watch_strike_candidate / _watch_consecutive_strikes.
## Kept
- Global circuit breaker across all sessions (15/10s → 30s cooldown) as a
secondary safety net for concurrent siblings. Still valuable when 20
short-lived processes each fire once — none individually violates the
per-session limit.
- Suppress-after-exit guard.
- Mutual exclusion resolver at the tool entry point.
## Tests
- 6 new tests in TestPerSessionRateLimit covering: first match delivers,
second in cooldown suppressed, multi-drop = single strike, 3 strikes
disables + promotes, clean window resets counter, suppressed count
carried to next emit.
- Global circuit breaker tests rewritten to use fresh sessions instead of
hacking removed per-window fields.
- 50/50 watch_patterns + notify_on_complete tests pass.
- 60/60 including test_terminal_tool.py pass.
`hermes tools` → "reconfigure existing" listed Spotify twice because
the Apr 24 refactor that moved Spotify into plugins/spotify/ (PR #15174)
left the entry in CONFIGURABLE_TOOLSETS. _get_effective_configurable_toolsets()
unconditionally appended get_plugin_toolsets() on top, so the same
'spotify' key showed up from both sources.
Dedupe by key — built-in CONFIGURABLE_TOOLSETS entry wins (it has the
nicer label and description). Also guards against future bundled plugins
that share a toolset key with a built-in.
Generalize the temperature-specific 400 retry that shipped in PR #15621 so
the same reactive strategy covers any provider that rejects an arbitrary
request parameter — — not just temperature.
- agent/auxiliary_client.py:
* New _is_unsupported_parameter_error(exc, param): matches the same six
phrasings the old temperature detector did plus 'unrecognized parameter'
and 'invalid parameter', against any named param.
* _is_unsupported_temperature_error is now a thin back-compat wrapper so
existing imports and tests keep working.
* The max_tokens → max_completion_tokens retry branch in call_llm and
async_call_llm now (a) gates on 'max_tokens is not None' so we do not
pop a key that was never set and silently substitute a None value on
the retry, and (b) also matches the generic helper in addition to the
legacy 'max_tokens' / 'unsupported_parameter' substring checks — picking
up phrasings like 'Unknown parameter: max_tokens' that previously slipped
through.
- tests/agent/test_unsupported_parameter_retry.py: 18 new tests covering
the generic detector across params, the back-compat wrapper, and the two
hardenings to the max_tokens retry branch (None gate + generic phrasing).
Credit: retry-generalization pattern from @nicholasrae's PR #15416. That PR
also proposed the reactive temperature retry which landed independently via
PR #15621 + #15623 (co-authored with @BlueBirdBack). This commit salvages
the remaining hardening ideas onto current main.
When the auxiliary compression model's context is smaller than the main
model's compression threshold, _check_compression_model_feasibility
auto-lowers the session threshold. Previously it set:
new_threshold = aux_context
This let the raw message list grow to exactly aux_context tokens. But
compression and flush_memories actually send system_prompt + tool_schemas
+ messages to the aux model. With 50+ tools that overhead is 25-30K
tokens, so the full request overflowed aux with HTTP 400.
Subtract a headroom estimate from aux_context before setting the new
threshold: the actual tool-schema token count (from
estimate_request_tokens_rough) plus a 12K allowance for the system
prompt (not yet built at __init__ time) and flush-instruction overhead.
Clamp to MINIMUM_CONTEXT_LENGTH so the session still starts even with
an unusually heavy tool schema.
This fixes the 'flush_memories overflow on busy toolsets' path that
Teknium flagged — where main and aux can be nominally the same model
but still 400 because the threshold left no room for the request
overhead. Same fix also protects the normal compression summarisation
request on the same binding aux.
Tests: two new regression tests cover the headroom reservation and the
MINIMUM_CONTEXT_LENGTH floor. Two existing tests updated for the new
(lower) threshold values now that empty-tools still produces a 12K
static headroom deduction.
Universal reactive fix for 'HTTP 400: Unsupported parameter: temperature'
across all providers/models — not just Codex Responses.
The same backend can accept temperature for some models and reject it for
others (e.g. gpt-5.4 accepts but gpt-5.5 rejects on the same OpenAI
endpoint; similar patterns on Copilot, OpenRouter reasoning routes, and
Anthropic Opus 4.7+ via OAI-compat). An allow/deny-list by model name does
not scale.
call_llm / async_call_llm now detect the concrete 'unsupported parameter:
temperature' 400 and transparently retry once without temperature. Kimi's
server-managed omission and Opus 4.7+'s proactive strip stay in place —
this is the safety net for everything else.
Changes:
- agent/auxiliary_client.py: add _is_unsupported_temperature_error helper;
wire into both sync and async call_llm paths before the existing
max_tokens/payment/auth retry ladder
- tests/agent/test_unsupported_temperature_retry.py: 19 tests covering
detector phrasings, sync + async retry, no-retry-without-temperature,
and non-temperature 400s not triggering the retry
Builds on PR #15620 (codex_responses fallback) which stripped temperature
up front for that one api_mode. This PR closes the gap for every other
provider/model combo via reactive retry.
Credit: retry approach and detector originate from @BlueBirdBack's PR #15578.
Co-authored-by: BlueBirdBack <BlueBirdBack@users.noreply.github.com>
The memory-flush fallback for api_mode='codex_responses' was unconditionally
adding `temperature` to codex_kwargs before calling _run_codex_stream. The
Responses API does not accept temperature on any supported backend:
- chatgpt.com/backend-api/codex rejects it outright
- api.openai.com + gpt-5/o-series reasoning models reject it
- Copilot Responses rejects it on reasoning models
The CodexAuxiliaryClient adapter and the codex_responses transport both
correctly omit temperature — the flush fallback was the only path putting
it back. On errors from the primary aux path (e.g. expired OAuth token),
users saw `⚠ Auxiliary memory flush failed: HTTP 400: Unsupported parameter:
temperature`.
Reported by Garik [NOUS] on GPT-5.5 via Codex OAuth Pro.
Both discord (read/participate) and discord_admin (server admin) are now
configurable via `hermes tools` with default-OFF. Previously the core
discord tool (fetch_messages, search_members, create_thread) auto-loaded
on every Discord install with DISCORD_BOT_TOKEN set — 19 tools the user
never opted into.
Adds a platform-scoping mechanism (_TOOLSET_PLATFORM_RESTRICTIONS) so
the discord toolsets only show up in the Discord platform's checklist,
not on CLI/Telegram/Slack/etc. Applied at four gates:
- _prompt_toolset_checklist: checklist filter
- _get_platform_tools: resolution filter (both branches)
- _save_platform_tools: save-time filter (covers 'Configure all
platforms' and hand-edited config.yaml)
- tools_disable_enable_command: rejects `hermes tools enable discord`
on non-Discord platforms with a clear error
build_session_context_prompt now injects the Discord IDs block only
when both conditions hold: the discord/discord_admin toolset is
enabled AND DISCORD_BOT_TOKEN is set. Toolset alone isn't enough —
the tool's check_fn gates on the token at registry time, so opting
in without a token yields no tools and the IDs block would lie.
Otherwise keep the stale-API disclaimer.
The feishu_doc and feishu_drive tools were registered in the tool
registry but never added to the hermes-feishu composite toolset.
The pipeline fix from the prior commit now recovers them automatically
once they are in the composite.
Split the monolithic discord_server tool (14 actions) into two:
- discord: core actions (fetch_messages, search_members, create_thread)
that are useful for the agent's normal operation. Auto-enabled on
the discord platform via the pipeline fix.
- discord_admin: server management actions (list channels/roles, pins,
role assignment) that require explicit opt-in via hermes tools.
Added to CONFIGURABLE_TOOLSETS and _DEFAULT_OFF_TOOLSETS.
The reverse-mapping loop in _get_platform_tools only checked
CONFIGURABLE_TOOLSETS, silently dropping platform-specific toolsets
like discord and feishu_doc whose tools were in the composite but
had no configurable key. Add a second pass over TOOLSETS that picks
up unclaimed toolsets whose tools are present in the resolved
composite.
The tool schema promised 'On update, pass an empty array to clear' but the
update branch ignored the context_from kwarg entirely — users could set
the field at create time and never modify or clear it afterward.
- tools/cronjob_tools.py: handle context_from in the update branch the
same way script/enabled_toolsets/workdir are handled: normalize str/list
to refs, validate each referenced job exists (same check the create
branch does), store as list-or-None to match create_job()'s shape.
Empty string or empty list clears the field.
- tests/cron/test_cron_context_from.py: 6 new tests covering add/change/
clear (both shapes)/bad-ref/preserve-across-unrelated-update.
YAML parses bare numeric toolset names (e.g. 12306:) as int, causing
TypeError in sorted() since the read path normalizes to str but the
save path did not.
The no_mcp sentinel was preserved in existing entries even when the
user re-enabled MCP servers, causing MCP to stay silently disabled.
update_model() recalculated threshold_tokens but left tail_token_budget
and max_summary_tokens at their __init__ values. When switching from a
200K model to 32K, the tail budget stayed at ~20K tokens (62% of 32K)
instead of the intended ~10%.
Adds budget recalculation in update_model() and 2 regression tests.
Subagents run inside a ThreadPoolExecutor. The CLI's interactive approval
callback lives in tools/terminal_tool.py's threading.local(), which worker
threads do not inherit. When a subagent hits a dangerous-command guard,
prompt_dangerous_approval() falls back to input() from the worker thread,
deadlocking against the parent's prompt_toolkit TUI that owns stdin.
Fix: install a non-interactive callback into every subagent worker thread
via ThreadPoolExecutor(initializer=set_approval_callback, initargs=(cb,)).
The callback is config-gated by delegation.subagent_auto_approve:
false (default) -> _subagent_auto_deny (safe; matches leaf tool blocklist)
true -> _subagent_auto_approve (opt-in YOLO for cron/batch)
Both emit a logger.warning audit line. Gateway sessions are unaffected
because they resolve approvals via tools/approval.py's per-session queue,
not through these TLS callbacks. Diagnosis credit: @MorAlekss (#14685).
- hermes_cli/config.py: DEFAULT_CONFIG.delegation.subagent_auto_approve: False
- cli-config.yaml.example: documented, commented (default)
- tools/delegate_tool.py: _subagent_auto_deny, _subagent_auto_approve,
_get_subagent_approval_callback, wired into the child timeout executor
- tests/tools/test_delegate.py: 7 tests covering defaults, truthy coercion,
and TLS scoping in the worker thread
Two adjustments to make CI pass:
- In gateway/platforms/matrix.py: `DeviceID` is `NewType("DeviceID", str)`,
so passing `client.device_id` directly (already a str) works identically
at runtime. The explicit import was cosmetic and tripped CI environments
where `mautrix.types` doesn't re-export DeviceID at the expected path
("cannot import name 'DeviceID' from 'mautrix.types' (unknown location)").
- In tests/gateway/test_matrix.py: add `put_device_id` to the hand-written
`PgCryptoStore` fake so the three encryption-path tests
(test_connect_with_access_token_and_encryption,
test_connect_uses_configured_device_id_over_whoami,
test_connect_registers_encrypted_event_handler_when_encryption_on) can
exercise the new crypto-store binding without AttributeError.
/model gpt-5.5 on openai-codex showed 'Context: 1,050,000 tokens' because
the display block used ModelInfo.context_window directly from models.dev.
Codex OAuth actually enforces 272K for the same slug, and the agent's
compressor already runs at 272K via get_model_context_length() — so the
banner + real context budget said 272K while /model lied with 1M.
Route the display context through a new resolve_display_context_length()
helper that always prefers agent.model_metadata.get_model_context_length
(which knows about Codex OAuth, Copilot, Nous caps) and only falls back
to models.dev when that returns nothing.
Fix applied to all 3 /model display sites:
cli.py _handle_model_switch
gateway/run.py picker on_model_selected callback
gateway/run.py text-fallback confirmation
Reported by @emilstridell (Telegram, April 2026).
The three google-workspace scripts (setup.py, google_api.py, gws_bridge.py)
each had their own way of resolving HERMES_HOME:
- setup.py imported hermes_constants (crashes outside Hermes process)
- google_api.py used os.getenv inline (no strip, no empty handling)
- gws_bridge.py defined its own local get_hermes_home() (duplicate)
Extract the common logic into _hermes_home.py which:
- Delegates to hermes_constants when available (profile support, etc.)
- Falls back to os.getenv with .strip() + empty-as-unset handling
- Provides display_hermes_home() with ~/ shortening for profiles
All three scripts now import from _hermes_home instead of duplicating.
7 regression tests cover the fallback path: env var override, default
~/.hermes, empty env var, display shortening, profile paths, and
custom non-home paths.
Closes#12722
Extracts _needs_kimi_tool_reasoning() for symmetry with the existing
_needs_deepseek_tool_reasoning() helper, so _copy_reasoning_content_for_api
uses the same detection logic as _build_assistant_message. Future changes
to either provider's signals now only touch one function.
Adds tests/run_agent/test_deepseek_reasoning_content_echo.py covering:
- All 3 DeepSeek detection signals (provider, model, host)
- Poisoned history replay (empty string fallback)
- Plain assistant turns NOT padded
- Explicit reasoning_content preserved
- Reasoning field promoted to reasoning_content
- Existing Kimi/Moonshot detection intact
- Non-thinking providers left alone
21 tests, all pass.
``run_conversation`` was calling ``memory_manager.sync_all(
original_user_message, final_response)`` at the end of every turn
where both args were present. That gate didn't consider the
``interrupted`` local flag, so an external memory backend received
partial assistant output, aborted tool chains, or mid-stream resets as
durable conversational truth. Downstream recall then treated the
not-yet-real state as if the user had seen it complete, poisoning the
trust boundary between "what the user took away from the turn" and
"what Hermes was in the middle of producing when the interrupt hit".
Extracted the inline sync block into a new private method
``AIAgent._sync_external_memory_for_turn(original_user_message,
final_response, interrupted)`` so the interrupt guard is a single
visible check at the top of the method instead of hidden in a
boolean-and at the call site. That also gives tests a clean seam to
assert on — the pre-fix layout buried the logic inside the 3,000-line
``run_conversation`` function where no focused test could reach it.
The new method encodes three independent skip conditions:
1. ``interrupted`` → skip entirely (the #15218 fix). Applies even
when ``final_response`` and ``original_user_message`` happen to
be populated — an interrupt may have landed between a streamed
reply and the next tool call, so the strings on disk are not
actually the turn the user took away.
2. No memory manager / no final_response / no user message →
preserve existing skip behaviour (nothing new for providerless
sessions, system-initiated refreshes, tool-only turns that never
resolved, etc.).
3. Sync_all / queue_prefetch_all exceptions → swallow. External
memory providers are strictly best-effort; a misconfigured or
offline backend must never block the user from seeing their
response.
The prefetch side-effect is gated on the same interrupt flag: the
user's next message is almost certainly a retry of the same intent,
and a prefetch keyed on the interrupted turn would fire against stale
context.
### Tests (16 new, all passing on py3.11 venv)
``tests/run_agent/test_memory_sync_interrupted.py`` exercises the
helper directly on a bare ``AIAgent`` (``__new__`` pattern that the
interrupt-propagation tests already use). Coverage:
- Interrupted turn with full-looking response → no sync (the fix)
- Interrupted turn with long assistant output → no sync (the interrupt
could have landed mid-stream; strings-on-disk lie)
- Normal completed turn → sync_all + queue_prefetch_all both called
with the right args (regression guard for the positive path)
- No final_response / no user_message / no memory manager → existing
pre-fix skip paths still apply
- sync_all raises → exception swallowed, prefetch still attempted
- queue_prefetch_all raises → exception swallowed after sync succeeded
- 8-case parametrised matrix across (interrupted × final_response ×
original_user_message) asserts sync fires iff interrupted=False AND
both strings are non-empty
Closes#15218
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Extends PR #15171 to also cover the server-side cancellation path (aiohttp
shutdown, request-level timeout) — previously only ConnectionResetError
triggered the incomplete-snapshot write, so cancellations left the store
stuck at the in_progress snapshot written on response.created.
Factors the incomplete-snapshot build into a _persist_incomplete_if_needed()
helper called from both the ConnectionResetError and CancelledError
branches; the CancelledError handler re-raises so cooperative cancellation
semantics are preserved.
Adds two regression tests that drive _write_sse_responses directly (the
TestClient disconnect path races the server handler, which makes the
end-to-end assertion flaky).
When display.busy_input_mode is 'queue', the runner-level PRIORITY block
in _handle_message was still calling running_agent.interrupt() for every
text follow-up to an active session. The adapter-level busy handler
already honors queue mode (commit 9d147f7fd), but this runner-level path
was an unconditional interrupt regardless of config.
Adds a queue-mode branch that queues the follow-up via
_queue_or_replace_pending_event() and returns without interrupting.
Salvages the useful part of #12070 (@knockyai). The config fan-out to
per-platform extra was redundant — runner already loads busy_input_mode
directly via _load_busy_input_mode().
skill_view response went to the model verbatim; duplicating the SKILL.md
body as raw_content on every tool call added token cost with no agent-facing
benefit. Remove the field and update tests to assert on content only.
The slash/preload caller (agent/skill_commands.py) already falls back to
content when raw_content is absent, and it calls skill_view(preprocess=False)
anyway, so content is already unrendered on that path.
Extends _repair_tool_call_arguments() to cover the most common local-model
JSON corruption pattern: llama.cpp/Ollama backends emit literal tabs and
newlines inside JSON string values (memory save summaries, file contents,
etc.). Previously fell through to '{}' replacement, losing the call.
Adds two repair passes:
- Pass 0: json.loads(strict=False) + re-serialise to canonical wire form
- Pass 4: escape 0x00-0x1F control chars inside string values, then retry
Ports the core utility from #12068 / PR #12093 without the larger plumbing
change (that PR also replaced json.loads at 8 call sites; current main's
_repair_tool_call_arguments is already the single chokepoint, so the
upgrade happens transparently for every existing caller).
Credit: @truenorth-lj for the original utility design.
4 new regression tests covering literal newlines, tabs, re-serialisation
to strict=True-valid output, and the trailing-comma + control-char
combination case.
When the streaming path (chat completions) assembled tool call deltas and
detected malformed JSON arguments, it set has_truncated_tool_args=True but
passed the broken args through unchanged. This triggered the truncation
handler which returned a partial result and killed the session (/new required).
_many_ malformations are repairable: trailing commas, unclosed brackets,
Python None, empty strings. _repair_tool_call_arguments() already existed
for the pre-API-request path but wasn't called during streaming assembly.
Now when JSON parsing fails during streaming assembly, we attempt repair
via _repair_tool_call_arguments() before flagging as truncated. If repair
succeeds (returns valid JSON), the tool call proceeds normally. Only truly
unrepairable args fall through to the truncation handler.
This prevents the most common session-killing failure mode for models like
GLM-5.1 that produce trailing commas or unclosed brackets.
Tests: 12 new streaming assembly repair tests, all 29 existing repair
tests still passing.
When a session is split by context compression mid-tool-call, an assistant
message may end up with truncated/invalid JSON in tool_calls[*].function.arguments.
On the next turn this is replayed verbatim and providers reject the entire request
with HTTP 400 invalid_tool_call_format, bricking the conversation in a loop that
cannot recover without manual session quarantine.
This patch adds a defensive sanitizer that runs immediately before
client.chat.completions.create() in AIAgent.run_conversation():
- Validates each assistant tool_calls[*].function.arguments via json.loads
- Replaces invalid/empty arguments with '{}'
- Injects a synthetic tool response (or prepends a marker to the existing one)
so downstream messages keep valid tool_call_id pairing
- Logs each repair with session_id / message_index / preview for observability
Defense in depth: corruption can originate from compression splits, manual edits,
or plugin bugs. Sanitizing at the send chokepoint catches all sources.
Adds 7 unit tests covering: truncated JSON, empty string, None, non-string args,
existing matching tool response (no duplicate injection), non-assistant messages
ignored, multiple repairs.
Fixes#15236
gpt-5.x on the Codex Responses API sometimes degenerates and emits
Harmony-style `to=functions.<name> {json}` serialization as plain
assistant-message text instead of a structured `function_call` item.
The intent never makes it into `response.output` as a function_call,
so `tool_calls` is empty and `_normalize_codex_response()` returns
the leaked text as the final content. Downstream (e.g. delegate_task),
this surfaces as a confident-looking summary with `tool_trace: []`
because no tools actually ran — the Taiwan-embassy-email bug report.
Detect the pattern, scrub the content, and return finish_reason=
'incomplete' so the existing Codex-incomplete continuation path
(run_agent.py:11331, 3 retries) gets a chance to re-elicit a proper
function_call item. Encrypted reasoning items are preserved so the
model keeps its chain-of-thought on the retry.
Regression tests: leaked text triggers incomplete, real tool calls
alongside leak-looking text are preserved, clean responses pass
through unchanged.
Reported on Discord (gpt-5.4 / openai-codex).
Covers the two bugs salvaged from PR #15161:
- test_batch_runner_checkpoint: TestFinalCheckpointNoDuplicates asserts
the final aggregated completed_prompts list has no duplicate indices,
and keeps a sanity anchor test documenting the pre-fix pattern so a
future refactor that re-introduces it is caught immediately.
- test_model_tools: TestCoerceNumberInfNan asserts _coerce_number
returns the original string for inf/-inf/nan/Infinity inputs and that
the result round-trips through strict (allow_nan=False) json.dumps.
TUI auto-resolves `display.personality` at session init, unlike the base CLI.
If config contains `agent.personalities: null`, `_resolve_personality_prompt`
called `.get()` on None and failed before model/provider selection.
Normalize null personalities to `{}` and surface a targeted config warning.
Tolerating null top-level keys silently drops user settings (e.g.
`agent.system_prompt` next to a bare `agent:` line is gone). Probe at
session create, log via `logger.warning`, and surface in the boot info
under `config_warning` — rendered in the TUI feed alongside the existing
`credential_warning` banner.
YAML parses bare keys like `agent:` or `display:` as None. `dict.get(key, {})`
returns that None instead of the default (defaults only fire on missing keys),
so every `cfg.get("agent", {}).get(...)` chain in tui_gateway/server.py
crashed agent init with `'NoneType' object has no attribute 'get'`.
Guard all 21 sites with `(cfg.get(X) or {})`. Regression test covers the
null-section init path reported on Twitter against the new TUI.
Follow-up to the canonical-identity session-key fix: pull the
JID/LID normalize/expand/canonical helpers into gateway/whatsapp_identity.py
instead of living in two places. gateway/session.py (session-key build) and
gateway/run.py (authorisation allowlist) now both import from the shared
module, so the two resolution paths can't drift apart.
Also switches the auth path from module-level _hermes_home (cached at
import time) to dynamic get_hermes_home() lookup, which matches the
session-key path and correctly reflects HERMES_HOME env overrides. The
lone test that monkeypatched gateway.run._hermes_home for the WhatsApp
auth path is updated to set HERMES_HOME env var instead; all other
tests that monkeypatch _hermes_home for unrelated paths (update,
restart drain, shutdown marker, etc.) still work — the module-level
_hermes_home is untouched.
Hermes' WhatsApp bridge routinely surfaces the same person under either
a phone-format JID (60123456789@s.whatsapp.net) or a LID (…@lid),
and may flip between the two for a single human within the same
conversation. Before this change, build_session_key used the raw
identifier verbatim, so the bridge reshuffling an alias form produced
two distinct session keys for the same person — in two places:
1. DM chat_id — a user's DM sessions split in half, transcripts and
per-sender state diverge.
2. Group participant_id (with group_sessions_per_user enabled) — a
member's per-user session inside a group splits in half for the
same reason.
Add a canonicalizer that walks the bridge's lid-mapping-*.json files
and picks the shortest/numeric-preferred alias as the stable identity.
build_session_key now routes both the DM chat_id and the group
participant_id through this helper when the platform is WhatsApp.
All other platforms and chat types are untouched.
Expose canonical_whatsapp_identifier and normalize_whatsapp_identifier
as public helpers. Plugins that need per-sender behaviour (role-based
routing, per-contact authorization, policy gating) need the same
identity resolution Hermes uses internally; without a public helper,
each plugin would have to re-implement the walker against the bridge's
internal on-disk format. Keeping this alongside build_session_key
makes it authoritative and one refactor away if the bridge ever
changes shape.
_expand_whatsapp_aliases stays private — it's an implementation detail
of how the mapping files are walked, not a contract callers should
depend on.
Exposes hermes --tui over a PTY-backed WebSocket so the dashboard can
embed the real TUI rather than reimplement its surface. The browser
attaches xterm.js to the socket; keystrokes flow in, PTY output bytes
flow out.
Architecture:
browser <Terminal> (xterm.js)
│ onData ───► ws.send(keystrokes)
│ onResize ► ws.send('\x1b[RESIZE:cols;rows]')
│ write ◄── ws.onmessage (PTY bytes)
▼
FastAPI /api/pty (token-gated, loopback-only)
▼
PtyBridge (ptyprocess) ── spawns node ui-tui/dist/entry.js ──► tui_gateway + AIAgent
Components
----------
hermes_cli/pty_bridge.py
Thin wrapper around ptyprocess.PtyProcess: byte-safe read/write on the
master fd via os.read/os.write (not PtyProcessUnicode — ANSI is
inherently byte-oriented and UTF-8 boundaries may land mid-read),
non-blocking select-based reads, TIOCSWINSZ resize, idempotent
SIGHUP→SIGTERM→SIGKILL teardown, platform guard (POSIX-only; Windows
is WSL-supported only).
hermes_cli/web_server.py
@app.websocket("/api/pty") endpoint gated by the existing
_SESSION_TOKEN (via ?token= query param since browsers can't set
Authorization on WS upgrades). Loopback-only enforcement. Reader task
uses run_in_executor to pump PTY bytes without blocking the event
loop. Writer loop intercepts a custom \x1b[RESIZE:cols;rows] escape
before forwarding to the PTY. The endpoint resolves the TUI argv
through a _resolve_chat_argv hook so tests can inject fake commands
without building the real TUI.
Tests
-----
tests/hermes_cli/test_pty_bridge.py — 12 unit tests: spawn, stdout,
stdin round-trip, EOF, resize (via TIOCSWINSZ + tput readback), close
idempotency, cwd, env forwarding, unavailable-platform error.
tests/hermes_cli/test_web_server.py — TestPtyWebSocket adds 7 tests:
missing/bad token rejection (close code 4401), stdout streaming,
stdin round-trip, resize escape forwarding, unavailable-platform ANSI
error frame + 1011 close, resume parameter forwarding to argv.
96 tests pass under scripts/run_tests.sh.
(cherry picked from commit 29b337bca70fc9efb082a5a852ea2cd5381af1a9)
feat(web): add Chat tab with xterm.js terminal + Sessions resume button
(cherry picked from commit 3d21aee8 by emozilla, conflicts resolved
against current main: BUILTIN_ROUTES table + plugin slot layout)
fix(tui): replace OSC 52 jargon in /copy confirmation
When the user ran /copy successfully, Ink confirmed with:
sent OSC52 copy sequence (terminal support required)
That reads like a protocol spec to everyone who isn't a terminal
implementer. The caveat was a historical artifact — OSC 52 wasn't
universally supported when this message was written, so the TUI
honestly couldn't guarantee the copy had landed anywhere.
Today every modern terminal (including the dashboard's embedded
xterm.js) handles OSC 52 reliably. Say what the user actually wants
to know — that it copied, and how much — matching the message the
TUI already uses for selection copy:
copied 1482 chars
(cherry picked from commit a0701b1d5a598dd1d3b94038a7bcbb2a3ab559fc)
docs: document the dashboard Chat tab
AGENTS.md — new subsection under TUI Architecture explaining that the
dashboard embeds the real hermes --tui rather than rewriting it,
with pointers to the pty_bridge + WebSocket endpoint and the rule
'never add a parallel chat surface in React.'
website/docs/user-guide/features/web-dashboard.md — user-facing Chat
section inside the existing Web Dashboard page, covering how it works
(WebSocket + PTY + xterm.js), the Sessions-page resume flow, and
prerequisites (Node.js, ptyprocess, POSIX kernel / WSL on Windows).
(cherry picked from commit 2c2e32cc4519973c77b63016316b065c0f656704)
feat(tui-gateway): transport-aware dispatch + WebSocket sidecar
Decouples the JSON-RPC dispatcher from its I/O sink so the same handler
surface can drive multiple transports concurrently. The PTY chat tab
already speaks to the TUI binary as bytes — this adds a structured
event channel alongside it for dashboard-side React widgets that need
typed events (tool.start/complete, model picker state, slash catalog)
that PTY can't surface.
- `tui_gateway/transport.py` — `Transport` protocol + `contextvars` binding
+ module-level `StdioTransport` fallback. The stdio stream resolves
through a lambda so existing tests that monkey-patch `_real_stdout`
keep passing without modification.
- `tui_gateway/ws.py` — WebSocket transport implementation; FastAPI
endpoint mounting lives in hermes_cli/web_server.py.
- `tui_gateway/server.py`:
- `write_json` routes via session transport (for async events) →
contextvar transport (for in-request writes) → stdio fallback.
- `dispatch(req, transport=None)` binds the transport for the request
lifetime and propagates it to pool workers via `contextvars.copy_context`
so async handlers don't lose their sink.
- `_init_session` and the manual-session create path stash the
request's transport so out-of-band events (subagent.complete, etc.)
fan out to the right peer.
`tui_gateway.entry` (Ink's stdio handshake) is unchanged externally —
it falls through every precedence step into the stdio fallback, byte-
identical to the previous behaviour.
feat(web): ChatSidebar — JSON-RPC sidecar next to xterm.js terminal
Composes the two transports into a single Chat tab:
┌─────────────────────────────────────────┬──────────────┐
│ xterm.js / PTY (emozilla #13379) │ ChatSidebar │
│ the literal hermes --tui process │ /api/ws │
└─────────────────────────────────────────┴──────────────┘
terminal bytes structured events
The terminal pane stays the canonical chat surface — full TUI fidelity,
slash commands, model picker, mouse, skin engine, wide chars all paint
inside the terminal. The sidebar opens a parallel JSON-RPC WebSocket
to the same gateway and renders metadata that PTY can't surface to
React chrome:
• model + provider badge with connection state (click → switch)
• running tool-call list (driven by tool.start / tool.progress /
tool.complete events)
• model picker dialog (gateway-driven, reuses ModelPickerDialog)
The sidecar is best-effort. If the WS can't connect (older gateway,
network hiccup, missing token) the terminal pane keeps working
unimpaired — sidebar just shows the connection-state badge in the
appropriate tone.
- `web/src/components/ChatSidebar.tsx` — new component (~270 lines).
Owns its GatewayClient, drives the model picker through
`slash.exec`, fans tool events into a capped tool list.
- `web/src/pages/ChatPage.tsx` — split layout: terminal pane
(`flex-1`) + sidebar (`w-80`, `lg+` only).
- `hermes_cli/web_server.py` — mount `/api/ws` (token + loopback
guards mirror /api/pty), delegate to `tui_gateway.ws.handle_ws`.
Co-authored-by: emozilla <emozilla@nousresearch.com>
refactor(web): /clean pass on ChatSidebar + ChatPage lint debt
- ChatSidebar: lift gw out of useRef into a useMemo derived from a
reconnect counter. React 19's react-hooks/refs and react-hooks/
set-state-in-effect rules both fire when you touch a ref during
render or call setState from inside a useEffect body. The
counter-derived gw is the canonical pattern for "external resource
that needs to be replaceable on user action" — re-creating the
client comes from bumping `version`, the effect just wires + tears
down. Drops the imperative `gwRef.current = …` reassign in
reconnect, drops the truthy ref guard in JSX. modelLabel +
banner inlined as derived locals (one-off useMemo was overkill).
- ChatPage: lazy-init the banner state from the missing-token check
so the effect body doesn't have to setState on first run. Drops
the unused react-hooks/exhaustive-deps eslint-disable. Adds a
scoped no-control-regex disable on the SGR mouse parser regex
(the \\x1b is intentional for xterm escape sequences).
All my-touched files now lint clean. Remaining warnings on web/
belong to pre-existing files this PR doesn't touch.
Verified: vitest 249/249, ui-tui eslint clean, web tsc clean,
python imports clean.
chore: uptick
fix(web): drop ChatSidebar tool list — events can't cross PTY/WS boundary
The /api/pty endpoint spawns `hermes --tui` as a child process with its
own tui_gateway and _sessions dict; /api/ws runs handle_ws in-process in
the dashboard server with a separate _sessions dict. Tool events fire on
the child's gateway and never reach the WS sidecar, so the sidebar's
tool.start/progress/complete listeners always observed an empty list.
Drop the misleading list (and the now-orphaned ToolCall primitive),
keep model badge + connection state + model picker + error banner —
those work because they're sidecar-local concerns. Surfacing tool calls
in the sidebar requires cross-process forwarding (PTY child opens a
back-WS to the dashboard, gateway tees emits onto stdio + sidecar
transport) — proper feature for a follow-up.
feat(web): wire ChatSidebar tool list to PTY child via /api/pub broadcast
The dashboard's /api/pty spawns hermes --tui as a child process; tool
events fire in the python tui_gateway grandchild and never crossed the
process boundary into the in-process WS sidecar — so the sidebar tool
list was always empty.
Cross-process forwarding:
- tui_gateway: TeeTransport (transport.py) + WsPublisherTransport
(event_publisher.py, sync websockets client). entry.py installs the
tee on _stdio_transport when HERMES_TUI_SIDECAR_URL is set, mirroring
every dispatcher emit to a back-WS without disturbing Ink's stdio
handshake.
- hermes_cli/web_server.py: new /api/pub (publisher) + /api/events
(subscriber) endpoints with a per-channel registry. /api/pty now
accepts ?channel= and propagates the sidecar URL via env. start_server
also stashes app.state.bound_port so the URL is constructable.
- web/src/pages/ChatPage.tsx: generates a channel UUID per mount,
passes it to /api/pty and as a prop to ChatSidebar.
- web/src/components/ChatSidebar.tsx: opens /api/events?channel=, fans
tool.start/progress/complete back into the ToolCall list. Restores
the ToolCall primitive.
Tests: 4 new TestPtyWebSocket cases cover channel propagation,
broadcast fan-out, and missing-channel rejection (10 PTY tests pass,
120 web_server tests overall).
fix(web): address Copilot review on #14890
Five threads, all real:
- gatewayClient.ts: register `message`/`close` listeners BEFORE awaiting
the open handshake. Server emits `gateway.ready` immediately after
accept, so a listener attached after the open promise could race past
the initial skin payload and lose it.
- ChatSidebar.tsx: wire `error`/`close` on the /api/events subscriber
WS into the existing error banner. 4401/4403 (auth/loopback reject)
surface as a "reload the page" message; mid-stream drops surface as
"events feed disconnected" with the existing reconnect button. Clean
unmount closes (1000/1001) stay silent.
- web-dashboard.md: install hint was `pip install hermes-agent[web]` but
ptyprocess lives in the `pty` extra, not `web`. Switch to
`hermes-agent[web,pty]` in both prerequisite blocks.
- AGENTS.md: previous "never add a parallel React chat surface" guidance
was overbroad and contradicted this PR's sidebar. Tightened to forbid
re-implementing the transcript/composer/PTY terminal while explicitly
allowing structured supporting widgets (sidebar / model picker /
inspectors), matching the actual architecture.
- web/package-lock.json: regenerated cleanly so the wterm sibling
workspace paths (extraneous machine-local entries) stop polluting CI.
Tests: 249/249 vitest, 10/10 PTY/events, web tsc clean.
refactor(web): /clean pass on ChatSidebar events handler
Spotted in the round-2 review:
- Banner flashed on clean unmount: `ws.close()` from the effect cleanup
fires `close` with code 1005, opened=true, neither 1000 nor 1001 —
hit the "unexpected drop" branch. Track `unmounting` in the effect
scope and gate the banner through a `surface()` helper so cleanup
closes stay silent.
- DRY the duplicated "events feed disconnected" string into a local
const used by both the error and close handlers.
- Drop the `opened` flag (no longer needed once the unmount guard is
the source of truth for "is this an expected close?").
## Problem
When a pooled HTTPS connection to the Bedrock runtime goes stale (NAT
timeout, VPN flap, server-side TCP RST, proxy idle cull), the next
Converse call surfaces as one of:
* botocore.exceptions.ConnectionClosedError / ReadTimeoutError /
EndpointConnectionError / ConnectTimeoutError
* urllib3.exceptions.ProtocolError
* A bare AssertionError raised from inside urllib3 or botocore
(internal connection-pool invariant check)
The agent loop retries the request 3x, but the cached boto3 client in
_bedrock_runtime_client_cache is reused across retries — so every
attempt hits the same dead connection pool and fails identically.
Only a process restart clears the cache and lets the user keep working.
The bare-AssertionError variant is particularly user-hostile because
str(AssertionError()) is an empty string, so the retry banner shows:
⚠️ API call failed: AssertionError
📝 Error:
with no hint of what went wrong.
## Fix
Add two helpers to agent/bedrock_adapter.py:
* is_stale_connection_error(exc) — classifies exceptions that
indicate dead-client/dead-socket state. Matches botocore
ConnectionError + HTTPClientError subtrees, urllib3
ProtocolError / NewConnectionError, and AssertionError
raised from a frame whose module name starts with urllib3.,
botocore., or boto3.. Application-level AssertionErrors are
intentionally excluded.
* invalidate_runtime_client(region) — per-region counterpart to
the existing reset_client_cache(). Evicts a single cached
client so the next call rebuilds it (and its connection pool).
Wire both into the Converse call sites:
* call_converse() / call_converse_stream() in
bedrock_adapter.py (defense-in-depth for any future caller)
* The two direct client.converse(**kwargs) /
client.converse_stream(**kwargs) call sites in run_agent.py
(the paths the agent loop actually uses)
On a stale-connection exception, the client is evicted and the
exception re-raised unchanged. The agent's existing retry loop then
builds a fresh client on the next attempt and recovers without
requiring a process restart.
## Tests
tests/agent/test_bedrock_adapter.py gets three new classes (14 tests):
* TestInvalidateRuntimeClient — per-region eviction correctness;
non-cached region returns False.
* TestIsStaleConnectionError — classifies botocore
ConnectionClosedError / EndpointConnectionError /
ReadTimeoutError, urllib3 ProtocolError, library-internal
AssertionError (both urllib3.* and botocore.* frames), and
correctly ignores application-level AssertionError and
unrelated exceptions (ValueError, KeyError).
* TestCallConverseInvalidatesOnStaleError — end-to-end: stale
error evicts the cached client, non-stale error (validation)
leaves it alone, successful call leaves it cached.
All 116 tests in test_bedrock_adapter.py pass.
Signed-off-by: Andre Kurait <andrekurait@gmail.com>
Bedrock's aws_sdk auth_type had no matching branch in
resolve_provider_client(), causing it to fall through to the
"unhandled auth_type" warning and return (None, None). This broke
all auxiliary tasks (compression, memory, summarization) for Bedrock
users — the main conversation loop worked fine, but background
context management silently failed.
Add an aws_sdk branch that creates an AnthropicAuxiliaryClient via
build_anthropic_bedrock_client(), using boto3's default credential
chain (IAM roles, SSO, env vars, instance metadata). Default
auxiliary model is Haiku for cost efficiency.
Closes#13919
## Problem
`get_model_context_length()` in `agent/model_metadata.py` had a resolution
order bug that caused every Bedrock model to fall back to the 128K default
context length instead of reaching the static Bedrock table (200K for
Claude, etc.).
The root cause: `bedrock-runtime.<region>.amazonaws.com` is not listed in
`_URL_TO_PROVIDER`, so `_is_known_provider_base_url()` returned False.
The resolution order then ran the custom-endpoint probe (step 2) *before*
the Bedrock branch (step 4b), which:
1. Treated Bedrock as a custom endpoint (via `_is_custom_endpoint`).
2. Called `fetch_endpoint_model_metadata()` → `GET /models` on the
bedrock-runtime URL (Bedrock doesn't serve this shape).
3. Fell through to `return DEFAULT_FALLBACK_CONTEXT` (128K) at the
"probe-down" branch — never reaching the Bedrock static table.
Result: users on Bedrock saw 128K context for Claude models that
actually support 200K on Bedrock, causing premature auto-compression.
## Fix
Promote the Bedrock branch from step 4b to step 1b, so it runs *before*
the custom-endpoint probe at step 2. The static table in
`bedrock_adapter.py::get_bedrock_context_length()` is the authoritative
source for Bedrock (the ListFoundationModels API doesn't expose context
window sizes), so there's no reason to probe `/models` first.
The original step 4b is replaced with a one-line breadcrumb comment
pointing to the new location, to make the resolution-order docstring
accurate.
## Changes
- `agent/model_metadata.py`
- Add step 1b: Bedrock static-table branch (unchanged predicate, moved).
- Remove dead step 4b block, replace with breadcrumb comment.
- Update resolution-order docstring to include step 1b.
- `tests/agent/test_model_metadata.py`
- New `TestBedrockContextResolution` class (3 tests):
- `test_bedrock_provider_returns_static_table_before_probe`:
confirms `provider="bedrock"` hits the static table and does NOT
call `fetch_endpoint_model_metadata` (regression guard).
- `test_bedrock_url_without_provider_hint`: confirms the
`bedrock-runtime.*.amazonaws.com` host match works without an
explicit `provider=` hint.
- `test_non_bedrock_url_still_probes`: confirms the probe still
fires for genuinely-custom endpoints (no over-reach).
## Testing
pytest tests/agent/test_model_metadata.py -q
# 83 passed in 1.95s (3 new + 80 existing)
## Risk
Very low.
- Predicate is identical to the original step 4b — no behaviour change
for non-Bedrock paths.
- Original step 4b was dead code for the user-facing case (always hit
the 128K fallback first), so removing it cannot regress behaviour.
- Bedrock path now short-circuits before any network I/O — faster too.
- `ImportError` fall-through preserved so users without `boto3`
installed are unaffected.
## Related
- This is a prerequisite for accurate context-window accounting on
Bedrock — the fix for #14710 (stale-connection client eviction)
depends on correct context sizing to know when to compress.
Signed-off-by: Andre Kurait <andrekurait@gmail.com>
Bedrock model IDs use dots as namespace separators (anthropic.claude-opus-4-7,
us.anthropic.claude-sonnet-4-5-v1:0), not version separators.
normalize_model_name() was unconditionally converting all dots to hyphens,
producing invalid IDs that Bedrock rejects with HTTP 400/404.
This affected both the main agent loop (partially mitigated by
_anthropic_preserve_dots in run_agent.py) and all auxiliary client calls
(compression, session_search, vision, etc.) which go through
_AnthropicCompletionsAdapter and never pass preserve_dots=True.
Fix: add _is_bedrock_model_id() to detect Bedrock namespace prefixes
(anthropic., us., eu., ap., jp., global.) and skip dot-to-hyphen
conversion for these IDs regardless of the preserve_dots flag.
A child running a legitimately long-running tool (terminal command,
browser fetch, big file read) holds current_tool set and keeps
api_call_count frozen while the tool runs. The previous stale check
treated that as idle after 5 heartbeat cycles (~150s), stopped
touching the parent, and let the gateway kill the session.
Split the threshold in two:
- _HEARTBEAT_STALE_CYCLES_IDLE=5 (~150s) — applied only when
current_tool is None (child wedged between turns)
- _HEARTBEAT_STALE_CYCLES_IN_TOOL=20 (~600s) — applied when the child
is inside a tool call
Stale counter also resets when current_tool changes (new tool =
progress). The hard child_timeout_seconds (default 600s) is still
the final cap, so genuinely stuck tools don't get to block forever.
Bug 3 — Stale OAuth token not detected in 'hermes model':
- _model_flow_anthropic used 'has_creds = bool(existing_key)' which treats
any non-empty token (including expired OAuth tokens) as valid.
- Added existing_is_stale_oauth check: if the only credential is an OAuth
token (sk-ant- prefix) with no valid cc_creds fallback, mark it stale
and force the re-auth menu instead of silently accepting a broken token.
Bug 4 — macOS Keychain credentials never read:
- Claude Code >=2.1.114 migrated from ~/.claude/.credentials.json to the
macOS Keychain under service 'Claude Code-credentials'.
- Added _read_claude_code_credentials_from_keychain() using the 'security'
CLI tool; read_claude_code_credentials() now tries Keychain first then
falls back to JSON file.
- Non-Darwin platforms return None from Keychain read immediately.
Tests:
- tests/agent/test_anthropic_keychain.py: 11 cases covering Darwin-only
guard, security command failures, JSON parsing, fallback priority.
- tests/hermes_cli/test_anthropic_model_flow_stale_oauth.py: 8 cases
covering stale OAuth detection, API key passthrough, cc_creds fallback.
Refs: #12905
Moves the Spotify integration from tools/ into plugins/spotify/,
matching the existing pattern established by plugins/image_gen/ for
third-party service integrations.
Why:
- tools/ should be reserved for foundational capabilities (terminal,
read_file, web_search, etc.). tools/providers/ was a one-off
directory created solely for spotify_client.py.
- plugins/ is already the home for image_gen backends, memory
providers, context engines, and standalone hook-based plugins.
Spotify is a third-party service integration and belongs alongside
those, not in tools/.
- Future service integrations (eventually: Deezer, Apple Music, etc.)
now have a pattern to copy.
Changes:
- tools/spotify_tool.py → plugins/spotify/tools.py (handlers + schemas)
- tools/providers/spotify_client.py → plugins/spotify/client.py
- tools/providers/ removed (was only used for Spotify)
- New plugins/spotify/__init__.py with register(ctx) calling
ctx.register_tool() × 7. The handler/check_fn wiring is unchanged.
- New plugins/spotify/plugin.yaml (kind: backend, bundled, auto-load).
- tests/tools/test_spotify_client.py: import paths updated.
tools_config fix — _DEFAULT_OFF_TOOLSETS now wins over plugin auto-enable:
- _get_platform_tools() previously auto-enabled unknown plugin
toolsets for new platforms. That was fine for image_gen (which has
no toolset of its own) but bad for Spotify, which explicitly
requires opt-in (don't ship 7 tool schemas to users who don't use
it). Added a check: if a plugin toolset is in _DEFAULT_OFF_TOOLSETS,
it stays off until the user picks it in 'hermes tools'.
Pre-existing test bug fix:
- tests/hermes_cli/test_plugins.py::test_list_returns_sorted
asserted names were sorted, but list_plugins() sorts by key
(path-derived, e.g. image_gen/openai). With only image_gen plugins
bundled, name and key order happened to agree. Adding plugins/spotify
broke that coincidence (spotify sorts between openai-codex and xai
by name but after xai by key). Updated test to assert key order,
which is what the code actually documents.
Validation:
- scripts/run_tests.sh tests/hermes_cli/test_plugins.py \
tests/hermes_cli/test_tools_config.py \
tests/hermes_cli/test_spotify_auth.py \
tests/tools/test_spotify_client.py \
tests/tools/test_registry.py
→ 143 passed
- E2E plugin load: 'spotify' appears in loaded plugins, all 7 tools
register into the spotify toolset, check_fn gating intact.
Three quality improvements on top of #15121 / #15130 / #15135:
1. Tool consolidation (9 → 7)
- spotify_saved_tracks + spotify_saved_albums → spotify_library with
kind='tracks'|'albums'. Handler code was ~90 percent identical
across the two old tools; the merge is a behavioral no-op.
- spotify_activity dropped. Its 'now_playing' action was a duplicate
of spotify_playback.get_currently_playing (both return identical
204/empty payloads). Its 'recently_played' action moves onto
spotify_playback as a new action — history belongs adjacent to
live state.
- Net: each API call ships 2 fewer tool schemas when the Spotify
toolset is enabled, and the action surface is more discoverable
(everything playback-related is on one tool).
2. Spotify skill (skills/media/spotify/SKILL.md)
Teaches the agent canonical usage patterns so common requests don't
balloon into 4+ tool calls:
- 'play X' = one search, then play by URI (not search + scan +
describe + play)
- 'what's playing' = single get_currently_playing (no preflight
get_state chain)
- Don't retry on '403 Premium required' or '403 No active device' —
both require user action
- URI/URL/bare-ID format normalization
- Full failure-mode reference for 204/401/403/429
3. Surfaced in 'hermes setup' tool status
Adds 'Spotify (PKCE OAuth)' to the tool status list when
auth.json has a Spotify access/refresh token. Matches the
homeassistant pattern but reads from auth.json (OAuth-based) rather
than env vars.
Docs updated to reflect the new 7-tool surface, and mention the
companion skill in the 'Using it' section.
Tests: 54 passing (client 22, auth 15, tools_config 35 — 18 = 54 after
renaming/replacing the spotify_activity tests with library +
recently_played coverage). Docusaurus build clean.
- probe_api_models: add api_mode param; use x-api-key + anthropic-version
headers for anthropic_messages mode (Anthropic's native Models API auth)
- probe_api_models: add User-Agent header to avoid Cloudflare 403 blocks
on third-party OpenAI-compatible endpoints
- validate_requested_model: pass api_mode through from switch_model
- validate_requested_model: for anthropic_messages mode, attempt probe with
correct auth; if probe fails (many proxies don't implement /v1/models),
accept the model with an informational warning instead of rejecting
- fetch_api_models: propagate api_mode to probe_api_models
Regression test for #14981. Verifies that _session_expiry_watcher fires
on_session_finalize for each session swept out of the store, matching
the contract documented for /new, /reset, CLI shutdown, and gateway stop.
Verified the test fails cleanly on pre-fix code (hook call list missing
sess-expired) and passes with the fix applied.
When the primary provider raises AuthError (expired OAuth token,
revoked API key), the error was re-raised before AIAgent was created,
so fallback_model was never consulted. Now both gateway/run.py and
cron/scheduler.py catch AuthError specifically and attempt to resolve
credentials from the fallback_providers/fallback_model config chain
before propagating the error.
Closes#7230
Two small fixes triggered by a support report where the user saw a
cryptic 'HTTP 400 - Error 400 (Bad Request)!!1' (Google's GFE HTML
error page, not a real API error) on every gemini-2.5-pro request.
The underlying cause was an empty GOOGLE_API_KEY / GEMINI_API_KEY, but
nothing in our output made that diagnosable:
1. hermes_cli/dump.py: the api_keys section enumerated 23 providers but
omitted Google entirely, so users had no way to verify from 'hermes
dump' whether the key was set. Added GOOGLE_API_KEY and GEMINI_API_KEY
rows.
2. agent/gemini_native_adapter.py: GeminiNativeClient.__init__ accepted
an empty/whitespace api_key and stamped it into the x-goog-api-key
header, which made Google's frontend return a generic HTML 400 long
before the request reached the Generative Language backend. Now we
raise RuntimeError at construction with an actionable message
pointing at GOOGLE_API_KEY/GEMINI_API_KEY and aistudio.google.com.
Added a regression test that covers '', ' ', and None.
Claude-style and some Anthropic-tuned models occasionally emit tool
names as class-like identifiers: TodoTool_tool, Patch_tool,
BrowserClick_tool, PatchTool. These failed strict-dict lookup in
valid_tool_names and triggered the 'Unknown tool' self-correction
loop, wasting a full turn of iteration and tokens.
_repair_tool_call already handled lowercase / separator / fuzzy
matches but couldn't bridge the CamelCase-to-snake_case gap or the
trailing '_tool' suffix that Claude sometimes tacks on. Extend it
with two bounded normalization passes:
1. CamelCase -> snake_case (via regex lookbehind).
2. Strip trailing _tool / -tool / tool suffix (case-insensitive,
applied twice so TodoTool_tool reduces all the way: strip
_tool -> TodoTool, snake -> todo_tool, strip 'tool' -> todo).
Cheap fast-paths (lowercase / separator-normalized) still run first
so the common case stays zero-cost. Fuzzy match remains the last
resort unchanged.
Tests: tests/run_agent/test_repair_tool_call_name.py covers the
three original reports (TodoTool_tool, Patch_tool, BrowserClick_tool),
plus PatchTool, WriteFileTool, ReadFile_tool, write-file_Tool,
patch-tool, and edge cases (empty, None, '_tool' alone, genuinely
unknown names).
18 new tests + 17 existing arg-repair tests = 35/35 pass.
Closes#14784
Previously 'hermes auth spotify' crashed with 'HERMES_SPOTIFY_CLIENT_ID
is required' if the user hadn't manually created a Spotify developer
app and set env vars. Now the command detects a missing client_id and
walks the user through the one-time app registration inline:
- Opens https://developer.spotify.com/dashboard in the browser
- Tells the user exactly what to paste into the Spotify form
(including the correct default redirect URI, 127.0.0.1:43827)
- Prompts for the Client ID
- Persists HERMES_SPOTIFY_CLIENT_ID to ~/.hermes/.env so subsequent
runs skip the wizard
- Continues straight into the PKCE OAuth flow
Also prints the docs URL at both the start of the wizard and the end
of a successful login so users can find the full guide.
Adds website/docs/user-guide/features/spotify.md with the complete
setup walkthrough, tool reference, and troubleshooting, and wires it
into the sidebar under User Guide > Features > Advanced.
Fixes a stale redirect URI default in the hermes_cli/tools_config.py
TOOL_CATEGORIES entry (was 8888/callback from the PR description
instead of the actual DEFAULT_SPOTIFY_REDIRECT_URI value
43827/spotify/callback defined in auth.py).
Streamable HTTP MCP servers may garbage-collect their server-side
session state while the OAuth token remains valid — idle TTL, server
restart, pod rotation, etc. Before this fix, the tool-call handler
treated the resulting "Invalid or expired session" error as a plain
tool failure with no recovery path, so **every subsequent call on
the affected server failed until the gateway was manually
restarted**. Reporter: #13383.
The OAuth-based recovery path (``_handle_auth_error_and_retry``)
already exists for 401s, but it only fires on auth errors. Session
expiry slipped through because the access token is still valid —
nothing 401'd, so the existing recovery branch was skipped.
Fix
---
Add a sibling function ``_handle_session_expired_and_retry`` that
detects MCP session-expiry via ``_is_session_expired_error`` (a
narrow allow-list of known-stable substrings: ``"invalid or expired
session"``, ``"session expired"``, ``"session not found"``,
``"unknown session"``, etc.) and then uses the existing transport
reconnect mechanism:
* Sets ``MCPServerTask._reconnect_event`` — the server task's
lifecycle loop already interprets this as "tear down the current
``streamablehttp_client`` + ``ClientSession`` and rebuild them,
reusing the existing OAuth provider instance".
* Waits up to 15 s for the new session to come back ready.
* Retries the original call once. If the retry succeeds, returns
its result and resets the circuit-breaker error count. If the
retry raises, or if the reconnect doesn't ready in time, falls
through to the caller's generic error path.
Unlike the 401 path, this does **not** call ``handle_401`` — the
access token is already valid and running an OAuth refresh would be
a pointless round-trip.
All 5 MCP handlers (``call_tool``, ``list_resources``, ``read_resource``,
``list_prompts``, ``get_prompt``) now consult both recovery paths
before falling through:
recovered = _handle_auth_error_and_retry(...) # 401 path
if recovered is not None: return recovered
recovered = _handle_session_expired_and_retry(...) # new
if recovered is not None: return recovered
# generic error response
Narrow scope — explicitly not changed
-------------------------------------
* **Detection is string-based on a 5-entry allow-list.** The MCP
SDK wraps JSON-RPC errors in ``McpError`` whose exception type +
attributes vary across SDK versions, so matching on message
substrings is the durable path. Kept narrow to avoid false
positives — a regular ``RuntimeError("Tool failed")`` will NOT
trigger spurious reconnects (pinned by
``test_is_session_expired_rejects_unrelated_errors``).
* **No change to the existing 401 recovery flow.** The new path is
consulted only after the auth path declines (returns ``None``).
* **Retry count stays at 1.** If the reconnect-then-retry also
fails, we don't loop — the error surfaces normally so the model
sees a failed tool call rather than a hang.
* **``InterruptedError`` is explicitly excluded** from session-expired
detection so user-cancel signals always short-circuit the same
way they did before (pinned by
``test_is_session_expired_rejects_interrupted_error``).
Regression coverage
-------------------
``tests/tools/test_mcp_tool_session_expired.py`` (new, 16 cases):
Unit tests for ``_is_session_expired_error``:
* ``test_is_session_expired_detects_invalid_or_expired_session`` —
reporter's exact wpcom-mcp text.
* ``test_is_session_expired_detects_expired_session_variant`` —
"Session expired" / "expired session" variants.
* ``test_is_session_expired_detects_session_not_found`` — server GC
variant ("session not found", "unknown session").
* ``test_is_session_expired_is_case_insensitive``.
* ``test_is_session_expired_rejects_unrelated_errors`` — narrow-scope
canary: random RuntimeError / ValueError / 401 don't trigger.
* ``test_is_session_expired_rejects_interrupted_error`` — user cancel
must never route through reconnect.
* ``test_is_session_expired_rejects_empty_message``.
Handler integration tests:
* ``test_call_tool_handler_reconnects_on_session_expired`` — reporter's
full repro: first call raises "Invalid or expired session", handler
signals ``_reconnect_event``, retries once, returns the retry's
success result with no ``error`` key.
* ``test_call_tool_handler_non_session_expired_error_falls_through``
— preserved-behaviour canary: random tool failures do NOT trigger
reconnect.
* ``test_session_expired_handler_returns_none_without_loop`` —
defensive: cold-start / shutdown race.
* ``test_session_expired_handler_returns_none_without_server_record``
— torn-down server falls through cleanly.
* ``test_session_expired_handler_returns_none_when_retry_also_fails``
— no retry loop on repeated failure.
Parametrised across all 4 non-``tools/call`` handlers:
* ``test_non_tool_handlers_also_reconnect_on_session_expired``
[list_resources / read_resource / list_prompts / get_prompt].
**15 of 16 fail on clean ``origin/main`` (``6fb69229``)** with
``ImportError: cannot import name '_is_session_expired_error'``
— the fix's surface symbols don't exist there yet. The 1 passing
test is an ordering artefact of pytest-xdist worker collection.
Validation
----------
``source venv/bin/activate && python -m pytest
tests/tools/test_mcp_tool_session_expired.py -q`` → **16 passed**.
Broader MCP suite (5 files:
``test_mcp_tool.py``, ``test_mcp_tool_401_handling.py``,
``test_mcp_tool_session_expired.py``, ``test_mcp_reconnect_signal.py``,
``test_mcp_oauth.py``) → **230 passed, 0 regressions**.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
`_normalize_for_deepseek` was mapping every non-reasoner input into
`deepseek-chat` on the assumption that DeepSeek's API accepts only two
model IDs. That assumption no longer holds — `deepseek-v4-pro` and
`deepseek-v4-flash` are first-class IDs accepted by the direct API,
and on aggregators `deepseek-chat` routes explicitly to V3 (DeepInfra
backend returns `deepseek-chat-v3`). So a user picking V4 Pro through
the model picker was being silently downgraded to V3.
Verified 2026-04-24 against Nous portal's OpenAI-compat surface:
- `deepseek/deepseek-v4-flash` → provider: DeepSeek,
model: deepseek-v4-flash-20260423
- `deepseek/deepseek-chat` → provider: DeepInfra,
model: deepseek/deepseek-chat-v3
Fix:
- Add `deepseek-v4-pro` and `deepseek-v4-flash` to
`_DEEPSEEK_CANONICAL_MODELS` so exact matches pass through.
- Add `_DEEPSEEK_V_SERIES_RE` (`^deepseek-v\d+(...)?$`) so future
V-series IDs (`deepseek-v5-*`, dated variants) keep passing through
without another code change.
- Update docstring + module header to reflect the new rule.
Tests:
- New `TestDeepseekVSeriesPassThrough` — 8 parametrized cases covering
bare, vendor-prefixed, case-variant, dated, and future V-series IDs
plus end-to-end `normalize_model_for_provider(..., "deepseek")`.
- New `TestDeepseekCanonicalAndReasonerMapping` — regression coverage
for canonical pass-through, reasoner-keyword folding, and
fall-back-to-chat behaviour.
- 77/77 pass.
Reported on Discord (Ufonik, Don Piedro): `/model > Deepseek >
deepseek-v4-pro` surfaced
`Normalized 'deepseek-v4-pro' to 'deepseek-chat'`. Picker listing
showed the v4 names, so validation also rejected the post-normalize
`deepseek-chat` as "not in provider listing" — the contradiction
users saw. Normalizer now respects the picker's choice.
Install tini in the container image and route ENTRYPOINT through
`/usr/bin/tini -g -- /opt/hermes/docker/entrypoint.sh`.
Without a PID-1 init, orphans reparented to hermes (MCP stdio servers,
git, bun, browser daemons) never get waited() on and accumulate as
zombies. Long-running gateway containers eventually exhaust the PID
table and hit "fork: cannot allocate memory".
tini is the standard container init (same pattern Docker's --init flag
and Kubernetes pause container use). It handles SIGCHLD, reaps orphans,
and forwards SIGTERM/SIGINT to the entrypoint so hermes's existing
graceful-shutdown handlers still run. The -g flag sends signals to the
whole process group so `docker stop` cleanly terminates hermes and its
descendants, not just direct children.
Closes#15012.
E2E-verified with a minimal reproducer image: spawning 5 orphans that
reparent to PID 1 leaves 5 zombies without tini and 0 with tini.
Concurrent Hermes processes (e.g. cron jobs) refreshing a Nous OAuth token
via resolve_nous_runtime_credentials() write the rotated tokens to auth.json.
The calling process's pool entry becomes stale, and the next refresh against
the already-rotated token triggers a 'refresh token reuse' revocation on
the Nous Portal.
_sync_nous_entry_from_auth_store() reads auth.json under the same lock used
by resolve_nous_runtime_credentials, and adopts the newer token pair before
refreshing the pool entry. This complements #15111 (which preserved the
obtained_at timestamps through seeding).
Partial salvage of #10160 by @konsisumer — only the agent/credential_pool.py
changes + the 3 Nous-specific regression tests. The PR also touched 10
unrelated files (Dockerfile, tips.py, various tool tests) which were
dropped as scope creep.
Regression tests:
- test_sync_nous_entry_from_auth_store_adopts_newer_tokens
- test_sync_nous_entry_noop_when_tokens_match
- test_nous_exhausted_entry_recovers_via_auth_store_sync
Extracts pool-rotation-room logic into `_pool_may_recover_from_rate_limit`
so single-credential pools no longer block the eager-fallback path on 429.
The existing check `pool is not None and pool.has_available()` lets
fallback fire only after the pool marks every entry as exhausted. With
exactly one credential in the pool (the common shape for Gemini OAuth,
Vertex service accounts, and any personal-key setup), `has_available()`
flips back to True as soon as the cooldown expires — Hermes retries
against the same entry, hits the same daily-quota 429, and burns the
retry budget in a tight loop before ever reaching the configured
`fallback_model`. Observed in the wild as 4+ hours of 429 noise on a
single Gemini key instead of falling through to Vertex as configured.
Rotation is only meaningful with more than one credential — gate on
`len(pool.entries()) > 1`. Multi-credential pools keep the current
wait-for-rotation behaviour unchanged.
Fixes#11314. Related to #8947, #10210, #7230. Narrower scope than
open PRs #8023 (classifier change) and #11492 (503/529 credential-pool
bypass) — this addresses the single-credential 429 case specifically
and does not conflict with either.
Tests: 6 new unit tests in tests/run_agent/test_provider_fallback.py
covering (a) None pool, (b) single-cred available, (c) single-cred in
cooldown, (d) 2-cred available rotates, (e) multi-cred all cooling-down
falls back, (f) many-cred available rotates. All 18 tests in the file
pass.
The least_used strategy selected entries via min(request_count) but
never incremented the counter. All entries stayed at count=0, so the
strategy degenerated to fill_first behavior with no actual load balancing.
Now increments request_count after each selection and persists the update.
The Copilot provider resolved context windows via models.dev static data,
which does not include account-specific models (e.g. claude-opus-4.6-1m
with 1M context). This adds the live Copilot /models API as a higher-
priority source for copilot/copilot-acp/github-copilot providers.
New helper get_copilot_model_context() in hermes_cli/models.py extracts
capabilities.limits.max_prompt_tokens from the cached catalog. Results
are cached in-process for 1 hour.
In agent/model_metadata.py, step 5a queries the live API before falling
through to models.dev (step 5b). This ensures account-specific models
get correct context windows while standard models still have a fallback.
Part 1 of #7731.
Refs: #7272
Raw GitHub tokens (gho_/github_pat_/ghu_) are now exchanged for
short-lived Copilot API tokens via /copilot_internal/v2/token before
being used as Bearer credentials. This is required to access
internal-only models (e.g. claude-opus-4.6-1m with 1M context).
Implementation:
- exchange_copilot_token(): calls the token exchange endpoint with
in-process caching (dict keyed by SHA-256 fingerprint), refreshed
2 minutes before expiry. No disk persistence — gateway is long-running
so in-memory cache is sufficient.
- get_copilot_api_token(): convenience wrapper with graceful fallback —
returns exchanged token on success, raw token on failure.
- Both callers (hermes_cli/auth.py and agent/credential_pool.py) now
pipe the raw token through get_copilot_api_token() before use.
12 new tests covering exchange, caching, expiry, error handling,
fingerprinting, and caller integration. All 185 existing copilot/auth
tests pass.
Part 2 of #7731.
When using GitHub Copilot as provider, HTTP 401 errors could cause
Hermes to silently fall back to the next model in the chain instead
of recovering. This adds a one-shot retry mechanism that:
1. Re-resolves the Copilot token via the standard priority chain
(COPILOT_GITHUB_TOKEN -> GH_TOKEN -> GITHUB_TOKEN -> gh auth token)
2. Rebuilds the OpenAI client with fresh credentials and Copilot headers
3. Retries the failed request before falling back
The fix handles the common case where the gho_* OAuth token remains
valid but the httpx client state becomes stale (e.g. after startup
race conditions or long-lived sessions).
Key design decisions:
- Always rebuild client even if token string unchanged (recovers stale state)
- Uses _apply_client_headers_for_base_url() for canonical header management
- One-shot flag guard prevents infinite 401 loops (matches existing pattern
used by Codex/Nous/Anthropic providers)
- No token exchange via /copilot_internal/v2/token (returns 404 for some
account types; direct gho_* auth works reliably)
Tests: 3 new test cases covering end-to-end 401->refresh->retry,
client rebuild verification, and same-token rebuild scenarios.
Docs: Updated providers.md with Copilot auth behavior section.
Pass an explicit HOME into Copilot ACP child processes so delegated ACP runs do not fail when the ambient environment is missing HOME.
Prefer the per-profile subprocess home when available, then fall back to HOME, expanduser('~'), pwd.getpwuid(...), and /home/openclaw. Add regression tests for both profile-home preference and clean HOME fallback.
Refs #11068.
Two narrow fixes motivated by #15099.
1. _seed_from_singletons() was dropping obtained_at, agent_key_obtained_at,
expires_in, and friends when seeding device_code pool entries from the
providers.nous singleton. Fresh credentials showed up with
obtained_at=None, which broke downstream freshness-sensitive consumers
(self-heal hooks, pool pruning by age) — they treated just-minted
credentials as older than they actually were and evicted them.
2. When the Nous Portal OAuth 2.1 server returns invalid_grant with
'Refresh token reuse detected' in the error_description, rewrite the
message to explain the likely cause (an external process consumed the
rotated RT without persisting it back) and the mitigation. The generic
reuse message led users to report this as a Hermes persistence bug when
the actual trigger was typically a third-party monitoring script calling
/api/oauth/token directly. Non-reuse errors keep their original server
description untouched.
Closes#15099.
Regression tests:
- tests/agent/test_credential_pool.py::test_nous_seed_from_singletons_preserves_obtained_at_timestamps
- tests/hermes_cli/test_auth_nous_provider.py::test_refresh_token_reuse_detection_surfaces_actionable_message
- tests/hermes_cli/test_auth_nous_provider.py::test_refresh_non_reuse_error_keeps_original_description
Cron jobs can now specify a per-job working directory. When set, the job
runs as if launched from that directory: AGENTS.md / CLAUDE.md /
.cursorrules from that dir are injected into the system prompt, and the
terminal / file / code-exec tools use it as their cwd (via TERMINAL_CWD).
When unset, old behaviour is preserved (no project context files, tools
use the scheduler's cwd).
Requested by @bluthcy.
## Mechanism
- cron/jobs.py: create_job / update_job accept 'workdir'; validated to
be an absolute existing directory at create/update time.
- cron/scheduler.py run_job: if job.workdir is set, point TERMINAL_CWD
at it and flip skip_context_files to False before building the agent.
Restored in finally on every exit path.
- cron/scheduler.py tick: workdir jobs run sequentially (outside the
thread pool) because TERMINAL_CWD is process-global. Workdir-less jobs
still run in the parallel pool unchanged.
- tools/cronjob_tools.py + hermes_cli/cron.py + hermes_cli/main.py:
expose 'workdir' via the cronjob tool and 'hermes cron create/edit
--workdir ...'. Empty string on edit clears the field.
## Validation
- tests/cron/test_cron_workdir.py (21 tests): normalize, create, update,
JSON round-trip via cronjob tool, tick partition (workdir jobs run on
the main thread, not the pool), run_job env toggle + restore in finally.
- Full targeted suite (tests/cron/, test_cronjob_tools.py, test_cron.py,
test_config_cwd_bridge.py, test_worktree.py): 314/314 passed.
- Live smoke: hermes cron create --workdir $(pwd) works; relative path
rejected; list shows 'Workdir:'; edit --workdir '' clears.
agent/redact.py snapshots _REDACT_ENABLED from HERMES_REDACT_SECRETS at
module-import time. hermes_cli/main.py calls setup_logging() early, which
transitively imports agent.redact — BEFORE any config bridge has run. So
users who set 'security.redact_secrets: false' in config.yaml (instead of
HERMES_REDACT_SECRETS=false in .env) had the toggle silently ignored in
both 'hermes chat' and 'hermes gateway run'.
Bridge config.yaml -> env var in hermes_cli/main.py BEFORE setup_logging.
.env still wins (only set env when unset) — config.yaml is the fallback.
Regression tests in tests/hermes_cli/test_redact_config_bridge.py spawn
fresh subprocesses to verify:
- redact_secrets: false in config.yaml disables redaction
- default (key absent) leaves redaction enabled
- .env HERMES_REDACT_SECRETS=true overrides config.yaml
json.JSONDecodeError inherits from ValueError. The agent loop's
non-retryable classifier at run_agent.py ~L10782 treated any
ValueError/TypeError as a local programming bug and short-circuited
retry. Without a carve-out, a transient JSONDecodeError from a
provider that returned a malformed response body, a truncated stream,
or a router-layer corruption would fail the turn immediately.
Add JSONDecodeError to the existing UnicodeEncodeError exclusion
tuple so the classified-retry logic (which already handles 429/529/
context-overflow/etc.) gets to run on bad-JSON errors.
Tests (tests/run_agent/test_jsondecodeerror_retryable.py):
- JSONDecodeError: NOT local validation
- UnicodeEncodeError: NOT local validation (existing carve-out)
- bare ValueError: IS local validation (programming bug)
- bare TypeError: IS local validation (programming bug)
- source-level assertion that run_agent.py still carries the carve-out
(guards against accidental revert)
Closes#14782
/model kimi-k2.6 on opencode-zen (or glm-5.1 on opencode-go) returned OpenCode's
website 404 HTML page when the user's persisted model.default was a Claude or
MiniMax model. The switched-to chat_completions request hit
https://opencode.ai/zen (or /zen/go) with no /v1 suffix.
Root cause: resolve_runtime_provider() computed api_mode from
model_cfg.get('default') instead of the model being requested. With a Claude
default, it resolved api_mode=anthropic_messages, stripped /v1 from base_url
(required for the Anthropic SDK), then switch_model()'s opencode_model_api_mode
override flipped api_mode back to chat_completions without restoring /v1.
Fix: thread an optional target_model kwarg through resolve_runtime_provider
and _resolve_runtime_from_pool_entry. When the caller is performing an explicit
mid-session model switch (i.e. switch_model()), the target model drives both
api_mode selection and the conditional /v1 strip. Other callers (CLI init,
gateway init, cron, ACP, aux client, delegate, account_usage, tui_gateway) pass
nothing and preserve the existing config-default behavior.
Regression tests added in test_model_switch_opencode_anthropic.py use the REAL
resolver (not a mock) to guard the exact Quentin-repro scenario. Existing tests
that mocked resolve_runtime_provider with 'lambda requested:' had their mock
signatures widened to '**kwargs' to accept the new kwarg.
When a subagent in delegate_task times out before making its first LLM
request, write a structured diagnostic file under
~/.hermes/logs/subagent-timeout-<sid>-<ts>.log capturing enough state
for the user (and us) to debug the hang. The old error message —
'Subagent timed out after Ns with no response. The child may be stuck
on a slow API call or unresponsive network request.' — gave no
observability for the 0-API-call case, which is the hardest to reason
about remotely.
The diagnostic captures:
- timeout config vs actual duration
- goal (truncated to 1000 chars)
- child config: model, provider, api_mode, base_url, max_iterations,
quiet_mode, platform, _delegate_role, _delegate_depth
- enabled_toolsets + loaded tool names
- system prompt byte/char count (catches oversized prompts that
providers silently choke on)
- tool schema count + byte size
- child's get_activity_summary() snapshot
- Python stack of the worker thread at the moment of timeout
(reveals whether the hang is in credential resolution, transport,
prompt construction, etc.)
Wiring:
- _run_single_child captures the worker thread via a small wrapper
around child.run_conversation so we can look up its stack at
timeout.
- After a FuturesTimeoutError, we pull child.get_activity_summary()
to read api_call_count. If 0 AND it was a timeout (not a raise),
_dump_subagent_timeout_diagnostic() is invoked.
- The returned path is surfaced in the error string so the parent
agent (and therefore the user / gateway) sees exactly where to look.
- api_calls > 0 timeouts keep the old 'stuck on slow API call'
phrasing since that's the correct diagnosis for those.
This does NOT change any behavior for successful subagent runs,
non-timeout errors, or subagents that made at least one API call
before hanging.
Tests: 7 cases (tests/tools/test_delegate_subagent_timeout_diagnostic.py)
- output format + required sections + field values
- long-goal truncation with [truncated] marker
- missing / already-exited worker thread branches
- unwritable HERMES_HOME/logs/ returns None without raising
- _run_single_child wiring: 0 API calls → dump + diagnostic_path in error
- _run_single_child wiring: N>0 API calls → no dump, old message
Refs: #14726
When /model selects Custom but model.provider in YAML still reflects a prior provider, trust model.base_url only for loopback hosts or when provider is custom. Consult CUSTOM_BASE_URL before OpenRouter defaults (#14676).
OpenAI's OAuth token endpoint returns errors in a nested shape —
{"error": {"code": "refresh_token_reused", "message": "..."}} —
not the OAuth spec's flat {"error": "...", "error_description": "..."}.
The existing parser only handled the flat shape, so:
- `err.get("error")` returned a dict, the `isinstance(str)` guard
rejected it, and `code` stayed `"codex_refresh_failed"`.
- The dedicated `refresh_token_reused` branch (with its actionable
"re-run codex + hermes auth" message and `relogin_required=True`)
never fired.
- Users saw the generic "Codex token refresh failed with status 401"
when another Codex client (CLI, VS Code extension) had consumed
their single-use refresh token — giving no hint that re-auth was
required.
Parse both shapes, mapping OpenAI's nested `code`/`type` onto the
existing `code` variable so downstream branches (`refresh_token_reused`,
`invalid_grant`, etc.) fire correctly.
Add regression tests covering:
- nested `refresh_token_reused` → actionable message + relogin_required
- nested generic code → code + message surfaced
- flat OAuth-spec `invalid_grant` still handled (back-compat)
- unparseable body → generic fallback message, relogin_required=False
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Google AI Studio's free tier (<= 250 req/day for gemini-2.5-flash) is
exhausted in a handful of agent turns, so the setup wizard now refuses
to wire up Gemini when the supplied key is on the free tier, and the
runtime 429 handler appends actionable billing guidance.
Setup-time probe (hermes_cli/main.py):
- `_model_flow_api_key_provider` fires one minimal generateContent call
when provider_id == 'gemini' and classifies the response as
free/paid/unknown via x-ratelimit-limit-requests-per-day header or
429 body containing 'free_tier'.
- Free -> print block message, refuse to save the provider, return.
- Paid -> 'Tier check: paid' and proceed.
- Unknown (network/auth error) -> 'could not verify', proceed anyway.
Runtime 429 handler (agent/gemini_native_adapter.py):
- `gemini_http_error` appends billing guidance when the 429 error body
mentions 'free_tier', catching users who bypass setup by putting
GOOGLE_API_KEY directly in .env.
Tests: 21 unit tests for the probe + error path, 4 tests for the
setup-flow block. All 67 existing gemini tests still pass.
PR #14935 added a Codex-aware context resolver but only new lookups
hit the live /models probe. Users who had run Hermes on gpt-5.5 / 5.4
BEFORE that PR already had the wrong value (e.g. 1,050,000 from
models.dev) persisted in ~/.hermes/context_length_cache.yaml, and the
cache-first lookup in get_model_context_length() returns it forever.
Symptom (reported in the wild by Ludwig, min heo, Gaoge on current
main at 6051fba9d, which is AFTER #14935):
* Startup banner shows context usage against 1M
* Compression fires late and then OpenAI hard-rejects with
'context length will be reduced from 1,050,000 to 128,000'
around the real 272k boundary.
Fix: when the step-1 cache returns a value for an openai-codex lookup,
check whether it's >= 400k. Codex OAuth caps every slug at 272k (live
probe values) so anything at or above 400k is definitionally a
pre-#14935 leftover. Drop that entry from the on-disk cache and fall
through to step 5, which runs the live /models probe and repersists
the correct value (or 272k from the hardcoded fallback if the probe
fails). Non-Codex providers and legitimately-cached Codex entries at
272k are untouched.
Changes:
- agent/model_metadata.py:
* _invalidate_cached_context_length() — drop a single entry from
context_length_cache.yaml and rewrite the file.
* Step-1 cache check in get_model_context_length() now gates
provider=='openai-codex' entries >= 400k through invalidation
instead of returning them.
Tests (3 new in TestCodexOAuthContextLength):
- stale 1.05M Codex entry is dropped from disk AND re-resolved
through the live probe to 272k; unrelated cache entries survive.
- fresh 272k Codex entry is respected (no probe call, no invalidation).
- non-Codex 1M entries (e.g. anthropic/claude-opus-4.6 on OpenRouter)
are unaffected — the guard is strictly scoped to openai-codex.
Full tests/agent/test_model_metadata.py: 88 passed.
Make the main-branch test suite pass again. Most failures were tests
still asserting old shapes after recent refactors; two were real source
bugs.
Source fixes:
- tools/mcp_tool.py: _kill_orphaned_mcp_children() slept 2s on every
shutdown even when no tracked PIDs existed, making test_shutdown_is_parallel
measure ~3s for 3 parallel 1s shutdowns. Early-return when pids is empty.
- hermes_cli/tips.py: tip 105 was 157 chars; corpus max is 150.
Test fixes (mostly stale mock targets / missing fixture fields):
- test_zombie_process_cleanup, test_agent_cache: patch run_agent.cleanup_vm
(the local name bound at import), not tools.terminal_tool.cleanup_vm.
- test_browser_camofox: patch tools.browser_camofox.load_config, not
hermes_cli.config.load_config (the source module, not the resolved one).
- test_flush_memories_codex._chat_response_with_memory_call: add
finish_reason, tool_call.id, tool_call.type so the chat_completions
transport normalizer doesn't AttributeError.
- test_concurrent_interrupt: polling_tool signature now accepts
messages= kwarg that _invoke_tool() passes through.
- test_minimax_provider: add _fallback_chain=[] to the __new__'d agent
so switch_model() doesn't AttributeError.
- test_skills_config: SKILLS_DIR MagicMock + .rglob stopped working
after the scanner switched to agent.skill_utils.iter_skill_index_files
(os.walk-based). Point SKILLS_DIR at a real tmp_path and patch
agent.skill_utils.get_external_skills_dirs.
- test_browser_cdp_tool: browser_cdp toolset was intentionally split into
'browser-cdp' (commit 96b0f3700) so its stricter check_fn doesn't gate
the whole browser toolset; test now expects 'browser-cdp'.
- test_registry: add tools.browser_dialog_tool to the expected
builtin-discovery set (PR #14540 added it).
- test_file_tools TestPatchHints: patch_tool surfaces hints as a '_hint'
key on the JSON payload, not inline '[Hint: ...' text.
- test_write_deny test_hermes_env: resolve .env via get_hermes_home() so
the path matches the profile-aware denylist under hermetic HERMES_HOME.
- test_checkpoint_manager test_falls_back_to_parent: guard the walk-up
so a stray /tmp/pyproject.toml on the host doesn't pick up /tmp as the
project root.
- test_quick_commands: set cli.session_id in the __new__'d CLI so the
alias-args path doesn't trip AttributeError when fuzzy-matching leaks
a skill command across xdist test distribution.
Gemini's Schema validator requires every `enum` entry to be a string,
even when the parent `type` is integer/number/boolean. Discord's
`auto_archive_duration` parameter (`type: integer, enum: [60, 1440,
4320, 10080]`) tripped this on every request that shipped the full
tool catalog to generativelanguage.googleapis.com, surfacing as
`Gateway: Non-retryable client error: Gemini HTTP 400 (INVALID_ARGUMENT)
Invalid value ... (TYPE_STRING), 60` and aborting the turn.
Sanitize by dropping the `enum` key when the declared type is numeric
or boolean and any entry is non-string. The `type` and `description`
survive, so the model still knows the allowed values; the tool handler
keeps its own runtime validation. Other providers (OpenAI,
OpenRouter, Anthropic) are unaffected — the sanitizer only runs for
native Gemini / cloudcode adapters.
Reported by @selfhostedsoul on Discord with hermes debug share.
Adds an optional bank_id_template config that derives the bank name at
initialize() time from runtime context. Existing users with a static
bank_id keep the current behavior (template is empty by default).
Supported placeholders:
{profile} — active Hermes profile (agent_identity kwarg)
{workspace} — Hermes workspace (agent_workspace kwarg)
{platform} — cli, telegram, discord, etc.
{user} — platform user id (gateway sessions)
{session} — session id
Unsafe characters in placeholder values are sanitized, and empty
placeholders collapse cleanly (e.g. "hermes-{user}" with no user
becomes "hermes"). If the template renders empty, the static bank_id
is used as a fallback.
Common uses:
bank_id_template: hermes-{profile} # isolate per Hermes profile
bank_id_template: {workspace}-{profile} # workspace + profile scoping
bank_id_template: hermes-{user} # per-user banks for gateway
Reusing session_id as document_id caused data loss on /resume: when
the session is loaded again, _session_turns starts empty and the next
retain replaces the entire previously stored content.
Now each process lifecycle gets its own document_id formed as
{session_id}-{startup_timestamp}, so:
- Same session, same process: turns accumulate into one document (existing behavior)
- Resume (new process, same session): writes a new document, old one preserved
- Forks: child process gets its own document; parent's doc is untouched
Also adds session lineage tags so all processes for the same session
(or its parent) can still be filtered together via recall:
- session:<session_id> on every retain
- parent:<parent_session_id> when initialized with parent_session_id
Closes#6602
The existing test_local_embedded_setup_materializes_profile_env expected
exact equality on ~/.hermes/.env content; the new HINDSIGHT_TIMEOUT=120
line from the timeout feature now appears in that file. Append it to the
expected string so the test reflects the new post_setup output.
The module-global `_loop` / `_loop_thread` pair is shared across every
`HindsightMemoryProvider` instance in the process — the plugin loader
creates one provider per `AIAgent`, and the gateway creates one `AIAgent`
per concurrent chat session (Telegram/Discord/Slack/CLI).
`HindsightMemoryProvider.shutdown()` stopped the shared loop when any one
session ended. That stranded the aiohttp `ClientSession` and `TCPConnector`
owned by every sibling provider on a now-dead loop — they were never
reachable for close and surfaced as the `Unclosed client session` /
`Unclosed connector` warnings reported in #11923.
Fix: stop stopping the shared loop in `shutdown()`. Per-provider cleanup
still closes that provider's own client via `self._client.aclose()`. The
loop runs on a daemon thread and is reclaimed on process exit; keeping
it alive between provider shutdowns means sibling providers can drain
their own sessions cleanly.
Regression tests in `tests/plugins/memory/test_hindsight_provider.py`
(`TestSharedEventLoopLifecycle`):
- `test_shutdown_does_not_stop_shared_event_loop` — two providers share
the loop; shutting down one leaves the loop live for the other. This
test reproduces the #11923 leak on `main` and passes with the fix.
- `test_client_aclose_called_on_cloud_mode_shutdown` — each provider's
own aiohttp session is still closed via `aclose()`.
Fixes#11923.
The cherry-picked model_picker test installed its own discord mock at
module-import time via a local _ensure_discord_mock(), overwriting
sys.modules['discord'] with a mock that lacked attributes other
gateway tests needed (Intents.default(), File, app_commands.Choice).
On pytest-xdist workers that collected test_discord_model_picker.py
first, the shared mock in tests/gateway/conftest.py got clobbered and
downstream tests failed with AttributeError / TypeError against
missing mock attrs. Classic sys.modules cross-test pollution (see
xdist-cross-test-pollution skill).
Fix:
- Extend the canonical _ensure_discord_mock() in tests/gateway/conftest.py
to cover everything the model_picker test needs: real View/Select/
Button/SelectOption classes (not MagicMock sentinels), an Embed
class that preserves title/description/color kwargs for assertion,
and Color.greyple.
- Strip the duplicated mock-setup block from test_discord_model_picker.py
and rely on the shared mock that conftest installs at collection
time.
Regression check:
scripts/run_tests.sh tests/gateway/ tests/hermes_cli/ -k 'discord or model or copilot or provider' -o 'addopts='
1291 passed (was 1288 passed + 3 xdist-ordered failures before this commit).
Keep Discord Copilot model switching responsive and current by refreshing picker data from the live catalog when possible, correcting the curated fallback list, and clearing stale controls before the switch completes.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Keep auxiliary provider resolution aligned with the switch and persisted main-provider paths when models.dev returns github-copilot slugs.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Xiaomi's API (api.xiaomimimo.com) requires lowercase model IDs like
"mimo-v2.5-pro" but rejects mixed-case names like "MiMo-V2.5-Pro"
that users copy from marketing docs or the ProviderEntry description.
Add _LOWERCASE_MODEL_PROVIDERS set and apply .lower() to model names
for providers in this set (currently just xiaomi) after stripping the
provider prefix. This ensures any case variant in config.yaml is
normalized before hitting the API.
Other providers (minimax, zai, etc.) are NOT affected — their APIs
accept mixed case (e.g. MiniMax-M2.7).
- Load prompt_caching.cache_ttl in AIAgent (5m default, 1h opt-in)
- Document DEFAULT_CONFIG and developer guide example
- Add unit tests for default, 1h, and invalid TTL fallback
Made-with: Cursor
Auxiliary tasks (session_search, flush_memories, approvals, compression,
vision, etc.) that route to a named custom provider declared under
config.yaml 'providers:' with 'api_mode: anthropic_messages' were
silently building a plain OpenAI client and POSTing to
{base_url}/chat/completions, which returns 404 on Anthropic-compatible
gateways that only expose /v1/messages.
Two gaps caused this:
1. hermes_cli/runtime_provider.py::_get_named_custom_provider — the
providers-dict branch (new-style) returned only name/base_url/api_key/
model and dropped api_mode. The legacy custom_providers-list branch
already propagated it correctly. The dict branch now parses and
returns api_mode via _parse_api_mode() in both match paths.
2. agent/auxiliary_client.py::resolve_provider_client — the named
custom provider block at ~L1740 ignored custom_entry['api_mode']
and unconditionally built an OpenAI client (only wrapping for
Codex/Responses). It now mirrors _try_custom_endpoint()'s three-way
dispatch: anthropic_messages → AnthropicAuxiliaryClient (async wrapped
in AsyncAnthropicAuxiliaryClient), codex_responses → CodexAuxiliaryClient,
otherwise plain OpenAI. An explicit task-level api_mode override
still wins over the provider entry's declared api_mode.
Fixes#15033
Tests: tests/agent/test_auxiliary_named_custom_providers.py gains a
TestProvidersDictApiModeAnthropicMessages class covering
- providers-dict preserves valid api_mode
- invalid api_mode values are dropped
- missing api_mode leaves the entry unchanged (no regression)
- resolve_provider_client returns (Async)AnthropicAuxiliaryClient for
api_mode=anthropic_messages
- full chain via get_text_auxiliary_client / get_async_text_auxiliary_client
with an auxiliary.<task> override
- providers without api_mode still use the OpenAI-wire path
When context compression fires mid-session, run_agent's _compress_context
ends the current session, creates a new child session linked by
parent_session_id, and resets the SQLite flush cursor. New messages land
in the child; the parent row ends up with message_count = 0. A user who
runs 'hermes --resume <original_id>' sees a blank chat even though the
transcript exists — just under a descendant id.
PR #12920 already fixed the exit banner to print the live descendant id
at session end, but that didn't help users who resume by a session id
captured BEFORE the banner update (scripts, sessions list, old terminal
scrollback) or who type the parent id manually.
Fix: add SessionDB.resolve_resume_session_id() which walks the
parent→child chain forward and returns the first descendant with at
least one message row. Wire it into all three resume entry points:
- HermesCLI._preload_resumed_session() (early resume at run() time)
- HermesCLI._init_agent() (the classical resume path)
- /resume slash command
Semantics preserved when the chain has no descendants with messages,
when the requested session already has messages, or when the id is
unknown. A depth cap of 32 guards against malformed loops.
This does NOT concatenate the pre-compression parent transcript into
the child — the whole point of compression is to shrink that, so
replaying it would blow the cache budget we saved. We just jump to
the post-compression child. The summary already reflects what was
compressed away.
Tests: tests/hermes_state/test_resolve_resume_session_id.py covers
- the exact 6-session shape from the issue
- passthrough when session has messages / no descendants
- passthrough for nonexistent / empty / None input
- middle-of-chain redirects
- fork resolution (prefers most-recent child)
Closes#15000
Pin the behaviour added in the preceding commit — `_get_proxy_for_base_url()`
must return None for hosts covered by NO_PROXY and the HTTPS_PROXY otherwise,
and the full `_create_openai_client()` path must NOT mount HTTPProxy for a
NO_PROXY host.
Refs: #14966
Follow-up to the allowed_channels wildcard fix in the preceding commit.
The same '*' literal trap affected two other Discord channel config lists:
- DISCORD_IGNORED_CHANNELS: '*' was stored as the literal string in the
ignored set, and the intersection check never matched real channel IDs,
so '*' was a no-op instead of silencing every channel.
- DISCORD_FREE_RESPONSE_CHANNELS: same shape — '*' never matched, so
the bot still required a mention everywhere.
Add a '*' short-circuit to both checks, matching the allowed_channels
semantics. Extend tests/gateway/test_discord_allowed_channels.py with
regression coverage for all three lists.
Refs: #14920
allowed_channels: "*" in config (or DISCORD_ALLOWED_CHANNELS="*" env var)
is meant to allow all channels, but the check was comparing numeric channel
IDs against the literal string set {"*"} via set intersection — always empty,
so every message was silently dropped.
Add a "*" short-circuit before the set intersection, consistent with every
other platform's allowlist handling (Signal, Slack, Telegram all do this).
Fixes#14920
Introduces a new plugin hook `pre_gateway_dispatch` fired once per
incoming MessageEvent in `_handle_message`, after the internal-event
guard but before the auth / pairing chain. Plugins may return a dict
to influence flow:
{"action": "skip", "reason": "..."} -> drop (no reply)
{"action": "rewrite", "text": "..."} -> replace event.text
{"action": "allow"} / None -> normal dispatch
Motivation: gateway-level message-flow patterns that don't fit cleanly
into any single adapter — e.g. listen-only group-chat windows (buffer
ambient messages, collapse on @mention), or human-handover silent
ingest (record messages while an owner handles the chat manually).
Today these require forking core; with this hook they can live in a
single profile-agnostic plugin.
Hook runs BEFORE auth so plugins can handle unauthorized senders
(e.g. customer-service handover ingest) without triggering the
pairing-code flow. Exceptions in plugin callbacks are caught and
logged; the first non-None action dict wins, remaining results are
ignored.
Includes:
- `VALID_HOOKS` entry + inline doc in `hermes_cli/plugins.py`
- Invocation block in `gateway/run.py::_handle_message`
- 5 new tests in `tests/gateway/test_pre_gateway_dispatch.py`
(skip, rewrite, allow, exception safety, internal-event bypass)
- 2 additional tests in `tests/hermes_cli/test_plugins.py`
- Table entry in `website/docs/user-guide/features/plugins.md`
Made-with: Cursor
- hermes_cli/auth.py: add _default_verify() with macOS Homebrew certifi
fallback (mirrors weixin 3a0ec1d93). Extend env var chain to include
REQUESTS_CA_BUNDLE so one env var works across httpx + requests paths.
- agent/model_metadata.py: add _resolve_requests_verify() reading
HERMES_CA_BUNDLE / REQUESTS_CA_BUNDLE / SSL_CERT_FILE in priority
order. Apply explicit verify= to all 6 requests.get callsites.
- Tests: 18 new unit tests + autouse platform pin on existing
TestResolveVerifyFallback to keep its "returns True" assertions
platform-independent.
Empirically verified against self-signed HTTPS server: requests honors
REQUESTS_CA_BUNDLE only; httpx honors SSL_CERT_FILE only. Hermes now
honors all three everywhere.
Triggered by Discord reports — Nous OAuth SSL failure on macOS
Homebrew Python; custom provider self-signed cert ignored despite
REQUESTS_CA_BUNDLE set in env.
Manual /compress crashed with 'LCMEngine' object has no attribute
'_align_boundary_forward' when any context-engine plugin was active.
The gateway handler reached into _align_boundary_forward and
_find_tail_cut_by_tokens on tmp_agent.context_compressor, but those
are ContextCompressor-specific — not part of the generic ContextEngine
ABC — so every plugin engine (LCM, etc.) raised AttributeError.
- Add optional has_content_to_compress(messages) to ContextEngine ABC
with a safe default of True (always attempt).
- Override it in the built-in ContextCompressor using the existing
private helpers — preserves exact prior behavior for 'compressor'.
- Rewrite gateway /compress preflight to call the ABC method, deleting
the private-helper reach-in.
- Add focus_topic to the ABC compress() signature. Make _compress_context
retry without focus_topic on TypeError so older strict-sig plugins
don't crash on manual /compress <focus>.
- Regression test with a fake ContextEngine subclass that only
implements the ABC (mirrors LCM's surface).
Reported by @selfhostedsoul (Discord, Apr 22).
faster-whisper's device="auto" picks CUDA when ctranslate2's wheel
ships CUDA shared libs, even on hosts without the NVIDIA runtime
(libcublas.so.12 / libcudnn*). On those hosts the model often loads
fine but transcribe() fails at first dlopen, and the broken model
stays cached in the module-global — every subsequent voice message
in the gateway process fails identically until restart.
- Add _load_local_whisper_model() wrapper: try auto, catch missing-lib
errors, retry on device=cpu compute_type=int8.
- Wrap transcribe() with the same fallback: evict cached model, reload
on CPU, retry once. Required because the dlopen failure only surfaces
at first kernel launch, not at model construction.
- Narrow marker list (libcublas, libcudnn, libcudart, 'cannot be loaded',
'no kernel image is available', 'no CUDA-capable device', driver
mismatch). Deliberately excludes 'CUDA out of memory' and similar —
those are real runtime failures that should surface, not be silently
retried on CPU.
- Tests for load-time fallback, runtime fallback (with cached-model
eviction verified), and the OOM non-fallback path.
Reported via Telegram voice-message dumps on WSL2 hosts where libcublas
isn't installed by default.
Local llama.cpp servers (e.g. ggml-org/llama.cpp:full-cuda) fail the entire
request with HTTP 400 'Unable to generate parser for this template. ...
Unrecognized schema: "object"' when any tool schema contains shapes its
json-schema-to-grammar converter can't handle:
* 'type': 'object' without 'properties'
* bare string schema values ('additionalProperties: "object"')
* 'type': ['X', 'null'] arrays (nullable form)
Cloud providers accept these silently, so they ship from external MCP
servers (Atlassian, GCloud, Datadog) and from a couple of our own tools.
Changes
- tools/schema_sanitizer.py: walks the finalized tool list right before it
leaves get_tool_definitions() and repairs the hostile shapes in a deep
copy. No-op on well-formed schemas. Recurses into properties, items,
additionalProperties, anyOf/oneOf/allOf, and $defs.
- model_tools.get_tool_definitions(): invoke the sanitizer as the last
step so all paths (built-in, MCP, plugin, dynamically-rebuilt) get
covered uniformly.
- tools/browser_cdp_tool.py, tools/mcp_tool.py: fix our own bare-object
schemas so sanitization isn't load-bearing for in-repo tools.
- tui_gateway/server.py: _load_enabled_toolsets() was passing
include_default_mcp_servers=False at runtime. That's the config-editing
variant (see PR #3252) — it silently drops every default MCP server
from the TUI's enabled_toolsets, which is why the TUI didn't hit the
llama.cpp crash (no MCP tools sent at all). Switch to True so TUI
matches CLI behavior.
Tests
tests/tools/test_schema_sanitizer.py (17 tests) covers the individual
failure modes, well-formed pass-through, deep-copy isolation, and
required-field pruning.
E2E: loaded the default 'hermes-cli' toolset with MCP discovery and
confirmed all 27 resolved tool schemas pass a llama.cpp-compatibility
walk (no 'object' node missing 'properties', no bare-string schema
values).
Wrap the existing version label in the welcome-banner panel title
('Hermes Agent v… · upstream … · local …') with an OSC-8 terminal
hyperlink pointing at the latest git tag's GitHub release page
(https://github.com/NousResearch/hermes-agent/releases/tag/<tag>).
Clickable in modern terminals (iTerm2, WezTerm, Windows Terminal,
GNOME Terminal, Kitty, etc.); degrades to plain text on terminals
without OSC-8 support. No new line added to the banner.
New get_latest_release_tag() helper runs 'git describe --tags
--abbrev=0' in the Hermes checkout (3s timeout, per-process cache,
silent fallback for non-git/pip installs and forks without tags).
