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.
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.
