* feat(session_search): single-shape tool with discovery, scroll, browse — no LLM
Replaces the LLM-summarized session_search with a single-shape tool that
returns actual messages from the DB. Three calling shapes inferred from
args (no mode parameter):
1. Discovery — pass query. FTS5 + anchored ±5 window + bookends per hit,
all in one call. ~20ms on a real DB instead of ~90s for the previous
three aux-LLM calls.
2. Scroll — pass session_id + around_message_id. Returns a window
centered on the anchor. To paginate, re-anchor on the first/last id
of the returned window. Boundary message appears in both windows
as the orientation marker. ~1ms per scroll call.
3. Browse — no args. Recent sessions chronologically.
Bookend_start (first 3 user+assistant msgs) and bookend_end (last 3) give
the agent goal + resolution on every discovery hit, so a single tool call
reconstructs a long session's arc without loading the whole transcript.
The aux-LLM summary path is gone: it cost ~$0.30/call, took ~30s, and
laundered FTS5 hits through a model that could confabulate when the right
session wasn't in the hit list. The merged shape returns byte-for-byte
content from SQLite.
History:
- PR #20238 (JabberELF) seeded the fast/summary dual-mode split.
- PR #26419 (yoniebans) expanded to fast/guided/summary with bookends,
multi-anchor drill-down, default-mode config, and a teaching skill.
This PR collapses that toolkit into one shape with explicit scroll
support, drops the summary path, drops the mode parameter, drops the
config knob, drops the skill. JabberELF's seed work is acknowledged via
the AUTHOR_MAP entry.
Validation:
- 38/38 tool tests pass (tests/tools/test_session_search.py)
- 12/12 get_messages_around tests pass (tests/hermes_state/)
- 11/11 get_anchored_view tests pass (tests/hermes_state/)
- Full tests/tools/ run: 5168 passing, 2 failures pre-exist on main
(test ordering in test_delegate.py, unrelated)
- E2E against live state DB: discovery 20ms, scroll 1ms, browse 280ms;
pagination forward+backward works with boundary-message orientation;
error paths return clean tool_error responses
Co-authored-by: JabberELF <abcdjmm970703@gmail.com>
Co-authored-by: yoniebans <jonny@nousresearch.com>
* chore(session_search): prune dead LLM-summary config and docs
Companion to the single-shape rewrite. The auxiliary.session_search config
block, max_concurrency / extra_body tunables, and matching docs sections
all referenced the removed LLM summarization path. Removing them so users
don't try to tune knobs that nothing reads.
- hermes_cli/config.py: drop dead auxiliary.session_search block from
DEFAULT_CONFIG. Leftover keys in user config.yaml are harmless and
ignored.
- hermes_cli/tips.py: drop two tips referencing the removed
max_concurrency / extra_body knobs.
- website/docs/user-guide/configuration.md: drop 'Session Search Tuning'
section and the auxiliary.session_search block from the example.
- website/docs/user-guide/features/fallback-providers.md: drop session_search
rows from the auxiliary-tasks tables and the dedicated tuning subsection.
- website/docs/reference/tools-reference.md: rewrite the session_search
entry to describe the new three-shape behaviour.
- CONTRIBUTING.md: update the file-tree description.
- tests/tools/test_llm_content_none_guard.py: remove TestSessionSearchContentNone
class and test_session_search_tool_guarded — both guard against an
unguarded .content.strip() call site in _summarize_session() that no
longer exists.
Validation: 97/97 targeted tests still pass (hermes_state + session_search +
llm_content_none_guard). Config tests 55/55.
---------
Co-authored-by: JabberELF <abcdjmm970703@gmail.com>
Co-authored-by: yoniebans <jonny@nousresearch.com>
The system prompt's 'Conversation started:' line carried minute precision
(%I:%M %p), making it byte-unstable across every rebuild path. Within a
CLI session the in-memory cache held, but on the gateway path (fresh
AIAgent per turn → restore from session DB), any silent failure in the
read or write path dropped the cache stem and forced a full re-prefill
on every subsequent turn. Local prefix-caching backends (llama.cpp /
vLLM) saw this as KV-cache invalidation; remote prefix-caching providers
saw it as an Anthropic-style cache miss.
Three changes:
1. Date-only timestamp ('Sunday, May 17, 2026' instead of '... 03:42 PM').
System prompt now byte-stable for the full day. The model can still
query exact time via tools when it actually needs it. Credit:
@iamfoz (PR #20451).
2. Loud logging on session DB write failures. The update_system_prompt
call used to log at DEBUG, hiding disk-full / locked-database / schema
drift behind a silent fall-through that forced fresh rebuilds on
every subsequent turn. Now WARN with the session id and exception so
persistent issues show up in agent.log without verbose mode.
3. Three-way stored-state distinction on read. The previous
'session_row.get("system_prompt") or None' collapsed three states
into one (missing row / null column / empty string). Now we tell them
apart and WARN when a continuing session lands on null/empty (which
means the previous turn's write never persisted — every subsequent
turn rebuilds and the prefix cache misses every time).
The restore block is extracted into _restore_or_build_system_prompt()
so the prefix-cache path can be unit-tested in isolation.
E2E proof: fresh AIAgent constructed for turn 2 across a minute-boundary
sleep restores byte-identical bytes from the session DB. NULL stored
prompt fires the new warning. Date-only timestamp survives the rebuild
path. All on real SessionDB, no mocks.
Tests:
- tests/agent/test_system_prompt_restore.py (10 new tests)
- tests/run_agent/test_run_agent.py::TestBuildSystemPrompt::
test_datetime_is_date_only_not_minute_precision
Closes#20451 (date-only), #18547 (prefix stabilization),
#8689 (stabilize timestamp across compression), #15866 (timestamp
caching question), #8687 (compression timestamp), #27339
(claim #3: live timestamp in cached system prompt).
Co-authored-by: Martyn Forryan <9133432+iamfoz@users.noreply.github.com>
Grok models hit the same failure modes that OPENAI_MODEL_EXECUTION_GUIDANCE
addresses for GPT/Codex: claiming completion without tool calls
('to be honest, I didn't create the file yet'), suggesting workarounds
instead of using existing tools (proposing a folder-based memory system
when the memory tool exists), replying with plans instead of executing.
TOOL_USE_ENFORCEMENT_GUIDANCE was already injected for any model whose
name contains 'grok' (TOOL_USE_ENFORCEMENT_MODELS). This extends the
follow-on family-specific block — OPENAI_MODEL_EXECUTION_GUIDANCE
(tool_persistence / mandatory_tool_use / act_dont_ask / prerequisite_checks
/ verification / missing_context) — to grok-named models too.
The OPENAI_ prefix is retained for backwards compat with imports/tests;
docstring + inline comment now note that the body is family-agnostic and
the prefix reflects origin, not exclusivity.
Tests cover the OpenRouter slug (x-ai/grok-4.3) and the xai-oauth bare
name (grok-4.3), plus a negative control on claude.
E2E verified against a real AIAgent build of the system prompt for both
xai-oauth and openrouter grok models.
7 new tests:
TestAuxiliaryFallbackLayering (3):
- configured_chain succeeds → main agent fallback NOT consulted
- chain returns nothing → main agent fallback runs and succeeds
- both exhausted → user-visible 'all fallbacks exhausted' warning
fires before the original error is re-raised
TestTryMainAgentModelFallback (4):
- returns (None, None, "") when main provider is 'auto'
- returns (None, None, "") when failed provider == main provider
(no point retrying the same backend)
- resolves the main provider's client when configured correctly
- skips when main provider is marked unhealthy
The two TestAuxiliaryClientPoisonedCacheEviction tests were written
when explicit-provider users got no fallback at all on connection
errors — they asserted ConnectionError propagated after eviction
because the fallback gate blocked the auto chain.
After the #26803 fix in the previous commit, capacity errors
(payment/quota/connection) now DO trigger fallback even on explicit
providers. The tests still verify cache eviction (their actual
contract) but now stub _try_payment_fallback so the fallback
machinery does not attempt a real network call.
Closes#26803
Root causes:
1. _is_payment_error() checked for billing keywords (credits, insufficient
funds, billing, payment required) but missed daily token quota exhaustion
phrases used by Bedrock, Vertex AI, and LiteLLM proxies — e.g.
'Too many tokens per day', 'quota exceeded', 'resource exhausted',
'daily limit'. These are functionally identical to credit exhaustion
(provider cannot serve the request) but don't trigger fallback.
2. The call_llm() fallback chain was gated on resolved_provider == 'auto'.
When a task resolves to a specific provider (e.g. 'custom' for a LiteLLM
proxy, or 'openrouter'), capacity failures (payment/quota/connection)
silently raise instead of trying alternatives. This is overly conservative:
capacity errors mean the provider *cannot* serve the request regardless of
user intent, so alternatives should always be tried.
Fixes:
- Add quota-related keywords to _is_payment_error(): quota_exceeded,
too many tokens per day, daily limit, tokens per day, daily quota,
resource exhausted (Vertex AI gRPC code).
- Allow fallback for capacity errors (payment + connection) even when
resolved_provider is not 'auto'. Rate-limit fallback stays gated on
is_auto to honour explicit provider constraints for transient limits.
- Apply both fixes to sync call_llm() and async acall_llm() paths.
- Add 6 targeted tests for the new quota-error detection cases.
Quarantine Nous OAuth state when refresh fails with terminal invalid_grant/invalid_token errors. Clear local and shared refresh material across runtime, managed access-token, proxy, and credential-pool paths so Hermes stops retrying revoked refresh sessions.
* feat(kanban): orchestrator-driven auto-decomposition on triage
Closes the core gap in the kanban system: dropping a one-liner into Triage
now decomposes it into a graph of child tasks routed to specialist
profiles by description, matching teknium's original vision ("main
orchestrator splits/creates actual tasks, doles them out to each agent").
The build
---------
- hermes_cli/profiles.py: new `description` + `description_auto` fields
on ProfileInfo, persisted in <profile_dir>/profile.yaml. Helpers
read_profile_meta / write_profile_meta. `create_profile` accepts
optional description.
- hermes_cli/profile_describer.py: new module — auto-generate a 1-2
sentence description from a profile's skills + model + name via the
auxiliary LLM (`auxiliary.profile_describer`).
- hermes_cli/main.py: new `hermes profile create --description ...`
flag; new `hermes profile describe [name] [--text ... | --auto |
--all --auto]` subcommand.
- hermes_cli/kanban_db.py: new `decompose_triage_task` atomic helper —
creates N child tasks, links the root as a child of every leaf
(root waits for the whole graph), flips root `triage -> todo` with
orchestrator assignee, records an audit comment + `decomposed` event
in a single write_txn.
- hermes_cli/kanban_decompose.py: new module — calls the auxiliary LLM
(`auxiliary.kanban_decomposer`) with the profile roster + descriptions
to produce a JSON task graph, then invokes the DB helper. Rewrites
unknown assignees to the configured `kanban.default_assignee` (or
the active default profile) so a task NEVER lands with assignee=None.
Falls back to specify-style single-task promotion when the LLM
returns `fanout: false`.
- hermes_cli/kanban.py: new `hermes kanban decompose [task_id | --all]`
CLI verb.
- hermes_cli/config.py: new DEFAULT_CONFIG keys —
kanban.orchestrator_profile, kanban.default_assignee,
kanban.auto_decompose (default True), kanban.auto_decompose_per_tick
(default 3), auxiliary.kanban_decomposer, auxiliary.profile_describer.
- gateway/run.py: kanban dispatcher watcher now runs auto-decompose
before each `_tick_once`, capped by `auto_decompose_per_tick` so a
bulk-load of triage tasks doesn't burst-spend the aux LLM.
- plugins/kanban/dashboard/plugin_api.py: new endpoints —
GET /profiles (list roster + descriptions),
PATCH /profiles/<name> (set description, user-authored),
POST /profiles/<name>/describe-auto (LLM-generate),
POST /tasks/<id>/decompose (run decomposer),
GET/PUT /orchestration (orchestrator/default-assignee/auto-decompose
pickers, with resolved fallbacks echoed back).
- plugins/kanban/dashboard/dist/index.js: new OrchestrationPanel
collapsible — dropdowns for orchestrator profile and default
assignee, auto-decompose toggle, per-profile description editor with
Save and Auto-generate buttons. New ⚗ Decompose button next to
✨ Specify on triage-column task drawers.
Behavior
--------
- A task in Triage gets fanned out into a small DAG of child tasks.
Children with no internal parents flip to `ready` immediately
(parallel dispatch). Children with sibling parents wait. The root
stays alive as a parent of every child — when the whole graph
finishes, it promotes to `ready` and the orchestrator profile wakes
back up to judge completion (the "adds more tasks until done" part
of the original vision).
- `kanban.orchestrator_profile` unset -> falls back to the default
profile (whichever `hermes` launches with no -p flag).
- `kanban.default_assignee` unset -> same fallback. Tasks NEVER end
up unassigned.
- `kanban.auto_decompose=true` (default) runs the decomposer
automatically on dispatcher ticks; manual `hermes kanban decompose`
is always available.
Tests
-----
- tests/hermes_cli/test_kanban_decompose_db.py — 7 tests for the
atomic DB helper (status transitions, dep graph, audit trail,
validation errors).
- tests/hermes_cli/test_kanban_decompose.py — 6 tests for the
decomposer module (fanout, no-fanout fallback, unknown-assignee
rewrite, malformed-JSON resilience, no-aux-client path).
- tests/hermes_cli/test_profile_describer.py — 10 tests for
profile.yaml r/w + the LLM auto-describer (yaml corrupt tolerance,
user-vs-auto description protection, --overwrite, fallback parsing).
E2E
---
- CLI end-to-end: created profiles with descriptions, dropped a triage
task, mocked the aux LLM with a 3-task graph -> verified all three
children were created with the right assignees, the dependency
edges matched the LLM's graph, root flipped to todo gated by every
child, audit comment + `decomposed` event recorded.
- Dashboard end-to-end: started the dashboard against an isolated
HERMES_HOME, verified all four new endpoints via curl (profile
listing, PATCH for description, PUT for orchestration settings,
POST for decompose). Opened the UI in the browser, confirmed the
OrchestrationPanel renders with all three pickers + the per-profile
description editor, typed a description, clicked Save, verified
~/.hermes/profile.yaml was written. Clicked Decompose on the triage
card and confirmed the inline error message surfaced as designed
("no auxiliary client configured").
* feat(kanban): surface decompose mode (Auto/Manual) as a one-click pill
The auto/manual toggle already existed as kanban.auto_decompose (default
true), but it was buried inside the collapsed Orchestration settings
panel — users couldn't tell at a glance which mode they were in. This
hoists it to a pill at the top of the kanban page so the state is always
visible and one click flips it.
UX
- New "⚗ Decompose: AUTO|MANUAL" pill in the kanban header. Emerald
styling when Auto is on (the default), muted/gray when Manual.
- Pill is visible both in the collapsed AND expanded Orchestration
settings views so context is preserved when the user opens the panel.
- Tooltip explains both states + what clicking does.
- Renamed the in-panel "Auto-decompose on triage / Enabled" checkbox
to "Decompose mode / Auto (default) | Manual" for language parity
with the pill.
Behavior preserved
- Default remains Auto (kanban.auto_decompose=true).
- Manual mode restores pre-PR behavior: triage tasks stay in triage
until the user clicks ⚗ Decompose on each card (or runs
`hermes kanban decompose <id>`).
Implementation
- plugins/kanban/dashboard/dist/index.js: load /orchestration on mount
(not just on expand) so the collapsed pill reflects real state.
Render mode pill in both collapsed and expanded headers. Reuses the
existing PUT /api/plugins/kanban/orchestration endpoint — no new
backend, no new tests required.
E2E verified
- Pill renders as "⚗ Decompose: AUTO" on page load (default).
- One click flips to "⚗ Decompose: MANUAL" with muted styling.
- config.yaml on disk shows auto_decompose: false after the flip.
- Second click round-trips back to Auto; config.yaml flips to true.
* feat(kanban): rename mode pill to "Orchestration: Auto/Manual"
Per Teknium feedback — "Decompose" was too implementation-specific.
"Orchestration" is the user-facing concept (the whole pitch is the
orchestrator profile routing work), and the pill is the front door to it.
- Pill text: "Orchestration: Auto" / "Orchestration: Manual" (title case,
no ⚗ prefix, no SHOUTY-CAPS for the mode value)
- In-panel checkbox label: "Orchestration mode" (was "Decompose mode")
- Tooltips updated to match
- No behavior change
* docs(kanban): document decompose, profile descriptions, orchestration mode
Brings the docs site up to parity with the PR. English build verified
locally (npx docusaurus build --locale en) — clean, no new broken links
or anchors. Pre-existing broken-link warnings (rl-training, llms.txt,
step-by-step-checklist, fallback-model) untouched.
- website/docs/reference/cli-commands.md
+ `hermes kanban decompose` action row in the action table, with
pointer to the Auto vs Manual orchestration section.
- website/docs/reference/profile-commands.md
+ `--description "<text>"` flag on `hermes profile create`.
+ Full `hermes profile describe` section: read, --text, --auto,
--overwrite, --all flags with examples.
- website/docs/user-guide/features/kanban.md (the big one)
+ Triage column intro rewritten around the Auto-decompose default
behavior, with pointer to the new Auto vs Manual section.
+ Status action row updated to mention both ⚗ Decompose and
✨ Specify on triage cards.
+ New "Auto vs Manual orchestration" section explaining the two
modes, how to flip them (pill, config), how routing-by-description
works, the no-None-assignee guarantee, plus a config knob table
(auto_decompose, auto_decompose_per_tick, orchestrator_profile,
default_assignee) and the two new auxiliary slots
(kanban_decomposer, profile_describer).
+ REST surface table gains 6 new endpoint rows: /tasks/:id/decompose,
/profiles (GET), /profiles/:name (PATCH), /profiles/:name/describe-auto,
/orchestration (GET + PUT).
- website/docs/user-guide/features/kanban-tutorial.md
+ Triage column blurb updated for Auto by default + Manual via the
pill, with cross-link to the Auto vs Manual orchestration section.
- website/docs/user-guide/profiles.md
+ Blank-profile flow now mentions --description and points to the
kanban routing model for context.
- website/docs/user-guide/configuration.md
+ `kanban_decomposer` and `profile_describer` added to the
`hermes model -> Configure auxiliary models` menu listing.
xAI's /responses endpoint rejects pattern and format JSON Schema keywords
in tool schemas with HTTP 400 'Invalid arguments passed to the model'.
The existing strip_pattern_and_format() only walked OpenAI-format tools
({'function': {'parameters': ...}}), missing Responses-format shapes
({'name': ..., 'parameters': ...}) used by codex_responses API mode.
This shows up most often with MCP-derived tools that carry validation
keywords (e.g. domain pattern regex in firecrawl, format: date-time)
through to the wire.
Extends the walk to handle both shapes. Auto-strip wiring is applied
separately in chat_completion_helpers (post-refactor location).
Closes#27197
14 focused tests on the extracted helper
``_xai_oauth_exchange_code_for_tokens`` cover:
Core contract:
* ``code_verifier`` is on the wire (RFC 7636 §4.5).
* ``code_challenge`` + ``code_challenge_method=S256`` are echoed
(the #26990 defense-in-depth that makes xAI's token endpoint
stop rejecting valid exchanges).
* ``grant_type=authorization_code``, ``code``, ``redirect_uri``,
and ``client_id`` are all locked.
* Content-Type is ``application/x-www-form-urlencoded`` (xAI
rejects ``application/json`` on this endpoint).
* The supplied ``token_endpoint`` URL is used verbatim — no
hard-coded constant sneaks in via a future refactor.
* ``timeout_seconds`` is forwarded; floored at 20s.
Sanity guard:
* Empty ``code_verifier`` raises ``xai_pkce_verifier_missing``
with a link to #26990 — and NOTHING is sent. Leaking the auth
code to a server that can't redeem it is the wrong failure mode.
* Empty ``code_challenge`` omits only the defensive echo; the
standards-compliant ``code_verifier`` request still goes out so
RFC-compliant servers keep working.
Error surfacing:
* Non-200 responses include both ``HTTP <status>`` and the body
verbatim — disambiguates 400 (PKCE / bad request) from 403
(tier denied, see #26847).
* Transport errors are wrapped as ``AuthError`` with the
``xai_token_exchange_failed`` code, so the surrounding
``format_auth_error`` UI mapping still fires.
* Non-dict JSON payloads raise ``xai_token_exchange_invalid``.
* 200 happy path returns the parsed payload dict verbatim.
End-to-end wire-format guard:
* A real ``httpx.Client`` with a stub transport captures the bytes
on the wire and asserts every PKCE field round-trips through
``urlencode``. Catches a future refactor that swaps
``data=`` for ``json=`` (which xAI would silently reject).
Addresses reviewer feedback: when resolve_runtime_provider returns a dict
without the 'provider' key, the result must be None regardless of
configured_provider. This guards against malformed runtime responses.
Test: test_runtime_missing_provider_key_returns_none
Named custom providers (e.g. crof.ai) resolve to provider='custom' at the
runtime level, causing subagents to lose their intended provider identity.
On retry/fallback, resolve_provider_client('custom', model=...) searches all
providers advertising that model and picks non-deterministically, routing to
Z.AI or Bailian instead of the configured target.
The fix preserves configured_provider when runtime['provider'] == 'custom',
restoring the original provider name so routing stays correct through retries.
Adds a named constant _RUNTIME_PROVIDER_CUSTOM instead of a magic string.
Adds three regression tests:
- test_named_custom_provider_preserves_provider_name: the #26954 case
- test_standard_provider_not_overwritten_by_configured_name: openrouter/nous
must still return their own identity, not the configured name
- test_custom_provider_with_empty_configured_provider_falls_back_to_runtime:
empty provider triggers the early-return None path as before
`hermes doctor` displayed OAuth status for Nous, Codex, Gemini, and MiniMax
but silently omitted xAI OAuth, even though `get_xai_oauth_auth_status()`
exists and the same information is already surfaced in `hermes status`.
Add xAI OAuth as a *separate* try/except block so an import failure cannot
silence the already-printed provider rows above it — consistent with the
per-provider isolation introduced in the doctor fallback fix.
Tests:
- 9 new tests in TestDoctorXaiOAuthStatus covering: logged-in ok, not-logged-in
warn, error line present/absent, import failure isolation, runtime exception
and None-return safety.
- 9 existing run_doctor helpers updated to mock get_xai_oauth_auth_status for
deterministic output.
hermes status listed Nous Portal, OpenAI Codex, Qwen OAuth, and MiniMax
OAuth in the Auth Providers section but omitted xAI OAuth entirely.
Users who authenticated via `hermes auth add xai-oauth` had no way to
verify their session state from the status output.
Add xAI OAuth display using the same field shape as OpenAI Codex:
auth_store (Auth file:), last_refresh (Refreshed:), and error when
not logged in. The import is isolated in its own try/except so an
import failure cannot affect the already-printed rows above it.
Tests cover:
- logged in: check mark, auth_store, last_refresh, error suppressed
- not logged in: login command hint, error shown, error absent = no line
- resilience: import failure, status function raises, returns None
- isolation: xAI import failure does not break Nous/MiniMax display
Shared try/except import block meant that if any one status function was
missing, all providers lost their OAuth fallback suppression. Split into
per-provider try/except so each branch is independently safe.
Add end-to-end test for xAI: bad XAI_API_KEY with healthy OAuth does not
surface a blocking issue in run_doctor output. Add tests for None return,
import failure isolation (xAI missing does not break Gemini), and move
test_returns_false_for_unknown_provider out of the xAI-specific class.
_has_healthy_oauth_fallback_for_apikey_provider() covers Gemini and
MiniMax (added by #26853) but omits xAI. The xAI provider profile
(plugins/model-providers/xai/__init__.py) has auth_type="api_key" and
env_vars=("XAI_API_KEY",), so it enters the generic API-key
connectivity loop. When XAI_API_KEY fails a 401 probe but xAI OAuth
is healthy, the failure is promoted to the blocking summary even though
xAI works fine via OAuth — the same false-positive #26853 fixed for
Gemini and MiniMax.
Fix: import get_xai_oauth_auth_status alongside the existing two
helpers and add the "xai" branch. get_xai_oauth_auth_status() already
exists in hermes_cli/auth.py and returns {"logged_in": True} when a
valid OAuth token is present.
Symmetric with the Gemini and MiniMax branches introduced in #26853.
No behavior change for providers without an OAuth path.
Addresses findings from two self-review passes pre-merge.
First pass (3-agent parallel review):
1. plugins/browser/browser_use/provider.py: drop the
``_ = managed_nous_tools_enabled`` dead-import-hider in
_get_config_or_none(). The import was actively misleading — the
helper IS used in _get_config() (separate method, separate import),
not here. The "keep static analysis happy" comment was wrong about
what the helper does in this scope.
2. agent/browser_provider.py: drop ``pragma: no cover`` from
is_configured() / provider_name() backward-compat aliases. They ARE
covered by ``TestLegacyAbcAliases`` — the pragma would have masked
future regressions.
3. tools/browser_tool.py: refactor _is_legacy_provider_registry_overridden()
to compare against a module-frozen _DEFAULT_PROVIDER_REGISTRY snapshot
instead of hardcoded set of 3 keys. Future maintainers adding a 4th
built-in provider now just extend _PROVIDER_REGISTRY; the override
detection adapts automatically. Previously the hardcoded
``set(...) != {"browserbase", "browser-use", "firecrawl"}`` would flip
True forever on any 4-key registry, silently routing every install
onto the legacy fixture path.
4. tools/browser_tool.py: when explicit ``browser.cloud_provider`` is set
but the registry has no matching plugin (typo, uninstalled plugin,
discovery failure), emit a WARNING with actionable text instead of
silently falling through to auto-detect. Legacy code surfaced a typed
credentials error via direct class instantiation; this log restores
the signal in the post-migration path.
5. agent/browser_registry.py: trim the triple-redundant _LEGACY_PREFERENCE
documentation. Module docstring + 13-line block-comment + 5-line
inline comment was repeating the same point. Kept the docstring and
trimmed the block-comment to 5 lines.
6. agent/browser_registry.py: upgrade is_available()-raised logging from
DEBUG to WARNING with exc_info=True. A provider's availability check
throwing is unusual enough that users debugging "no cloud provider"
need the traceback in logs.
7. tests/plugins/browser/check_parity_vs_main.py: drop dead top-level
imports (os, shutil, tempfile — only referenced inside the
SUBPROCESS_SCRIPT string literal that runs in a child process).
Second pass (architecture + claim-verification review):
8. tools/browser_tool.py: rewrite the inline comment in _get_cloud_provider
auto-detect branch. Prior text claimed it "routes through the plugin
registry's legacy preference walk so third-party plugins still get a
chance to be selected when they're explicitly configured" — false on
both counts. The branch uses module-level legacy class aliases
(BrowserUseProvider / BrowserbaseProvider) directly; third-party
plugins are intentionally reachable only via explicit
``browser.cloud_provider``. Corrected comment now matches behaviour
and cross-references _LEGACY_PREFERENCE for the firecrawl gate
rationale.
9. tools/browser_tool.py + tests/tools/test_managed_browserbase_and_modal.py:
drop the unused ``get_active_browser_provider as
_registry_get_active_browser_provider`` alias from the
``from agent.browser_registry import ...`` block. It was never
referenced; matching test-stub line in the agent.browser_registry
SimpleNamespace also dropped. ``get_provider`` is still imported (used
by the explicit-config dispatch path at line 535).
10. plugins/browser/firecrawl/provider.py: align emergency_cleanup()
with the early-guard pattern used in browserbase + browser_use
plugins. Previously firecrawl tried the DELETE and relied on
``_headers()`` raising ValueError to trip a "missing credentials"
warning; same final outcome but a different control flow that read
like a bug to a maintainer skimming the three modules. Now: if
is_available() is False, log+return early — identical shape to the
other two providers.
Verification: 54/54 unit tests + 13/13 parity scenarios still pass.
Two changes that go together:
1. tools/browser_tool.py — add _ensure_browser_plugins_loaded() and call
it from _get_cloud_provider() before consulting the registry. Normally
model_tools triggers discover_plugins() as an import side-effect, but
_get_cloud_provider() can be reached from contexts that haven't gone
through model_tools (standalone scripts, certain unit-test paths, the
new parity-sweep harness). Without the defensive call, the registry is
empty and _registry_get_browser_provider() returns None — silently
downgrading users to local mode when they explicitly configured a
cloud provider with no credentials yet. The behavior-parity sweep
below caught this as 4 scenario regressions (explicit-X-no-creds for
all 3 providers, and explicit-firecrawl-with-creds).
2. tests/plugins/browser/check_parity_vs_main.py — subprocess harness
that pins one Python invocation to origin/main and one to this PR's
worktree via sys.path.insert(), runs _get_cloud_provider() across a
13-scenario config matrix, and diffs the reduced shape tuple
(is_local, provider_name, is_available). Provider_name pulls from
provider.provider_name() which is the legacy CloudBrowserProvider
API and remains as a backward-compat alias on the new BrowserProvider
ABC, so the comparison is apples-to-apples regardless of class
identity.
Final result: PARITY OK across 13 scenarios. The four observable
config/credential matrices that exercise the dispatcher all match
origin/main bit-for-bit:
- no-config + no-env → local
- explicit local + any env → local
- explicit BB / BU / FC + no creds → provider returned with
is_available()==False (so dispatcher surfaces typed credentials
error; matches main exactly)
- explicit BB / BU / FC + creds → provider returned with
is_available()==True
- no-config + BU creds → Browser Use
- no-config + BB creds → Browserbase
- no-config + both → Browser Use (legacy walk first hit)
- no-config + FC only → local (firecrawl NOT in legacy walk)
- no-config + FC + BB → Browserbase (legacy walk skips firecrawl)
Per the dev skill's "behavior-parity for refactor PRs" rule — without
this subprocess sweep, 31/31 unit tests pass while the production code
path is silently broken for users who type `browser.cloud_provider:
browserbase` and run a single browser command without prior model_tools
import. Caught + fixed before push.
Mirrors tests/plugins/web/test_web_search_provider_plugins.py from PR #25182.
31 tests across 5 classes:
TestBundledPluginsRegister (8 tests)
- Three plugins register (browserbase, browser-use, firecrawl)
- Each plugin's name + display_name accessible
- get_setup_schema() returns picker-shaped dict with post_setup hook
- All three lifecycle methods (create_session, close_session,
emergency_cleanup) overridden on every plugin
TestIsAvailable (4 tests)
- browserbase needs BOTH BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID
- browserbase: api_key alone or project_id alone insufficient
- browser-use satisfied by BROWSER_USE_API_KEY
- firecrawl satisfied by FIRECRAWL_API_KEY
TestRegistryResolution (8 tests) — most valuable, locks down
pre-migration semantics:
- _resolve(None) with no creds returns None (local mode)
- _resolve('local') short-circuits to None
- _resolve('browserbase') returns provider even when unavailable
(so dispatcher surfaces typed credentials error)
- _resolve('firecrawl') same: explicit-config wins
- _resolve('unknown') falls through to auto-detect
- Legacy walk picks browser-use over browserbase
- browserbase-only configuration: browserbase wins
- **Regression**: firecrawl is NEVER auto-selected even when
single-eligible (preserves pre-migration gate; FIRECRAWL_API_KEY
shared with web firecrawl must not silently route to paid cloud
browser)
TestLegacyAbcAliases (6 tests)
- is_configured() delegates to is_available() for all three plugins
- provider_name() returns display_name for all three plugins
TestPickerIntegration (3 tests)
- _plugin_browser_providers() exposes all three plugins as rows
- Each row carries post_setup='agent_browser'
- browser_plugin_name marker matches browser_provider
All tests use real imports — no mocking of provider classes — so the
suite catches drift in the ABC, registry, picker injection, and plugin
glue layer simultaneously.
31/31 passing.
The four files in tools/browser_providers/ (base.py, browserbase.py,
browser_use.py, firecrawl.py) have been migrated into
plugins/browser/<vendor>/provider.py over the previous commits. No
in-tree code references them anymore — the legacy class names
(BrowserbaseProvider / BrowserUseProvider / FirecrawlProvider) are
re-exported from tools.browser_tool as aliases to the plugin classes,
so existing test patches keep working.
Updates tests/tools/test_managed_browserbase_and_modal.py:
- Adds _load_plugin_module() helper next to _load_tool_module().
- Reroutes five _load_tool_module('tools.browser_providers.X', ...)
calls to _load_plugin_module('plugins.browser.X.provider', ...).
- Renames BrowserbaseProvider/BrowserUseProvider -> the new plugin
class names (BrowserbaseBrowserProvider / BrowserUseBrowserProvider).
- Updates is_configured() -> is_available() on the one assertion that
cared about the rename (the others stay on is_configured() via the
BrowserProvider ABC's backward-compat alias).
Net diff: -630 / +39 lines (tests + dead-code deletion). Verified
23/23 tests in test_browser_cloud_*.py + test_managed_browserbase_and_modal.py
still pass.
Closes the file-tree mismatch portion of #25214. Remaining work:
new plugin-level test coverage under tests/plugins/browser/, behaviour
parity subprocess sweep vs origin/main, and full tests/tools/ regression
sweep before opening the PR.
Switches tools.browser_tool's cloud-provider lookup from the hardcoded
_PROVIDER_REGISTRY class-instantiation pattern to the
agent.browser_registry singleton registry that plugins self-populate.
Changes:
- tools/browser_tool.py top imports: pull BrowserProvider from
agent.browser_provider (re-exported as CloudBrowserProvider for legacy
callers) and the three provider classes from plugins/browser/<vendor>/.
Legacy class names (BrowserbaseProvider, BrowserUseProvider, FirecrawlProvider)
remain on tools.browser_tool as re-export shims so existing test patches
(monkeypatch.setattr(browser_tool, 'BrowserUseProvider', ...)) keep working.
- _get_cloud_provider() now consults agent.browser_registry.get_provider()
for explicit-config lookups. The auto-detect fallback still uses
BrowserUseProvider() / BrowserbaseProvider() at the module level so the
cache-policy test fixtures (which patch those names) keep driving the
function. Test-time _PROVIDER_REGISTRY overrides are detected by class
identity and routed through the legacy factory-call path.
- agent/browser_provider.py: BrowserProvider grows is_configured() and
provider_name() as thin backward-compat aliases for the legacy
CloudBrowserProvider API. Subclasses MUST implement is_available() and
name; the aliases delegate. This keeps ~6 caller sites in browser_tool.py
working without churning them.
- tests/tools/test_managed_browserbase_and_modal.py: _install_fake_tools_package
grows stubs for agent.browser_provider / agent.browser_registry /
plugins.browser.<vendor>.provider so the test's spec-loader path
(sys.modules-reset + reload-tool-from-disk) can satisfy tools.browser_tool's
top-level imports.
Verified: all 23 existing tests in test_browser_cloud_*.py +
test_managed_browserbase_and_modal.py still pass post-cutover.
The legacy tools/browser_providers/ directory is NOT yet deleted; several
tests still _load_tool_module() those files via spec_from_file_location.
The deletion + test-path updates land in a later commit.
Address code review feedback on _parse_response:
1. Restore isinstance(raw, str) guard so non-string message/reason values
(e.g. integers, lists) from a malformed hook response fall back to the
default rather than being forwarded as-is. This keeps the contract that
message in the returned dict is always a string.
2. Extract the repeated literal 'Blocked by shell hook.' into a module-level
constant _DEFAULT_BLOCK_MESSAGE to avoid duplication and make it easy to
change in one place.
Four new unit tests added to tests/agent/test_shell_hooks.py covering:
- action block with no message (uses default)
- decision block with no reason (uses default)
- action block with empty string message (uses default)
- action block with non-string message, e.g. integer (uses default)
qwen3.6-plus did not have an explicit entry in DEFAULT_CONTEXT_LENGTHS,
so the longest-substring fallback matched the generic 'qwen': 131072
catch-all. That dropped the effective context limit from 1,048,576
tokens to 131,072, prematurely lowered the compression threshold, and
produced misleading warnings about main/compression context mismatch
in long sessions.
Add an explicit 'qwen3.6-plus': 1048576 entry before the catch-all and
cover it with a regression test (bare, qwen/, and dashscope/ prefixes).
Note: PR #6599 also mentions touching model_metadata.py but the actual
diff only edits hermes_cli/models.py, so this fix is independent and
not duplicated by that PR.
Closes#27008
The restart-drain test previously asserted equality between two calls
to t("gateway.draining", count=1), which masked the original
xdist failure mode in #22266: if the locale catalog is not resolved
from the worker's import path, t() returns the bare key path and
both sides of the equality still match.
Add a guard that the resolved value is not the raw catalog key and
contains the English placeholder substitution. This keeps the test
loudly failing when locale resolution silently degrades.
Six days after #23937 (608 fixes) the codebase had accumulated 241 new
PLR6201 violations. Same mechanical `x in (...)` → `x in {...}` fix,
same zero-risk profile: set lookup is O(1) vs O(n) for tuple and the
two are semantically equivalent for hashable scalar membership tests.
All 241 instances fixed via `ruff check --select PLR6201 --fix
--unsafe-fixes`, zero remaining. Every changed value is a hashable
scalar (str/int/None/enum/signal); no risk of unhashable runtime
errors. No behavior change.
Test plan:
- 119 files changed, +244/-244 (net zero) — exactly one-line edits
- `ruff check` clean afterward
- Compile checks pass on the largest touched files (cli.py, run_agent.py,
gateway/run.py, gateway/platforms/discord.py, model_tools.py)
- Subset broad test run on tests/gateway/ tests/hermes_cli/ tests/agent/
tests/tools/: 18187 passed, 59 pre-existing failures (verified against
origin/main with the same shape — identical failure count, identical
category — all xdist test-order flakes unrelated to this change)
Follows the same template as PR #23937 ([tracker: #23972](https://github.com/NousResearch/hermes-agent/issues/23972)).
When Hermes runs on a remote host over SSH, MCP OAuth loopback flows
silently fail: the OAuth provider redirects the user's browser to
http://127.0.0.1:<port>/callback, which reaches the callback server
on the *remote* machine — not the local machine where the browser is
running.
_redirect_handler already detected SSH (via _can_open_browser) and
printed "Headless environment detected — open the URL manually." but
gave no guidance on how to actually reach the callback server. Users
got silent timeouts or "Could not establish connection" errors.
This is the same bug fixed for xAI-oauth and Spotify in #26592, which
added _print_loopback_ssh_hint() in hermes_cli/auth.py. mcp_oauth.py
uses the identical loopback callback pattern (http://127.0.0.1:<port>/callback
via _configure_callback_port / _wait_for_callback) but was missing the hint.
Fix: when SSH_CLIENT or SSH_TTY is set and _oauth_port is available,
print the ssh -N -L port-forward command and the OAuth-over-SSH guide
URL to stderr, consistent with the rest of _redirect_handler's output.
Tests: 4 new cases in TestRedirectHandlerSshHint covering SSH_CLIENT,
SSH_TTY, local session (no hint), and missing _oauth_port (no hint).
_configure_provider() calls _run_post_setup() after collecting env vars
(line 2286). _reconfigure_provider() did not — providers with both
env_vars and post_setup (Browserbase, Browser Use, Firecrawl, Camofox)
skipped the installation step on reconfiguration.
Fix: mirror the _configure_provider() call. post_setup hooks are
idempotent (check before installing), so no behaviour change for users
who already have the dependencies installed.
The x_search toolset is gated on xAI credentials (SuperGrok OAuth or
XAI_API_KEY), but it was staying off-by-default even for users who had
already configured those credentials — they had to also click through
`hermes tools` → X (Twitter) Search to flip it on. The HASS_TOKEN →
homeassistant rule already handles the parallel case cleanly; x_search
needs the same treatment.
Why a separate code path from HASS_TOKEN: `ha_*` tools live inside
the `hermes-cli` composite, so the subset-inference loop picks them
up and the HASS branch just unmasks default_off. `x_search` is its
own one-tool toolset NOT in the composite, so the subset loop never
adds it — it has to be injected directly.
* Add `_xai_credentials_present()` — side-effect-free check for stored
xAI OAuth tokens or XAI_API_KEY (dotenv or env). No network.
* In `_get_platform_tools()` else branch (no explicit user config),
inject `x_search` and carve a parallel hole in default_off.
* Auto-enable does NOT fire when the user has saved an explicit toolset
list via `hermes tools` — that list stays authoritative.
* `agent.disabled_toolsets: [x_search]` still wins (global override).
Tests: 4 new in test_tools_config.py covering OAuth path, API-key path,
no-creds path, and explicit-config-respect. All pass alongside existing
70/70 in that file.
The 5-second startup-grace filter in _on_room_message silently drops
events where event_ts < startup_ts - 5. When the host clock is set
ahead of real time, the comparison flips against every live event and
the bot 'connects but never replies' — exactly the symptom in #12614.
Reporter Schnurzel700 chased this for several weeks before tracing it
to their Debian VM's clock being out of sync. The current /1000.0
millisecond->second conversion is correct (mautrix returns ms); the
failure mode is purely environmental.
Add a one-shot WARNING that fires when:
- we are >30s past startup (initial-sync replay window closed), AND
- 3 consecutive drops share the same skew within 60s (a constant
clock offset, not varied-age backfill from an invited room).
State is reset in connect() so reconnects after fixing NTP rearm the
detector. Includes the NTP fix instruction in the warning message
itself and a new Troubleshooting entry in the Matrix docs.
5 new tests cover the happy path, initial-sync backfill, under-
threshold drops, varied-age backfill, and the reconnect rearm path.
run_agent.py taken from HEAD (the extracted forwarder structure). The 25
run_agent.py fixes that landed on main during the PR's life need to be
ported into the agent/* extracted modules in follow-up commits.
Tests in TestReadClaudeCodeCredentials were not mocking
_read_claude_code_credentials_from_keychain, which was added after the
tests were written. On macOS machines with real Claude Code credentials
stored in the Keychain, the function returns live credentials instead of
the test fixtures, causing assertions to fail and leaking real tokens in
test output.
Add an autouse fixture that stubs the keychain reader to None so all
tests in the class exercise only the file-based credential path.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Four fixes from PR #27248 review:
1. **__init__ forwarder is now keyword-forwarded** (daimon-nous review).
Previously the run_agent.AIAgent.__init__ wrapper forwarded all 64
params positionally to agent.agent_init.init_agent, so adding a
65th param on main would require three lockstep edits (signature,
init_agent signature, forwarder call) or silently shift every value.
Keyword forwarding makes this trivially safe — adding a param now
only needs the two signatures and one extra keyword line.
2. **Drop dead _ra() in agent/codex_runtime.py** (daimon-nous + Copilot).
The lazy run_agent reference was defined but never called inside
this module — the codex paths use agent.* accessors only.
3. **Drop unused imports in agent/codex_runtime.py** (Copilot):
contextvars, threading, time, uuid, Optional. Carried over from
run_agent.py during the original extraction.
4. **Tighten three source-introspection test guards** (Copilot):
- test_memory_nudge_counter_hydration.py — was scanning the
concatenated source of run_agent.py + agent/conversation_loop.py
and matching self.X or agent.X form. Now asserts the
hydration block lives in agent/conversation_loop.py specifically
with the agent.X form — the body never moves back, so if it
ever drifts a future re-introduction fails the guard.
- test_run_agent.py::TestMemoryNudgeCounterPersistence — anchor on
agent.iteration_budget = IterationBudget exactly (was just
iteration_budget = IterationBudget) so an unrelated identifier
ending in iteration_budget can't match.
- test_run_agent.py::TestMemoryProviderTurnStart — assert the
agent._user_turn_count form directly (the extracted body uses
agent.X, not self.X — accepting either was a transitional fudge).
- test_jsondecodeerror_retryable.py — scan agent/conversation_loop.py
only, not the concatenation.
Not addressed in this commit:
* Pre-existing bugs in agent/tool_executor.py (heartbeat index
mismatch when calls are blocked, _current_tool clobber in result
loop, blocked-counted-as-completed in spinner summary, dead
result_preview computation). These were preserved byte-for-byte from
the original _execute_tool_calls_concurrent — worth a separate
follow-up PR with proper tests.
* _OpenAIProxy.__instancecheck__ concern — pre-existing, not flagged
by any of the original test patches (nothing actually does
isinstance(x, OpenAI) against the proxy instance).
* agent_init.py:949 mem_config potential NameError — pre-existing;
only triggers if _agent_cfg.get('memory', {}) itself raises, which
it can't with a stock dict.
tests/run_agent/ + tests/agent/: 4313 passed, 1 pre-existing
test_auxiliary_client failure (unchanged).
run_agent.py: 3821 -> 3937 lines (+116 from the keyword-forwarded
init call's verbosity). Final: 16083 -> 3937 (-12146, 75% reduction).
Closes#26924 (and supersedes #26926) in spirit.
DeepSeek was missing `default_aux_model` on its `ProviderProfile`, so
`_get_aux_model_for_provider("deepseek")` returned an empty string and
the compression / vision / session-search paths emitted
"No auxiliary LLM provider configured -- context compression will
drop middle turns without a summary."
on every DeepSeek session, even when the user had perfectly working
DeepSeek credentials.
Fix lands at the profile layer rather than the legacy
`_API_KEY_PROVIDER_AUX_MODELS_FALLBACK` dict the original PR targeted.
Every modern provider (gemini, zai, minimax, anthropic, kimi-coding,
stepfun, ollama-cloud, gmi, novita, kilocode, ai-gateway, opencode-zen)
sets `default_aux_model` on its `ProviderProfile`; the fallback dict
only exists for providers that predate the profiles system.
Tests added under `tests/plugins/model_providers/test_deepseek_profile.py`:
- `test_profile_advertises_deepseek_chat` -- pins the profile attribute
- `test_consumer_api_returns_deepseek_chat` -- pins the consumer API behavior
- `test_consumer_api_returns_non_empty` -- regression guard for the
symptom in the issue
Original diagnosis and aux-model choice from @kriscolab in PR #26926;
moved one layer up.
Co-authored-by: kriscolab <71590782+kriscolab@users.noreply.github.com>
Add test_returns_none_when_skill_load_fails to verify that
build_skill_invocation_message() returns None when a registered
skill exists in the command cache but _load_skill_payload() fails.
This guards against regression of the fix in 877d01b.
Consume multi-byte non-CSI ESC sequences during ANSI sanitization and handle UnicodeDecodeError for `hermes send --file` so review findings are resolved without regressions.
Avoid Terminal.app paint corruption by disabling fast-echo in that terminal, sanitizing non-SGR control sequences before ANSI rendering, and defaulting Apple Terminal back to the safer 256-color path unless truecolor is explicitly requested.
Pass skip_memory=True to the AIAgent constructor used by
_spawn_background_review() so the review fork's __init__ no longer
rebuilds a _memory_manager wired to honcho / mem0 / supermemory /
etc. under the parent's session_id.
Before this change, the review fork ingested its harness prompt
(the 'Review the conversation above and update the skill library...'
text) into the user's real memory namespace via three sites in
run_conversation():
- on_turn_start(turn_count, prompt) cadence + turn-message
- prefetch_all(prompt) recall query
- sync_all(prompt, review_output, ...) harness + review output
recorded as a
(user, assistant) pair
Built-in MEMORY.md / USER.md state is still rebound from the parent
right after construction, so memory(action='add') writes from the
review continue to land on disk; only the external-plugin side
effects are removed.
Reported by @Utku.
The Discord adapter silently dropped any attachment whose extension wasn't
in the SUPPORTED_DOCUMENT_TYPES allowlist (PDF, text family, zip, office).
Users uploading .wav / .bin / other unrecognized formats saw nothing in
their conversation — the file got logged as 'Unsupported document type'
and discarded before the agent ever saw it.
Add discord.allow_any_attachment (default false) to bypass the allowlist.
When on:
- Any file is downloaded, cached under ~/.hermes/cache/documents/, and
surfaced as a DOCUMENT-typed event with application/octet-stream MIME
- gateway/run.py already emits a context note with the cached path,
auto-translated via to_agent_visible_cache_path() for Docker/Modal
sandboxed terminals
- File body is NOT inlined — only the path — so binary uploads don't
blow up the context window
- Allowlisted text formats (.txt/.md/.log) keep their 100 KiB inline
behavior unchanged
Also adds discord.max_attachment_bytes (default 32 MiB matches the
historical hardcoded cap; 0 = unlimited) since users opting into arbitrary
types may want to raise the cap. The whole attachment is held in memory
while being cached, so unlimited carries a real memory cost.
Env overrides: DISCORD_ALLOW_ANY_ATTACHMENT, DISCORD_MAX_ATTACHMENT_BYTES.
Discord-only by deliberate scope. Telegram has hard 20 MB API limits and
Slack has its own caps — extending the same flag there is a separate
follow-up if/when requested.
The 3,877-line run_conversation body — the agent loop itself — moves out
of run_agent.py into a dedicated module. AIAgent.run_conversation is
now a thin forwarder that delegates to agent.conversation_loop.run_conversation
with the AIAgent instance as the first argument.
This is the largest single extraction in the run_agent.py refactor.
The body keeps all 163 self.X references intact (rewritten as agent.X),
all nested closures, all retry/backoff/compression machinery. Symbols
that tests or callers patch on run_agent (_set_interrupt,
handle_function_call, AIAgent class attrs) are resolved through _ra()
inside the extracted module so the patch surface is preserved.
Five tests doing inspect.getsource(AIAgent.run_conversation) updated to
scan agent.conversation_loop.run_conversation. Two source-introspection
tests (TestMemoryNudgeCounterPersistence, TestMemoryProviderTurnStart)
updated to accept either self.X (legacy) or agent.X (extracted
form) in the matched assertions.
Live E2E verified on three model paths:
* openai/gpt-5.4 (OpenAI chat completions via OpenRouter)
* anthropic/claude-sonnet-4.6 (Anthropic Messages via OpenRouter)
* moonshotai/kimi-k2-thinking (reasoning model, reasoning_content path)
Plus read_file tool execution, terminal tool, web_search.
tests/run_agent/ + tests/agent/: 4313 passed, 1 pre-existing failure
(test_auxiliary_client::test_custom_endpoint... — same as on main).
run_agent.py: 9800 -> 5944 lines (-3856).
Total reduction since baseline: 16083 -> 5944 (-10139, 63%).
Move _interruptible_streaming_api_call out of run_agent.py — the biggest
single method in the file. Body lives next to interruptible_api_call
in agent/chat_completion_helpers.py so streaming + non-streaming code
share one home.
Nested closures (_call_chat_completions, _call_anthropic, the codex
stream branch) all come along with the body and still capture the
parent function's locals as expected.
AIAgent keeps a thin forwarder method. is_local_endpoint added to
the import block (used by the stream stale-timeout disable logic).
One source-introspection test in TestAnthropicInterruptHandler is
updated to scan agent.chat_completion_helpers.interruptible_streaming_api_call
instead of AIAgent._interruptible_streaming_api_call.
tests/run_agent/ + tests/agent/: 4312 passed (same pre-existing
test_auxiliary_client failure).
run_agent.py: 12277 -> 11385 lines (-892).
Move the two big tool-dispatch methods out of run_agent.py:
* execute_tool_calls_concurrent — 408-line concurrent path (interrupt
pre-flight, guardrail+plugin block, callback fan-out, ContextVar-
preserving ThreadPoolExecutor, periodic heartbeats for the gateway
inactivity monitor, per-tool result handling with subdir hints +
guardrail observations + checkpoint, /steer drain)
* execute_tool_calls_sequential — 441-line sequential path (the
original behavior used for single-tool batches and interactive
tools)
Both take the parent AIAgent as their first argument; AIAgent keeps
thin forwarders so call sites unchanged. handle_function_call is
routed through _ra() so tests that patch run_agent.handle_function_call
keep working. _set_interrupt likewise.
The AST guard in test_tool_executor_contextvar_propagation.py is
updated to scan both run_agent.py AND agent/tool_executor.py so it
still catches the executor.submit(_run_tool, ...) regression
regardless of which file the body lives in.
tests/run_agent/ + tests/agent/: 4313 passed (same pre-existing
test_auxiliary_client failure as before).
run_agent.py: 14309 -> 13461 lines (-848).
After context compression, the protected tail messages retain their
original image parts. When those include multi-MB pasted screenshots,
every subsequent API request re-ships the same base-64 blobs forever —
which can push the request past provider body-size limits and wedge the
session even though compression 'succeeded'.
Add _strip_historical_media() to agent/context_compressor.py. After the
summary is built, find the newest user message that carries an image
part and replace image parts in every earlier message with a short
text placeholder ('[Attached image — stripped after compression]').
The newest image-bearing user turn keeps its media so the model can
still analyse what the user just sent.
Handles all three multimodal shapes:
- OpenAI chat.completions image_url
- OpenAI Responses API input_image
- Anthropic native {type: image, source: ...}
Includes 27 unit tests covering the helpers and the end-to-end
compress() integration, plus a manual E2E check confirming a ~4MB
two-image conversation shrinks to ~2MB after compression.
Add a TestDiscoverAllPlugins class covering the six cases the recursive
scan needs to handle:
- flat plugin uses its manifest ``name:`` as the key
- category-namespaced plugin keys off ``<category>/<dirname>`` even when
the manifest ``name:`` is bare (regression test for the original bug —
``plugins/observability/langfuse/`` with ``name: langfuse`` must
surface as ``observability/langfuse``, not ``langfuse``)
- user-installed plugin overrides bundled on key collision
- depth cap: anything below ``<root>/<category>/<plugin>/`` is ignored
- bundled ``memory/`` and ``context_engine/`` are skipped (they have
their own loaders), but user plugins under those category names are
still scanned
Also add an in-source comment next to the key derivation pointing at the
loader's matching line (``PluginManager._parse_manifest`` in
plugins.py:1027-1028), so future renames of one site flag the other.
Both items raised in Copilot review on #27161.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Introduces a thin CLI wrapper around the existing send_message_tool so
shell scripts, cron scripts, CI hooks, and monitoring daemons can reuse
the gateway's already-configured platform credentials without
reimplementing each platform's REST client.
hermes send --to telegram "deploy finished"
echo "RAM 92%" | hermes send --to telegram:-1001234567890
hermes send --to discord:#ops --file report.md
hermes send --to slack:#eng --subject "[CI]" --file build.log
hermes send --list # all targets
hermes send --list telegram # filter by platform
Supports all platforms the send_message tool already does (Telegram,
Discord, Slack, Signal, SMS, WhatsApp, Matrix, Feishu, DingTalk, WeCom,
Weixin, Email, etc.), including threaded targets and #channel-name
resolution via the channel directory.
hermes_cli/send_cmd.py delegates to tools.send_message_tool.send_message_tool,
which means there is zero new platform-specific code. The subcommand just:
1. Bridges ~/.hermes/.env and top-level ~/.hermes/config.yaml scalars into
os.environ (same bootstrap the gateway does at startup) — required so
TELEGRAM_HOME_CHANNEL and friends are visible to load_gateway_config().
2. Resolves the message body from positional arg, --file, or piped stdin.
3. Calls the shared tool and translates its JSON result to exit codes:
0 success, 1 delivery failure, 2 usage error.
No running gateway is required for bot-token platforms (Telegram, Discord,
Slack, Signal, SMS, WhatsApp) — the tool hits each platform's REST API
directly. Plugin platforms that rely on a live adapter connection still
need the gateway running; the error message is forwarded verbatim.
- New guide: website/docs/guides/pipe-script-output.md covering real-world
patterns (memory watchdogs, CI hooks, cron pipes, long-running task
completion pings) and the security/gateway notes.
- Cross-links added from automate-with-cron.md ("no LLM? use hermes send")
and developer-guide/gateway-internals.md (delivery-path section).
tests/hermes_cli/test_send_cmd.py (20 tests, all green):
- Happy paths: positional message, stdin, --file, --file -, --subject,
--json, --quiet.
- Error paths: missing --to, missing body, file not found, tool returns
error payload (exit 1), tool skipped-send result (exit 0).
- --list: human output, --json output, platform filter, unknown platform.
- Env loader: bridges config.yaml scalars into env, does not override
existing env vars, gracefully handles missing files.
- Registrar contract: register_send_subparser() returns a working parser.
Smoke-tested end-to-end against a live Telegram bot before commit.
In long-lived interactive sessions, _try_activate_fallback() advances
_fallback_index before attempting client resolution. When resolution
fails (provider not configured, etc.) the function returns False without
ever setting _fallback_activated=True. _restore_primary_runtime() then
skips its reset block entirely (guarded by `if not _fallback_activated`),
leaving _fallback_index >= len(_fallback_chain) for all subsequent turns.
The eager-fallback guard at the top of the retry loop checks
`_fallback_index < len(_fallback_chain)`, so the condition fails silently
and no fallback is ever attempted again for that session.
Cron jobs spawn a fresh AIAgent per run and never hit this path, which is
why the same fallback chain works reliably for cron but not interactive.
Fix: reset _fallback_index=0 in the `not _fallback_activated` early-return
branch so every new turn starts with the full chain available.
Fixes#20465
xAI's Responses stream emits 'type=error' as the FIRST SSE frame when an
OAuth account is unsubscribed/exhausted or rejects the encrypted-reasoning
replay introduced in the May 2026 SuperGrok rollout. The SDK helper
raises RuntimeError(Expected to have received response.created before
error), which the caller correctly routes to
_run_codex_create_stream_fallback. The fallback then opens a new stream
that emits the same 'error' frame — but the fallback loop only handled
{response.completed, response.incomplete, response.failed} and silently
continue'd past 'error' events. Result: the loop fell off the end of
the stream and raised the useless 'fallback did not emit a terminal
response' RuntimeError, which the classifier marked retryable=True and
looped 3x before failing with no clue what went wrong.
Now: 'error' frames raise a synthesized _StreamErrorEvent with an OpenAI
SDK-shaped .body so _summarize_api_error, _extract_api_error_context,
_is_entitlement_failure, and classify_api_error all see the real
provider message. Users on unsubscribed accounts now see 'do not have
an active Grok subscription' once, not three RuntimeErrors.
Verified end-to-end: classifier returns reason=auth retryable=False;
entitlement detector matches even with status_code=None; summarizer
returns the full xAI message.
Tests: 4 new in TestCodexFallbackErrorEvent covering xAI subscription
message, dict-shaped events, summarizer integration, and the empty-stream
case (must still raise the original RuntimeError so 'truncated mid-flight'
stays distinguishable from 'provider rejected the call').
Adds a pure-local recap of recent session activity — turn counts,
tools used, files touched, last user ask, last assistant reply —
appended to the existing /status output. Useful when juggling multiple
sessions and you want a one-glance reminder of where this one left off.
Inspired by Claude Code 2.1.114's /recap, but folded into /status so
we don't add a 6th info command. Pure local computation: no LLM call,
no auxiliary model, no prompt-cache invalidation, instant and free.
Salvage of #18587 — kept the shared hermes_cli.session_recap.build_recap
helper and its 13 unit tests, dropped the /recap slash command +
ACTIVE_SESSION_BYPASS_COMMANDS entry + Level-2 bypass since /status
already covers both surfaces.
Tailored to hermes-agent's tool vocabulary: file-editing tools
(patch, write_file, read_file, skill_manage, skill_view) surface
touched paths; tool-call counts highlight which classes of work
drove the session.
Source: https://code.claude.com/docs/en/whats-new/2026-w17
Surface live background-task count in the prompt_toolkit status bar so users
can see at a glance that a /background task exists and is running — no need
to ask the agent about it (the agent has no visibility into bg sessions by
design).
- _get_status_bar_snapshot now reports active_background_tasks from len()
of the live _background_tasks dict (entries are removed in the task
thread's finally block, so this reflects truly-running tasks)
- Indicator shown only on medium (<76) and wide (>=76) tiers; narrow (<52)
stays minimal since it's already cramped
- No invalidate plumbing needed: status bar fragments are pulled via lambda
on every redraw, and the bg thread already calls _app.invalidate() on exit
Refs #8568
xAI announced on 2026-05-16 (https://x.ai/news/grok-hermes) that X Premium
subscriptions now work in Hermes Agent. The hint we shipped in PR #26644
asserted the opposite ("X Premium+ does NOT include xAI API access — only
standalone SuperGrok subscribers can use this provider"), which would now
misdirect Premium+ users who hit any other 403 (no Grok sub at all, wrong
tier, exhausted quota) into thinking they need to switch subscriptions
when their sub is in fact valid.
Remove _decorate_xai_entitlement_error and its two call sites in
_summarize_api_error. xAI's own body text already says "Manage subscriptions
at https://grok.com/?_s=usage" — surface that verbatim and let xAI's wording
do the diagnosis.
The _is_entitlement_failure guard (which prevents credential-pool refresh
loops on entitlement 403s) and the reasoning-replay gating for xai-oauth
are unrelated and untouched.
Update tests to assert the body still surfaces verbatim and that no
Hermes-side editorializing is appended.
Port from anomalyco/opencode#25019 ("fix: handle invalid mcp urls").
Previously: a typo in `config.yaml` (missing scheme, wrong scheme,
empty string, non-string value) slipped past `_is_http()` and hit
`httpx.URL(url)` or `streamablehttp_client(url, ...)` deep in the
transport layer. That raised a generic exception which went through
the reconnect-backoff loop, so a bad URL caused _MAX_INITIAL_CONNECT_RETRIES
attempts with doubling backoff — about a minute of pointless retries
plus an opaque error — before the server was marked failed.
Now: we validate the URL once, at the top of `run()`, before
entering the retry loop. A malformed URL raises `InvalidMcpUrlError`
(a `ValueError` subclass) with a message that names the offending
server and explains exactly what was wrong. `_ready` is set and
`_error` is populated, so `start()` re-raises and the server shows
up as failed in `hermes mcp list` without any backoff burn.
Validation rules:
- Must be a string (rejects None, dict, int)
- Must be non-empty (rejects '' and whitespace-only)
- Scheme must be http or https (rejects file://, ws://, stdio://)
- Must have a non-empty host (rejects http:///, http://:8080)
Tests (21 new cases in tests/tools/test_mcp_invalid_url.py):
- TestValidUrlsAccepted: http, https, IPv6, ports, paths, query strings
- TestInvalidUrlsRejected: every rejection path above + clear error text
- TestErrorIsValueError: downstream code catching ValueError still works
E2E verified: a misconfigured server with `url: not-a-valid-url`
now fails in <0.001s with the clear error, instead of minutes of retries.
Doesn't touch stdio servers (they use `command`, not `url`) — the
validator only fires when `_is_http()` returns True.
Port from anomalyco/opencode#24730: Moonshot's JSON Schema validator rejects
two shapes that the rest of the JSON Schema ecosystem accepts:
1. $ref nodes with sibling keywords. Moonshot expands the reference before
validation and then rejects the node if keys like `description`, `type`,
or `default` appear alongside $ref. MCP-sourced tool schemas commonly
put a `description` on $ref-typed properties so the model sees the
field hint — which worked on every provider except Moonshot.
2. Tuple-style `items` arrays (positional element schemas). Moonshot's
engine requires ONE schema applied to every array element. Common in
tool schemas generated from Go/Protobuf that model fixed-length arrays
as `[{type:number}, {type:number}]`.
Repairs applied in `agent/moonshot_schema.py`:
- Rule 3: when a node has `$ref`, return `{"$ref": <value>}` only
(strip every sibling). The referenced definition still carries its own
description on the target node, which Moonshot accepts.
- Rule 4: when `items` is a list, collapse to the first element schema
(falling back to `{}` which is then filled by the generic missing-type
rule). Preserves `minItems` / `maxItems` / other siblings.
Tests: 10 new cases across TestRefSiblingStripping + TestTupleItems,
plus the existing TestMissingTypeFilled::test_ref_node_is_not_given_synthetic_type
still passes (it asserted plain $ref passes through; now it passes through
as exactly `{"$ref": "..."}` which is strictly compatible).
All 35 tests in test_moonshot_schema.py pass.
Emit a grep-friendly '[MEMORY] rss=...MB ...' line in agent.log /
gateway.log every N minutes (default 5) so slow leaks in the long-lived
gateway process show up as a time series. Based on
https://github.com/cline/cline/pull/10343
(src/standalone/memory-monitor.ts).
- gateway/memory_monitor.py: new module. Daemon thread, baseline on
start, final snapshot on stop. Uses resource.getrusage() (stdlib)
first, falls back to psutil, disables itself with one WARNING if
neither is available.
- gateway/run.py: start monitor right after setup_logging() in
start_gateway(); stop it in the shutdown block next to MCP teardown.
- hermes_cli/config.py: logging.memory_monitor { enabled, interval_seconds }
defaults under the existing logging section.
- tests/gateway/test_memory_monitor.py: 10 unit tests covering format,
baseline/shutdown snapshots, double-start noop, periodic timer,
daemon thread invariant, and unavailable-RSS warn-and-skip path.
Adapted from TypeScript/Node to Python (threading.Event-based daemon
thread instead of setInterval/unref), added Python-specific gc + thread
counts to the log line (handier than ext/arrayBuffers for diagnosing
Python gateway leaks), and gated behind a config.yaml toggle so users
can silence the periodic line if they want.
No heap-snapshot-on-OOM equivalent — CPython doesn't have V8's
--heapsnapshot-near-heap-limit; tracemalloc would be the Python
equivalent but adds non-trivial overhead, so leaving that out.
Port from google-gemini/gemini-cli#19332.
Users can now exit with '/exit --delete' (or '/quit --delete', '/exit -d')
to permanently remove the current session's SQLite history plus on-disk
transcripts (*.json / *.jsonl / request_dump_*) in one shot. Useful for
privacy-sensitive workflows and one-off interactions where leaving a
session recording behind is undesirable.
Implementation:
- New HermesCLI._delete_session_on_exit one-shot flag (defaults False).
- process_command() parses --delete / -d after /exit or /quit and arms
the flag. Unknown args print a hint and keep the CLI running (prevents
typos like '/exit -delete' from accidentally exiting).
- Shutdown path calls SessionDB.delete_session(session_id, sessions_dir=...)
right after end_session() when the flag is set. That API already
existed for 'hermes sessions delete' and handles both SQLite removal
(orphaning child sessions so FK constraints hold) and on-disk file
cleanup.
- /quit CommandDef now advertises '[--delete]' in args_hint so /help
and CLI autocomplete surface it.
Tests: tests/cli/test_exit_delete_session.py (12 cases covering both
aliases, case insensitivity, whitespace, short form, unknown-arg
rejection, and registry metadata).
E2E-verified with isolated HERMES_HOME: session row deleted, all three
transcript/request-dump files removed, second delete_session call
correctly returns False.
`hermes update` ran the repo-root and ui-tui npm installs with both
`--silent` and `subprocess.run(..., capture_output=True)`, which hides
all output from optional postinstall scripts. The largest of those —
`@askjo/camofox-browser`'s `npx camoufox-js fetch` — downloads a
Firefox-fork browser binary that can take many minutes on slow
connections. Because nothing was printed during that wait, the updater
appeared to hang at "Updating Node.js dependencies..." and users
Ctrl-C'd, sometimes leaving `node_modules` partially installed.
Drop `--silent` and pass `capture_output=False` for the repo-root and
ui-tui paths so npm streams its `info run …` postinstall lines straight
to the terminal. Output is still mirrored to `~/.hermes/logs/update.log`
by the existing `_UpdateOutputStream` wrapper, so SSH-disconnect safety
is preserved.
The `web/` install path is untouched — its build step is fast and does
not run binary-fetching postinstalls.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The `@askjo/camofox-browser` npm package was a top-level entry in
the root `package.json` `dependencies` block, so `hermes update`
ran its postinstall on every user, every update. That postinstall
calls `npx camoufox-js fetch`, which silently downloads a ~300MB
Firefox-fork browser binary from GitHub Releases — multi-minute on
fast connections, and a hard block for users on slow / restricted
networks (notably users in China running through a VPN).
Camofox is an explicit opt-in browser backend. The runtime check
in `tools/browser_tool.py` only routes through Camofox when the
user has set `CAMOFOX_URL` (selected via `hermes tools` →
Browser Automation → Camofox). Users who never opted in never
touched the package at runtime, yet every `hermes update` paid
for the binary fetch anyway.
This change:
* Removes `@askjo/camofox-browser` from root `package.json`
dependencies (and the regenerated `package-lock.json` drops
Camofox's entire transitive tree, ~2.6k lines).
* Updates the Camofox `post_setup` handler in
`hermes_cli/tools_config.py` to install
`@askjo/camofox-browser@^1.5.2` explicitly when the user
selects Camofox, and streams npm output (no `--silent`, no
`capture_output`) so the ~300MB download is visible rather
than appearing frozen.
* Adds `tests/test_package_json_lazy_deps.py` as a regression
guard so future PRs can't silently re-add Camofox (or any
binary-postinstall package) to eager root dependencies.
`agent-browser` stays eager — it is the default Chromium-driving
backend used by every session that does not have a cloud browser
provider configured, and its postinstall is small.
Validation:
| | Before | After |
|---|---|---|
| `hermes update` time on slow network | multi-minute hang at `→ Updating Node.js dependencies...` | seconds (no binary fetch) |
| Camofox opt-in install visibility | silent, looked frozen | streamed npm output |
| Regression guard against re-adding | none | `test_package_json_lazy_deps.py` |
Tests:
- `tests/test_package_json_lazy_deps.py`: 3/3 pass
- `tests/tools/test_browser_camofox*`: 92/92 pass
- `tests/hermes_cli/test_tools_config.py`: 66/66 pass
- `tests/hermes_cli/test_cmd_update.py` + adjacent: green
Reported by lulu (Discord, May 2026) — `hermes update` hangs at
`→ Updating Node.js dependencies...` in China.
Related: #18840, #18869.
Port from qwibitai/nanoclaw#1962: modern Signal V2-only groups surface on
dataMessage.groupV2.id, not groupInfo.groupId. signal-cli versions differ
in which field they expose for V2 groups — some forward the underlying
libsignal envelope verbatim (groupV2), others normalize everything into
groupInfo. Without a groupV2 read, V2-only groups appear as DMs because
groupInfo is undefined and the adapter misroutes them to the sender's
DM session.
Reads groupV2.id first, falls back to groupInfo.groupId. Also hardens
chat_name extraction against non-dict groupInfo payloads (crashed with
AttributeError under malformed envelopes).
6 new tests cover V2 routing, V1 legacy compatibility, V2-preferred
precedence, no-group DM path, allowlist enforcement, and malformed
payloads.
Switches `_replay_session_history` from `loop.call_soon`-deferred (after the
`LoadSessionResponse` is written) to `await`-inline (before the response is
constructed) for both `session/load` and `session/resume`. Adds defensive
try/except around the awaited call so a replay helper crash still yields a
successful load response — partial transcripts are acceptable, total
load failure is not.
The deferral was added on May 2 in commit 19854c7cd with the rationale "Zed
only attaches streamed transcript/tool updates once the load/resume response
has completed." That justification was incorrect:
- Zed's current ACP integration (zed-industries/zed
crates/agent_servers/src/acp.rs) explicitly registers the session-update
routing entry BEFORE awaiting the loadSession RPC, with the comment:
"so that any session/update notifications that arrive during the call
(e.g. history replay during session/load) can find the thread."
- Every other reference ACP server (Codex, Claude Code, OpenCode, Pi, agentao)
replays history BEFORE responding to the load request.
- The ACP spec wording ("Stream the entire conversation history back to the
client via notifications") and the natural JSON-RPC reading both mean
"during the request's lifetime", not "after the response resolves".
Empirical reproduction (reported by Biraj on @agentclientprotocol/sdk
v0.21.1): the same custom ACP client works correctly against Codex /
Claude Code / OpenCode / Pi but receives 0 notifications from Hermes
because it measures the per-call notification count at the moment
`loadSession` resolves — which on Hermes was before the `call_soon`-
scheduled replay coroutine had a chance to run.
Changes:
- `acp_adapter/server.py`: remove `_schedule_history_replay`; both
`load_session` and `resume_session` now `await self._replay_session_history`
before returning, wrapped in try/except that logs and continues on
helper exceptions.
- `tests/acp/test_server.py`: replace the single
`test_load_session_schedules_history_replay_after_response`
(which encoded the now-incorrect post-response ordering) with two tests
asserting `events == ["replay", "returned"]` for load and resume.
Add two regression tests confirming that a replay helper raising still
yields a `LoadSessionResponse` / `ResumeSessionResponse` rather than
propagating the exception out as a JSON-RPC error.
Result: 240 ACP tests pass (was 238), ruff clean. Verified end-to-end:
biraj's synchronous notification-counter pattern now sees 6 notifications
during `loadSession` for a 5-message session, matching all other reference
ACP servers.
The `_fenced_text` change in `acp_adapter/tools.py` from the same May 2
commit is orthogonal and intentionally left intact — it's a separate,
still-valid fix for Zed's pipe-as-table rendering.
Refs #12285. Follows up #26943 (which added thought-chunk replay but kept
the deferral).
Persisted assistant `reasoning_content` / `reasoning` fields are now emitted
as ACP `agent_thought_chunk` notifications during `_replay_session_history`,
so editor clients (Zed, etc.) rebuild collapsed Thinking panes when the user
re-opens a session that used a thinking model.
Ordering matches live streaming: thought precedes message text within the
same assistant turn, mirroring how `reasoning_callback` deltas arrive before
`stream_delta_callback` deltas in `events.py::make_thinking_cb` /
`make_message_cb`.
Behavior on non-reasoning histories is unchanged; the replay loop's existing
text / tool_call / tool_call_update / plan emission is preserved bit-for-bit.
Closes#12285.
Credit:
- @Yukipukii1 (#14691) — original thought-replay design via
`acp.update_agent_thought_text`; the tool-call portion of that PR has
since landed via #19139, but the reasoning replay is theirs.
- @HenkDz (#17652 / #18578) — established the `_replay_session_history` and
`_history_*` helper conventions this builds on.
- @D1zzyDwarf (#16531) — also closed by this work.
Two unit tests for run_hermes_oauth_login_pure():
1. test_authorization_url_state_is_not_pkce_verifier — asserts state in the
auth URL is independent from the PKCE code_verifier sent in the token
exchange, and that the verifier never appears in the URL.
2. test_callback_state_mismatch_aborts — asserts the flow returns None
(no token exchange) when the callback state does not match the value
we generated.
Negative control verified: reintroducing the b17e5c10 vulnerable pattern
(state = verifier, no callback validation) makes both tests fail.
Also adds AUTHOR_MAP entry for shaun0927 (contributor of the fix).
When the agent is running and the user sends multiple TEXT messages in
rapid succession, base.py's active-session branch stored the pending
event as a single-slot replacement:
self._pending_messages[session_key] = event
Three rapid messages A, B, C landed as: A (interrupts), B (replaces A
before consumer reads), C (replaces B). Only C reached the next turn —
A and B were silently dropped. This is the symptom in #4469.
Route the follow-up through merge_pending_message_event(..., merge_text=True)
so TEXT events accumulate into the existing pending event's text instead
of clobbering it. Photo and media bursts already merged through the same
helper; this just extends the merge_text path (already used by the
Telegram bursty-grace branch in gateway/run.py) to all platforms.
Test exercises BasePlatformAdapter.handle_message directly with the
session marked active and asserts three rapid TEXT events merge to
'part two\\npart three' rather than dropping the middle message.
Sanity-checked the test would fail without the fix.
Credits @devorun for the original investigation and analysis in #4491
that surfaced the underlying queue handling, though their fix targeted
GatewayRunner._pending_messages which is now dead state on main.
Follow-up improvements on top of @konsisumer's cherry-picked fix for #10648:
1. Deprecation patterns required BOTH a product fingerprint ('gh-copilot') and
a deprecation marker. The previous list included 'copilot-cli' and bare
'deprecation', which would false-positive on stderr from the NEW
@github/copilot CLI — whose repo is literally github.com/github/copilot-cli
and which legitimately surfaces those substrings in its own messages.
2. Replace the deprecation hint. The user in #10648 installed
'gh extension install github/gh-copilot' (the deprecated extension)
thinking that's what ACP mode uses, when ACP actually spawns the new
'copilot' binary from '@github/copilot'. The hint now points users at the
correct install command ('npm install -g @github/copilot') with the new
CLI's repo URL, and demotes provider-switching to a fallback alternative.
3. Change _URL_TO_PROVIDER value for models.inference.ai.azure.com from the
'github-models' alias to the canonical 'copilot' provider id, matching the
convention used by every other entry in the table.
4. Sharpen the 413 hint message. The free tier's ~8K cap is below the
system-prompt floor, so this endpoint is fundamentally incompatible with
an agentic loop — not a 'use a different URL' problem.
Tests:
- New parametrized false-positive coverage for the new CLI's stderr shape.
- Updated assertion to require canonical 'copilot' provider mapping.
- All 14 deprecation/URL tests pass.
Cover the deprecation pattern matching against real gh-copilot stderr
output, verify the GitHub Models Azure URL is in _URL_TO_PROVIDER, and
confirm _is_github_models_base_url recognises the Azure endpoint.
Fixes#26693
`hermes doctor` currently promotes invalid direct API keys into the final
summary even when the matching OAuth path is already healthy. That makes
the setup look more broken than it really is.
This change keeps the failed API Connectivity row visible but stops
treating it as a blocking summary issue when a healthy OAuth fallback
already exists for the same provider family.
Covered cases:
- Gemini OAuth + invalid direct Gemini key
- MiniMax OAuth + invalid direct MiniMax key
Based on #26704 by @worlldz.
Port three hardening patches from Claude Code 2.1.113's expanded deny
rules to hermes' detect_dangerous_command() pattern list.
1. macOS /private/{etc,var,tmp,home} system paths
/etc, /var, /tmp, /home are symlinks to /private/<name> on macOS.
A write to /private/etc/sudoers works identically to /etc/sudoers
but bypassed the plain /etc/ pattern check. Extracted a shared
_SYSTEM_CONFIG_PATH fragment so /etc/ and the /private/ mirror
stay in sync across redirect / tee / cp / mv / install / sed -i
patterns.
2. killall -9 / -KILL / -SIGKILL / -s KILL / -r <regex>
Parallel to the existing pkill -9 pattern. killall -9 against
non-hermes processes was previously unprotected, and killall -r
can sweep unrelated processes matching a regex.
3. find -execdir rm
Same destructive effect as find -exec rm but ran in each match's
directory. The previous pattern required a literal '-exec ' so
-execdir slipped through.
Guarded by 32 new test cases in 4 test classes:
- TestMacOSPrivateSystemPaths (11 cases)
- TestKillallKillSignals (9 cases)
- TestFindExecdir (4 cases)
- TestEtcPatternsUnaffectedByRefactor (6 regression guards on
the existing /etc/ coverage after the _SYSTEM_CONFIG_PATH refactor)
Inspiration: https://github.com/anthropics/claude-code/releases
(Claude Code 2.1.113, April 17 2026 - "Enhanced deny rules" and
"Dangerous path protection")
Port from openai/codex#17667: MCP servers can now opt-in to parallel
tool execution by setting supports_parallel_tool_calls: true in their
config. This allows tools from the same server to run concurrently
within a single tool-call batch, matching the behavior already available
for built-in tools like web_search and read_file.
Previously all MCP tools were forced sequential because they weren't in
the _PARALLEL_SAFE_TOOLS set. Now _should_parallelize_tool_batch checks
is_mcp_tool_parallel_safe() which looks up the server's config flag.
Config example:
mcp_servers:
docs:
command: "docs-server"
supports_parallel_tool_calls: true
Changes:
- tools/mcp_tool.py: Track parallel-safe servers in _parallel_safe_servers
set, populated during register_mcp_servers(). Add is_mcp_tool_parallel_safe()
public API.
- run_agent.py: Add _is_mcp_tool_parallel_safe() lazy-import wrapper. Update
_should_parallelize_tool_batch() to check MCP tools against server config.
- 11 new tests covering the feature end-to-end.
- Updated MCP docs and config reference.
Subagent delegation hardcoded api_mode='chat_completions' for any
delegation.base_url that didn't match three specific hostnames
(chatgpt.com, api.anthropic.com, api.kimi.com/coding), and never
read delegation.api_mode from config. Azure AI Foundry's
https://foundry.services.ai.azure.com/anthropic endpoint fell through
and got chat_completions, causing 404s on every delegate_task call.
The main agent already handles this correctly via the shared
_detect_api_mode_for_url() helper (anything ending in /anthropic →
anthropic_messages); delegation reimplemented its own narrower check.
Reuse the shared detector and honor an explicit delegation.api_mode
when set so users can also force the transport on non-standard
endpoints the URL heuristic can't classify.
Fixes#10213.
Co-authored-by: HiddenPuppy <HiddenPuppy@users.noreply.github.com>
* feat(x_search): gated X (Twitter) search tool with OAuth-or-API-key auth
Salvages tools/x_search_tool.py from the closed PR #10786 (originally by
@Jaaneek) and reworks its credential resolution so the tool registers
when EITHER xAI credential path is available:
* XAI_API_KEY (paid xAI API key) is set in ~/.hermes/.env or the env, OR
* The user is signed in via xAI Grok OAuth — SuperGrok subscription —
i.e. hermes auth add xai-oauth has been run
Both paths route through xAI's built-in x_search Responses tool at
https://api.x.ai/v1/responses. When both credentials exist OAuth wins,
matching tools/xai_http.py's existing preference order (uses SuperGrok
quota instead of paid API spend).
The check_fn calls resolve_xai_http_credentials() which auto-refreshes
the OAuth access token if it's within the refresh skew window, so a
True return means the bearer is fetchable AND non-empty.
Wiring
- tools/x_search_tool.py — new tool, ~370 LOC. Schema gated by check_fn,
bearer resolved per-call so revoked OAuth surfaces a clean tool_error
rather than an HTTP 401.
- toolsets.py — "x_search" toolset def. NOT added to _HERMES_CORE_TOOLS;
users opt in via hermes tools.
- hermes_cli/tools_config.py — CONFIGURABLE_TOOLSETS entry + TOOL_CATEGORIES
block with two provider options (OAuth + API key) sharing the existing
xai_grok post_setup hook for credential bootstrap.
- hermes_cli/config.py — DEFAULT_CONFIG["x_search"] with model /
timeout_seconds / retries. Additive nested key; no version bump.
- tests/tools/test_x_search_tool.py — 13 tests covering HTTP shape,
handle validation, citation extraction, 4xx/5xx/timeout handling,
and the full credential-resolution matrix (OAuth-only, API-key-only,
both-set, neither-set, resolver-raises, config overrides, registry
registration).
- website/docs/guides/xai-grok-oauth.md — adds X Search to the
direct-to-xAI tools section with off-by-default note.
- website/docs/user-guide/features/tools.md — new row in the tools table.
Off by default — users enable via `hermes tools` → 🐦 X (Twitter) Search.
Schema only appears to the model when xAI credentials are configured.
Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com>
* docs(x_search): add dedicated feature page + reference entries
- website/docs/user-guide/features/x-search.md (new) — full feature
walkthrough: authentication, enablement, configuration, parameters,
returned fields, example, troubleshooting, see-also links.
- website/docs/reference/tools-reference.md — new "x_search" toolset
section with parameter docs and credential gating note.
- website/docs/reference/toolsets-reference.md — new row in the
toolset catalog table.
- website/sidebars.ts — wires the new feature page under
Media & Web, after web-search.
---------
Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com>
Adds _sanitize_tool_error() in model_tools and routes both error paths
through it: registry.dispatch's try/except (the primary path for tool
exceptions) and handle_function_call's outer except (defense in depth).
Stripping targets structural framing tokens that the model itself can
react to even though json.dumps already handles wire-layer escaping:
XML role tags (tool_call, function_call, result, response, output,
input, system, assistant, user), CDATA sections, and markdown code
fences. Caps message body at 2000 chars and wraps with [TOOL_ERROR]
prefix.
Defense-in-depth: a tool exception carrying '<tool_call>...' won't
break message framing (json escapes it), but the model still reads
those tokens and they nudge it toward role-confusion framing.
Ported from ironclaw#1639 (one piece of #3838's three-feature scout).
The truncated-tool-call (#1632) and empty-response-recovery (#1677,
#1720) pieces are skipped because main now implements both far more
thoroughly (run_agent.py L8147/L12209/L13012 for truncation retry +
length rewrite; L4500/L15090+ for empty-response scaffolding stripper,
multi-stage nudge, fallback model activation).
Plugins can now replace a built-in tool by passing override=True to
ctx.register_tool(). Without it, the registry rejects any registration
that would shadow an existing tool from a different toolset (unchanged
default behavior).
Unlocks the use case from #11049: drop-in replacement of browser/web
backends without forking core. Composes with the existing pre_tool_call
hook for runtime interception of any implementation.
The override is audit-logged at INFO so it surfaces in agent.log.
Thin wrapper around Imbue's darwinian_evolver (AGPL-3.0, subprocess-only).
Ships a working OpenRouter driver (parrot_openrouter.py), a snapshot
inspector (show_snapshot.py), and a custom-problem template. SKILL.md
has 58-char description, Pitfalls sourced from actually running the loop:
non-viable seed trap, Azure content filter killing runs, loop.run() being
a generator, nested-pickle snapshots, and aggressive default concurrency.
Salvaged from #12719 by @Bihruze — original PR shipped 12,289 LOC across
61 files (29 Python modules, FastAPI dashboard, VS Code extension,
benchmark hub, marketplace, etc.) which was far beyond the scope of the
underlying issue (#336). This version stays at the ~700-LOC scope that
issue actually asked for. Authorship of the original effort credited via
AUTHOR_MAP entry and the SKILL.md author field.
Verified end-to-end: seed 'Say {{ phrase }}' (score 0.000) evolved into
'Please repeat the following phrase exactly as it is, without any
modifications or additional formatting: {{ phrase }}' (score 0.750)
across 3 iterations on gpt-4o-mini via OpenRouter.
Co-authored-by: Bihruze <98262967+Bihruze@users.noreply.github.com>
Tirith ships no Windows binary, so on every Windows CLI startup users
saw a scary 'tirith security scanner enabled but not available' banner
they could not act on. The banner suggested degraded security; in
reality pattern-matching guards still run and the message was pure noise.
Fix:
- New public is_platform_supported() helper in tools/tirith_security.py
that returns False when _detect_target() doesn't resolve (Windows, any
non-x86_64/aarch64 arch).
- ensure_installed(), _resolve_tirith_path(), and check_command_security()
short-circuit on unsupported platforms: cache _resolved_path =
_INSTALL_FAILED with reason 'unsupported_platform', skip PATH probes,
skip the background download thread, skip the disk failure marker, and
return allow with an empty summary from check_command_security so the
spawn loop never fires.
- Explicit user-configured tirith_path is still honored everywhere (a
user who built tirith themselves under WSL keeps that path).
- CLI banner in cli.py gated on is_platform_supported() — fires only on
platforms where tirith *should* work but isn't installed.
- Docs note tirith's supported-platform list and point Windows users at
WSL.
Tests: tests/tools/test_tirith_security.py +8 tests covering Linux
x86_64, Darwin arm64, Windows, and unknown-arch verdicts plus the
silent ensure_installed / check_command_security / _resolve_tirith_path
fast-paths and the explicit-path override.
test_tirith_security.py 75 passed (8 new + 67 pre-existing)
test_command_guards.py 19 passed
The #1 confusing cause of the xAI 403 (per Teknium): X Premium+
subscribers see Grok inside the X app and assume API access is
included. It is NOT — only standalone SuperGrok subscribers can use
xai-oauth with Hermes today. Without calling this out, every Premium+
user hits the 403 with no idea why.
PR #26666's neutral 4-cause list was correct but buried the most
common cause. Lead with the Premium+ gotcha, then list the other
possibilities (no subscription, wrong tier, exhausted quota) as
fallbacks. Same neutral framing — does not accuse anyone of being
unsubscribed.
PR #26644 confidently told users "xAI OAuth account lacks SuperGrok /
X Premium entitlement" on any 403 from xAI's permission-denied surface.
But that body is returned for at least four distinct causes that
Hermes cannot distinguish from the wire:
* Account has no Grok subscription at all
* Account has SuperGrok but the tier doesn't include the requested
model (e.g. grok-4.3 needs SuperGrok Heavy)
* Monthly quota for the subscribed tier is exhausted
* SuperGrok is active but the API access add-on isn't enabled
Don Piedro pushed back that he IS subscribed yet still hit this.
Picking the worst-case interpretation ("you're not subscribed")
reads as wrong and insulting to subscribers, and points them at a
fix they already did.
New wording lists all 4 possibilities and points at
https://grok.com/?_s=usage where the user can check which applies.
The detection logic and credential-pool short-circuit (PR #26664)
are unchanged — only the user-facing wording is rephrased.
Don Piedro's 18-minute hang on grok-4.3 traced to two issues PR #26644
didn't cover:
- _recover_with_credential_pool classifies 403 as FailoverReason.auth
and calls pool.try_refresh_current(). For xAI OAuth on an
unsubscribed account, refresh succeeds (mints a new token from the
same account) but the next API call 403s with the same entitlement
error. Result: infinite refresh → retry → 403 loop until Ctrl+C
(1133s in Don's log). New _is_entitlement_failure(error_context,
status_code) detects the subscription-shape body ("do not have an
active Grok subscription" / "out of available resources" + grok /
"does not have permission" + grok) and short-circuits recovery so
_summarize_api_error surfaces PR #26644's friendly hint.
- grok-4.3 resolved to 256k via the grok-4 catch-all in
DEFAULT_CONTEXT_LENGTHS. Per docs.x.ai/developers/models/grok-4.3
the model ships with 1M context. Add explicit grok-4.3 entry
before the grok-4 fallback (longest-first substring matching
ensures grok-4.3 and grok-4.3-latest both land on the new value).
Tests: 8 new (23 total in test_codex_xai_oauth_recovery.py).
E2E verified Don's 100-iteration loop bails out with 0 refresh calls
while genuine auth failures still refresh once and recover.
The cherry-picked PR #15251 from @tw2818 correctly identified the
DeepSeek 400 root cause but placed the fix in the legacy fallback path
of `build_kwargs`, which DeepSeek never reaches — DeepSeek has a
registered ProviderProfile and goes through `_build_kwargs_from_profile`
instead. The legacy-path block was therefore dead code.
This commit pivots the fix to where it actually fires:
- New `DeepSeekProfile` in `plugins/model-providers/deepseek/__init__.py`
overrides `build_api_kwargs_extras` to emit DeepSeek's expected wire
format (mirrors `KimiProfile`):
{"reasoning_effort": "<low|medium|high|max>",
"extra_body": {"thinking": {"type": "enabled" | "disabled"}}}
- Model gating: only `deepseek-v4-*` and `deepseek-reasoner` emit
thinking control. `deepseek-chat` (V3) is untouched — current behavior.
- Effort mapping: low/medium/high passthrough, xhigh/max → max, unset →
omitted (DeepSeek server applies its own default).
- Revert the legacy-path additions from PR #15251 — they were dead code,
and the `_copy_reasoning_content_for_api` strip block specifically
would have nullified the existing reasoning_content padding machinery
(`_needs_deepseek_tool_reasoning` → space-pad on replay) that the
active provider already relies on for replay correctness.
- Unit tests pin the wire-shape contract and the model gating rules
(26 tests, all passing). Existing transport + provider profile suites
(321 tests) continue to pass.
- AUTHOR_MAP: map twebefy@gmail.com → tw2818 for release notes credit.
Closes#15700, #17212, #17825.
Co-authored-by: tw2818 <twebefy@gmail.com>
Three fixes for the May 2026 xAI OAuth (SuperGrok / X Premium) rollout
failures:
- _run_codex_stream: when openai SDK raises RuntimeError("Expected to
have received `response.created` before `<type>`"), retry once then
fall back to responses.create(stream=True) — same path used for
missing-response.completed postlude. Fallback surfaces the real
provider error with body+status_code intact. Also fixes#8133
(response.in_progress prelude on custom relays) and #14634
(codex.rate_limits prelude on codex-lb).
- _summarize_api_error: when error body matches xAI's entitlement
shape, append a one-line hint pointing to https://grok.com and
/model. Once-only, applies to both auxiliary warnings and
main-loop error surfacing.
- _chat_messages_to_responses_input: new is_xai_responses kwarg
drops replayed codex_reasoning_items (encrypted_content) before
they reach xAI. Also drops reasoning.encrypted_content from the
xAI include array. Native Codex behavior unchanged. Grok still
reasons natively each turn; coherence rides on visible message
text alone.
Closes#8133, #14634.
Two log-spam fixes surfaced by a Windows user (Git Bash + Python 3.11.9):
1. LocalEnvironment cwd warn spam
============================
Git Bash's `pwd -P` emits paths like `/c/Users/x`. The base-class
`_extract_cwd_from_output` was assigning this verbatim to `self.cwd`
without validation, then `_resolve_safe_cwd`'s `os.path.isdir(/c/...)`
returned False on Windows, triggering:
LocalEnvironment cwd '/c/Users/NVIDIA' is missing on disk;
falling back to '/' so terminal commands keep working.
...on every terminal call. The pre-existing Windows-path translation
inside `_run_bash` ran AFTER the safe-cwd check, so it could never
prevent the warning.
Fix:
- New `_msys_to_windows_path` helper (idempotent, no-op off Windows).
- `_resolve_safe_cwd` normalizes before `isdir`, so a valid MSYS path
is recognized as the real directory it points at.
- `LocalEnvironment._update_cwd` and a new override of
`_extract_cwd_from_output` translate + validate before mutating
`self.cwd`. Stale / non-existent marker paths roll back to the
previous cwd instead of clobbering it.
- The fallback warning still fires when the directory really is gone
(deletion-recovery scenario from #17558 still covered).
2. tirith spawn-failed warn spam
=============================
When tirith isn't installed (background install in flight, or marked
failed for the day) and the configured path stays as the bare string
`tirith`, every `subprocess.run([tirith_path, ...])` raises OSError
and logged:
tirith spawn failed: [WinError 2] The system cannot find the file specified
...on every command. fail_open=True means behaviour is correct, but
the log noise is severe.
Fix:
- `_warn_once(key, ...)` thread-safe dedupe helper.
- Three hot-path warnings (`tirith path resolved to None`,
`tirith spawn failed: ...`, `tirith timed out after Ns`) now log
once per (exception class, errno) / timeout-value / path-none key.
- Dedupe set is cleared on `_clear_install_failed` so a successful
install lets a subsequent failure surface again.
Tests
=====
- `tests/tools/test_local_env_windows_msys.py`: 12 tests covering the
MSYS→Windows translator, the resolve fast-path, update_cwd validation,
and extract_cwd_from_output rollback.
- `tests/tools/test_tirith_security.py`: 4 new dedupe tests (15 spawn
failures → 1 log line; distinct exc types → 2 lines; timeout dedupe;
path-None dedupe).
Targeted runs:
test_local_env_windows_msys.py 12 passed
test_local_env_cwd_recovery.py 7 passed (pre-existing, no regressions)
test_tirith_security.py 67 passed (63 pre-existing + 4 new)
test_base_environment + local_* 37 passed (no regressions)
test_local_env_blocklist + neighbours 114 passed
Reported via Hermes log capture: 19× cwd warnings + 15× tirith warnings
in a single short session.
- dep_ensure.py: use get_hermes_home() instead of hand-rolled env var
- dep_ensure.py: add "chrome" to browser name list (was inconsistent with browser_tool.py)
- main.py _cmd_update_check: use detect_install_method() directly instead of redundant .git check
- main.py _cmd_update_pip: build command list directly instead of fragile split() on display string
- banner.py: rename _check_via_pypi → check_via_pypi (cross-module public API)
One-shot bootstrap that installs non-Python deps (node, browser,
ripgrep, ffmpeg) via ensure_dependency(), then runs setup if no
provider is configured. Closes the gap between `pip install` and
the full user-facing experience.
Also fixes 3 pre-existing test regressions caused by earlier commits:
- test_recommended_update_command: mock detect_install_method for git env
- test_check_for_updates_no_git_dir: now falls back to PyPI, not None
- test_plist_path_includes_node_modules_bin: skip when dir absent
Adds detect_install_method() to identify nixos/homebrew/git/pip installs,
and recommended_update_command_for_method() to return the right upgrade command
for each method. Updates recommended_update_command() to use these for pip-installed
instances (no .git dir, not managed).
Add _find_bundled_tui() that checks for hermes_cli/tui_dist/entry.js
(present in wheel installs) and wire it into _make_tui_argv() between
the HERMES_TUI_DIR prebuilt path and the npm install fallback.
Extract PATH building into _build_service_path_dirs() that skips directories
which don't exist on disk (e.g. node_modules/.bin for pip installs) and also
includes ~/.hermes/node/bin and ~/.hermes/node_modules/.bin for agent-browser.
For pip-installed hermes-agent (no .git directory), fall back to
querying PyPI's JSON API to compare __version__ against the latest
published release, using stdlib only (urllib + json, no packaging dep).
Stop the gateway from exiting (or systemd-restart-looping) when a single
messaging adapter fails at startup or runtime. A misconfigured WhatsApp
(npm install timeout, unpaired bridge, missing creds.json) used to take
the entire gateway down, killing cron jobs and any other connected
platforms with it.
Changes:
• Startup (gateway/run.py): when connected_count==0 but the only
errors are retryable, log a degraded-state warning and keep the
gateway alive instead of returning False. Reconnect watcher then
recovers platforms as their underlying problem clears.
• Runtime (gateway/run.py _handle_adapter_fatal_error): when the last
adapter goes down with a retryable error and is queued for
reconnection, stay alive instead of exit-with-failure. Previously
this triggered systemd Restart=on-failure, which created infinite
restart loops on persistent retryable failures (proxy outage,
repeated bridge crashes).
• Reconnect watcher (gateway/run.py _platform_reconnect_watcher):
replace the 20-attempt hard drop with a circuit-breaker pause.
After _PAUSE_AFTER_FAILURES (10) consecutive retryable failures, the
platform stays in _failed_platforms with paused=True so the watcher
skips it but the operator can still see and resume it. Non-retryable
errors still drop out of the queue immediately. Resolves#17063
(gateway giving up on Telegram after 20 attempts).
• WhatsApp preflight (gateway/platforms/whatsapp.py): refuse to start
the Node bridge when creds.json is missing. Sets a non-retryable
whatsapp_not_paired fatal error so the watcher drops it cleanly
with a single 'run hermes whatsapp' log line instead of paying the
30s bridge bootstrap timeout on every gateway start.
• WhatsApp setup ordering (hermes_cli/main.py cmd_whatsapp): only set
WHATSAPP_ENABLED=true once pairing actually succeeds. Previously
the wizard wrote the env var at step 2 (before npm install and QR
pairing), so any Ctrl+C left .env claiming WhatsApp was ready when
the bridge had no creds.json. Also propagate the env var when the
user keeps an existing pairing on a re-run.
• /platform slash command (hermes_cli/commands.py + gateway/run.py):
new gateway-only command for manual circuit-breaker control.
/platform list — show connected + failed/paused platforms
/platform pause <name> — silence a known-broken platform
/platform resume <name> — re-queue a paused platform
Tests:
• New: pause/resume helpers, /platform list|pause|resume command,
WhatsApp creds.json preflight, WhatsApp setup ordering.
• Updated: stale assertions that codified the old 'exit and let
systemd restart' behavior in test_runner_fatal_adapter.py,
test_runner_startup_failures.py, and test_platform_reconnect.py
(the 20-attempt give-up test became a circuit-breaker pause test).
5488 tests pass in tests/gateway/.
Two loopback-redirect OAuth flows (xAI Grok, Spotify) silently fail when
Hermes runs on a remote host: the auth server redirects to
127.0.0.1:<port> on the user's laptop, not on the remote box. The
--no-browser flag only suppresses webbrowser.open() — it doesn't change
the bind address. Symptom xAI surfaces is 'Could not establish
connection. We couldn't reach your app.', followed by a 'xAI
authorization timed out waiting for the local callback' on the CLI side.
Changes
- hermes_cli/auth.py: new _print_loopback_ssh_hint() helper, called from
_xai_oauth_loopback_login() and _spotify_login() right after they
print the redirect URI. Silent off SSH; on SSH prints the exact
'ssh -N -L <port>:127.0.0.1:<port>' command using the actually-bound
port (not the hardcoded constant — the listener auto-bumps when the
preferred port is busy), a provider-specific docs URL, and a link to
the new shared guide.
- website/docs/guides/oauth-over-ssh.md (new): single source of truth
for the tunnel pattern — TL;DR command, jump-box / ProxyJump variant,
mosh+tmux+ControlMaster gotchas, troubleshooting.
- website/docs/guides/xai-grok-oauth.md: fix the two sections that
claimed --no-browser alone was enough; link to the shared guide.
- website/docs/user-guide/features/spotify.md: expand the existing
one-liner; link to the shared guide.
- website/sidebars.ts: register the new page.
- tests/hermes_cli/test_auth_loopback_ssh_hint.py: 7 unit tests
covering SSH-vs-not, loopback-vs-not, malformed URIs, port echo,
with and without provider docs URL.
Wraps every sync->async coroutine-scheduling site in the codebase with a
new agent.async_utils.safe_schedule_threadsafe() helper that closes the
coroutine on scheduling failure (closed loop, shutdown race, etc.)
instead of leaking it as 'coroutine was never awaited' RuntimeWarnings
plus reference leaks.
22 production call sites migrated across the codebase:
- acp_adapter/events.py, acp_adapter/permissions.py
- agent/lsp/manager.py
- cron/scheduler.py (media + text delivery paths)
- gateway/platforms/feishu.py (5 sites, via existing _submit_on_loop helper
which now delegates to safe_schedule_threadsafe)
- gateway/run.py (10 sites: telegram rename, agent:step hook, status
callback, interim+bg-review, clarify send, exec-approval button+text,
temp-bubble cleanup, channel-directory refresh)
- plugins/memory/hindsight, plugins/platforms/google_chat
- tools/browser_supervisor.py (3), browser_cdp_tool.py,
computer_use/cua_backend.py, slash_confirm.py
- tools/environments/modal.py (_AsyncWorker)
- tools/mcp_tool.py (2 + 8 _run_on_mcp_loop callers converted to
factory-style so the coroutine is never constructed on a dead loop)
- tui_gateway/ws.py
Tests: new tests/agent/test_async_utils.py covers helper behavior under
live loop, dead loop, None loop, and scheduling exceptions. Regression
tests added at three PR-original sites (acp events, acp permissions,
mcp loop runner) mirroring contributor's intent.
Live-tested end-to-end:
- Helper stress test: 1500 schedules across live/dead/race scenarios,
zero leaked coroutines
- Race exercised: 5000 schedules with loop killed mid-flight, 100 ok /
4900 None returns, zero leaks
- hermes chat -q with terminal tool call (exercises step_callback bridge)
- MCP probe against failing subprocess servers + factory path
- Real gateway daemon boot + SIGINT shutdown across multiple platform
adapter inits
- WSTransport 100 live + 50 dead-loop writes
- Cron delivery path live + dead loop
Salvages PR #2657 — adopts contributor's intent over a much wider site
list and a single centralized helper instead of inline try/except at
each site. 3 of the original PR's 6 sites no longer exist on main
(environments/patches.py deleted, DingTalk refactored to native async);
the equivalent fix lives in tools/environments/modal.py instead.
Co-authored-by: JithendraNara <jithendranaidunara@gmail.com>
Build on @aydnOktay's cronjob fix by routing the cronjob check through
the shared 'env_var_enabled' helper in utils.py (same truthy set:
1/true/yes/on) and applying the same semantics to the 8 sibling call
sites that read HERMES_INTERACTIVE / HERMES_GATEWAY_SESSION /
HERMES_EXEC_ASK / HERMES_CRON_SESSION with bare os.getenv() truthy
checks:
- tools/approval.py: _is_gateway_approval_context (2), check_command_safety (2),
check_all_command_guards (3) -- 7 sites total
- tools/terminal_tool.py: _handle_sudo_failure, sudo password prompt -- 2 sites
- tools/skills_tool.py: _is_gateway_surface -- 1 site
Without this, a user who exports HERMES_INTERACTIVE=0 in their shell
still gets interactive sudo prompts, approval prompts, and gateway
skill-install paths -- only the cronjob tool was hardened. Now all
consumers agree on the same false-like values.
Also drops the duplicate _is_truthy_env helper from cronjob_tools.py
in favour of the existing canonical utils.env_var_enabled.
Tests: extend the parametrized regression coverage to all three
session env vars (HERMES_INTERACTIVE / HERMES_GATEWAY_SESSION /
HERMES_EXEC_ASK) symmetrically. tests/tools/test_cronjob_tools.py:
60/60 pass; tests/tools/{approval,terminal_tool,skills_tool,
cron_approval_mode,hardline_blocklist}.py: 378/378 pass.
Per @mark-xai's review on PR #26457 and the xAI model retirement on
2026-05-15: grok-code-fast-1 is being retired today and aliases redirect
to grok-4.3 (already pinned to the top of the xAI model list by this
PR). Update the two xAI Responses-API test fixtures Mark flagged plus
the picker fallback default in hermes_cli/main.py that uses the same
literal.
The xAI prompt_cache_key block carried two long comment paragraphs
that either restated setdefault semantics, narrated the SDK
type-validation mechanism, or recapped the historical motivation for
the extra_body indirection — all already covered by the test
docstring at test_xai_responses_sends_cache_key_via_extra_body
(which links to the xAI docs). Also restored the truncated link in
the body-injection comment.
No behavior change.
The new resolve_xai_http_credentials() resolver was using os.getenv()
for the XAI_API_KEY/XAI_BASE_URL fallback path, which dropped the
~/.hermes/.env contract guarded by PR #17140 / #17163. Users with
XAI_API_KEY in dotenv only would see "No xAI credentials found" even
though the key was configured.
Separately, _transcribe_xai started consulting creds["base_url"] (which
always returns at least the default https://api.x.ai/v1) ahead of the
public XAI_STT_BASE_URL env override, so the per-tool override stopped
working.
- tools/xai_http.py: add module-level get_env_value() wrapper that
reads ~/.hermes/.env first (via hermes_cli.config.get_env_value),
then os.environ. Resolver uses it for the API-key/base-url fallback.
- tools/transcription_tools.py: restore precedence so XAI_STT_BASE_URL
wins over creds["base_url"].
- tests/tools/test_transcription_dotenv_fallback.py +
tests/tools/test_tts_dotenv_fallback.py: repoint the per-call-site
patches at the new resolution point (tools.xai_http.get_env_value).
The end-to-end regression-guard test (which patches load_env) is
unchanged and still passes.
Two bugs in the `hermes tools` reconfigure flow caused picking xAI Grok
Imagine for video_gen (or image_gen) to feel like a no-op:
1. `_is_provider_active()` had a branch for `image_gen_plugin_name` but
none for `video_gen_plugin_name`, so a row marked as the active xAI
video provider was never recognized as active. The picker fell through
to the env-var fallback in `_detect_active_provider_index()`, which
matched the FAL row (because `FAL_KEY` is set), so the picker visually
defaulted to FAL even though the user had selected xAI.
2. `_plugin_video_gen_providers()` and `_plugin_image_gen_providers()`
built picker rows from the plugin's `get_setup_schema()` but only
copied `name`, `badge`, `tag`, `env_vars`. The xAI plugins declare
`post_setup: "xai_grok"` so the picker should run the OAuth /
API-key prompt hook after selection — that key was silently dropped,
so the hook never fired from the picker rows.
Adds the missing `video_gen_plugin_name` branch (placed before the
`managed_nous_feature` block, mirroring the existing image_gen branch)
and propagates `post_setup` from the plugin schema into both picker-row
builders. Adds focused tests in `test_video_gen_picker.py` and
`test_image_gen_picker.py`.
Adds a new authentication provider that lets SuperGrok subscribers sign
in to Hermes with their xAI account via the standard OAuth 2.0 PKCE
loopback flow, instead of pasting a raw API key from console.x.ai.
Highlights
----------
* OAuth 2.0 PKCE loopback login against accounts.x.ai with discovery,
state/nonce, and a strict CORS-origin allowlist on the callback.
* Authorize URL carries `plan=generic` (required for non-allowlisted
loopback clients) and `referrer=hermes-agent` for best-effort
attribution in xAI's OAuth server logs.
* Token storage in `auth.json` with file-locked atomic writes; JWT
`exp`-based expiry detection with skew; refresh-token rotation
synced both ways between the singleton store and the credential
pool so multi-process / multi-profile setups don't tear each other's
refresh tokens.
* Reactive 401 retry: on a 401 from the xAI Responses API, the agent
refreshes the token, swaps it back into `self.api_key`, and retries
the call once. Guarded against silent account swaps when the active
key was sourced from a different (manual) pool entry.
* Auxiliary tasks (curator, vision, embeddings, etc.) route through a
dedicated xAI Responses-mode auxiliary client instead of falling back
to OpenRouter billing.
* Direct HTTP tools (`tools/xai_http.py`, transcription, TTS, image-gen
plugin) resolve credentials through a unified runtime → singleton →
env-var fallback chain so xai-oauth users get them for free.
* `hermes auth add xai-oauth` and `hermes auth remove xai-oauth N` are
wired through the standard auth-commands surface; remove cleans up
the singleton loopback_pkce entry so it doesn't silently reinstate.
* `hermes model` provider picker shows
"xAI Grok OAuth (SuperGrok Subscription)" and the model-flow falls
back to pool credentials when the singleton is missing.
Hardening
---------
* Discovery and refresh responses validate the returned
`token_endpoint` host against the same `*.x.ai` allowlist as the
authorization endpoint, blocking MITM persistence of a hostile
endpoint.
* Discovery / refresh / token-exchange `response.json()` calls are
wrapped to raise typed `AuthError` on malformed bodies (captive
portals, proxy error pages) instead of leaking JSONDecodeError
tracebacks.
* `prompt_cache_key` is routed through `extra_body` on the codex
transport (sending it as a top-level kwarg trips xAI's SDK with a
TypeError).
* Credential-pool sync-back preserves `active_provider` so refreshing
an OAuth entry doesn't silently flip the active provider out from
under the running agent.
Testing
-------
* New `tests/hermes_cli/test_auth_xai_oauth_provider.py` (~63 tests)
covers JWT expiry, OAuth URL params (plan + referrer), CORS origins,
redirect URI validation, singleton↔pool sync, concurrency races,
refresh error paths, runtime resolution, and malformed-JSON guards.
* Extended `test_credential_pool.py`, `test_codex_transport.py`, and
`test_run_agent_codex_responses.py` cover the pool sync-back,
`extra_body` routing, and 401 reactive refresh paths.
* 165 tests passing on this branch via `scripts/run_tests.sh`.
* fix(langfuse): reject placeholder credentials with one-shot warning
When operators leave HERMES_LANGFUSE_PUBLIC_KEY / HERMES_LANGFUSE_SECRET_KEY
at a template value like 'placeholder', 'test-key', or 'your-langfuse-key',
the Langfuse SDK silently accepts the credentials at construction time and
drops every trace at flush time. No warning, no error — just an empty
Langfuse dashboard the operator only notices hours later.
Add prefix-based validation in _get_langfuse() against the documented
'pk-lf-' / 'sk-lf-' prefixes that Langfuse always issues server-side.
Anything else fires a single warning naming the offending env var(s)
with a log-safe value preview (full string for short placeholders so the
operator knows which template they left in place; truncated for long
values so a real secret pasted into the wrong field never hits the log),
then short-circuits via the existing _INIT_FAILED cache so the warning
fires once per process, not once per hook invocation.
The check sits after the 'Langfuse is None' SDK-installed guard so hosts
without the optional langfuse SDK don't see misleading 'set real keys'
hints when the actionable fix is 'pip install langfuse'. Missing
credentials remains the documented opt-out path and stays silent — no
log noise for unconfigured installs.
Fixes#22763Fixes#23823
* fix(langfuse): use actual API request messages for generation input
on_pre_llm_request previously used the messages kwarg alone, which
could be None when Hermes passes the payload via request_messages,
conversation_history, or user_message instead. Add _coerce_request_messages
to pick the first available list across all variants, falling back to a
synthetic user message. Generations now show the real outbound payload
rather than an empty input.
* fix(langfuse): record tool call outputs in traces
Tool observations showed input (arguments) but output was always
undefined. Root cause: when tool_call_id is empty, pre_tool_call stored
observations under a unique time-based key that post_tool_call could
never reconstruct, so every tool span was closed without output by the
_finish_trace sweep.
Fix pre/post matching by routing empty-tool_call_id tools through a
per-name FIFO queue (pending_tools_by_name) instead of the time-based
key. Tools with a tool_call_id continue to use the id-keyed dict.
Also:
- Preserve OpenAI-style nested function shape in serialized tool calls
so Langfuse renders name/arguments correctly
- Keep name + tool_call_id on role:tool messages for proper pairing
- Backfill tool results onto the matching turn_tool_calls entry so the
generation's tool-call record carries the result alongside arguments
- Coerce request messages from whichever field the runtime provides
(request_messages, messages, conversation_history, user_message)
* fix(langfuse): salvage-review polish — drop dead is_first_turn, shallow-copy request_messages, real threaded FIFO test
Self-review of the combined #22345 + #23831 salvage surfaced three issues
worth fixing in the same PR rather than as follow-ups:
1. Drop is_first_turn from the pre_api_request hook. The boolean expression
`not bool(conversation_history)` was wrong: conversation_history is
reassigned to None mid-run after compression (5 sites in run_agent.py),
so the value flips False -> True mid-conversation on every post-compression
API call. The langfuse plugin never consumed it, so the kwarg was both
misleading AND dead.
2. Replace copy.deepcopy(request_messages) with shallow list() copy. The
pre_api_request hook contract discards return values (invoke_hook never
writes back to api_kwargs), and the langfuse plugin's _serialize_messages
already builds its own snapshot dicts via _safe_value. A deepcopy on every
API call would walk every tool result and base64 image — significant
overhead for no real isolation benefit. Shallow copy of the outer list
protects against later mutations of api_messages without paying for the
inner-dict walk.
3. Rename test_empty_tool_call_id_concurrent_fifo_order ->
test_empty_tool_call_id_observations_are_fifo_within_tool_name and add a
real test_threaded_post_calls_preserve_fifo_under_lock that spawns 8
threads behind a barrier to actually exercise _STATE_LOCK on the
pending_tools_by_name queue. The original test was sequential and only
validated Python list semantics; this one validates the lock discipline.
4. Fix stale 'Cleared by reset_cache_for_tests()' comment on _INIT_FAILED —
that function does not exist. Tests reload the module via sys.modules.pop
+ importlib.import_module instead.
Tests: 37 langfuse plugin tests pass, 658 plugin tests overall pass.
---------
Co-authored-by: xxxigm <tuancanhnguyen706@gmail.com>
Co-authored-by: Brian Conklin <brian@dralth.com>
Builds on @steezkelly's Bug A fix (#25857, top-level default_permissions
via _insert_managed_block_at_top_level) by addressing the other two
config-corruption bugs described in #26250:
Bug B (duplicate [plugins.X] tables)
- Codex itself writes [plugins."<name>@<marketplace>"] tables to
config.toml when the user runs `codex plugins enable` directly,
before hermes-agent's managed block exists. On the next migrate run,
_query_codex_plugins() re-discovers the same plugins via plugin/list
and render_codex_toml_section() re-emits them inside the managed
block. Codex's strict TOML parser then rejects the duplicate table
header on startup.
- Add _strip_unmanaged_plugin_tables() that drops [plugins.*] tables
from the user-content portion of the file. Only run it when
plugin/list succeeded — if the RPC failed we can't re-emit and
must preserve the user's tables. plugin/list is the source of
truth when it answers.
Bug C (HERMES_HOME pytest-tempdir leak into ~/.codex/config.toml)
- _build_hermes_tools_mcp_entry() read HERMES_HOME directly from
os.environ, so a sibling pytest's monkeypatch.setenv("HERMES_HOME",
tmp_path) silently burned a transient pytest tempdir into the
user's real ~/.codex/config.toml. After pytest reaped the tempdir,
every codex-routed hermes-tools tool call failed silently.
- Derive HERMES_HOME from get_hermes_home() (the canonical resolver
that goes through the profile-aware path) and refuse to emit
obvious test-tempdir paths via _looks_like_test_tempdir() as
belt-and-suspenders for any other callsite that forgets to patch
migrate().
- test_enable_succeeds_when_codex_present in test_codex_runtime_switch.py
invoked the real migrate() (no mock), writing to Path.home() / .codex
using whatever HERMES_HOME the running pytest session had set. Add
the same migrate patch the other apply() tests already use, so the
suite stops touching the user's real ~/.codex/config.toml.
E2E verification (replicating the issue's repro):
- Pre-state config.toml with user [mcp_servers.omx_team_run] +
codex-installed [plugins."tasks@openai-curated"],
HERMES_HOME="/private/var/folders/.../pytest-of-.../..."
- On origin/main: tomllib refuses to load the result with
"Cannot declare ('plugins', 'tasks@openai-curated') twice" AND
the pytest-tempdir HERMES_HOME is burned in.
- On this branch: file parses cleanly, default_permissions is
top-level, exactly one [plugins."tasks@openai-curated"] table
inside the managed block, no HERMES_HOME in the MCP env.
7 new regression tests covering all three bugs + the test-leak guard.
`bash scripts/run_tests.sh tests/hermes_cli/test_codex_runtime_*.py` —
95 passed, 0 failed.
Closes#26250
Replace O(n²) string concatenation of truncated_response_prefix in the
length-continuation retry loop with a list + ''.join(). Functionally
equivalent: same partial response on early return, same prepend on
final assembly. The legacy retry path is capped at 3 iterations, so
the practical wall-clock win is small, but the new idiom matches the
rest of the codebase and removes a needless repeated allocation.
Salvaged from PR #2717 (the run_conversation portion only — trajectory
refactor dropped because it silently rewrote </tool_response> to </think>).
Co-authored-by: Teknium <127238744+teknium1@users.noreply.github.com>
SimpleX Chat (https://simplex.chat) is a private, decentralised messenger
with no persistent user IDs — every contact is identified by an opaque
internal ID generated at connection time. This adds it as a Hermes
gateway platform via the plugin system.
The adapter connects to a local simplex-chat daemon via WebSocket,
listens for inbound messages, and sends replies. Originally proposed in
PR #2558 as a core-modifying integration; reshaped here as a self-
contained plugin under plugins/platforms/simplex/ with no edits to any
core file. Discovery is filesystem-based (scanned by gateway.config),
and the platform identity is resolved on demand via Platform("simplex").
Plugin contract:
- check_requirements() requires SIMPLEX_WS_URL AND the websockets package
- validate_config() / is_connected() accept env or config.yaml input
- _env_enablement() seeds PlatformConfig.extra (ws_url + home_channel)
- _standalone_send() supports out-of-process cron delivery
- interactive_setup() provides a stdin wizard for hermes gateway setup
- register() wires the adapter into the registry with required_env,
install_hint, cron_deliver_env_var, allowed_users_env, and a
platform_hint for the LLM.
Lazy dependency: the websockets Python package is imported inside the
functions that need it. The plugin is importable and discoverable even
when websockets is missing — check_requirements() simply returns False
until `pip install websockets` is run. No new pyproject extras are
introduced.
Environment variables:
SIMPLEX_WS_URL WebSocket URL of the daemon (required)
SIMPLEX_ALLOWED_USERS Comma-separated allowed contact IDs
SIMPLEX_ALLOW_ALL_USERS Set true to allow all contacts
SIMPLEX_HOME_CHANNEL Default contact for cron delivery
SIMPLEX_HOME_CHANNEL_NAME Human label for the home channel
Closes#2557.
The Zed ACP Registry path (uvx --from 'hermes-agent[acp]==X' hermes-acp)
gets a Python-only install. Browser tools depend on the agent-browser npm
package + Chromium, neither of which are in the wheel. Without an
explicit bootstrap, registry users have no path to working browser tools.
Ship a bundled, idempotent bootstrap script (Linux/macOS bash + Windows
PowerShell) inside acp_adapter/bootstrap/ as wheel package-data. New
entry points:
hermes acp --setup-browser # interactive; prompts before Chromium download
hermes acp --setup-browser --yes # non-interactive
hermes-acp --setup-browser
The terminal-auth flow (hermes acp --setup) also offers the browser
bootstrap as a follow-up after model selection, so first-run registry
users get the option without knowing the flag exists.
Key design choices:
- npm install -g --prefix $NODE_PREFIX so we never need sudo. System Node
on PATH is respected; only the install target is redirected to the
user-writable Hermes-managed Node prefix.
- tools/browser_tool.py::_browser_candidate_path_dirs() already walks
$HERMES_HOME/node/bin, so installed binaries are discovered with no
agent-side code change.
- System Chrome/Chromium detection short-circuits the ~400 MB Playwright
download when a suitable browser already exists.
- Bash + PowerShell live as ONE copy each under acp_adapter/bootstrap/.
Not duplicated under scripts/. install.sh and install.ps1 keep their
inline browser blocks for the source-checkout path.
E2E validated end-to-end:
bash bootstrap_browser_tools.sh --skip-chromium
→ installs agent-browser into ~/.hermes/node/bin/
tools.browser_tool._find_agent_browser()
→ returns the installed path
check_browser_requirements()
→ returns True (browser tools register)
Tests:
- tests/acp/test_entry.py: 11 tests covering --setup-browser dispatch
(linux + windows + --yes forwarding + failure propagation), the
terminal-auth follow-up prompt path, and a package-data wheel-shipping
assertion that catches any future pyproject.toml regression.
Docs: website/docs/user-guide/features/acp.md gains a 'Browser tools
(optional)' subsection with the two-line install + what-it-does.
Cron mutation operations (run/pause/resume/remove) and 'hermes cron edit'
now accept a job name in addition to the hex ID, with case-insensitive
matching. Before this, 'hermes cron run my_job_name' died with
'Job with ID my_job_name not found' and forced the user to look up the
hex ID first.
The original PR matched by name but silently picked the first match when
two jobs shared a name. This version refuses to act on an ambiguous name
and surfaces every matching job (id, name, schedule, next_run_at) so the
caller can pick a specific ID.
- cron/jobs.py:
- get_job() stays ID-only (preserves existing call-site semantics for
web_server/api_server/curator/scheduler/test code that always passes
real IDs).
- resolve_job_ref() is the new name-or-ID resolver, used by pause/
resume/trigger/remove_job. Exact ID match wins over a name match
even if a different job's name happens to equal that ID. Ambiguous
name match raises AmbiguousJobReference with all candidate IDs.
- tools/cronjob_tools.py: dispatch site uses resolve_job_ref, surfaces
ambiguous matches as a structured error with the matching IDs.
- hermes_cli/cron.py: 'cron edit' uses resolve_job_ref so editing by
name works and ambiguous names are reported with IDs.
- tests/cron/test_jobs.py: new TestResolveJobRef covering ID match,
case-insensitive name match, ID-wins-over-name, ambiguous refusal,
and that pause/resume/trigger/remove all refuse on ambiguity.
Closes#2627
When the in-tree FAL path has no API key (and no managed gateway), the
handler used to return a bare 'FAL_KEY environment variable not set'
error. Users had no idea where to get a key, that a managed Nous
gateway exists, or that plugin-registered providers are an option.
Now `image_generate_tool` returns a structured multi-line message:
- signup link (https://fal.ai)
- managed-gateway status (if Nous tools are enabled)
- pointer to `hermes tools` / `hermes plugins list` for alternate
backends, so users on a stale `image_gen.provider` know where to look
The schema is untouched — `check_fn` still gates the tool out of the
schema when no backend is reachable at startup, consistent with every
other conditional tool. This patch fixes the call-time failure modes:
managed-gateway 5xx, plugin provider disappearing mid-session, etc.
Inspired by #2546 / @Mibayy. The PR was ~5700 commits stale against
the new plugin-aware image_gen architecture, so this is a forward port
of the actionable-error idea rather than a cherry-pick.
Closes#2543
Co-authored-by: Mibayy <mibayy@users.noreply.github.com>
ResponseStore.put() and .delete() now remove conversations rows that
reference evicted or deleted response IDs, preventing 404 errors when
a conversation name is reused after its backing response was purged.
Adds regression tests for delete, eviction, and handler-level reuse.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
was_auto_reset, auto_reset_reason, and reset_had_activity were not
included in SessionEntry.to_dict() / from_dict(), so a gateway restart
between session expiry and the user's next message would silently drop
the auto-reset notification and context note.
Add the three fields to the serialization roundtrip with safe defaults
(False / None / False) so existing sessions.json files load cleanly.
Add three roundtrip tests to test_session_reset_notify.py.
#25975 (salvaging #24403) clamped decorative scrollback Panels and
streaming box rules to `max(32, min(width, 56))` as a defense against
terminal-emulator reflow when columns shrink. On any modern wide
terminal this made the response/reasoning borders look stubby — 56
cols inside a 200-col viewport.
#26137 (salvaging #25981, by @OutThisLife) landed a more fundamental
fix: prompt_toolkit's `_output_screen_diff` is monkey-patched so its
reserve-vertical-space cursor move no longer pushes chrome into
scrollback at all. With that in place, the clamp is no longer
load-bearing for the chrome-into-scrollback class of bugs — the
remaining risk is purely cosmetic reflow of *already stamped*
Panel borders during an aggressive column shrink, which we now
accept as a tradeoff for restoring proper full-width rendering.
Changes:
- `_scrollback_box_width()` returns `max(32, width)` (just the floor,
no upper cap). All 10 call sites stay valid.
- Updated `test_scrollback_box_width_caps_to_resize_safe_value` to
the new `test_scrollback_box_width_returns_viewport_width` asserting
full-width passthrough above the 32-col floor.
Floor of 32 is kept so `'─' * (w - 2)` math stays positive on tiny
terminals.
Refs #18449#19280#22976 (the original reflow class) and #25975
(the clamp this reverts).
Adds 16 unit tests covering the light/dark terminal detection path
introduced in the previous commit:
- Env override priority (HERMES_LIGHT, HERMES_TUI_LIGHT,
HERMES_TUI_THEME, HERMES_TUI_BACKGROUND, COLORFGBG)
- Detection cache stickiness
- _maybe_remap_for_light_mode() no-op in dark mode
- Known dark-mode color remap (#FFF8DC -> #1A1A1A etc)
- Case-insensitive lookup
- Unknown color passthrough
- Status-bar paired colors (#C0C0C0, #888888, #555555, #8B8682) are
intentionally NOT remapped — regression guard for the patch-11 fix,
since remapping them would produce dark-on-dark on the status bar's
navy bg
- SkinConfig.get_color() wrapper is installed and idempotent
- SkinConfig.get_color() does remap in light mode and passes through
in dark mode
We don't try to fake an OSC 11 reply — that path is exercised
end-to-end in real Terminal.app; the env-override path covers the
algorithmic logic.
The ACP Registry schema supports uvx as a first-class distribution method
alongside npx and binary. Pointing the registry directly at the existing
hermes-agent PyPI release removes:
- the @nousresearch npm scope (we don't own it)
- a separate npm publish step on every weekly release
- 90 lines of Node launcher + tests in packages/hermes-agent-acp/
The Zed registry now installs Hermes via:
uvx --from 'hermes-agent[acp]==<version>' hermes-acp
This is the same command the npm launcher was shelling out to anyway, so
end-user behavior is unchanged. Registry CI validates the PyPI URL +
version-pin exact match automatically.
Changes:
- acp_registry/agent.json: distribution.npx -> distribution.uvx
- delete packages/hermes-agent-acp/ entirely
- scripts/release.py: drop npm-launcher bump paths, keep manifest lockstep
- tests/acp/test_registry_manifest.py: assert uvx shape + version pin
- tests/scripts/test_release_acp_registry.py: rewrite for uvx-only shape
- docs (user-guide + dev-guide): drop all npm-launcher references
- delete docs/plans/acp-registry-zed-integration.md (stale, npm-shaped)
Validated against agentclientprotocol/registry agent.schema.json via
jsonschema. hermes-agent==0.13.0 is already live on PyPI.
The ACP Registry manifest (acp_registry/agent.json), the npm launcher
package.json, and the launcher's HERMES_AGENT_VERSION constant must all
match pyproject.toml exactly — tests/acp/test_registry_manifest.py
enforces this lockstep.
Without a release-script hook, the next weekly version bump fails that
test until someone hand-edits four files. Extend update_version_files()
to drive the ACP bump alongside __init__.py and pyproject.toml, and
add tests covering the lockstep and the missing-files no-op path.
Also map adam.manning@gmail.com -> am423 for the salvage commit.
The 'sessions' command has been registered in the central command
registry since #20805 (May 2025) and surfaces in /help and tab-completion,
but the classic CLI's process_command() never had an elif branch for it.
The canonical name fell through and printed 'Unknown command: sessions'.
The TUI side was wired up correctly via the SessionPicker overlay; only
the legacy CLI was missing the dispatch.
Adds _handle_sessions_command() which mirrors /resume's no-arg behavior
inline (the CLI has no overlay primitive equivalent to the TUI picker):
- /sessions and /sessions list → print the recent-sessions table
- /sessions <id_or_title> → delegates to _handle_resume_command
Includes regression tests covering the dispatcher wiring (the original
bug) plus the three handler branches.
Pre-existing diagnostics below an edit point used to surface as 'LSP
diagnostics introduced by this edit' whenever the edit deleted or
inserted lines. The delta-filter key included the diagnostic's
range, so the same logical error reported at a different line in
the post-edit snapshot looked like a brand new diagnostic.
Concrete case: deleting 14 lines in cli.py caused Pyright errors at
lines 9873, 10590, 12413, 13004 (unrelated to the edit) to be
reported as introduced by it.
Fix: build a piecewise-linear line-shift map (via difflib's
SequenceMatcher) from pre and post content, and remap baseline
diagnostics into post-edit coordinates before the set-difference.
Diagnostics in deleted regions drop out cleanly; diagnostics below
the edit shift by the right amount; diagnostics above are untouched.
The strict (range-aware) equality key stays — so a genuinely new
instance of an identical error class at a different line still
surfaces as new.
Pieces:
- agent/lsp/range_shift.py — build_line_shift, shift_diagnostic_range,
shift_baseline. Pure functions, no LSP state.
- agent/lsp/manager.py — LSPService.get_diagnostics_sync gains an
optional line_shift kwarg; baseline is shift_baseline'd before
computing the seen-set. _diag_key keeps the strict range key.
- tools/file_operations.py — write_file captures pre_content for any
LSP-handled extension (not just LINTERS_INPROC) and passes pre/post
to _maybe_lsp_diagnostics, which builds the shift map.
- New _lsp_handles_extension helper guards the pre_content read.
Trade-offs preserved:
- Genuinely new same-class errors at different lines still surface
(content-only key would have swallowed them).
- Pre-existing errors at unshifted positions still get filtered
(covered by the strict-key path with no shift).
- Best-effort: when pre_content can't be captured (file didn't
exist, permissions), the unshifted comparison still catches
most pre-existing errors; the edge case it misses is a new file
with a non-empty baseline, which is structurally impossible.
Follow-up to snav's PR #25463 contribution: flip default to on, broaden
scope so backfill fires whenever require_mention gates the bot (not just
shared-session channels).
Why:
- The mention-gate creates a session-transcript gap regardless of whether
the channel is shared or per-user. In per-user sessions, Alice's session
is still missing other participants' messages and her own pre-mention
messages — backfill fills both gaps.
- Threads naturally scope to thread-only history because discord.py's
channel.history() on a thread returns only that thread's messages.
- DMs still skip — every DM triggers the bot, so the session transcript
is already complete.
Changes:
- hermes_cli/config.py: discord.history_backfill default → true
- gateway/platforms/discord.py: drop the _is_shared gate, keep _is_dm
skip and _needed_mention gate; env var DISCORD_HISTORY_BACKFILL
default → 'true'
- cli-config.yaml.example + website docs: update defaults and prose;
add the DISCORD_HISTORY_BACKFILL / _LIMIT env var rows that were
documented in the PR description but missing from the env-var table
- tests/gateway/test_discord_free_response.py:
- flip test_discord_per_user_channel_does_not_backfill →
test_discord_per_user_channel_backfills_too (new behavior)
- add test_discord_dm_does_not_backfill (DM skip is invariant)
- give FakeThread a no-op history() so existing thread tests don't hit
a fake discord.Forbidden when backfill now fires on threads too
Tests: 160/160 in target files; 400/400 across all tests/gateway/ -k discord.
Adds optional channel-context backfill for Discord shared-channel sessions
so the agent can see recent messages it missed between its own turns
(typically when require_mention=true filters out most traffic).
Previously the agent only saw the @mention message that triggered it, which
led to disorienting replies in active multi-user channels where the
conversation context was invisible. With backfill enabled, a configurable
number of recent messages are fetched per-turn and prepended to the trigger
message as a context block, kept separate from sender-prefix logic so
attribution remains clean.
This re-opens the work from #13063 (approved by @OutThisLife on 2026-04-20,
closed when I closed the branch to address the simpolism:main head-branch
issue plus an ordering bug I caught later in live use). Filing against the
freshly-rewritten problem statement in #13054 so the design is grounded in
the failure mode rather than the implementation shape.
The implementation follows the **push-mode last-self-anchored** design from
the two options laid out in #13054. See the issue for the trade-off
discussion vs pull-mode (#13120 was an earlier closed PR using that shape).
Treating this as a reference implementation — happy to rewrite as
last-trigger anchoring or as a hybrid with #13120 if maintainers prefer.
Changes:
- gateway/platforms/discord.py:
- new `_discord_history_backfill()` / `_discord_history_backfill_limit()`
helpers (config.extra > env > default), mirroring the existing
`_discord_require_mention()` shape
- new `_fetch_channel_context()` that scans `channel.history()` backwards
from the trigger to the bot's last message (or limit), formats as
`[Recent channel messages] / [name] msg / ...`, respects DISCORD_ALLOW_BOTS,
skips system messages
- per-channel `_last_self_message_id` cache to narrow the fetch window
on hot paths (avoids full history scan when the bot has spoken recently)
- **IMPORTANT**: passes `oldest_first=False` explicitly to `channel.history()`.
discord.py 2.x silently flips the default to True when `after=` is supplied,
which would select the EARLIEST N messages after our last response instead
of the LATEST N before the trigger. In high-traffic windows this would
return stale tool traces and drop the actual final answer the user is
asking about. See regression test below. Caught in live use during a
Codex tool-trace burst on May 13 2026.
- gateway/config.py: discord_history_backfill + discord_history_backfill_limit
settings + yaml→env bridge
- gateway/platforms/base.py: channel_context field on MessageEvent
- gateway/run.py: prepend channel_context after sender-prefix so the
[sender name] tag applies to the trigger message alone, not to the backfill
- hermes_cli/config.py: defaults for new discord.history_backfill and
discord.history_backfill_limit keys
- cli-config.yaml.example: documented defaults
- tests/gateway/test_discord_free_response.py: 7 new tests covering
cold-start backfill, self-message stop boundary, other-bot filtering,
cache hot-path narrowing, stale-cache fallback, shared-channel +
per-user backfill paths, and the ordering regression test
(`test_fetch_channel_context_cache_uses_latest_window_when_after_set`)
- tests/gateway/test_config.py: yaml→env bridge tests
- tests/gateway/test_session.py: prefix-order edge cases
- website/docs/user-guide/messaging/discord.md: env vars + config keys +
usage docs
Tested on Ubuntu 24.04 — empirically validated in my own multi-bot Discord
research server for the past three weeks.
Fixes#13054
Supersedes #13063 (closed)
Adds 'hermes proxy start' — a local HTTP server that lets external apps
(OpenViking, Karakeep, Open WebUI, ...) use a Hermes-managed provider
subscription as their LLM endpoint. The proxy attaches the user's real
OAuth-resolved credentials to each forwarded request, refreshing them
automatically; the client can send any bearer (it gets stripped).
Ships with one adapter — Nous Portal. The UpstreamAdapter ABC and
registry in hermes_cli/proxy/adapters/ are designed for additional
OAuth providers to plug in by name without server changes.
Commands:
hermes proxy start [--provider nous] [--host 127.0.0.1] [--port 8645]
hermes proxy status
hermes proxy providers
Allowed Portal paths: /v1/chat/completions, /v1/completions,
/v1/embeddings, /v1/models. Anything else returns 404 with a clear
error pointing at the allowed list.
aiohttp is gated like gateway/platforms/api_server.py (try-import,
clean runtime error if missing). No new core dependency.
Tests: 24 unit tests + 1 separate E2E that spawns the real subprocess
and verifies the upstream receives the right bearer with the client's
header stripped.
When the terminal shrinks, already-printed box-drawing rules (response,
reasoning, streaming TTS, background-task Panels) reflow into multiple
narrower rows — visible as duplicated horizontal separators / ghost
lines in scrollback. Similarly, prompt_toolkit redraws a fresh status
bar on SIGWINCH on top of one the terminal just reflowed, producing
double-bar artifacts on column shrink.
Two surgical changes:
1. Decorative scrollback boxes now use a new
`HermesCLI._scrollback_box_width()` helper that clamps to
`max(32, min(width, 56))`. The live TUI footer is unaffected and still
uses the full width. Covers: streaming response box (open + close),
reasoning box (open + close, both streaming and post-stream paths),
streaming-TTS box close, final-response Rich Panel, and the
background-task Rich Panel.
2. `_recover_after_resize()` now also sets a new
`_status_bar_suppressed_after_resize` flag so the dynamic status bar
and both input separator rules stay hidden until the next user input.
The flag is cleared in the process loop the moment the user submits
their next prompt, restoring chrome cleanly.
Tests:
- New `test_input_rules_hide_after_resize_until_next_input` covers the
flag's effect on rule heights.
- New `test_scrollback_box_width_caps_to_resize_safe_value` covers the
helper at floor / cap / mid-range / overflow.
- Existing resize-recovery test extended to assert the flag flips.
Refs: #18449#19280#22976
Salvage of #24403.
Co-authored-by: Szymonclawd <szymonclawd@mac.home>
When codex app-server fails outside the OAuth-classified path
(non-auth turn/start errors, plain TimeoutErrors, generic turn-ended
status, subprocess silently exits, hard deadline timeout), the user
got a bare 'Internal error' / 'turn/start failed: ...' with no
context. Diagnosing config/provider/auth-bridge issues forced a
re-run with verbose codex flags.
Add a _format_error_with_stderr helper that appends the last few
stderr lines via agent.redact.redact_sensitive_text(force=True),
and use it at every catch-all error site:
- ensure_started() failures (codex init / thread/start) now return
a TurnResult.error with should_retire=True instead of bubbling
- non-OAuth turn/start CodexAppServerError / TimeoutError
- subprocess-died branch (previously dumped raw stderr_blob[-300:]
with no redaction — a leak risk)
- turn ended with non-completed status
- hard turn-timeout deadline
OAuth-classified failures and the post-tool quiet watchdog already
produce clean hints and stay unchanged. The redactor catches sk-*,
gh*_*, Authorization: Bearer, query-string tokens, JWTs, private
keys, etc., so provider error payloads can't leak into chat output
or trajectories.
Inspired by openclaw#80718, adapted for our app-server transport.
When the stream consumer's got_done handler successfully delivers the
final response content via _send_or_edit but the subsequent edit
(e.g. cursor removal) fails, final_response_sent remains False even
though the user has already received the final answer. The gateway's
fallback send path then re-delivers the same content, causing the
user to see the response twice on Telegram.
Introduce a new _final_content_delivered flag on the stream consumer,
set by the got_done handler when the final content has reached the
user. The _run_agent suppression logic now treats this flag as an
additional signal (alongside final_response_sent and
response_previewed) that final delivery is already complete.
This preserves the existing behavior for intermediate-text-only
streams (where already_sent=True but no final content has been
delivered) — those still receive the gateway's fallback send, matching
the test expectation in test_partial_stream_output_does_not_set_already_sent.
Adds TestFinalContentDeliveredSuppression with two cases covering
both the suppression (content delivered + edit failed) and the
non-suppression (intermediate text only) branches.
`hermes config set gateway.streaming.*` writes the streaming block
nested under a `gateway:` key in config.yaml, but the config loader
only checked for a top-level `streaming:` key — silently ignoring
the nested variant.
Fall back to `yaml_cfg['gateway']['streaming']` when the top-level
key is absent, matching the pattern already used for other nested
config sections.
Closes#25676
WhatsApp pseudo-chats (Status updates / Stories, Channels / Newsletters,
broadcast lists) were being routed through the full agent pipeline. A
user's gateway.log showed the agent replying to a contact's Story
('status@broadcast') with 345 chars plus title-generation cost, which
also shows up in the contact's status feed.
Drop these JIDs at _should_process_message() before the policy gate so
they're filtered regardless of dm_policy or allowlist state. Covers:
- status@broadcast (Stories)
- *@newsletter (Channels)
- *@broadcast (broadcast lists, future-proofing)
The bridge.js already filters these on the fromMe outbound path, but
inbound events on self-chat mode skipped that check.
Tests:
- status@broadcast dropped on open policy
- broadcast filter wins over allowlisted senders
- real DMs still pass through
- helper unit cases (case-insensitive, whitespace-tolerant)
26/26 tests/gateway/test_whatsapp_group_gating.py pass; 59/59 adjacent
WhatsApp test suites pass.
The Debian/Ubuntu branch of install_node_deps() ran 'npx playwright install
--with-deps chromium' unconditionally. Playwright invokes sudo interactively
to apt-install Chromium's system libraries, which blocks the installer for
non-sudo users (systemd service accounts, unprivileged operator users) on
an unsatisfiable password prompt.
Changes:
- install.sh: gate --with-deps behind a sudo capability check on the apt
branch (matches the existing Arch/pacman branch pattern). Non-sudo users
fall back to 'npx playwright install chromium' alone and the installer
prints the exact 'sudo npx playwright install-deps chromium' command an
administrator can run separately.
- install.sh: add --skip-browser (alias --no-playwright) to skip the
Playwright step entirely for headless installs that don't need browser
automation. Mirrors the existing --no-venv / --skip-setup shape.
- installation.md: add a 'Non-Sudo / System Service User Installs' section
covering the admin/service-user split, the --skip-browser flag, and the
~/.local/bin PATH gotcha (the root cause of the 'No module named dotenv'
error users hit when running the repo source 'hermes' script with system
Python instead of the venv launcher).
- test_install_sh_browser_install.py: regression coverage for the
--skip-browser flag and the sudo-gate on the apt branch.
Reported by @ssilver in Discord.
_make_stream_chunk built delta_kwargs with only `role`, so a reasoning-only
chunk produced a SimpleNamespace without a `.content` attribute. Downstream
consumers that read `delta.content` then raised AttributeError on Gemini 2.5
Flash, where the thinking delta arrives before any content delta.
Seed `content`, `tool_calls`, `reasoning`, and `reasoning_content` as None
up front, matching the pattern already used in gemini_native_adapter.py.
Key-present arguments still override the defaults.
Fixes#24974
References: Related open PR #24984 (luyao618) applies the same 1-line fix; this PR adds a regression test that #24984 omits
Co-Authored-By: Claude <noreply@anthropic.com>
Pyproject's [all] extra was slimmed down in May 2026 — ~20 optional
backends moved to tools/lazy_deps.py and only install on first use.
hermes update runs uv pip install -e .[all] which doesn't touch any of
them, so pin bumps in LAZY_DEPS (CVE response, transitive fixes) were
silently ignored on already-activated backends.
Two changes:
1. _is_satisfied() now parses the spec and checks the installed version
against the constraint via packaging.specifiers. Previously it
returned True the moment the package name was importable, which made
ensure() a name-presence gate rather than a version-pin gate.
2. New active_features() / refresh_active_features() pair: lists every
feature with at least one of its packages currently installed, then
re-runs ensure() on each. Refresh is invoked at the end of
_cmd_update_impl, right after the [all] install completes. Cold
backends (never activated) stay quiet — no churn for them.
Output during update is one summary block:
→ Refreshing 4 active lazy backend(s)...
↑ 1 refreshed: provider.anthropic
✓ 3 already current
or
⚠ memory.honcho failed to refresh: <pip stderr>
Failures never raise out of update — backends keep their previously-
installed version and we tell the user to rerun once upstream is fixed.
security.allow_lazy_installs=false is honored: features get marked
"skipped" with the reason shown.
Tests: 18 new unit tests covering version-aware satisfaction (exact pin,
range, extras blocks, missing package, malformed spec), active feature
discovery, and refresh status reporting. All 61 lazy_deps tests pass.
Adds regression tests pinning web search into the WhatsApp and api-server
default platform-coverage toolsets. Pure test additions, no runtime change.
Salvage of the test-addition commit from #25692 by @wesleysimplicio.
(The AUTHOR_MAP fixup commit from the same PR landed separately as
529ec85c7.)
Mirrors openclaw beta.8's app-server resilience fixes so a stuck codex
subprocess can't burn the full turn deadline and so users get a
`codex login` pointer instead of raw RPC errors when their token expires.
- TurnResult.should_retire signals the caller to drop+respawn codex.
- Deadline-hit path and dead-subprocess detection set should_retire so
the next turn doesn't ride a CPU-spinning or auth-broken process.
- Post-tool watchdog (post_tool_quiet_timeout=90s): if a tool item
completes and codex goes silent past the threshold without further
output or turn/completed, fast-fail instead of waiting the full 600s.
Resets on any non-tool activity so normal think-after-tool flows are
not affected.
- <turn_aborted> and <turn_aborted/> in agent text are treated as
terminal — some codex builds tear down a turn that way without
emitting turn/completed.
- _classify_oauth_failure() inspects RPC error message + stderr tail
for invalid_grant / token refresh / 401 / etc. and rewrites
user-facing errors to 'run codex login'. Conservative: generic
failures still surface verbatim. Fires at turn/start failure,
turn/completed failure, and dead-subprocess paths.
- thread/start cross-fill: tolerate thread.id, thread.sessionId,
top-level sessionId/threadId so future codex schema drift doesn't
KeyError us at handshake.
- run_agent.py: when run_turn returns should_retire=True OR raises,
close + null self._codex_session so the next turn respawns.
Tests: +30 cases across session + integration suites.
tests/agent/transports/test_codex_app_server_session.py 50/50 pass
tests/run_agent/test_codex_app_server_integration.py 27/27 pass
Broader codex scope (transports + cli runtime/migration) 376/376 pass
The cherry-picked PR over-indented the edit_message_text block for
the mm: (model selected → switch) success path so the confirmation
edit lived inside the preceding 'except Exception as exc' branch and
only fired when the callback raised. Dedent the try/except back to
12-space indent so it runs after the callback succeeds, restoring
the original flow that removes the inline buttons and shows the
'Switched to ...' confirmation.
Add a regression test (test_model_selected_edits_message_on_success)
that asserts edit_message_text is awaited and the result text is
routed through format_message (MARKDOWN_V2 + backtick survival).
Add phuongvm to scripts/release.py AUTHOR_MAP.
Use MarkdownV2 formatting for Telegram callback follow-ups and interactive prompts where dynamic names or user text can break legacy Markdown parsing. Add regression coverage for reload-mcp, model picker, approval callbacks, and update prompts.
Brings Discord to parity with Telegram on the clarify tool's interactive
UX. Overrides BasePlatformAdapter.send_clarify on DiscordAdapter to attach
a button view when choices are present.
- ClarifyChoiceView: one discord.ui.Button per choice (max 24, Discord's
25-component view cap leaves one slot for Other) plus a final
'Other (type answer)' button.
- Numeric click -> tools.clarify_gateway.resolve_gateway_clarify(
clarify_id, choice_text) using the canonical choice text from the
gateway entry (falls back to the button label if the entry vanished).
- Other click -> tools.clarify_gateway.mark_awaiting_text(clarify_id) so
the gateway's text-intercept captures the next user message in this
session as the response.
- Auth via the shared _component_check_auth helper (same OR-semantics as
ExecApprovalView / SlashConfirmView / UpdatePromptView / ModelPickerView).
- Open-ended (no choices) path renders the prompt as a plain embed and
relies on the existing text-intercept resolution.
- Single-use: first valid click disables every button and updates the
embed footer with who answered and what they chose.
No changes to BasePlatformAdapter.send_clarify or the gateway's
clarify_callback wiring -- the existing scaffolding already drives all
adapters; Discord just inherits the default text fallback today and gains
buttons by virtue of this override.
Test conftest extended: _FakeEmbed gains add_field() / set_footer() stubs
so tests can construct embedded views without monkey-patching per-test.
Original PR: #19249 by @LeonSGP43. This is a reshape of the contributor's
work onto current main's clarify infrastructure (clarify_id + entry-based
resolution shared with Telegram, instead of a parallel on_answer-closure
mechanism). The button view structure and UX shape are preserved.
Tests: 14 new tests in tests/gateway/test_discord_clarify_buttons.py.
391/391 existing Discord gateway tests still pass.
Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>
setup_path() writes the user-facing hermes shim with `cat >`, which
follows existing symlinks. Older installs created
`$command_link_dir/hermes` as a symlink to `$HERMES_BIN`
(`venv/bin/hermes`), so re-running install.sh stomped the pip entry
point with a bash shim that exec'd itself in an infinite loop.
`rm -f` the link target before writing so the shim lands at
`$command_link_dir/hermes` and the venv entry point is left intact.
Adds a regression test that reproduces the symlink-stomp end-to-end
(creates the symlink, drives the real shim-write block from setup_path,
asserts the venv pip script body survives and the shim is now a regular
file). Both new assertions fail on origin/main and pass with the fix.
Closes#21454.
Follow-up to Alex-wuhu's NovitaAI provider commit. Adds:
- _pricing_cache hit/write in _fetch_novita_pricing (was missing — every
pricing fetch was re-hitting the network), mirroring the
fetch_ai_gateway_pricing pattern. force_refresh now also propagates
from get_pricing_for_provider.
- TestNovitaProvider in tests/hermes_cli/test_api_key_providers.py
covering profile load, alias resolution, registry auto-registration,
model list parity between main.py and models.py, _URL_TO_PROVIDER,
_PROVIDER_PREFIXES, context_size in _CONTEXT_LENGTH_KEYS, pricing
unit conversion, and pricing cache behavior.
- AUTHOR_MAP entry for yanglongwei06@gmail.com → @Alex-yang00.
Previously ACP dangerous-command approvals mixed an invalid ACP
payload shape with partial Hermes option mapping, and the callback
plumbing was shared across worker threads. This commit uses ACP
tool-call updates, preserves Hermes once/session/always semantics,
and scopes approval callbacks to the current worker thread.
- Build permission requests with `update_tool_call` and unique
`perm-check-*` ids in `acp_adapter/permissions.py`
- Keep ACP option mapping explicit and fail closed on unknown outcomes
or request failures
- Set approval callbacks inside the ACP executor worker and read them
from thread-local state in `tools/terminal_tool.py`
- Replace duplicated ACP bridge coverage with focused tests in
`tests/acp/test_permissions.py` and add a thread-local callback test
The salvaged regression test called skin.get_spinner_list() which
doesn't exist on SkinConfig. Replace with direct dict access on
skin.spinner — same intent (verify default empty spinner is preserved
when user override is invalid).
* feat(goals): /subgoal — user-added criteria appended to active /goal
Layers a /subgoal command on top of the existing freeform Ralph judge
loop. The user can append extra criteria mid-loop; the judge factors
them into its done/continue verdict and the continuation prompt
surfaces them to the agent. No new tool, no agent self-judging — the
existing judge model just sees a richer prompt.
Forms:
/subgoal show current subgoals
/subgoal <text> append a criterion
/subgoal remove <n> drop subgoal n (1-based)
/subgoal clear wipe all subgoals
How it integrates:
- GoalState gains `subgoals: List[str]` (default []), backwards-compat
for existing state_meta rows.
- judge_goal accepts an optional subgoals kwarg; non-empty switches to
JUDGE_USER_PROMPT_WITH_SUBGOALS_TEMPLATE which lists them as
numbered criteria and asks 'is the goal AND every additional
criterion satisfied?'
- next_continuation_prompt picks CONTINUATION_PROMPT_WITH_SUBGOALS_TEMPLATE
when non-empty so the agent sees what to target.
- /subgoal is allowed mid-run on the gateway since it only touches the
state the judge reads at turn boundary — no race with the running
turn.
- Status line shows '... , N subgoals' when present.
Surface:
- hermes_cli/goals.py — field, prompt blocks, manager methods, judge weave
- hermes_cli/commands.py — /subgoal CommandDef
- cli.py — _handle_subgoal_command
- gateway/run.py — _handle_subgoal_command + mid-run dispatch
- tests/hermes_cli/test_goals.py — 15 new tests (backcompat, mutation,
persistence, prompt template selection, judge-prompt content via mock,
status-line rendering)
77 goal-related tests passing across goals + cli + gateway + tui.
* fix(goals): slash commands don't preempt the goal-continuation hook
Two findings from live-testing /subgoal:
1. Slash commands queued while the agent is running landed in
_pending_input (same queue as real user messages). The goal hook's
'is a real user message pending?' check returned True and silently
skipped — but the slash command consumes its queue slot via
process_command() which never re-fires the goal hook, so the loop
stalls indefinitely. Now the hook peeks the queue and only defers
when a non-slash payload is present.
2. The with-subgoals judge prompt was too soft — opus 4.7 said 'done,
implying all requirements met' without verifying. Tightened to
demand specific per-criterion evidence (file contents, output line,
command result) and explicitly reject phrases like 'implying it was
done.'
Live verified: /subgoal injected mid-loop now correctly forces the
judge to refuse done until the new criterion is met. Agent gets the
continuation prompt with subgoals listed, updates the script, judge
confirms done with specific evidence cited.
The cherry-picked tests from #6173 set HERMES_HOME outside Path.home()/.hermes,
which forces get_default_hermes_root() down its Docker branch and returns
HERMES_HOME directly — so _get_default_hermes_home() never resolves to the
~/.hermes directory the tests were trying to assert about.
Rewire both tests to use the real profile layout (HERMES_HOME pointing at
~/.hermes/profiles/<name>) so _get_default_hermes_home() resolves back to
~/.hermes and the default-profile fallback is actually exercised.
Surfaced by local E2E behavior-parity testing of PR vs origin/main: the
plugin-migrated dispatchers were quietly changing the error envelope
shape returned to function-calling models on unconfigured systems.
Two findings, both from per-result error wrapping bleeding into the
pre-flight configuration error path:
1. **search**: ``firecrawl.search()`` caught the
``ValueError("Web tools are not configured...")`` from
``_get_firecrawl_client()`` and returned it as
``{"success": False, "error": ...}``, losing the legacy
``{"error": "Error searching web: ..."}`` envelope that
``tool_error()`` emits on main. Models that special-case the
``error`` key still detect the failure, but the prefix is part of
the legacy contract some users rely on.
2. **crawl**: ``firecrawl.crawl()`` caught the same pre-flight
``ValueError`` and wrapped it as a per-page error inside
``results[0]``. Main short-circuits on ``check_firecrawl_api_key()``
BEFORE dispatching, so its unconfigured response is
``{"success": False, "error": "web_crawl requires Firecrawl..."}``
at the top level. The PR's per-page burying hid the failure inside
``results[]`` where models that check ``result.get("error")`` would
miss it.
Fix:
- ``plugins/web/firecrawl/provider.py``: pull
``_get_firecrawl_client()`` outside the broad ``try`` in
``search()``. Pre-flight ``ValueError`` / ``ImportError`` propagate
to the dispatcher's top-level exception handler. In-flight SDK
errors still get wrapped as ``{"success": False, ...}``.
- ``tools/web_tools.py``: mirror main's upstream availability gate in
``web_crawl_tool``. When the resolved crawl provider is
``is_available()==False``, short-circuit BEFORE dispatching with the
same top-level error shape main emits.
- ``tests/tools/test_web_providers.py``: 2 regression tests
(``TestUnconfiguredErrorEnvelopeParity``) lock in the behavior so
future plugin work can't undo this.
Verified via local subprocess-based parity test (14/14 scenarios match
origin/main shape exactly) and full 210/210 web test suite green.
The web-provider migration originally left firecrawl crawl as the only
provider-specific code remaining inline in tools/web_tools.py (~250
lines of Firecrawl-specific crawl orchestration that didn't fit the
plugin's existing surface). This commit closes that gap.
What this adds
--------------
1. plugins/web/firecrawl/provider.py: implement async ``crawl(url, **kwargs)``
- Accepts the same kwargs as the dispatcher passes to any crawl
provider (``instructions``, ``depth``, ``limit``); Firecrawl's
/crawl endpoint ignores ``instructions`` and ``depth`` so we log
and drop with a clear info message.
- Wraps the sync SDK ``crawl()`` call in asyncio.to_thread so the
gateway event loop isn't blocked on a multi-page crawl.
- Preserves the response-shape normalization across pydantic /
typed-object / dict variants that the legacy inline code did.
- Preserves per-page website-policy re-check (catches blocked
redirects after the SDK returns).
- Returns the same {"results": [...]} shape so the dispatcher's
shared LLM-summarization post-processing path works unchanged.
- Sets supports_crawl() to True so the dispatcher routes through
the plugin instead of the legacy fallthrough.
2. tools/web_tools.py: delete the entire legacy firecrawl crawl block
that used to run after "No registered provider supports crawl" —
~270 lines including:
- check_firecrawl_api_key gate + typed error
- inline SSRF + website-policy seed-URL gate (dispatcher already
does this)
- Firecrawl client setup with crawl_params
- 100+ lines of pydantic/dict/typed-object normalization
- Per-page LLM-processing loop (kept in the dispatcher's shared
post-processing path; that's where it always belonged)
- trimming + base64 image cleanup (still done in the dispatcher's
shared path)
Replaced with a single typed-error branch when no crawl-capable
provider is available: "web_crawl has no available backend. Set
FIRECRAWL_API_KEY (or FIRECRAWL_API_URL for self-hosted), or set
TAVILY_API_KEY for Tavily."
Test updates
------------
- tests/tools/test_website_policy.py:
- test_web_crawl_short_circuits_blocked_url: dispatcher seed-URL
gate still runs on web_tools.check_website_access (no change to
that patch), but the firecrawl client lockdown moved to the
plugin module — patch firecrawl_provider._get_firecrawl_client
instead of web_tools._get_firecrawl_client. The dispatcher
short-circuits before the plugin runs, so the test still passes.
- test_web_crawl_blocks_redirected_final_url: patch the per-page
policy gate at plugins.web.firecrawl.provider.check_website_access
(where it now runs) AND on web_tools (where the seed-URL gate
still runs). Patch firecrawl_provider._get_firecrawl_client for
the FakeCrawlClient injection. Both checks flow through the same
fake_check function.
- tests/plugins/web/test_web_search_provider_plugins.py:
- Update parametrized capability-flag spec: firecrawl supports_crawl
is now True.
- Add test_firecrawl_crawl_returns_error_dict_when_unconfigured —
verifies inspect.iscoroutinefunction(p.crawl) is True and that
the async crawl returns a per-page error dict (not a raise) when
FIRECRAWL_API_KEY is missing.
Verified
--------
- 218/218 web tests pass (was 173, +44 plugin tests + 1 new firecrawl
crawl test from this commit = 218 with the test deduplication).
- Compile-clean (py_compile passes on both files).
- Provider capabilities matrix confirmed end-to-end:
name search extract crawl async-extract? async-crawl?
firecrawl True True True True True
tavily True True True False False
Both crawl-capable providers exercise the dispatcher's
inspect.iscoroutinefunction async-or-sync detection.
Net diff
--------
- tools/web_tools.py: -254 lines (legacy inline crawl gone)
- plugins/web/firecrawl/provider.py: +185 lines (crawl method)
- test_website_policy.py: +14/-9 lines (patch locations)
- test_web_search_provider_plugins.py: +22/-1 lines (capability flag
+ new firecrawl crawl test)
- Total: -32 net LoC; tools/web_tools.py is now 1509 lines (was 1763
before this commit, 2227 before the migration started).
Adds 44 focused tests under tests/plugins/web/ covering the surface that
the PR #25182 web-provider migration introduced. Complements the
existing tests/tools/ coverage which is dispatcher-centric; this file is
plugin-centric and tests each plugin + the registry directly.
Test classes (44 tests, ~1.1s on 4 workers)
-------------------------------------------
TestBundledPluginsRegister (16 tests)
- All seven plugins present in the registry after
_ensure_plugins_discovered()
- Per-plugin parametrized capability-flag assertions
(brave-free / ddgs / searxng: search-only;
exa / parallel / firecrawl: search + extract;
tavily: search + extract + crawl)
- Every plugin exposes name + display_name properties
- Every plugin returns a picker-compatible get_setup_schema() dict
TestIsAvailable (7 tests)
- Each premium plugin reports is_available()==False when its env var is
absent and True once set (brave-free / searxng / tavily / exa /
parallel)
- firecrawl recognizes either FIRECRAWL_API_KEY or FIRECRAWL_API_URL
as a "configured" signal
- ddgs is the always-on fallback and must not raise from is_available()
TestRegistryResolution (4 tests)
- Option B semantics validated end-to-end:
1. Explicit configured provider wins even when is_available()==False
(dispatcher surfaces typed credential errors, no silent switch)
2. Unknown/typo name falls back to first available legacy-preference
provider
3. Asking for extract via a search-only backend falls back to an
extract-capable available provider (capability-incompatible
branch in _resolve())
4. No config + no credentials → None (or ddgs if installed)
TestAsyncExtractDispatch (4 tests)
- parallel + firecrawl extract() are coroutine functions (async path
in dispatcher uses await)
- exa + tavily extract() are sync (dispatcher wraps in
asyncio.to_thread)
TestErrorResponseShapes (7 tests)
- Plugins return typed error dicts (success=False + "error" key) when
credentials are missing, never raise
- async extract() returns list of per-URL error dicts
- tavily crawl() returns {"results": [{"error": ...}]} on missing
credentials
Design notes
------------
- All tests use real imports of plugin modules — no mocking of provider
classes themselves — so they catch drift in the ABC, registry, and
glue layer simultaneously. Per the hermes-agent-dev skill's E2E
testing guidance.
- The autouse _isolate_env fixture clears every web-provider env var
before each test so is_available() reflects the test's setup.
- Resolution tests use the lower-level _resolve() directly rather than
rebuilding the HERMES_HOME config dance — same observable behavior,
no sys.modules.pop side-effects that would break the ABC isinstance
check inside ctx.register_web_search_provider().
Removes the legacy in-tree provider scaffolding that PR #25182 fully
replaced with the plugin architecture:
tools/web_providers/__init__.py (6 lines)
tools/web_providers/base.py (89 lines — old ABCs)
tools/web_providers/ARCHITECTURE.md (73 lines — old design doc)
These were the staging-ground ABCs and provider modules that the
plugin migration absorbed. All seven web providers now implement the
single :class:`agent.web_search_provider.WebSearchProvider` ABC and
live under ``plugins/web/<vendor>/``. Nothing else in the tree imports
``tools.web_providers`` — verified via grep before deletion.
Test migration (tests/tools/test_web_providers.py)
--------------------------------------------------
Rewrote ``TestWebProviderABCs`` to test the new unified ABC at
:mod:`agent.web_search_provider`:
- test_cannot_instantiate_abc_directly — abstract ``name`` + ``is_available``
- test_concrete_search_only_provider_works — exercise default
``supports_extract=False`` / ``supports_crawl=False`` flags
- test_concrete_multi_capability_provider_works — exercise all three
capabilities, async extract supported (declared sync here for
simplicity; real plugins like parallel + firecrawl use async)
- test_search_only_provider_skips_extract_and_crawl — verify
``supports_*()`` flags default to False so search-only providers
don't have to implement extract() or crawl()
The 9 other tests in the file (per-capability backend selection,
DEFAULT_CONFIG merge, dispatcher routing) test public helpers in
``tools.web_tools`` that still exist and pass unchanged.
agent/web_search_provider.py docstring updated to reflect that the
legacy ABCs no longer exist; the response-shape contract is preserved
bit-for-bit so external consumers see no behavioral change.
Net diff
--------
- tools/web_providers/ removed (-168 lines)
- tests/tools/test_web_providers.py rewritten ABC section (+78/-30 net,
same coverage, new API)
- agent/web_search_provider.py docstring (-3/+5 lines)
Verified
--------
- 173/173 targeted web tests pass
- 12/12 ABC contract tests pass with the new interface
- No remaining grep hits for ``tools.web_providers`` outside of
intentional historical references in plugin docstrings.
Two regressions discovered by running the full tests/tools/ suite after
the dispatcher cutover, both fixed in this commit:
1. web_crawl_tool incorrectly errored "search-only" for firecrawl
---------------------------------------------------------------------
The cutover treated any provider with supports_crawl()==False as a
search-only backend and returned the typed search-only error. But
firecrawl can crawl via the legacy multi-page-extract path inside
web_crawl_tool — it just doesn't expose supports_crawl on the plugin
(adding native firecrawl crawl is a clean follow-up).
Fix: only emit the search-only error when the provider supports
NEITHER crawl NOR extract (brave-free / ddgs / searxng). When the
provider supports extract but not crawl (firecrawl), fall through to
the legacy firecrawl-via-extract path below.
2. firecrawl plugin's check_website_access wasn't patchable
---------------------------------------------------------------------
The plugin imported `from tools.website_policy import check_website_access`
INSIDE the extract() function body, so monkeypatching the name on
plugins.web.firecrawl.provider had no effect — the inner import re-bound
the name on every call.
Fix: hoist the import to module level. Cheap (website_policy itself
has no heavy deps) and makes the standard
monkeypatch.setattr(firecrawl_provider, "check_website_access", ...)
pattern work.
Test updates (tests/tools/test_website_policy.py — 4 tests):
- test_web_extract_short_circuits_blocked_url
- test_web_extract_blocks_redirected_final_url
Both: patch the gate at plugins.web.firecrawl.provider (where it
runs after migration) and force the firecrawl plugin to be the
active extract provider via FIRECRAWL_API_KEY.
- test_web_crawl_short_circuits_blocked_url
- test_web_crawl_blocks_redirected_final_url
Both: unchanged — the dispatcher-level gate at tools.web_tools.py
line 1651 still uses the imported `check_website_access` name and
the firecrawl-fallthrough path is exercised as before.
Verified: 22/22 tests/tools/test_website_policy.py pass.
Cuts over web_search_tool, web_extract_tool, and web_crawl_tool in
tools/web_tools.py to dispatch through agent.web_search_registry
instead of the legacy hardcoded if-elif backend chains.
Per-tool changes:
web_search_tool (sync)
Replace 5 backend branches (parallel, exa, registry-3-providers,
tavily, firecrawl-fallthrough) with a single registry path:
1. _get_search_backend() resolves the configured name
2. _wsp_get_provider(name) for explicit-config-wins semantics
3. get_active_search_provider() fallback for typo / unknown name
4. provider.search(query, limit) — sync for all 7 providers
web_extract_tool (async)
Replace 4 backend branches (parallel-async, exa-sync, tavily-sync,
search-only-error, firecrawl-perurl-loop) with:
1. Same provider resolution as search.
2. When configured backend IS registered but doesn't support
extract (search-only providers like brave-free), surface a
typed "search-only" error matching the legacy text — tests
assert that wording.
3. inspect.iscoroutinefunction(provider.extract) detects sync vs
async: parallel + firecrawl are async; exa + tavily are sync.
Sync extracts run in asyncio.to_thread() so we don't block.
web_crawl_tool (async)
Replace tavily-specific branch + search-only-error block with:
1. _wsp_get_provider(backend) — explicit config first
2. Search-only typed error when the configured name doesn't
support crawl (matches legacy phrasing)
3. get_active_crawl_provider() fallback otherwise
4. provider.crawl(url, **kwargs) — async-or-sync dispatch as above
5. Response post-processing (LLM summarization, trimming) stays
unchanged — it's not provider-specific.
When no plugin advertises supports_crawl, falls through to the
existing Firecrawl-via-web-summarize path below (unchanged).
Test updates (2 tests in tests/tools/test_web_tools_config.py):
- test_web_search_clamps_limit_before_backend_call:
patch("tools.web_tools._parallel_search") -> patch the registry
provider returned by agent.web_search_registry.get_provider
- test_search_error_response_does_not_expose_diagnostics:
patch("tools.web_tools._get_firecrawl_client") -> same pattern
Tests unchanged (still pass):
- All TestXBackendWiring classes (test _get_backend / _is_backend_available
config-resolution, independent of dispatch)
- All TestXSearchOnlyErrors classes (test the search-only error path
via web_extract_tool / web_crawl_tool — error text preserved)
- 141 passing web tests total, 0 regressions.
Dead-code cleanup deferred to a follow-up commit so this diff stays
focused on the cutover. After this commit:
- tools.web_tools._exa_search / _exa_extract / _parallel_search /
_parallel_extract / _tavily_request / _normalize_tavily_* /
_get_firecrawl_client / _extract_web_search_results /
_extract_scrape_payload / _to_plain_object / _normalize_result_list
are no longer called by the dispatchers, but still exist.
- The config-resolution layer (_get_backend, _is_backend_available,
_is_tool_gateway_ready, _has_direct_firecrawl_config) IS still in
use and must stay.
- The Firecrawl proxy and check_firecrawl_api_key are still imported
by integration tests and patched by unit tests — must stay (or be
re-exported from the plugin).
Deletes tools/web_providers/{brave_free,ddgs,searxng}.py — the three
providers that moved to plugins/web/ in prior commits. tools/web_tools.py
no longer imports them (registry dispatch as of d8735963f), so removing
them is purely a cleanup pass.
Also migrates the existing tests to the new import paths:
tests/tools/test_web_providers_brave_free.py
tests/tools/test_web_providers_ddgs.py
tests/tools/test_web_providers_searxng.py
Mechanical rewrites:
- `from tools.web_providers.X import YSearchProvider`
-> `from plugins.web.X.provider import YWebSearchProvider`
- `.is_configured()` -> `.is_available()` (legacy method -> new method)
- `.provider_name()` -> `.name` (legacy method -> new property)
- `from tools.web_providers.base import WebSearchProvider`
-> `from agent.web_search_provider import WebSearchProvider`
(the subclass-check asserts membership in the new plugin-facing ABC)
- `sys.modules.delitem("tools.web_providers.ddgs")` updated to point at
`plugins.web.ddgs.provider` (cache-busting for lazy ddgs imports)
The TestXBackendWiring / TestXSearchOnlyErrors classes (covering
_is_backend_available, _get_backend, check_web_api_key, and the
"search-only" error paths in web_extract/web_crawl) are untouched —
those still test web_tools.py's backend-selection logic, which continues
to recognize the names "brave-free" / "ddgs" / "searxng" even after the
modules behind them moved to plugins.
tools/web_providers/base.py is intentionally NOT deleted by this commit
— it's the parent ABC of the legacy modules and shares its name with
agent/web_search_provider.py::WebSearchProvider. Removing it surfaces the
naming collision (see PR description Finding 0); the real migration PR
deletes it in the same commit that drops the _WEB_PLUGIN_SKIPLIST
guards in hermes_cli/tools_config.py.
Test results:
bash scripts/run_tests.sh tests/tools/test_web_providers_*.py
-> 65 passed in 3.41s (all rewritten unit tests + unchanged integration tests)
bash scripts/run_tests.sh tests/tools/test_web_*.py
-> 141 passed in 4.70s (full web test set, post-deletion)
Three call-sites in the codebase each duplicated the same config-slice
+ list_authenticated_providers + post-processing pattern:
- hermes_cli/web_server.py /api/model/options
- tui_gateway/server.py model.options JSON-RPC
- tui_gateway/server.py model.save_key JSON-RPC
This consolidates them onto hermes_cli/inventory.py:
load_picker_context() -> ConfigContext
Replaces the 17-LOC config-slice (model.{default,name,provider,
base_url}, providers:, custom_providers:) every consumer did
inline.
ConfigContext.with_overrides(*, current_provider=, current_model=,
current_base_url=) -> ConfigContext
Truthy-only overlay for TUI agent-session state on top of disk
config. Empty getattr(agent, ...) attrs MUST NOT clobber disk.
build_models_payload(ctx, *, include_unconfigured, picker_hints,
canonical_order, max_models) -> dict
Single payload builder. Delegates curation to
list_authenticated_providers (does not call provider_model_ids
per row \u2014 that pulls non-agentic models). picker_hints +
canonical_order produce the TUI ModelPickerDialog shape;
defaults match the dashboard's existing /api/model/options
contract.
Two latent bugs fixed by consolidation:
1. The dashboard read cfg.get('custom_providers') directly, missing
the v12+ keyed providers: form. Now both surfaces go through
get_compatible_custom_providers().
2. The TUI's canonical-merge keyed on is_user_defined to decide order.
Section 3 of list_authenticated_providers sets is_user_defined=True
on rows from the providers: config dict even when the slug is
canonical \u2014 that silently demoted them to the picker tail.
_reorder_canonical now keys on slug membership instead.
Stats: +666 / -145 (net +521). Module 240 LOC; 18 behavior tests.
This PR replaces the rejected #23369 (which bundled the consolidation
with new scriptable CLI surfaces \u2014 hermes models list/status, hermes
providers list \u2014 and a JSON contract that have no external user
demand). Just the refactor; the CLI surface is deferred to a separate
PR gated on actual demand.
Refs #23359.
Follow-up on the salvaged feat commit:
- Keep the constructor / config / yaml-example default at 3 so existing
gateway and CLI users see no behavioural change. PR #13754 (which this
builds on) had lowered the default to 2 to chase pre-feature parity in
the system-prompt-present case, at the cost of quietly halving the
protected head for the gateway path (which strips the system prompt
before calling compress()). With the new "system prompt is implicit"
semantics, default 3 gives every caller a stable head shape.
- agent/context_engine.py: bring the ABC's protect_first_n docstring in
line with the new semantics so plugin context engines interpret the
config key the same way the built-in compressor does.
- tests: adjust the default-value test (3, not 2) and a stale comment;
per-test protect_first_n=2/3/1 values added in PR #13754 stay as-is
since those tests fix concrete head shapes.
The number of head messages preserved verbatim across context compactions
was previously hardcoded to 3 in AIAgent.__init__. Expose it as
`compression.protect_first_n` in config, matching the existing
`protect_last_n` pattern.
Motivation: users who rely on rolling compaction for long-running sessions
had the opening user/assistant exchange pinned as head forever, which
doesn't always match how they want the session framed after many
compactions. Lowering to 1 preserves the system prompt + first non-system
message; lowering to 0 preserves only the system prompt and lets the
entire first exchange age out naturally through the summary.
Semantics: `protect_first_n` counts non-system head messages protected
**in addition to** the system prompt, which is always implicitly protected
when present. Same meaning across both code paths:
protect_first_n=0 → system prompt only (or nothing if no system message)
protect_first_n=2 → system prompt + first 2 non-system messages (default)
This unifies the CLI path (which reads messages with the system prompt at
position 0) and the gateway path (where the gateway /compress handler
strips the system prompt before calling compress() — see
gateway/run.py L9150-9154 on the parent fork). Previously these two paths
disagreed:
CLI path: protect_first_n=1 → protect system prompt only
Gateway path: protect_first_n=1 → protect first USER turn forever
In practice on long-running gateway sessions the old semantics pinned
whatever stale aside happened to be the first user message, reinserting
it into every compaction summary indefinitely.
Default chosen as 2 (not 3) so that the effective protected head count
remains 3 messages in the common case — assuming a system prompt is
present, default protection becomes system + 2 non-system = 3 total,
matching the pre-feature behaviour where `protect_first_n` was hardcoded
to protect 3 messages total. Sessions without a system prompt will see a
small behaviour change (2 protected head messages instead of 3), but this
is the rare path and the new semantics make the system-prompt-present
case the well-defined one.
Changes:
- agent/context_compressor.py: redefine protect_first_n as the count of
non-system head messages protected beyond the implicit system-prompt
guarantee; both paths converge. Constructor default updated to 2.
- hermes_cli/config.py: add `compression.protect_first_n` default (2),
matching the new semantics. `show_config` label tweaked to
'Protect first: N non-system head messages' for clarity.
- run_agent.py: read protect_first_n from config; 0 is now valid (system
prompt is always implicitly protected).
- cli-config.yaml.example: document the new key and rationale.
- tests/agent/test_context_compressor.py: cover default, override, the
end-to-end `protect_first_n=0` and `protect_first_n=1` behaviour,
the no-system-prompt (gateway) path, and the new shared-semantics
regression test.
Fixes#13751
Tested on Ubuntu 24.04.
By default, once Hermes participates in a Discord thread (auto-created on
@mention or replied in once) it auto-responds to every subsequent message
in that thread without requiring further @mentions. That's the right default
for one-on-one conversations and isolated channel threads.
But it's a confirmed footgun in multi-bot threads. When a user invokes one
bot per turn — addressing Codex first, then Hermes — every other bot in the
thread also fires on every message, burning credits and spamming the channel.
Author has hit this personally in active multi-bot research-team threads.
Add a new `discord.thread_require_mention` config key (env:
`DISCORD_THREAD_REQUIRE_MENTION`), default `false` to preserve existing
behavior. When `true`, the in-thread mention shortcut is disabled and
threads are gated the same way channels are. Explicit @mentions still pass
through as expected.
Mirrors the existing helper shape (config.extra > env > default) and the
existing yaml→env bridge pattern used by `require_mention`.
Changes:
- gateway/platforms/discord.py: new `_discord_thread_require_mention()`
helper; in_bot_thread shortcut now AND's with `not _discord_thread_require_mention()`
- gateway/config.py: bridge `discord.thread_require_mention` from config.yaml
to `DISCORD_THREAD_REQUIRE_MENTION` env var (mirrors the existing
`require_mention` bridge two lines above)
- hermes_cli/config.py: add `thread_require_mention: False` default to
DEFAULT_CONFIG['discord']
- tests/gateway/test_discord_free_response.py: 4 new tests covering default
behaviour (in-thread shortcut still works), enabled behaviour (mention
required in threads), enabled+mentioned (mention still passes through),
and yaml-via-config.extra path. Also clears DISCORD_* env vars in the
`adapter` fixture so process-env state from the contributor's shell
doesn't leak into per-test behaviour.
- tests/gateway/test_config.py: 2 new tests covering the yaml→env bridge
(both the apply-from-yaml and env-precedence-over-yaml paths)
- website/docs/user-guide/messaging/discord.md: document the new env var
+ config key with multi-bot rationale; cross-link from `auto_thread`
section
Tested on Ubuntu 24.04.
Free-response channels are intended as lightweight chat surfaces — the bot
responds to every message without requiring an @mention. But the auto-thread
gate only checked DISCORD_NO_THREAD_CHANNELS, not DISCORD_FREE_RESPONSE_CHANNELS,
so every message in a free-response channel still spawned a brand-new thread.
That turns a chat channel into a thread-spawning machine: 1 thread per message.
The user-facing docs at website/docs/user-guide/messaging/discord.md already
describe the intended behavior ("Free-response channels also skip auto-threading
— the bot replies inline rather than spinning off a new thread per message"),
so this is a code-vs-docs gap, not a design change.
Fix: OR is_free_channel into skip_thread alongside the existing no_thread_channels
check. One-line production change.
Regression test added at tests/gateway/test_discord_free_response.py:
test_discord_free_response_channel_skips_auto_thread asserts that a message
in a free-response channel never calls _auto_create_thread. Reverting the
one-line fix causes the test to fail with 'Expected mock to not have been
awaited. Awaited 1 times.' — i.e. the test demonstrates the bug concretely.
Lets platform plugins own their YAML→env config bridge instead of forcing
core gateway/config.py to know every platform's schema.
The hook receives the full parsed config.yaml and the platform's own
sub-dict, may mutate os.environ (env > YAML precedence preserved via the
standard `not os.getenv(...)` guards), and may return a dict to merge
into PlatformConfig.extra. It runs during load_gateway_config() after
the existing generic shared-key loop and before _apply_env_overrides(),
mirroring the env_enablement_fn dispatch pattern (#21306, #21331).
Pure addition — no behavior change for existing platforms. Each of the
eight platforms with hardcoded YAML→env blocks today (discord, telegram,
whatsapp, slack, dingtalk, mattermost, matrix, feishu, ~252 LOC in
gateway/config.py) can migrate in independent follow-up PRs; the
hardcoded blocks remain functional in the meantime, and their
`not os.getenv(...)` guards make them no-ops for any env var the hook
already set.
Test coverage: 10 new tests in tests/gateway/test_platform_registry.py
covering field default, callable acceptance, env mutation, extras
merge, both signature args, exception swallowing, missing/non-dict
sections, and env > YAML precedence.
Refs #3823, #24356.
Closes#24836.
Followup to PR #24182 — caught when scanning OpenClaw for recent codex
fixes we hadn't considered. OpenClaw learned the hard way (#80815) that
migrating plugins which codex itself reports as unavailable produces
config that fails at activation time.
Our /codex-runtime codex_app_server enable path queries codex's
plugin/list and migrates everything where installed=true. We were
trusting codex's installation state and ignoring its availability
field. So a plugin that's installed=true but availability=UNAVAILABLE
(broken local install) or REQUIRES_AUTH (OAuth expired or never
completed) would get an [plugins."<n>@openai-curated"] entry in
~/.codex/config.toml — and the user's first codex turn after enabling
the runtime would fail because codex refuses to activate it.
Fix: filter on availability in _query_codex_plugins(). Only emit
plugins where availability is empty (older codex versions without the
field — preserve backward compat) or explicitly AVAILABLE.
Tests:
test_plugin_discovery_skips_unavailable_plugins — verifies 4 cases:
- good-plugin (installed=True, availability=AVAILABLE) → migrated
- broken-plugin (installed=True, availability=UNAVAILABLE) → skipped
- auth-pending (installed=True, availability=REQUIRES_AUTH) → skipped
- legacy-plugin (installed=True, no availability field) → migrated
(older codex versions; preserve backward compat)
Docs:
Added bullet to 'What's NOT migrated' list in the docs page calling
out the availability filter and why.
Other OpenClaw codex PRs I reviewed but did NOT apply (with reasoning):
- #81591 (load Codex for selectable models): we resolve runtime
per-call already, no startup-time gating to fix
- #81510 (cron compatibility): we documented cron as untested; their
fix is for OpenClaw-specific cron orchestration shape
- #81223 (rotate incompatible context-engine threads): we don't
have a Lossless context engine equivalent
- #80688 (constrain sandbox): we don't have an outer-sandbox concept
- #80616 (release on turn_aborted): we already handle status=
interrupted in turn/completed correctly
- #80278 (expose activeModel in plugin SDK): not our surface
- #80792 (default destructive_actions on): we don't expose that knob
56 codex-runtime migration tests still green (+1 new).
- test_background_review_does_not_narrow_toolset_schema: review fork must
NOT pass enabled_toolsets to AIAgent (full parent schema = matching
Anthropic cache key on the 'tools' field).
- test_background_review_installs_thread_local_whitelist: the runtime
whitelist that replaces schema-level narrowing must contain memory +
skills tools and exclude terminal / send_message / delegate_task /
web_search / execute_code.
- test_review_fork_inherits_parent_cached_system_prompt: new test for
PR #17276's first root cause — the fork's _cached_system_prompt must
equal the parent's byte-for-byte.
- test_review_fork_pins_session_start_and_session_id: defensive belt-and-
suspenders for the cached-prompt inheritance.
Inverted the original test_background_review_agent_uses_restricted_toolsets
(which asserted the schema-level narrowing) — that narrowing was the
direct cause of #25322's cache miss, and the runtime whitelist replaces
its safety claim without breaking cache parity.
Refs #25322, #15204, PR #17276.
Adds set_thread_tool_whitelist / clear_thread_tool_whitelist to
hermes_cli/plugins.py. When set on the current thread, restricts which
tools can pass through get_pre_tool_call_block_message; non-whitelisted
tools are blocked with a configurable deny message.
Mirrors the per-thread approval-callback pattern already used by
set_approval_callback (tools/terminal_tool.py:190). Used by
_spawn_background_review to deny non-memory/non-skill tools at runtime
while inheriting the parent agent's full tools schema for prefix-cache
parity (see follow-up commit).
Tests cover allow / deny / clear / cross-thread isolation.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Follow-up on @pty819's t2a_v2 endpoint fix:
- Default model: speech-02 -> speech-02-hd (bare 'speech-02' is not in the
supported enum; t2a_v2 rejects it with 400). Official enum: speech-01-hd,
speech-01-turbo, speech-02-hd, speech-02-turbo, speech-2.6-hd/turbo,
speech-2.8-hd/turbo.
- Default voice: female-shaonv -> English_expressive_narrator. The
legacy speech-01-series short ID doesn't resolve cleanly on the
speech-02+ models that are now the default.
- Default base URL: api.minimaxi.com -> api.minimax.io (matches the
canonical host in the published docs; api-uw.minimax.io is the
reduced-latency alt).
- Add GroupId support via tts.minimax.group_id config or MINIMAX_GROUP_ID
env var. Some MiniMax accounts scope TTS requests by group; without it,
requests 401. Only appended when not already in the user's base_url.
Tests rewritten to cover both the default t2a_v2 path (hex-encoded audio
in JSON, nested voice_setting/audio_setting) and the legacy
text_to_speech path (raw audio bytes, flat payload). Adds coverage for
GroupId config/env wiring and error surfacing.
Also adds AUTHOR_MAP entry for pty819's GitHub-noreply email.
Slack platform-blocks native slash commands inside thread replies ("/queue
is not supported in threads. Sorry!") and there is no app-side setting to
re-enable them. As a workaround, rewrite a leading '!' to '/' for any known
gateway command before downstream processing — so '!queue', '!stop',
'!model gpt-5.4' etc. work inside Slack threads (and anywhere else).
Only the first token is checked against is_gateway_known_command(), so
casual messages like '!nice work' pass through to the agent unchanged.
Downstream pipeline (MessageType.COMMAND tagging, gateway dispatcher,
thread reply routing) is unchanged.
Adds 6 tests covering rewrite, args preservation, thread routing,
casual-message passthrough, '@bot' suffix, and plain '/' still-works.
`hermes tools` -> "All Platforms" took ~14s to render the checklist
because building the toolset labels called `get_nous_auth_status()` ~31x
transitively (`_toolset_has_keys` -> `_visible_providers` ->
`get_nous_subscription_features` -> `managed_nous_tools_enabled`).
Each call did a synchronous OAuth refresh POST to
portal.nousresearch.com (~350ms even on the failure path), so one menu
paint burned >13s of HTTP and 31 single-use Nous refresh tokens.
Secondary hot spot: every `get_env_value()` re-read and re-sanitised
the entire .env file. 116 reads with O(lines x known-keys) scanning
added ~300ms of CPU per render.
Fix is two process-level caches, both mtime-keyed so login/logout/edit
invalidate naturally:
* `hermes_cli/auth.py`: memoise `get_nous_auth_status()` for 15s keyed
on auth.json mtime. Splits `_compute_nous_auth_status()` as the
uncached impl. Adds `invalidate_nous_auth_status_cache()`.
* `hermes_cli/config.py`: memoise `load_env()` keyed on .env
(path, mtime, size). Adds `invalidate_env_cache()`, wired into
`save_env_value`, `remove_env_value`, and the sanitize-on-load
writer so writers don't return stale dicts on same-second writes.
Before/after on Teknium's box (real HERMES_HOME, no Nous login):
* "All Platforms" cold path: ~13,874ms -> ~691ms label-build
* Warm re-open within the same process: ~122ms -> ~17ms
Side benefit: stops burning a Nous refresh token on every menu paint,
which was risking the portal's reuse-detection revocation logic.
`_reconfigure_provider()` handled `image_gen_plugin_name` in both
branches (no-env-vars early return and post-env-vars) but never mirrored
the same handling for `video_gen_plugin_name`. The first-time
`_configure_provider()` path correctly routes to
`_select_plugin_video_gen_provider()`; reconfigure forgot to.
Repro:
1. Enable video_gen in `hermes tools` → Configure for All Platforms.
2. Go back into `hermes tools` → Reconfigure tool → Video Generation.
3. Pick xAI (with XAI_API_KEY already set).
4. Hit Enter at the "keep current key?" prompt.
Expected: `video_gen.provider: xai` written to config.yaml.
Actual: function returns silently; no `video_gen:` block ever written;
`video_generate` tool fails with "No video generation backend is
configured."
Fix: add the missing `video_gen_plugin_name` branch in both code paths
of `_reconfigure_provider()`, mirroring the existing
`image_gen_plugin_name` handling and the first-time configure logic.
Tests: `tests/hermes_cli/test_video_gen_picker.py` covers both branches
(env-vars-set keep-current and no-env-vars paths).
* feat(codex-runtime): scaffold optional codex app-server runtime
Foundational commit for an opt-in alternate runtime that hands OpenAI/Codex
turns to a 'codex app-server' subprocess instead of Hermes' tool dispatch.
Default behavior is unchanged.
Lands in three pieces:
1. agent/transports/codex_app_server.py — JSON-RPC 2.0 over stdio speaker
for codex's app-server protocol (codex-rs/app-server). Spawn, init
handshake, request/response, notification queue, server-initiated
request queue (for approval round-trips), interrupt-friendly blocking
reads. Tested against real codex 0.130.0 binary end-to-end during
development.
2. hermes_cli/runtime_provider.py:
- Adds 'codex_app_server' to _VALID_API_MODES.
- Adds _maybe_apply_codex_app_server_runtime() helper, called at the
end of _resolve_runtime_from_pool_entry(). Inert unless
'model.openai_runtime: codex_app_server' is set in config.yaml AND
provider in {openai, openai-codex}. Other providers cannot be
rerouted (anthropic, openrouter, etc. preserved).
3. tests/agent/transports/test_codex_app_server_runtime.py — 24 tests
covering api_mode registration, the rewriter helper (default-off,
case-insensitive, opt-in, non-eligible providers preserved), version
parser, missing-binary handling, error class. Does NOT require codex
CLI installed.
This commit is wire-only: the api_mode is recognized but AIAgent does
not yet branch on it. Followup commits add the session adapter, event
projector, approval bridge, transcript projection (so memory/skill
review still works), plugin migration, and slash command.
Existing tests remain green:
- tests/cli/test_cli_provider_resolution.py (29 passed)
- tests/agent/test_credential_pool_routing.py (included above)
* feat(codex-runtime): add codex item projector for memory/skill review
The translator that lets Hermes' self-improvement loop keep working under the
Codex runtime: converts codex 'item/*' notifications into Hermes' standard
{role, content, tool_calls, tool_call_id} message shape that
agent/curator.py already knows how to read.
Item taxonomy (matches codex-rs/app-server-protocol/src/protocol/v2/item.rs):
- userMessage → {role: user, content}
- agentMessage → {role: assistant, content: text}
- reasoning → stashed in next assistant's 'reasoning' field
- commandExecution → assistant tool_call(name='exec_command') + tool result
- fileChange → assistant tool_call(name='apply_patch') + tool result
- mcpToolCall → assistant tool_call(name='mcp.<server>.<tool>') + tool result
- dynamicToolCall → assistant tool_call(name=<tool>) + tool result
- plan/hookPrompt/etc → opaque assistant note, no fabricated tool_calls
Invariants preserved:
- Message role alternation never violated: each tool item produces at most
one assistant + one tool message in that order, correlated by call_id.
- Streaming deltas (item/<type>/outputDelta, item/agentMessage/delta)
don't materialize messages — only item/completed does. Mirrors how
Hermes already only writes the assistant message after streaming ends.
- Tool call ids are deterministic (codex item id-based) so replays produce
identical messages and prefix caches stay valid (AGENTS.md pitfall #16).
- JSON args use sorted_keys for the same reason.
Real wire formats verified against codex 0.130.0 by capturing live
notifications from thread/shellCommand and including one as a fixture
(COMMAND_EXEC_COMPLETED).
23 new tests, all green:
- Streaming deltas don't materialize (3 paths)
- Turn/thread frame events are silent
- commandExecution: 5 tests including non-zero exit annotation +
deterministic id stability across replays
- agentMessage + reasoning attachment + reasoning consumption
- fileChange: summary without inlined content
- mcpToolCall: namespaced naming + error surfacing
- userMessage: text fragments only (drops images/etc)
- opaque items: no fabricated tool_calls
- Helpers: deterministic id stability + sorted JSON args
- Role alternation invariant across all four tool-shaped item types
This commit is a pure addition. AIAgent integration (the wire that uses the
projector) is the next commit.
* feat(codex-runtime): add session adapter + approval bridge
The third self-contained module: CodexAppServerSession owns one Codex
thread per Hermes session, drives turn/start, consumes streaming
notifications via CodexEventProjector, handles server-initiated approval
requests, and translates cancellation into turn/interrupt.
The adapter has a single public per-turn method:
result = session.run_turn(user_input='...', turn_timeout=600)
# result.final_text → assistant text for the caller
# result.projected_messages → list ready to splice into AIAgent.messages
# result.tool_iterations → tick count for _iters_since_skill nudge
# result.interrupted → True on Ctrl+C / deadline / interrupt
# result.error → error string when the turn cannot complete
# result.turn_id, thread_id → for sessions DB / resume
Behavior:
- ensure_started() spawns codex, does the initialize handshake, and
issues thread/start with cwd + permissions profile. Idempotent.
- run_turn() blocks until turn/completed, drains server-initiated
requests (approvals) before reading notifications so codex never
deadlocks waiting for us, projects every item/completed via the
projector, and increments tool_iterations for the skill nudge gate.
- request_interrupt() is thread-safe (threading.Event); the next loop
iteration issues turn/interrupt and unwinds.
- turn_timeout deadlock guard issues turn/interrupt and records an
error if the turn never completes.
- close() escalates terminate → kill via the underlying client.
Approval bridge:
Codex emits server-initiated requests for execCommandApproval and
applyPatchApproval. The adapter translates Hermes' approval choice
vocabulary onto codex's decision vocabulary:
Hermes 'once' → codex 'approved'
Hermes 'session' or 'always' → codex 'approvedForSession'
Hermes 'deny' / anything else → codex 'denied'
Routing precedence:
1. _ServerRequestRouting.auto_approve_* flags (cron / non-interactive)
2. approval_callback wired by the CLI (defers to
tools.approval.prompt_dangerous_approval())
3. Fail-closed denial when neither is wired
Unknown server-request methods are answered with JSON-RPC error -32601
so codex doesn't hang waiting for us.
Permission profile mapping mirrors AGENTS.md:
Hermes 'auto' → codex 'workspace-write'
Hermes 'approval-required' → codex 'read-only-with-approval'
Hermes 'unrestricted/yolo' → codex 'full-access'
20 new tests, all green. Combined with prior commits this PR now has
67 tests across three modules:
- test_codex_app_server_runtime.py: 24 (api_mode + transport surface)
- test_codex_event_projector.py: 23 (item taxonomy projections)
- test_codex_app_server_session.py: 20 (turn loop + approvals + interrupts)
Full tests/agent/transports/ directory: 249/249 pass — no regressions
to existing transport tests.
Still no wire into AIAgent.run_conversation(); that integration commit
is small and goes next.
* feat(codex-runtime): wire codex_app_server runtime into AIAgent
The integration commit. AIAgent.run_conversation() now early-returns to a
new helper _run_codex_app_server_turn() when self.api_mode ==
'codex_app_server', bypassing the chat_completions tool loop entirely.
Three small surgical edits to run_agent.py (~105 LOC total):
1. Line ~1204 (constructor api_mode validation set):
Add 'codex_app_server' so an explicit api_mode='codex_app_server'
passed to AIAgent() isn't silently rewritten to 'chat_completions'.
2. Line ~12048 (run_conversation, just before the while loop):
Early-return to _run_codex_app_server_turn() when self.api_mode is
'codex_app_server'. Placed AFTER all standard pre-loop setup —
logging context, session DB, surrogate sanitization, _user_turn_count
and _turns_since_memory increments, _ext_prefetch_cache, memory
manager on_turn_start — so behavior outside the model-call loop is
identical between paths. Default Hermes flow is unchanged when the
flag is off.
3. End-of-class (line ~15497):
New method _run_codex_app_server_turn(). Lazy-instantiates one
CodexAppServerSession per AIAgent (reused across turns), runs the
turn, splices projected_messages into messages, increments
_iters_since_skill by tool_iterations (since the chat_completions
loop normally does that per iteration), fires
_spawn_background_review on the same cadence as the default path.
Counter accounting:
_turns_since_memory ← already incremented at run_conversation:11817
(gated on memory store configured) — codex
helper does NOT touch it (would double-count).
_user_turn_count ← already incremented at run_conversation:11793
— codex helper does NOT touch it.
_iters_since_skill ← incremented in the chat_completions loop per
tool iteration. Codex helper increments by
turn.tool_iterations since the loop is bypassed.
User message:
ALREADY appended to messages by run_conversation pre-loop (line 11823)
before the early-return reaches us. Helper does NOT append again.
Regression test test_user_message_not_duplicated guards this.
Approval callback wiring:
Lazy-fetches tools.terminal_tool._get_approval_callback at session
spawn time, passes to CodexAppServerSession. CLI threads with
prompt_toolkit get interactive approvals; gateway/cron contexts get
the codex-side fail-closed deny.
Error path:
Codex session exceptions become a 'partial' result with completed=False
and a final_response that explicitly tells the user how to switch back:
'Codex app-server turn failed: ... Fall back to default runtime with
/codex-runtime auto.' Same return-dict shape as the chat_completions
path so all callers (gateway, CLI, batch_runner, ACP) work unchanged.
9 new integration tests in tests/run_agent/test_codex_app_server_integration.py:
- api_mode='codex_app_server' is accepted on AIAgent construction
- run_conversation returns the expected codex shape
(final_response, codex_thread_id, codex_turn_id, completed, partial)
- Projected messages are spliced into messages list
- _iters_since_skill ticks per tool iteration
- _user_turn_count delegated to standard flow (not double-counted)
- User message appears exactly once (regression guard)
- _spawn_background_review IS invoked (memory/skill review keeps working)
- chat.completions.create is NEVER called (loop fully bypassed)
- Session exception → partial result with /codex-runtime auto hint
- Interrupted turn → partial result with error preserved
Adjacent test runs confirm no regressions:
- tests/run_agent/test_memory_nudge_counter_hydration.py: green
- tests/run_agent/test_background_review.py: green
- tests/run_agent/test_fallback_model.py: green
- tests/agent/transports/: 249/249 green
Still missing for full feature: /codex-runtime slash command, plugin
migration helper, docs page, live e2e test gated on codex binary. Those
are the remaining followup commits.
* feat(codex-runtime): add /codex-runtime slash command (CLI + gateway)
User-facing toggle for the optional codex app-server runtime. Follows the
'Adding a Slash Command (All Platforms)' pattern from AGENTS.md exactly:
single CommandDef in the central registry → CLI handler → gateway handler
→ running-agent guard → all surfaces (autocomplete, /help, Telegram menu,
Slack subcommands) update automatically.
Surface:
/codex-runtime — show current state + codex CLI status
/codex-runtime auto — Hermes default runtime
/codex-runtime codex_app_server — codex subprocess runtime
/codex-runtime on / off — synonyms
Files changed:
hermes_cli/codex_runtime_switch.py (new):
Pure-Python state machine shared by CLI and gateway. Parse args,
read/write model.openai_runtime in the config dict, gate enabling
behind a codex --version check (don't let users opt in to a runtime
they have no binary for; print npm install hint instead).
Returns a CodexRuntimeStatus dataclass that callers render however
suits their surface.
hermes_cli/commands.py:
Single CommandDef entry, no aliases (codex-runtime is its own thing).
cli.py:
Dispatch in process_command() + _handle_codex_runtime() handler that
delegates to the shared module and renders results via _cprint.
gateway/run.py:
Dispatch in _handle_message() + _handle_codex_runtime_command() that
returns a string (gateway sends as message). On a successful change
that requires a new session, _evict_cached_agent() forces the next
inbound message to construct a fresh AIAgent with the new api_mode —
avoids prompt-cache invalidation mid-session.
gateway/run.py running-agent guard:
/codex-runtime joins /model in the early-intercept block so a runtime
flip mid-turn can't split a turn across two transports.
Tests:
tests/hermes_cli/test_codex_runtime_switch.py — 25 tests covering the
state machine: arg parsing (10 cases incl. case-insensitive and
synonyms), reading current runtime (5 cases incl. malformed configs),
writing runtime (3 cases), apply() entry point covering read-only,
no-op, codex-missing-blocked, codex-present-success, disable-no-binary-check,
and persist-failure paths (8 cases). All green.
Adjacent test suites confirm no regressions:
- tests/hermes_cli/test_commands.py + test_codex_runtime_switch.py:
167/167 green
- tests/agent/transports/: 283/283 green when combined with prior commits
Still missing: plugin migration helper, docs page, live e2e test gated on
codex binary. Followup commits.
* feat(codex-runtime): auto-migrate Hermes MCP servers to ~/.codex/config.toml
Translates the user's mcp_servers config from ~/.hermes/config.yaml into
the TOML format codex's MCP client expects. Wired into the
/codex-runtime codex_app_server enable path so users get their MCP tool
surface in the spawned subprocess automatically.
The migration runs on every enable. Failures are non-fatal — the runtime
change still proceeds and the user gets a warning so they can fix the
codex config manually.
What translates (mapping verified against codex-rs/core/src/config/edit.rs):
Hermes mcp_servers.<n>.command/args/env → codex stdio transport
Hermes mcp_servers.<n>.url/headers → codex streamable_http transport
Hermes mcp_servers.<n>.timeout → codex tool_timeout_sec
Hermes mcp_servers.<n>.connect_timeout → codex startup_timeout_sec
Hermes mcp_servers.<n>.cwd → codex stdio cwd
Hermes mcp_servers.<n>.enabled: false → codex enabled = false
What does NOT translate (warned + skipped per server):
Hermes-specific keys (sampling, etc.) — codex's MCP client has no
equivalent. Listed in the per-server skipped[] field of the report.
What's NOT migrated (intentional):
AGENTS.md — codex respects this file natively in its cwd. Hermes' own
AGENTS.md (project-level) is already in the worktree, so codex picks
it up without translation. No code needed.
Idempotency design:
All managed content lives between a 'managed by hermes-agent' marker
and the next non-mcp_servers section header. _strip_existing_managed_block
removes the prior managed region cleanly, preserving any user-added
codex config (model, providers.openai, sandbox profiles, etc.) above
or below.
Files added:
hermes_cli/codex_runtime_plugin_migration.py — pure-Python migration
helper. Public API: migrate(hermes_config, codex_home=None,
dry_run=False) returns MigrationReport with .migrated/.errors/
.skipped_keys_per_server. No external TOML dependency — minimal
formatter handles strings/numbers/booleans/lists/inline-tables.
tests/hermes_cli/test_codex_runtime_plugin_migration.py — 39 tests
covering:
- per-server translation (12): stdio/http/sse, cwd, timeouts,
enabled flag, command+url precedence, sampling drop, unknown keys
- TOML formatter (8): types, escaping, inline tables, error case
- existing-block stripping (4): no marker, alone, with user content
above, with user content below
- end-to-end migrate() (8): empty, dry-run, round-trip, idempotent
re-run, preserves user config, error reporting, invalid input,
summary formatting
Files changed:
hermes_cli/codex_runtime_switch.py — apply() now calls migrate() in
the codex_app_server enable branch. Migration failure logs a warning
in the result message but does NOT fail the runtime change. Disable
path (auto) explicitly skips migration.
tests/hermes_cli/test_codex_runtime_switch.py — 3 new tests:
test_enable_triggers_mcp_migration, test_disable_does_not_trigger_migration,
test_migration_failure_does_not_block_enable.
All 325 feature tests green:
- tests/agent/transports/: 249 (incl. 67 new)
- tests/run_agent/test_codex_app_server_integration.py: 9
- tests/hermes_cli/test_codex_runtime_switch.py: 28 (3 new)
- tests/hermes_cli/test_codex_runtime_plugin_migration.py: 39 (new)
* perf(codex-runtime): cache codex --version check within apply()
Single /codex-runtime invocation could spawn 'codex --version' up to 3
times (state report, enable gate, success message). Each spawn is ~50ms,
so the cumulative cost wasn't a crisis, but it was wasteful and turned a
trivial slash command into something noticeably laggy on slower systems.
Refactored to lazy-once via a closure over a nonlocal cache. First call
spawns; subsequent calls in the same apply() reuse the result.
Behavior unchanged — same return shape, same error handling, same install
hint when codex is missing. Just one subprocess per call instead of three.
Two regression-guard tests added:
- test_binary_check_cached_within_apply: enable path → call_count == 1
- test_binary_check_cached_on_read_only_call: state-report path → call_count == 1
Total tests for /codex-runtime now 30 (was 28); all 143 codex-runtime
tests still green.
* fix(codex-runtime): correct protocol field names found via live e2e test
Three real bugs caught only by running a turn end-to-end against codex
0.130.0 with a real ChatGPT subscription. Unit tests passed because they
asserted on our own (incorrect) wire shapes; the wire format from
codex-rs/app-server-protocol/src/protocol/v2/* is the source of truth and
my initial reading of the README was incomplete.
Bug 1: thread/start.permissions wire format
Was sending {"profileId": "workspace-write"}.
Real format per PermissionProfileSelectionParams enum (tagged union):
{"type": "profile", "id": "workspace-write"}
AND requires the experimentalApi capability declared during initialize.
AND requires a matching [permissions] table in ~/.codex/config.toml or
codex fails the request with 'default_permissions requires a [permissions]
table'.
Fix: stop overriding permissions on thread/start. Codex picks its default
profile (read-only unless user configures otherwise), which matches what
codex CLI users expect — they configure their default permission profile
in ~/.codex/config.toml the standard way. Trying to be clever about
profile selection broke every turn we tested.
Live error before fix: 'Invalid request: missing field type' on every
turn/start, even though our turn/start payload was correct — the field
codex was complaining about was inside the permissions sub-object we
shouldn't have been sending.
Bug 2: server-request method names
Was matching 'execCommandApproval' and 'applyPatchApproval'.
Real names per common.rs ServerRequest enum:
item/commandExecution/requestApproval
item/fileChange/requestApproval
item/permissions/requestApproval (new third method)
Fix: match the documented names. Added handler for
item/permissions/requestApproval that always declines — codex sometimes
asks to escalate permissions mid-turn and silent acceptance would surprise
users.
Live symptom before fix: agent.log showed
'Unknown codex server request: item/commandExecution/requestApproval'
and codex stalled because we replied with -32601 (unsupported method)
instead of an approval decision. The agent reported back 'The write
command was rejected' even though Hermes never showed the user an
approval prompt.
Bug 3: approval decision values
Was sending decision strings 'approved'/'approvedForSession'/'denied'.
Real values per CommandExecutionApprovalDecision enum (camelCase):
accept, acceptForSession, decline, cancel
(also AcceptWithExecpolicyAmendment and ApplyNetworkPolicyAmendment
variants we don't currently use).
Fix: rename _approval_choice_to_codex_decision return values; update
auto_approve_* fallbacks; update fail-closed default from 'denied' to
'decline'. Test mapping table updated to match.
Live test verified after fixes:
$ hermes (with model.openai_runtime: codex_app_server)
> Run the shell command: echo hermes-codex-livetest > .../proof.txt
then read it back
Approval prompt fired with 'Codex requests exec in <cwd>'.
User chose 'Allow once'. Codex executed the command, wrote the file,
read it back. Final response: 'Read back from proof.txt:
hermes-codex-livetest'. File contents on disk match.
agent.log confirms:
codex app-server thread started: id=019e200e profile=workspace-write
cwd=/tmp/hermes-codex-livetest/workspace
All 20 session tests still green after wire-format updates.
* fix(codex-runtime): correct apply_patch approval params + ship docs
Live e2e revealed FileChangeRequestApprovalParams doesn't carry the
changeset (just itemId, threadId, turnId, reason, grantRoot) — Codex's
'reason' field describes what the patch wants to do. Test config and
display logic updated to use it. The first 'apply_patch (0 change(s))'
display from the live test is now 'apply_patch: <reason>'.
Adds website/docs/user-guide/features/codex-app-server-runtime.md
covering enable/disable, prerequisites, approval UX, MCP migration
behavior, permission profile delegation to ~/.codex/config.toml, known
limitations, and the architecture diagram. Wired into the Automation
category in sidebars.ts.
Live e2e validation across the path matrix:
✓ thread/start handshake
✓ turn/start with text input
✓ commandExecution items + projection
✓ item/commandExecution/requestApproval → Hermes UI → response
✓ Approve once → command runs
✓ Deny → command rejected, codex falls back to read-only message
✓ Multi-turn (codex remembers prior turn's results)
✓ apply_patch via Codex's fileChange path
✓ item/fileChange/requestApproval → Hermes UI
✓ MCP server migration loads inside spawned codex (verified via
'use the filesystem MCP tool' prompt)
✓ /codex-runtime auto → codex_app_server toggle cycle
✓ Disable doesn't trigger migration
✓ Enable with codex CLI present succeeds + migrates
✓ Hermes-side interrupt path (turn/interrupt request issued cleanly
even if codex finishes before the interrupt lands)
Known live-validated limitations now documented in the docs page:
- delegate_task subagents unavailable on this runtime
- permission profile selection delegated to ~/.codex/config.toml
- apply_patch approval prompt has no inline changeset (codex protocol
doesn't expose it)
145/145 codex-runtime tests still green.
* feat(codex-runtime): native plugin migration + UX polish (quirks 2/4/5/10/11)
Major: migrate native Codex plugins (#7 in OpenClaw's PR list)
Discovers installed curated plugins via codex's plugin/list RPC and
writes [plugins."<name>@<marketplace>"] entries to ~/.codex/config.toml
so they're enabled in the spawned Codex sessions. This is the
'YouTube-video-worthy' bit Pash highlighted: when a user has
google-calendar, github, etc. installed in their Codex CLI, those
plugins activate automatically when they enable Hermes' codex runtime.
Implementation:
- hermes_cli/codex_runtime_plugin_migration.py: new _query_codex_plugins()
helper spawns 'codex app-server' briefly and walks plugin/list. Returns
(plugins, error) — failures are non-fatal so MCP migration still works.
- render_codex_toml_section() now takes plugins + permissions args.
- migrate() defaults: discover_plugins=True, default_permission_profile=
'workspace-write'. Explicit None on either disables that side.
- _strip_existing_managed_block() now also strips [plugins.*] and
[permissions]/[permissions.*] sections inside the managed block, so
re-runs replace plugins cleanly without touching codex's own config.
Quirk fixes:
#2 Default permissions profile written on enable.
Without this, Codex's read-only default kicks in and EVERY write
triggers an approval prompt. Now writes [permissions] default =
'workspace-write' so the runtime feels normal out of the box. Set
default_permission_profile=None to opt out.
#4 apply_patch approval prompt now shows what's changing.
Codex's FileChangeRequestApprovalParams doesn't carry the changeset.
Session adapter now caches the fileChange item from item/started
notifications and looks it up by itemId when codex requests approval.
Prompt shows '1 add, 1 update: /tmp/new.py, /tmp/old.py' instead of
'apply_patch (0 change(s))'.
Side benefit: also drains pending notifications BEFORE handling a
server request, so the projector and per-turn caches are up to date
when the approval decision fires. Bounded to 8 notifications per
loop iter to avoid starving codex's response.
#5/#10 Exec approval prompt never shows empty cwd.
When codex omits cwd in CommandExecutionRequestApprovalParams, fall
back to the session's cwd. If somehow neither is available, show
'<unknown>' explicitly instead of an empty string.
Also surfaces 'reason' from the approval params when codex provides
it — gives users more context on why codex wants to run something.
#11 Banner indicates the codex_app_server runtime when active.
New 'Runtime: codex app-server (terminal/file ops/MCP run inside
codex)' line appears in the welcome banner only when the runtime is
on. Default banner is unchanged.
Tests:
- 7 new tests in test_codex_runtime_plugin_migration.py covering
plugin discovery (mocked), failure handling, dry-run skip, opt-out
flag, idempotent re-runs, and permissions writing.
- 3 new tests in test_codex_app_server_session.py covering the
enriched approval prompts: cwd fallback, change summary on
apply_patch, fallback when no item/started cache exists.
- All 26 session tests + 46 migration tests green; 153 total in PR.
* feat(codex-runtime): hermes-tools MCP callback + native plugin migration
The big architectural addition: when codex_app_server runtime is on,
Hermes registers its own tool surface as an MCP server in
~/.codex/config.toml so the codex subprocess can call back into Hermes
for tools codex doesn't ship with — web_search, browser_*, vision,
image_generate, skills, TTS.
Also: 'migrate native codex plugins' (Pash's YouTube-video-worthy bit) —
when the user has plugins like Linear, GitHub, Gmail, Calendar, Canva
installed via 'codex plugin', Hermes discovers them via plugin/list and
writes [plugins.<name>@openai-curated] entries so they activate
automatically.
New module: agent/transports/hermes_tools_mcp_server.py
FastMCP stdio server exposing 17 Hermes tools. Each call dispatches
through model_tools.handle_function_call() — same code path as the
Hermes default runtime. Run with:
python -m agent.transports.hermes_tools_mcp_server [--verbose]
Exposed: web_search, web_extract, browser_navigate / _click / _type /
_press / _snapshot / _scroll / _back / _get_images / _console /
_vision, vision_analyze, image_generate, skill_view, skills_list,
text_to_speech.
NOT exposed (deliberately):
- terminal/shell/read_file/write_file/patch — codex has built-ins
- delegate_task/memory/session_search/todo — _AGENT_LOOP_TOOLS in
model_tools.py:493, require running AIAgent context. Documented
as a limitation and surfaced in the slash command output.
Migration changes (hermes_cli/codex_runtime_plugin_migration.py):
- _query_codex_plugins() spawns 'codex app-server' briefly to walk
plugin/list and pull installed openai-curated plugins. Failures are
non-fatal — MCP migration still completes.
- render_codex_toml_section() now takes plugins + permissions args
AND wraps the managed block with a MIGRATION_END_MARKER comment so
the stripper can reliably find both ends, even when the block
contains top-level keys (default_permissions = ...).
- migrate() defaults: discover_plugins=True, expose_hermes_tools=True,
default_permission_profile=':workspace' (built-in codex profile name
— must be prefixed with ':'). All three opt-out via explicit args.
- _build_hermes_tools_mcp_entry() builds the codex stdio entry with
HERMES_HOME and PYTHONPATH passthrough so a worktree-launched
Hermes points the MCP subprocess at the same module layout.
Live-caught wire bugs fixed during this turn:
1. Permission profile config key is top-level , NOT a [permissions] table. The [permissions] table is
for *user-defined* profiles with structured fields. Built-in
profile names start with ':' (':workspace', ':read-only',
':danger-no-sandbox'). Was emitting
which codex rejected with 'invalid type: string "X", expected
struct PermissionProfileToml'.
2. Built-in profile is , NOT . Codex
rejected with 'unknown built-in profile'.
3. Codex's MCP layer sends for
tool-call confirmation. We weren't handling it, so codex stalled
and returned 'MCP tool call was rejected'. Now: auto-accept for
our own hermes-tools server (user already opted in by enabling
the runtime), decline for third-party servers.
Quirk fixes shipped (from the limitations list):
#2 default permissions: workspace profile written on enable. No more
approval prompt on every write.
#4 apply_patch approval shows what's changing: cache fileChange
items from item/started, look up by itemId when codex sends
item/fileChange/requestApproval. Prompt: '1 add, 1 update:
/tmp/new.py, /tmp/old.py' instead of '0 change(s)'.
#5/#10 exec approval cwd never empty: fall back to session cwd, then
'<unknown>'. Also surfaces 'reason' from codex when present.
#11 banner shows 'Runtime: codex app-server' line when active so
users understand why tool counts may not match what's reachable.
Tests:
- 5 new tests in test_codex_runtime_plugin_migration.py covering
plugin discovery, expose_hermes_tools entry generation, idempotent
re-runs, opt-out flag, permissions profile.
- 3 new tests in test_codex_app_server_session.py covering enriched
approval prompts (cwd fallback, fileChange summary).
- 2 new tests for mcpServer/elicitation/request handling (accept
hermes-tools, decline others).
- New test file test_hermes_tools_mcp_server.py covering module
surface, EXPOSED_TOOLS safety invariants (no shell/file_ops,
no agent-loop tools), and main() error paths.
- 166 codex-runtime tests total, all green.
Live e2e validated against codex 0.130.0 + ChatGPT subscription:
✓ /codex-runtime codex_app_server enables, migrates filesystem MCP,
registers hermes-tools, writes default_permissions = ':workspace'
✓ Banner shows 'Runtime: codex app-server' line in subsequent sessions
✓ Shell command runs without approval prompt (workspace profile works)
✓ Multi-turn — codex remembers prior turn's results
✓ apply_patch path via fileChange request approval
✓ web_search via hermes-tools MCP callback returns real Firecrawl
results: 'OpenAI Codex CLI – Getting Started' end-to-end in 13s
✓ Disable cycle clean
Docs updated: website/docs/user-guide/features/codex-app-server-runtime.md
Full re-write covering native plugin migration, the hermes-tools
callback architecture, the prerequisites change ('codex login is
separate from hermes auth login codex'), the trade-off table now
reflecting which Hermes tools work via callback, and the limitations
list updated with what's actually unavailable on this runtime.
* feat(codex-runtime): pin user-config preservation invariant for quirk #6
Quirk #6 from the limitations list — user MCP servers / overrides /
codex-only sections in ~/.codex/config.toml that live OUTSIDE the
hermes-managed block must survive re-migration verbatim.
This already worked thanks to the MIGRATION_MARKER + MIGRATION_END_MARKER
pair I added when fixing the default_permissions wire format (so the
strip can find both ends of the managed region even with top-level
keys like default_permissions). But it was an emergent property
without a test pinning it.
Now explicitly tested:
- User MCP server above the managed block survives migration
- User MCP server below the managed block survives migration
- Both above + below survive a second re-migration
- User content (model, providers, sandbox, otel, etc.) outside our
region is left untouched
Docs added a section "Editing ~/.codex/config.toml safely" explaining
the marker contract — so users know they can add their own MCP
servers, override permissions, configure codex-only options, etc.
without fear of Hermes overwriting their work.
167 codex-runtime tests, all green.
* docs(codex-runtime): clarify the actual tool surface — shell covers terminal/read/write/find
Previous docs and PR description undersold what codex's built-in
toolset actually provides. apply_patch alone made it sound like the
runtime could only edit files in patch format — implying you'd lose
terminal use, read_file, write_file, search/find. That was wrong.
Codex's 'shell' tool runs arbitrary shell commands inside the sandbox,
which covers everything you'd do in bash: cat/head/tail (read), echo>
or heredocs (write), find/rg/grep (search), ls/cd (navigate), build/
test/git/etc. apply_patch is for structured multi-file edits on top
of that. update_plan is its in-runtime todo. view_image loads images.
And codex has its own web_search built in (in addition to the
Firecrawl-backed one Hermes exposes via MCP callback).
Docs now have a 'What tools the model actually has' section right
after Why, breaking the surface into three clearly-labeled buckets:
1. Codex's built-in toolset (always on) — shell, apply_patch,
update_plan, view_image, web_search; covers everything terminal-
adjacent.
2. Native Codex plugins (auto-migrated from your codex plugin
install) — Linear, GitHub, Gmail, Calendar, Outlook, Canva, etc.
3. Hermes tool callback (MCP server in ~/.codex/config.toml) —
web_search/web_extract via Firecrawl, browser_*, vision_analyze,
image_generate, skill_view/skills_list, text_to_speech.
Plus a 'What's NOT available' callout listing the four agent-loop tools
(delegate_task, memory, session_search, todo) that need running
AIAgent context and can't reach the codex runtime.
Trade-offs table broken out: shell, apply_patch, update_plan,
view_image, sandbox each get their own row with a one-line description
so users can see at a glance what's available natively.
Architecture diagram updated to list the codex built-ins by name
instead of 'apply_patch + shell + sandbox'.
No code changes — purely docs clarification. 167 codex-runtime tests
still green.
* fix(codex-runtime): _spawn_background_review signature + review fork api_mode downgrade
Two real bugs in the self-improvement loop integration that the previous
test mocked away.
Bug 1: wrong call signature
The codex helper was calling self._spawn_background_review() with no
args after every turn. That function actually requires:
messages_snapshot=list (positional or keyword)
review_memory=bool (at least one trigger must be True)
review_skills=bool
So the call would have raised TypeError at runtime — except the only
test that exercised this path mocked _spawn_background_review entirely
and just asserted spawn.called, so the wrong-arg shape never surfaced.
Bug 2: review fork inherits codex_app_server api_mode
The review fork is constructed with:
api_mode = _parent_runtime.get('api_mode')
So when the parent is codex_app_server, the review fork ALSO runs as
codex_app_server. But the review fork's whole job is to call agent-loop
tools (memory, skill_manage) which require Hermes' own dispatch — they
short-circuit with 'must be handled by the agent loop' on the codex
runtime. So the review fork would have run, decided to save something,
called memory or skill_manage, and silently no-op'd.
Fixed in run_agent.py:_spawn_background_review() — when the parent
api_mode is 'codex_app_server', the review fork is downgraded to
'codex_responses' (same OAuth credentials, same openai-codex provider,
but talks to OpenAI's Responses API directly so Hermes owns the loop).
Also rewrote the codex helper's review wiring to match the
chat_completions path:
- Computes _should_review_memory in the pre-loop block (was already
being computed; now passed through to the helper as an arg).
- Computes _should_review_skills AFTER the codex turn returns +
counters tick (line ~15432 pattern in chat_completions).
- Calls _spawn_background_review(messages_snapshot=, review_memory=,
review_skills=) only when at least one trigger fires.
- Adds the external memory provider sync (_sync_external_memory_for_turn)
that the chat_completions path runs after every turn.
Tests:
Replaced the broken test_background_review_invoked (which only
asserted spawn.called) with three sharper tests:
- test_background_review_NOT_invoked_below_threshold:
single turn at default thresholds → no review fires (would have
caught the original 'every turn calls spawn with no args' bug)
- test_background_review_skill_trigger_fires_above_threshold:
10 tool_iterations at threshold=10 → review fires with
messages_snapshot=list, review_skills=True, counter resets
- test_background_review_signature_never_breaks: regression guard
asserting positional args are always empty and kwargs include
messages_snapshot
New TestReviewForkApiModeDowngrade class:
- test_codex_app_server_parent_downgrades_review_fork: drives the
real _spawn_background_review function (no mock at that level),
asserts the review_agent gets api_mode='codex_responses' when
the parent was codex_app_server.
Live-validated against real run_conversation:
- Counter ticked from 0 to 5 after a 5-tool-iteration turn
- _spawn_background_review fired exactly once with kwargs-only signature
- review_skills=True, review_memory=False
- messages_snapshot was 12 entries (5 assistant tool_calls + 5 tool
results + 1 final assistant + initial system/user)
- Counter reset to 0 after fire
170 codex-runtime tests, all green.
Docs: added a Self-improvement loop section to the codex runtime page
explaining both how the trigger logic stays equivalent and that the
review fork is auto-downgraded to codex_responses for the agent-loop
tools. Also clarified that apply_patch and update_plan ARE codex's
built-in tools (the previous version made it sound like they were
separate from 'codex's stuff' — they're not, all five tools listed
in 'What tools the model actually has' section 1 are codex built-ins).
* feat(codex-runtime): expose kanban tools through Hermes MCP callback
Kanban workers spawn as separate hermes chat -q subprocesses that read
the user's config.yaml. If model.openai_runtime: codex_app_server is set
globally (which is the whole point of opt-in), every dispatched worker
ALSO comes up on the codex runtime.
That mostly works — codex's built-in shell + apply_patch + update_plan
do the actual task work fine — but it had one critical break: the
worker handoff tools (kanban_complete, kanban_block, kanban_comment,
kanban_heartbeat) are Hermes-registered tools, not codex built-ins.
On the codex runtime, codex builds its own tool list and these never
reach the model, so the worker would do the work but not be able to
report back, hanging until the dispatcher's timeout escalates it as
zombie.
Fix: add all 9 kanban tools to the EXPOSED_TOOLS list in the Hermes
MCP callback. They dispatch statelessly through handle_function_call()
just like web_search and the others — they read HERMES_KANBAN_TASK
from env (set by the dispatcher), gate correctly (worker tools require
the env var, orchestrator tools require it unset), and write to
~/.hermes/kanban.db.
Why kanban tools work via stateless dispatch when delegate_task/memory/
session_search/todo don't: those four are listed in _AGENT_LOOP_TOOLS
(model_tools.py:493) and short-circuit in handle_function_call() with
'must be handled by the agent loop' — they need to mutate AIAgent's
mid-loop state. Kanban tools have no such requirement; they're pure
side-effect functions against the kanban.db plus state_meta.
Tools exposed:
Worker handoff (require HERMES_KANBAN_TASK):
kanban_complete, kanban_block, kanban_comment, kanban_heartbeat
Read-only board queries:
kanban_show, kanban_list
Orchestrator (require HERMES_KANBAN_TASK unset):
kanban_create, kanban_unblock, kanban_link
Tests:
- test_kanban_worker_tools_exposed: complete/block/comment/heartbeat
in EXPOSED_TOOLS (regression guard for the would-hang-worker bug)
- test_kanban_orchestrator_tools_exposed: create/show/list/unblock/link
Docs:
- New 'Workflow features' section in the docs page covering /goal,
kanban, and cron behavior on this runtime
- /goal: works fully via run_conversation feedback; only caveat is
approval-prompt noise on long writes-heavy goals (mitigated by
the default :workspace permission profile)
- Kanban: enumerated which tools are reachable via the callback and
why the env var propagates correctly through the codex subprocess
to the MCP server subprocess
- Cron: documented as 'not specifically tested' — same rules as the
CLI apply since cron runs through AIAgent.run_conversation
- Trade-offs table gained rows for /goal, kanban worker, kanban
orchestrator
172/172 codex-runtime tests green (+2 from kanban tests).
* docs(codex-runtime): wire /codex-runtime into slash-commands ref + flag aux token cost
Three docs gaps caught during a final audit:
1. /codex-runtime was only in the feature docs page, not in the
slash-commands reference. Added rows to both the CLI section and
the Messaging section so users discover it where they'd look for
slash command syntax.
2. CODEX_HOME and HERMES_KANBAN_TASK weren't in environment-variables.md.
CODEX_HOME lets users redirect Codex CLI's config dir (the migration
honors it). HERMES_KANBAN_TASK is set by the kanban dispatcher and
propagates to the codex subprocess + the hermes-tools MCP subprocess
so kanban worker tools gate correctly — documented as 'don't set
manually' since it's an internal handoff.
3. Aux client behavior on this runtime. When openai_runtime=
codex_app_server is on with the openai-codex provider, every aux
task (title generation, context compression, vision auto-detect,
session search summarization, the background self-improvement review
fork) flows through the user's ChatGPT subscription by default.
This is true for the existing codex_responses path too, but it's
more visible / important here because users explicitly opted in for
subscription billing. Added a 'Auxiliary tasks and ChatGPT
subscription token cost' section to the docs page with a YAML
example showing how to override specific aux tasks to a cheaper
model (typically google/gemini-3-flash-preview via OpenRouter).
Also documents how the self-improvement review fork gets
auto-downgraded from codex_app_server to codex_responses by the
fix earlier in this PR.
No code changes — pure docs. 172 codex-runtime tests still green.
* docs+test(codex-runtime): pin HOME passthrough, document multi-profile + CODEX_HOME
OpenClaw hit a real footgun in openclaw/openclaw#81562: when spawning
codex app-server they were synthesizing a per-agent HOME alongside
CODEX_HOME. That made every subprocess codex's shell tool launches
(gh, git, aws, npm, gcloud, ...) see a fake $HOME and miss the user's
real config files. They had to back it out in PR #81562 — keep
CODEX_HOME isolation, leave HOME alone.
Audit confirms Hermes' codex spawn doesn't have this problem. We do
os.environ.copy() and only overlay CODEX_HOME (when provided) and
RUST_LOG. HOME passes through unchanged. But it was an emergent
property without a test pinning it, so adding a regression guard:
test_spawn_env_preserves_HOME — confirms parent HOME survives intact
in the subprocess env
test_spawn_env_sets_CODEX_HOME_when_provided — confirms codex_home
arg still isolates
codex state correctly
Docs additions:
'HOME environment variable passthrough' section — calls out the
contract explicitly: CODEX_HOME isolates codex's own state, HOME
stays user-real so gh/git/aws/npm/etc. find their normal config.
Cites openclaw#81562 as the cautionary tale.
'Multi-profile / multi-tenant setups' section — addresses the
related concern: profiles share ~/.codex/ by default. For users who
want per-profile codex isolation (separate auth, separate plugins),
documents the manual CODEX_HOME=<profile-scoped-dir> approach.
Explains why we DON'T auto-scope CODEX_HOME per profile: doing so
would silently invalidate existing codex login state for anyone
upgrading to this PR with tokens already at ~/.codex/auth.json.
Opt-in is safer than surprising users.
174 codex-runtime tests (+2 from HOME guards), all green.
* fix(codex-runtime): TOML control-char escapes + atomic config.toml write
Two footguns caught in a final audit pass before merge.
Bug 1: TOML control characters not escaped
The _format_toml_value() helper escaped backslashes and double quotes
but passed literal control characters (\n, \t, \r, \f, \b) through
unchanged. TOML basic strings don't allow literal control characters
— a path or env var containing a newline would produce invalid TOML
that codex refuses to load.
Realistic exposure: pathological cases like a HERMES_HOME with a
trailing newline (env var concatenation accident), or a PYTHONPATH
with a tab from a multi-line shell heredoc.
Fix: escape all five TOML basic-string control sequences (\b \t \n
\f \r) in addition to \\ and \" that we already did. Order
matters — backslash must come first or the other escapes get
re-escaped.
Bug 2: config.toml write wasn't atomic
If the python process crashed between target.mkdir() and the
write_text() finishing, a half-written config.toml could be left
behind. On NFS / Windows / some FUSE mounts this is a real concern;
on ext4/APFS small writes are usually atomic in practice but not
guaranteed.
Fix: write to a tempfile.mkstemp() temp file in the same directory,
then Path.replace() (atomic same-dir rename on POSIX, ReplaceFile on
Windows). On rename failure, clean up the temp file so repeated
failed migrations don't pile up .config.toml.* files.
Tests:
- test_string_with_newline_escaped — \n in value → \n in output
- test_string_with_tab_escaped — \t in value → \t in output
- test_string_with_other_controls_escaped — \r, \f, \b
- test_windows_path_escaped_correctly — backslash doubling
- test_atomic_write_no_temp_leak_on_success — no .config.toml.*
left over after a successful write
- test_atomic_write_cleanup_on_rename_failure — temp file removed
when Path.replace raises (simulated disk full)
180 codex-runtime tests, all green (+6 from this commit).
Footguns audited but NOT fixed (with rationale):
- Concurrent migrations race. Two Hermes processes hitting
/codex-runtime codex_app_server within seconds of each other could
cause one writer to lose entries. Low probability (you'd have to
enable from two surfaces simultaneously) and low impact (just re-run
migration). Adding fcntl/msvcrt locking is more code than it's
worth here. The atomic rename above means each individual write is
consistent — only the merge step is racy.
- Codex protocol version drift. We pin MIN_CODEX_VERSION=0.125 and
check at runtime but don't reject too-new versions. Right call —
the protocol has been stable through 0.125 → 0.130. If OpenAI
breaks it later we'd see the error in test_codex_app_server_runtime
on CI before users hit it.
* feat(video_gen): unified video_generate tool with pluggable provider backends
One core video_generate tool, every backend a plugin. Mirrors the
image_gen + memory_provider + context_engine architecture: ABC, registry,
plugin-context registration hook, and per-plugin model catalogs surfaced
through hermes tools.
Surface (one schema, every backend):
- operation: generate / edit / extend
- modalities: text-to-video (prompt only), image-to-video (prompt +
image_url), video edit (prompt + video_url), video extend (video_url)
- reference_image_urls, duration, aspect_ratio, resolution,
negative_prompt, audio, seed, model override
- Providers ignore unknown kwargs and declare what they support via
VideoGenProvider.capabilities() — backend-specific quirks stay in the
backend, the agent learns one tool
Backends shipped:
- plugins/video_gen/xai/ — Grok-Imagine, full generate/edit/extend +
image-to-video + reference images (salvaged from PR #10600 by
@Jaaneek, reshaped into the plugin interface)
- plugins/video_gen/fal/ — Veo 3.1 (t2v + i2v), Kling O3 i2v,
Pixverse v6 i2v with model-aware payload building that drops keys a
model doesn't declare
Wiring:
- agent/video_gen_provider.py — VideoGenProvider ABC, normalize_operation,
success_response / error_response, save_b64_video / save_bytes_video,
$HERMES_HOME/cache/videos/
- agent/video_gen_registry.py — thread-safe register/get/list +
get_active_provider() reading video_gen.provider from config.yaml
- hermes_cli/plugins.py — PluginContext.register_video_gen_provider()
- hermes_cli/tools_config.py — Video Generation category in
hermes tools, plugin-only providers list, model picker per plugin,
config write to video_gen.{provider,model}
- toolsets.py — new video_gen toolset
- tests: 31 new tests covering ABC, registry, tool dispatch, both plugins
- docs: developer-guide/video-gen-provider-plugin.md (parallel to the
image-gen guide), sidebar + toolsets-reference + plugin guides updated
Supersedes: #25035 (FAL), #17972 (FAL), #14543 (xAI), #13847 (HappyHorse),
#10458 (provider categories), #10786 (xAI media+search bundle), #2984
(FAL duplicate), #19086 (Google Veo standalone — easy port to plugin
interface).
Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com>
* feat(video_gen): dynamic schema reflects active backend's capabilities
Address the 'capability variance' question — instead of one tool with a
static schema that lies about what every backend supports, the
video_generate tool now rebuilds its description at get_definitions()
time based on the configured video_gen.provider and video_gen.model.
The agent sees backend-specific guidance up-front:
- 'fal-ai/veo3.1/image-to-video': 'image-to-video only — image_url is
REQUIRED; text-only prompts will be rejected'
- 'fal-ai/veo3.1' (t2v): no image_url restriction shown
- xAI grok-imagine-video: 'operations: generate, edit, extend; up to 7
reference_image_urls'
- Backends without edit/extend: 'not supported on this backend — surface
that they need to switch backends via hermes tools'
This is the same pattern PR #22694 used for delegate_task self-capping —
documented in the dynamic-tool-schemas skill. Cache invalidation is
free: get_tool_definitions() already memoizes on config.yaml mtime, so a
mid-session backend swap rebuilds the schema automatically.
Tested:
- Empirical FAL OpenAPI schema check confirms image-to-video models
require image_url (FAL returns HTTP 422 otherwise) — client-side
rejection in FALVideoGenProvider.generate() now prevents the wasted
round-trip
- Live E2E: fal-ai/veo3.1/image-to-video + prompt-only → clean
missing_image_url error; fal-ai/veo3.1 + prompt-only → dispatches
- 6 new tests cover the builder (no config / image-only / full-surface /
text-only / unknown provider / registry wiring), all passing
- 37/37 in the slice, 134/134 in the broader regression set
* test(video_gen/xai): full surface integration tests + cleaner schema
Verified end-to-end that the xAI plugin handles every documented mode
from PR #10600's surface: text-to-video, image-to-video,
reference-images-to-video, video edit, video extend (with and without
prompt). All five modes route to the correct xAI endpoint
(/videos/generations, /videos/edits, /videos/extensions) with the right
payload shape (image / reference_images / video keys), and all five
client-side rejections fire before the network: edit-without-prompt,
extend-without-video_url, image+refs conflict, >7 references, and
duration/aspect_ratio clamping.
15 new integration tests grouped into four classes (endpoint routing,
modalities, validation, clamping). httpx is stubbed via a small fake
AsyncClient that records POSTs so the tests assert the actual payload
the plugin would send to xAI — not just the success/error envelope.
Also cleaned up a description redundancy: when a model's operations
match the backend's overall set, we no longer print the duplicate
'operations supported by this model' line. xAI's description now reads:
Active backend: xAI . model: grok-imagine-video
- operations supported by this backend: edit, extend, generate
- modalities supported by this backend: image, reference_images, text
- aspect_ratio choices: 16:9, 1:1, 2:3, 3:2, 3:4, 4:3, 9:16
- resolution choices: 480p, 720p
- duration range: 1-15s
- reference_image_urls: up to 7 images
Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com>
* feat(video_gen): collapse surface to t2v + i2v, family-based auto-routing
Two design changes per Teknium:
1) Drop edit/extend from the tool surface entirely. Only text-to-video
and image-to-video remain. The agent sees a clean tool with two
modalities; backend-specific quirks like xAI's edit/extend endpoints
stay out of the unified schema.
2) FAL: pick a model FAMILY once, the plugin routes between the
family's text-to-video and image-to-video endpoints based on whether
image_url was passed. Users no longer pick 'fal-ai/veo3.1' AND
'fal-ai/veo3.1/image-to-video' as separate options — they pick
'veo3.1', and the plugin handles the rest.
Catalog rewritten as families:
veo3.1 fal-ai/veo3.1 / fal-ai/veo3.1/image-to-video
pixverse-v6 fal-ai/pixverse/v6/text-to-video / fal-ai/pixverse/v6/image-to-video
kling-o3-standard fal-ai/kling-video/o3/standard/text-to-video / fal-ai/kling-video/o3/standard/image-to-video
xAI uses a single endpoint (/videos/generations) for both modes,
routed by the presence of the 'image' field in the payload — no
edit/extend exposure.
Schema changes:
- VIDEO_GENERATE_SCHEMA: drop operation, drop video_url. Final params:
prompt (required), image_url, reference_image_urls, duration,
aspect_ratio, resolution, negative_prompt, audio, seed, model.
- VideoGenProvider ABC: drop normalize_operation, VALID_OPERATIONS,
DEFAULT_OPERATION. capabilities() drops 'operations' key.
- success_response: add 'modality' field ('text' | 'image') so the
agent and logs can see which endpoint was actually hit.
Dynamic schema builder simplified — no operations bullet, no
'switch backends if you need edit/extend' guidance. When the active
backend supports both modalities (the common case), description reads:
Active backend: FAL . model: pixverse-v6
- supports both text-to-video (omit image_url) and image-to-video
(pass image_url) - routes automatically
- aspect_ratio choices: 16:9, 9:16, 1:1
- resolution choices: 360p, 540p, 720p, 1080p
- duration range: 1-15s
- audio: pass audio=true to enable native audio (pricing tier)
- negative_prompt: supported
Tests: 51 in the video_gen slice, 216 across the broader image+video
sweep, all passing. New FAL routing tests prove pixverse-v6 + no image
hits text-to-video endpoint, pixverse-v6 + image_url hits
image-to-video endpoint, same for veo3.1 and kling-o3-standard.
Docs updated: developer-guide page rewrites the 'model families' pattern
as a first-class section so external plugin authors know the convention.
toolsets-reference and toolsets.py descriptions match the new surface.
Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com>
* feat(video_gen/fal): expand catalog to 6 families, cheap + premium tiers
Catalog now covers everything Teknium specced from FAL:
Cheap tier:
ltx-2.3 fal-ai/ltx-2.3-22b/text-to-video / image-to-video
pixverse-v6 fal-ai/pixverse/v6/text-to-video / image-to-video
Premium tier:
veo3.1 fal-ai/veo3.1 / fal-ai/veo3.1/image-to-video
seedance-2.0 bytedance/seedance-2.0/text-to-video / image-to-video
kling-v3-4k fal-ai/kling-video/v3/4k/text-to-video / image-to-video
happy-horse fal-ai/happy-horse/text-to-video / image-to-video
DEFAULT_MODEL moved from veo3.1 (premium) to pixverse-v6 (cheap, sane
defaults, both modalities) — better first-run UX for users who haven't
explicitly picked a model.
New family-entry knob: image_param_key. Kling v3 4K's image-to-video
endpoint expects start_image_url instead of image_url; declaring
image_param_key='start_image_url' on the family lets _build_payload
remap correctly. Other families default to plain image_url.
Per-family capability flags reflect each model's docs:
- LTX 2.3 + Happy Horse: minimal payloads (no duration/aspect/resolution
enum exposed by FAL — let endpoint apply defaults)
- Seedance: 6 aspect ratios incl 21:9, durations 4-15, audio supported,
negative prompts NOT supported per docs
- Kling v3 4K: 16:9/9:16/1:1, 3-15s, audio + negative
- Veo 3.1: unchanged, 16:9/9:16, 4/6/8s
Tests: +5 covering the new families (full catalog, Kling 4K
start_image_url remap, Seedance routing, LTX payload minimality, Happy
Horse minimality). 56/56 in the slice green.
Note: I did NOT add the FAL-hosted xAI Grok-Imagine variant. Hermes
already has a direct xAI plugin that talks to xAI's own API; routing
the same model through FAL's wrapper would duplicate the surface
without adding capabilities. Users on FAL who want Grok-Imagine should
use the xAI plugin directly; flag if you want both routes available.
* test(video_gen): tool-surface routing matrix — every model x modality
End-to-end matrix test driven through _handle_video_generate() — the
actual function the agent's video_generate tool call lands in. Writes
config.yaml, invokes the registered handler with a raw args dict, then
asserts the outbound HTTP/SDK call hit the right endpoint with the right
payload shape.
Parametrized over FAL_FAMILIES.keys() so the matrix auto-discovers new
families as they're added (add a family to FAL_FAMILIES and you get
both modalities tested for free).
Coverage:
- All 6 FAL families x {text-only, text+image} = 12 cases
- xAI x {text-only, text+image} = 2 cases
- tool-level model= arg overrides config = 2 cases
For each case, verifies:
- result['success'] is True
- result['modality'] matches input shape ('text' if no image_url, 'image' otherwise)
- outbound endpoint URL matches the family's text_endpoint or image_endpoint
- text-only payloads carry no image-shaped keys
- text+image payloads carry the family's image key (image_url for most,
start_image_url for kling-v3-4k, wrapped 'image' object for xAI)
All 16 cases passing. Confirms the tool surface routes every
(provider, model, modality) combination correctly with zero leakage.
* feat(video_gen): keep video_gen out of first-run setup, surface in status
Two changes:
1. video_gen joins _DEFAULT_OFF_TOOLSETS, so it is NOT pre-selected in
the first-run toolset checklist. Video gen is niche, paid, and slow —
most users don't want it nagging them during initial setup. Anyone
who wants it opts in via 'hermes tools' -> Video Generation, which
already routes to the provider+model picker.
2. The 'hermes setup' status panel learns about video_gen — but only
shows the row when a plugin reports available. Users without
FAL_KEY/XAI_API_KEY see nothing about video gen; users with one of
those keys see 'Video Generation (FAL) ✓' as confirmation it's wired.
Verified live:
- Fresh install (no creds): zero video_gen mentions in wizard.
- With FAL_KEY: status row appears with active backend name.
- 160/160 in the setup + tools_config + video_gen test slice.
Rationale: image_gen is on by default because it's a featured creative
tool used in casual chat (telegrams, etc). Video gen is heavier — long
wait, paid per-second pricing. Default-off matches user intent better.
---------
Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com>
Replace tenant-specific example text in the transcript offset regression with generic follow-up turns so the upstream test documents the bug without customer-specific wording.
Keep the outer history_offset when _run_agent drains queued follow-ups recursively so transcript persistence includes every queued turn in the chain instead of only the last one.
Recover from SIGWINCH without clearing the physical screen or scrollback
buffer. The startup banner and tool summary are printed before
prompt_toolkit owns the live chrome, so they live in normal terminal
scrollback. Calling erase_screen() + \x1b[3J] on every resize removed
that UI permanently — _replay_output_history cannot reconstruct it
because the banner was never added to _OUTPUT_HISTORY.
Instead, just reset prompt_toolkit's renderer cache and invalidate so
the next incremental redraw starts from a clean slate, then let the
original on_resize handler recalculate layout for the new terminal
size. This matches the behaviour of bash/zsh/fish on SIGWINCH.
FixesNousResearch/hermes-agent#22999
skill_view ran the direct-path strategy across every skill dir before
the recursive strategy, so a top-level skill in an external dir could
silently shadow a same-named nested local skill. /skills correctly
listed the local version (deduped local-first by _find_all_skills) but
skill_view loaded the external one — confusing, and a real bug class
for users with skills.external_dirs registered alongside categorized
local skills.
Pick a louder fix than @polkn's PR #6136 proposed: collect every match
across all dirs (direct path, recursive by parent dir name, legacy
flat <name>.md), and if there's more than one, refuse with an error
that surfaces every matching path plus a hint to load by the
categorized form. Local-first precedence would have replaced silent
external-shadowing with silent same-name collisions between two
externals, or made an externally-shadowed-by-local skill unreachable
by bare name with no signal. Refusing forces the user to disambiguate
once and never wonder which skill ran.
Recovery: pass the full categorized path
("foundations/runtime/explore-codebase" instead of
"explore-codebase"), or rename one of the colliding skills.
Co-authored-by: pol <pol.kuijken@gmail.com>
Removes the 'Launch hermes chat now? (Y/n)' prompt at the end of
hermes setup. The summary already prints 'Ready to go! → hermes'
so the auto-launch was redundant, and on macOS 26+ it could crash
in prompt_toolkit when setup was invoked from the curl install
script with stdin redirected from /dev/tty (#5884, #6128).
After setup, users run 'hermes' themselves like every other CLI
tool. Same pattern applies to the Windows installer.
Closes#6128 (narrower env-var-guarded fix superseded by removing
the prompt outright).
Adds an explicit API compatibility mode prompt to the `hermes model -> custom`
flow so Codex-compatible third-party endpoints (and any other non-default
backend whose URL doesn't match the existing heuristics in
`_detect_api_mode_for_url`) can be selected explicitly instead of silently
falling back to chat_completions.
Choices: Auto-detect / chat_completions / codex_responses / anthropic_messages.
Persists `api_mode` to:
- `model.api_mode` (active session config)
- the matching `custom_providers[*]` entry (so re-activating the named
provider next time replays the same transport)
Salvaged from PR #6125 onto current main: kept the new prompt and the
`_save_custom_provider(api_mode=...)` plumbing; the named-custom flow
already extracts and applies `api_mode` from the saved entry on current
main so those changes are preserved as-is. Test fixtures updated for the
new prompt and the existing display-name prompt.
Co-authored-by: littlewwwhite <1095245867@qq.com>
- memory_setup.py: use shlex.split() for plugin dep checks instead of shell=True
- transcription_tools.py: avoid shell=True for auto-detected whisper commands
(user-provided templates via env var still use shell=True for compatibility)
- cli.py: add comment clarifying intentional shell=True for user quick_commands
- Add test verifying auto-detected template is shlex-safe
Addresses CONTRIBUTING.md Priority #3 (Security hardening — shell injection).
These two functions in hermes_cli/profiles.py have no callers — the live
`hermes completion {bash,zsh}` command uses hermes_cli/completion.py's
generate_bash() / generate_zsh() instead. Multiple PRs (incl. #6141) tried
to fix the trailing-`_hermes "$@"` zsh bug here, only to discover the
patch never reached users. Delete the dead code so future contributors
patch the right file.
The actual user-facing fix lives in the preceding cherry-picked commits
to hermes_cli/completion.py.
* feat(nous): unified client=hermes-client-v<version> tag on every Portal request
Every Hermes request to Nous Portal now carries the same
client=hermes-client-v<__version__> tag (e.g. client=hermes-client-v0.13.0
on this release), sourced live from hermes_cli.__version__. The release
script's regex bump auto-aligns it on every release.
Centralized in agent/portal_tags.py and wired into all four call sites:
- NousProfile.build_extra_body (main agent loop, every chat completion)
- auxiliary_client.NOUS_EXTRA_BODY + _build_call_kwargs (aux client)
- run_agent.py compression-summary fallback path
- tools/web_tools.py web_extract fallback
Replaces the client=aux marker added in #24194 with the unified version
tag. Tests assert against the helper output (invariant) rather than the
literal string, so they don't need updating on every release.
* feat(nous): cover /goal judge and kanban specify aux paths
Two aux-using surfaces bypassed call_llm by invoking
client.chat.completions.create() directly without extra_body, so they
were missing the unified Portal client tag:
- hermes_cli/goals.py — /goal standing-goal judge
- hermes_cli/kanban_specify.py — kanban triage specifier
Both now pass extra_body=get_auxiliary_extra_body() or None so they
inherit the version tag when the aux client points at Nous Portal, and
emit nothing otherwise (no tag leak to OpenRouter/Anthropic auxes).
The long-lived prefix-cache layout split the system prompt into stable/
context/volatile blocks and re-derived them on every API call. The
volatile tier (timestamp + memory snapshot + USER profile) ticks per
turn, so the system message bytes mutated mid-conversation and broke
upstream prompt caches (OpenRouter, Nous Portal, Anthropic).
Diagnosed via live wire-format diffing: an 8-turn conversation showed
OLD layout flipping system block[1] sha mid-session at the minute
boundary, dropping cached_tokens to 0 on that turn (cumulative
66.6% vs 83.3% for the single-block layout). Hermes invariant:
history (system + all but the last 1-2 messages) must be static.
Fix: drop the long-lived layout entirely. Single layout everywhere —
system_and_3 with one cached system string built once on first turn,
replayed verbatim on every subsequent turn. Loses cross-session 1h
prefix caching for Claude (the feature that motivated the split), but
within-session caching now actually works on every provider.
Removed:
- run_agent.py: _use_long_lived_prefix_cache flag, _long_lived_cache_ttl,
_supports_long_lived_anthropic_cache method, the long-lived branch in
run_conversation, mark_tools_for_long_lived_cache call site
- agent/prompt_caching.py: apply_anthropic_cache_control_long_lived,
mark_tools_for_long_lived_cache, _mark_system_stable_block helper
- hermes_cli/config.py: prompt_caching.long_lived_prefix and
prompt_caching.long_lived_ttl config keys
- tests/agent/test_prompt_caching_live.py (entire file)
- tests/agent/test_prompt_caching.py: TestMarkToolsForLongLivedCache,
TestApplyAnthropicCacheControlLongLived
- tests/run_agent/test_anthropic_prompt_cache_policy.py:
TestSupportsLongLivedAnthropicCache
Targeted tests: 62/62 pass.
The test_restart_command_while_busy_requests_drain_without_interrupt test
was asserting against a hardcoded emoji string that was valid before the
i18n migration. After gateway/run.py switched to t("gateway.draining",
count=N), the test sees the translated output (or the raw key when the
locale catalog isn't resolved in xdist workers).
Fix by asserting against t("gateway.draining", count=1) — this produces
the correct expected value regardless of whether the locale file is
available in the test environment.
PR #24151 routed Portal Qwen (qwen3.6-plus) through the prefix_and_2
long-lived cache layout, attaching {"type":"ephemeral","ttl":"1h"}
markers to the tools[-1] entry and the stable system-prefix block.
That layout works for Portal Claude because Anthropic / OpenRouter on
Anthropic routes honour 1h TTL — but Portal Qwen ultimately proxies to
Alibaba DashScope, which documents a single "ephemeral" TTL of 5
minutes on its Context Cache. The ttl="1h" qualifier is silently
dropped upstream, so the two highest-value breakpoints (tools array +
system prefix) never land. Only the rolling-window 5m markers on the
last 2 messages cache, which matches the observed ~25% read rate.
Fix: keep Portal Qwen on cache_control via _anthropic_prompt_cache_policy
returning (True, False), but drop it from _supports_long_lived_anthropic_cache
so it rides the standard system_and_3 5m layout (system + last 3 messages,
all at 5m). Same 4 breakpoints, all in a TTL the upstream actually honours.
Refs: https://www.alibabacloud.com/help/en/model-studio/context-cachehttps://openrouter.ai/docs/features/prompt-caching (Alibaba Qwen
section: "TTL: 5 minutes")
- _supports_long_lived_anthropic_cache: Portal scope narrowed back to Claude
- tests: flip the two qwen long-lived expectations to False, retitle
non_claude_non_qwen_rejected -> non_claude_rejected
Three follow-ups to PR #24168 found during live E2E testing on TS/bash files:
1. typescript-language-server now installs the typescript SDK (tsserver)
alongside it. Without that sibling install, initialize() failed with
"Could not find a valid TypeScript installation" and the server was
marked broken — no diagnostics ever reached the agent. New extra_pkgs
field on INSTALL_RECIPES makes that explicit and reusable for future
peer-dep cases.
2. _check_lint now treats "linter command exists on PATH but cannot
actually run" as skipped instead of error. The motivating case is
npx tsc when typescript is not in node_modules — npx prints its
"This is not the tsc command you are looking for" banner and exits
non-zero, which previously blocked the LSP semantic tier (gated on
success or skipped). Pattern-matched per base command (npx,
rustfmt, go) so genuine lint errors still flow through normally.
3. hermes lsp status now surfaces a Backend warnings section when
bash-language-server is installed but shellcheck is missing. The
server itself spawns fine but bash-language-server delegates
diagnostics to shellcheck — without it on PATH the integration
looks alive but never reports any problems. Same warning is
logged once at server spawn time.
Validation:
- 12 new tests in tests/agent/lsp/test_install_and_lint_fixes.py:
* recipe carries typescript SDK
* _install_npm passes both pkg + extras to npm CLI
* backwards compat: recipes without extras still work
* _backend_warnings quiet when bash absent / both present
* _backend_warnings fires when bash installed without shellcheck
* status output includes the Backend warnings section
* _looks_like_linter_unusable catches the npx tsc banner
* real TS type errors not misclassified as unusable
* unfamiliar linters fall through normally
* _check_lint returns skipped on npx tsc unusable
* _check_lint returns error on real tsc type errors
- Full lsp + file_operations test suite: 245/245 pass
- Live E2E:
* try_install("typescript-language-server") installs both packages
into node_modules
* write_file(bad.ts, ...) returns lint=skipped + lsp_diagnostics
with two real TS errors (was lint=error, no lsp_diagnostics)
* hermes lsp status renders the shellcheck warning when bash is
installed but shellcheck is not on PATH
When the user runs /stop or a session is interrupted mid-flight, the
👀 in-progress reaction lingered on the user's message indefinitely.
Without another agent run to swap it for 👍/👎, the eyes stayed there
forever — visually misleading (looks like the agent is still working).
Fix: on ProcessingOutcome.CANCELLED, call set_message_reaction with
reaction=None to clear all reactions on the message. Documented Bot API
semantics (equivalent to Bot API 10.0's deleteMessageReaction, but works
on PTB 22.6 already without the version bump).
Test changes:
- Renamed test_on_processing_complete_cancelled_keeps_existing_reaction
→ test_on_processing_complete_cancelled_clears_reaction; updated
assertion to expect set_message_reaction(reaction=None).
- Added test_on_processing_complete_cancelled_skipped_when_disabled
(TELEGRAM_REACTIONS=false short-circuits).
- Added test_clear_reactions_handles_api_error_gracefully and
test_clear_reactions_returns_false_without_bot to cover the new
_clear_reactions helper.
Built-in commands with required args (e.g. /queue, /steer, /background)
were excluded from Telegram setMyCommands output, making them invisible
in the autocomplete menu. However, their handlers already return usage
text when invoked without arguments, so hiding them hurts discoverability.
This commit removes the _requires_argument filter for built-in commands
(COMMAND_REGISTRY) while keeping it for plugin-registered slash commands,
which may not provide a no-arg usage fallback.
Closes#24312
The clarify tool returned 'not available in this execution context' for
every gateway-mode agent because gateway/run.py never passed
clarify_callback into the AIAgent constructor. Schema actively encouraged
calling it; users never saw the question.
Changes:
- tools/clarify_gateway.py — new event-based primitive mirroring
tools/approval.py: register/wait_for_response/resolve_gateway_clarify
with per-session FIFO, threading.Event blocking with 1s heartbeat
slices (so the inactivity watchdog keeps ticking), and
clear_session for boundary cleanup.
- gateway/platforms/base.py — abstract send_clarify with a numbered-text
fallback so every adapter (Discord, Slack, WhatsApp, Signal, Matrix,
etc.) gets a working clarify out of the box. Plus an active-session
bypass: when the agent is blocked on a text-awaiting clarify, the next
non-command message routes inline to the runner's intercept instead
of being queued + triggering an interrupt. Same shape as the /approve
deadlock fix from PR #4926.
- gateway/platforms/telegram.py — concrete send_clarify renders one
inline button per choice plus '✏️ Other (type answer)'. cl: callback
handler resolves numeric choices immediately, flips to text-capture
mode for Other, with the same authorization guards as exec/slash
approvals.
- gateway/run.py — clarify_callback wired at the cached-agent per-turn
callback assignment site (only the user-facing agent path; cron and
hygiene-compress agents have no human attached). Bridges sync→async
via run_coroutine_threadsafe, blocks with the configured timeout, and
returns a '[user did not respond within Xm]' sentinel on timeout so
the agent adapts rather than pinning the running-agent guard. Text-
intercept added to _handle_message before slash-confirm intercept
(skipping slash commands). clear_session called in the run's finally
to cancel any orphan entries.
- hermes_cli/config.py — agent.clarify_timeout default 600s.
- website/docs/user-guide/messaging/telegram.md — Interactive Prompts
section.
Tests:
- tests/tools/test_clarify_gateway.py (14 tests) — full primitive
coverage: button resolve, open-ended auto-await, Other flip, timeout
None, unknown-id idempotency, clear_session cancellation, FIFO
ordering, register/unregister notify, config default.
- tests/gateway/test_telegram_clarify_buttons.py (12 tests) — render
paths (multi-choice/open-ended/long-label/HTML-escape/not-connected),
callback dispatch (numeric resolve/Other flip/already-resolved/
unauthorized/invalid-token), and base-adapter text fallback.
Out of scope: bot-to-bot, guest mode, checklists, poll media, live
photos. Closes#24191.
PR #24500 introduced stale-lock detection that calls
`_looks_like_gateway_process` to confirm a running PID is not an
unrelated process that reused the slot. On Windows neither `/proc`
nor `ps` is available, so `_read_process_cmdline` always returns
`None` and `_looks_like_gateway_process` always returns `False` —
causing every valid Windows gateway lock to be marked stale and
immediately evicted.
Fix: after `_looks_like_gateway_process` returns `False`, call
`_read_process_cmdline` directly. If the result is non-`None` the
live cmdline was readable and confirms the PID is foreign → stale.
If it is `None` (cmdline unreadable, e.g. Windows without ps), fall
back to `_record_looks_like_gateway` which validates the stored
`argv` the gateway wrote into the lock file at startup. Both
oracles must say "not a gateway" before the lock is evicted — the
same two-oracle pattern already used in `get_running_pid` (line 941).
Adds a regression test that simulates a Windows host where
`_looks_like_gateway_process` returns `False` for every PID and
`_read_process_cmdline` returns `None`, confirming the lock is kept
when the record's argv identifies it as a gateway process.
deepseek-v4-pro has been routable since v0.12 but was missing from
the _OFFICIAL_DOCS_PRICING table. Sessions using this model showed
as "unknown cost" in hermes insights instead of a dollar estimate.
Add pricing entry using published list prices:
- input: \$1.74/M tokens
- output: \$3.48/M tokens
- cache_read: \$0.0145/M tokens
Uses standard list rates (not the 75% promo) so estimates remain
accurate after promo expires 2026-05-31.
Closes#24218
* feat(lsp): semantic diagnostics from real language servers in write_file/patch
Wire ~26 language servers (pyright, gopls, rust-analyzer, typescript-language-server,
clangd, bash-language-server, ...) into the post-write lint check used by write_file
and patch. The model now sees type errors, undefined names, missing imports, and
project-wide semantic issues introduced by its edits, not just syntax errors.
LSP is gated on git workspace detection: when the agent's cwd or the file being
edited is inside a git worktree, LSP runs against that workspace; otherwise the
existing in-process syntax checks are the only tier. This keeps users on
user-home cwds (Telegram/Discord gateway chats) from spawning daemons.
The post-write check is layered: in-process syntax check first (microseconds),
then LSP semantic diagnostics second when syntax is clean. Diagnostics are
delta-filtered against a baseline captured at write start, so the agent only
sees errors its edit introduced. A flaky/missing language server can never
break a write -- every LSP failure path falls back silently to the syntax-only
result.
New module agent/lsp/ split into:
- protocol.py: Content-Length JSON-RPC framer + envelope helpers
- client.py: async LSPClient (spawn, initialize, didOpen/didChange,
ContentModified retry, push/pull diagnostic stores)
- workspace.py: git worktree walk-up + per-server NearestRoot resolver
- servers.py: registry of 26 language servers (extension match,
root resolver, spawn builder per language)
- install.py: auto-install dispatch (npm install --prefix, go install
with GOBIN, pip install --target) into HERMES_HOME/lsp/bin/
- manager.py: LSPService (per-(server_id, root) client registry, lazy
spawn, broken-set, in-flight dedupe, sync facade for tools layer)
- reporter.py: <diagnostics> block formatter (severity-1-only, 20-per-file)
- cli.py: hermes lsp {status,list,install,install-all,restart,which}
Wired into tools/file_operations.py:
- write_file/patch_replace now call _snapshot_lsp_baseline before write
- _check_lint_delta gains a third tier: LSP semantic diagnostics when
syntax is clean
- All LSP code paths swallow exceptions; write_file's contract unchanged
Config: 'lsp' section in DEFAULT_CONFIG with enabled (default true),
wait_mode, wait_timeout, install_strategy (default 'auto'), and per-server
overrides (disabled, command, env, initialization_options).
Tests: tests/agent/lsp/ -- 49 tests covering protocol framing (encode and
read_message round-trip, EOF/truncation/missing Content-Length), workspace
gate (git walk-up, exclude markers, fallback to file location), reporter
(severity filter, max-per-file cap, truncation), service-level delta filter,
and an in-process mock LSP server that exercises the full client lifecycle
including didChange version bumps, dedup, crash recovery, and idempotent
teardown.
Live E2E verified end-to-end through ShellFileOperations: pyright
auto-installed via npm into HERMES_HOME, baseline captured, type error
introduced, single delta diagnostic surfaced with correct line/column/code/
source, then patch fix removes the diagnostic from the output.
Docs: new website/docs/user-guide/features/lsp.md page covering supported
languages, configuration knobs, performance characteristics, and
troubleshooting; cli-commands.md updated with the 'hermes lsp' reference;
sidebar updated.
* feat(lsp): structured logging, backend gate, defensive walk caps
Cherry-picks the substantive ideas from #24155 (different scope, same
problem space) onto our PR.
agent/lsp/eventlog.py (new): dedicated structured logger
``hermes.lint.lsp`` with steady-state silence. Module-level dedup sets
keep a 1000-write session at exactly ONE INFO line ("active for
<root>") at the default INFO threshold; clean writes log at DEBUG so
they never reach agent.log under normal config. State transitions
(server starts, no project root for a file, server unavailable) fire
at INFO/WARNING once per (server_id, key); novel events (timeouts,
unexpected errors) fire WARNING per call. Grep recipe: ``rg 'lsp\\['``.
agent/lsp/manager.py: wire the eventlog into _get_or_spawn and
get_diagnostics_sync so users can answer "did LSP fire on this edit?"
with a single grep, plus surface "binary not on PATH" warnings once
instead of silently retrying every write.
tools/file_operations.py: backend-type gate. ``_lsp_local_only()``
returns False for non-local backends (Docker / Modal / SSH /
Daytona); ``_snapshot_lsp_baseline`` and ``_maybe_lsp_diagnostics``
now skip entirely on remote envs. The host-side language server
can't see files inside a sandbox, so this prevents pretending to
lint a file the host process can't open.
agent/lsp/protocol.py: 8 KiB cap on the header block in
``read_message``. A pathological server that streams headers
without ever emitting CRLF-CRLF would have looped forever consuming
bytes; now raises ``LSPProtocolError`` instead.
agent/lsp/workspace.py: 64-step cap on ``find_git_worktree`` and
``nearest_root`` upward walks, plus try/except containment around
``Path(...).resolve()`` and child ``.exists()`` calls. Defensive
against pathological inputs (symlink loops, encoding errors,
permission failures mid-walk) — the lint hook is hot-path code and
must never raise.
Tests:
- tests/agent/lsp/test_eventlog.py: 18 tests covering steady-state
silence (clean writes stay DEBUG), state-transition INFO-once
semantics (active for, no project root), action-required
WARNING-once (server unavailable), per-call WARNING (timeouts,
spawn failures), and the "1000 clean writes => 1 INFO" contract.
- tests/agent/lsp/test_backend_gate.py: 5 tests verifying
_lsp_local_only / snapshot_baseline / maybe_lsp_diagnostics skip
the LSP layer for non-local backends and route correctly for
LocalEnvironment.
- tests/agent/lsp/test_protocol.py: new test_read_message_rejects_runaway_header
exercising the 8 KiB cap.
Validation:
- 73/73 LSP tests pass (49 original + 18 eventlog + 5 backend-gate + 1 framer cap)
- 198/198 pass when run alongside existing file_operations tests
- Live E2E re-run with pyright still surfaces "ERROR [2:12] Type
... reportReturnType (Pyright)" through the full path, then patch
fix removes it on the next call.
* feat(lsp): atexit cleanup + separate lsp_diagnostics JSON field
Two improvements salvaged from #24414's plugin-form alternative,
keeping our core-integrated design:
1. atexit cleanup of spawned language servers
----------------------------------------------------------------
``agent/lsp/__init__.get_service`` now registers an ``atexit``
handler on first creation that tears down the LSPService on
Python exit. Without this, every ``hermes chat`` exit was
leaking pyright/gopls/etc. processes for a few seconds while
their stdout buffers drained -- they got reaped by the kernel
eventually but a watchful ``ps aux`` would catch them.
The handler runs once per process (gated by
``_atexit_registered``); idempotent ``shutdown_service``
ensures double-fire is a no-op. Errors during shutdown are
swallowed at debug level since by the time atexit fires the
user has already seen the agent's final response.
2. Separate ``lsp_diagnostics`` field on WriteResult / PatchResult
----------------------------------------------------------------
Previously the LSP layer folded its diagnostic block into the
``lint.output`` string, conflating the syntax-check tier with
the semantic tier. The agent (and any downstream parsers) now
read syntax errors and semantic errors as independent signals:
{
"bytes_written": 42,
"lint": {"status": "ok", "output": ""},
"lsp_diagnostics": "<diagnostics file=...>\nERROR [2:12] ..."
}
``_check_lint_delta`` returns to its original two-tier shape
(syntax check + delta filter); ``write_file`` and
``patch_replace`` independently fetch LSP diagnostics via
``_maybe_lsp_diagnostics`` and pass them into the new field.
``patch_replace`` propagates the inner write_file's
``lsp_diagnostics`` so the outer PatchResult carries the patch's
delta correctly.
Tests: 19 new
- tests/agent/lsp/test_lifecycle.py (8 tests): atexit registration
fires once and only once across N get_service calls; the
registered callable is our internal shutdown wrapper;
shutdown_service is idempotent and safe when never started;
exceptions during shutdown are swallowed; inactive service is
cached so we don't rebuild on every check.
- tests/agent/lsp/test_diagnostics_field.py (11 tests): WriteResult
/ PatchResult dataclass shape, to_dict include/omit semantics,
channel separation (lint and lsp_diagnostics carry independent
signals), write_file populates the field via
_maybe_lsp_diagnostics only when the syntax tier is clean,
patch_replace propagates the field forward from its internal
write_file.
Validation:
- 92/92 LSP tests pass (73 prior + 8 lifecycle + 11 diagnostics field)
- 217/217 pass with file_operations + LSP combined
- Live E2E reverified: clean writes -> both fields empty/none; type
error introduced -> lint clean (parses), lsp_diagnostics carries
the pyright reportReturnType block; patch fix -> both fields
clean again.
* fix(lsp): broken-set short-circuit so a wedged server isn't paid every write
Discovered while auditing failure paths: a language server binary that
hangs (sleep forever, no LSP traffic on stdin/stdout) caused EVERY
subsequent write to re-pay the 8s snapshot_baseline timeout. Five
writes = ~64s of dead time.
The bug: ``_get_or_spawn`` adds the (server_id, root) pair to
``_broken`` inside its inner exception handler, but when the OUTER
``_loop.run`` timeout fires, it cancels the inner task before that
handler runs. The pair never makes it to broken-set, so the next
write re-enters the spawn path and re-pays the timeout.
Fix:
- New ``_mark_broken_for_file`` helper at the service layer marks
the (server_id, workspace_root) pair broken from the OUTSIDE when
the outer timeout fires. Called from the except branches in
``snapshot_baseline``, ``get_diagnostics_sync`` (asyncio.TimeoutError
+ generic Exception). Also kills any orphan client process that
survived the cancelled future, fire-and-forget with a 1s ceiling.
- ``enabled_for`` now consults the broken-set BEFORE returning True.
Files in already-broken (server_id, root) pairs short-circuit to
False, so the file_operations layer skips the LSP path entirely
with no spawn cost. Until the service is restarted (``hermes lsp
restart``) or the process exits.
- A single eventlog WARNING is emitted on first mark-broken so the
user knows which server gave up. Subsequent edits in the same
project stay silent.
Tests: 7 new in tests/agent/lsp/test_broken_set.py — covers the
key shape (server_id, per_server_root), enabled_for short-circuit,
sibling-file skip in same project, project isolation (broken in
A doesn't affect B), graceful no-op for missing-server / no-workspace,
and an end-to-end test that snapshots after a failure and verifies
the next ``enabled_for`` returns False.
Validation:
- Live retest of the wedged-binary scenario: 5 sequential writes,
first 8.88s (the one snapshot timeout), subsequent four ~0.84s
(no LSP cost). Down from 5x12.85s = 64s before this fix.
- 99/99 LSP tests pass (92 prior + 7 broken-set)
- 224/224 pass with file_operations + LSP combined
- Happy path E2E reverified — clean write, type error introduced,
patch fix all behave correctly with the new broken-set logic.
Note: the FIRST write to a wedged binary still pays 8s (the
snapshot_baseline timeout). We could shorten that, but pyright/
tsserver normally take 2-3s and slow CI rust-analyzer can need
5+ seconds, so 8s is the conservative ceiling. Subsequent writes
are instant.
Daytona ships breaking SDK changes on June 10, 2026 — `list()` returns
an iterator and the `page=` offset parameter is removed. We pin
daytona==0.155.0 so we're past the May 24 hard-cutoff, but the
legacy-sandbox resume path in DaytonaEnvironment still passes `page=1`
and reads `.items` off the result.
Switch to `next(iter(results), None)` against a single-result
`list(labels=..., limit=1)` call. Update tests to use `iter([...])`
and drop the `page=1` kwarg from list() assertions.
Allow integrations to share a visible Camofox identity with Hermes and recover existing tabs without carrying local patches.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(install): use `--extra all` not `--all-extras`; drop lazy-covered extras from [all]
Two coupled fixes for the Windows install hang where uv sync built
python-olm from sdist and failed on missing make.
# Root cause: --all-extras vs --extra all (credit: ethernet)
`uv sync --all-extras` installs every key in [project.optional-
dependencies], bypassing the curated [all] extra entirely. So even
when [all] excluded [matrix], [rl], [yc-bench], etc., the installer
pulled them anyway because they were still defined as extras. On
Windows that meant python-olm (no wheel, needs make to build from
sdist) and the install died there.
The right flag is `--extra all` — install just the [all] extra's
contents, respecting curation. Empirically verified via dry-run:
--all-extras: pulls python-olm, mautrix, ctranslate2, onnxruntime,
atroposlib, tinker, wandb, modal, daytona, vercel,
python-telegram-bot, discord.py, slack-bolt,
dingtalk-stream, lark-oapi, anthropic, boto3,
edge-tts, elevenlabs, exa-py, fal-client, faster-
whisper, firecrawl-py, honcho-ai, parallel-web
--extra all: pulls none of those — just [all]'s curated set
Dockerfile already uses `--extra all` (with comment explaining the
gotcha) — knowledge existed; the gap was install.sh / install.ps1 /
setup-hermes.sh.
Sites fixed: scripts/install.sh L1118, scripts/install.ps1 L809,
setup-hermes.sh L245.
# Companion fix: drop lazy-covered extras from [all]
`tools/lazy_deps.py` already covers anthropic, bedrock, exa,
firecrawl, parallel-web, fal, edge-tts, elevenlabs, modal, daytona,
vercel, all messaging platforms (telegram/discord/slack/matrix/
dingtalk/feishu), honcho, and faster-whisper. They were ALSO in
[all], which defeats the whole point of lazy-install — fresh
installs eager-pulled them and inherited whatever was broken
upstream (the matrix → python-olm → no Windows wheel chain being
the proximate symptom).
[all] now contains only what genuinely can't be lazy-installed:
cron, cli, dev, pty, mcp, homeassistant, sms, acp, google, web,
youtube. Same trim applied to [termux-all]. New regression test
asserts the contract: every extra in LAZY_DEPS must NOT also appear
in [all].
# Companion fix: surface uv progress + errors
setup-hermes.sh's hash-verified path swallowed uv's stderr to a
tempfile, identical to the install.sh bug fixed in PR #24504. Same
fix applied: stream stderr through directly so users see live
progress instead of staring at a frozen prompt.
# Files
- pyproject.toml: trim [all] and [termux-all] to non-lazy extras only.
- scripts/install.sh: --all-extras → --extra all; trim _ALL_EXTRAS /
_PYPI_EXTRAS to match.
- scripts/install.ps1: --all-extras → --extra all; trim $allExtras /
$pypiExtras to match.
- setup-hermes.sh: --all-extras → --extra all; stream stderr.
- tests/test_project_metadata.py: invert matrix-in-[all] assertion;
add lazy-coverage contract test.
- uv.lock: regenerated.
# Validation
5/5 metadata tests pass. 37/37 in update_autostash + tool_token_
estimation. `uv lock --check` passes. Empirical dry-run confirms
`--extra all` excludes python-olm + RL chain on the new lockfile.
* fix(install): parse [all] from pyproject.toml instead of mirroring it
ethernet's review point: the previous patch left two hand-mirrored
copies of [all]'s contents (in install.sh's $_ALL_EXTRAS and
install.ps1's $allExtras). That guarantees future drift the next
time pyproject.toml's [all] changes.
Now both scripts parse pyproject.toml at install time using stdlib
tomllib (Python 3.11+, which the bootstrap step already requires).
Single source of truth. The only purpose of the parsed list is to
build the 'Tier 2: [all] minus broken extras' fallback spec — so we
parse, filter against $brokenExtras, and rebuild the .[a,b,c] spec.
Also: removed redundant fallback tiers.
Before: Tier 1 [all]
Tier 2 [all] minus broken
Tier 3 PyPI-only extras (no git deps)
Tier 4 [web,mcp,cron,cli,messaging,dev]
Tier 5 .
After: Tier 1 [all]
Tier 2 [all] minus broken
Tier 3 .
Tier 3 (PyPI-only) and Tier 4 (dashboard+core) used to dodge the [rl]
git+sdist deps and the [matrix] python-olm build. Both are no longer
in [all] post-2026-05-12 lazy-install migration, so the carve-out
tiers had no remaining content. Tier 4 also referenced [messaging],
which is now lazy-installed — the hardcoded fallback was actually
inconsistent with the new policy.
Defensive fallback: if tomllib parse fails (corrupted pyproject,
unexpected schema), Tier 2 collapses to '.[all]' (same as Tier 1) so
the broken-extras path becomes a no-op rather than crashing.
* fix(gateway): hide Matrix from setup picker on Windows
Matrix is the one messaging platform that has no working install path
on Windows: [matrix] -> mautrix[encryption] -> python-olm, which has
Linux-only wheels and needs make + libolm to build from sdist. The
[all] cleanup in this PR keeps mautrix out of fresh installs, but a
user who picked Matrix in 'hermes setup gateway' would still walk
into the same sdist build failure when the wizard tried to install
the extra.
Hide the option at the picker so users never get the chance to try.
The gate lives in _all_platforms() — single source of truth for the
setup wizard, the curses gateway-config menu, and any future picker.
Adapter loading at runtime is intentionally NOT gated: users who
already have MATRIX_* env vars set (e.g. config copied from a Linux
install) keep working if they somehow have python-olm available.
This is the lowest-friction fix — picker visibility only.
Tests cover linux/darwin/win32 and verify other platforms aren't
collateral damage.
Post-#21561 the liveness probe in acquire_scoped_lock() routes through
gateway.status._pid_exists (psutil-first, safe on Windows), not
os.kill(pid, 0). The two new macOS regression tests were patching
status.os.kill, which had no effect — the unmocked psutil call returned
False for PID 99999, marking the lock stale before the new code branch
ran. The 'replaces' test passed only because acquired=True was already
the expected outcome; the 'keeps' test failed in CI.
Switch both tests to monkeypatch status._pid_exists directly, matching
the existing test_acquire_scoped_lock_rejects_live_other_process pattern,
so they actually exercise the new start_time=None + cmdline-based
staleness branch.
On macOS (and Windows), /proc is unavailable so _get_process_start_time()
always returns None. When a gateway creates a scoped lock record with
start_time=None and then exits, macOS can reuse that PID for an unrelated
process. On restart, acquire_scoped_lock() sees:
1. os.kill(pid, 0) succeeds (PID is alive — but it's bluetoothuserd, not
the gateway)
2. existing.start_time is None and current_start is None, so the
start_time comparison is inconclusive
3. The lock is treated as active, blocking gateway startup with:
"Telegram bot token already in use (PID 873). Stop the other gateway
first."
Root cause: _read_process_cmdline() only reads /proc/<pid>/cmdline, which
doesn't exist on macOS. It always returns None, making
_looks_like_gateway_process() always return False, so the cmdline fallback
path in acquire_scoped_lock() was unreachable on macOS.
Fix (two parts):
1. _read_process_cmdline(): Add a ps(1) fallback for platforms without
/proc. When /proc/<pid>/cmdline doesn't exist, we now run
"ps -p <pid> -o command=" to retrieve the process command line. The
/proc path is tried first (preserving Linux performance); ps is only
invoked as a fallback.
2. acquire_scoped_lock(): When both the lock record's start_time and the
live process's start_time are None (the macOS case), fall back to
checking whether the live PID still looks like a Hermes gateway process
via _looks_like_gateway_process(). If it doesn't, the lock is stale.
Closes#16376
Detect when write_file / patch calls fail during a turn and are never
superseded by a successful write to the same path. When the final
text response is delivered, append an advisory footer listing the
files that did NOT change — so models that over-claim 'patched 5 files'
after 4 silent failures can't hide the lie.
Catches the failure mode reported in Ben Eng's llm-wiki session:
grok-4.1-fast issued batches of parallel patches, half failed with
'Could not find old_string', and the agent summarised the turn
claiming every file was edited. The user had to manually run
'git status' each turn to catch it.
The verifier is a pure post-hoc check on tool results — no new LLM
calls, no synthetic messages injected into history (prompt cache
preserved), no changes to tool argument dispatch. Per-turn state is
keyed by path; a later successful write to the same path clears the
failure entry so single-file retry recovery is not flagged.
Wired into both _execute_tool_calls_concurrent and
_execute_tool_calls_sequential, so batched parallel patches and one-at-
a-time edits are both covered. Footer emission happens after the
agent loop exits, before transform_llm_output / post_llm_call plugin
hooks run, so plugins still see (and can modify) the augmented text.
Config: display.file_mutation_verifier (bool, default true) +
HERMES_FILE_MUTATION_VERIFIER env override.
31 unit tests in tests/run_agent/test_file_mutation_verifier.py cover
target extraction (write_file, patch-replace, patch-v4a single and
multi-file), error-preview extraction (JSON .error field and plain
string), per-turn state transitions (first-error-wins on repeated
failure, success supersedes failure), footer rendering (truncation
at 10 entries, user-actionable hint), and env/config precedence.
Companion docs updated: user-guide/configuration.md +
reference/environment-variables.md.
* feat(security): supply-chain advisory checker + lazy-install framework + tiered install fallback
Three coordinated mitigations for the Mini Shai-Hulud worm hitting
mistralai 2.4.6 on PyPI (2026-05-12) and for the next single-package
compromise that follows.
# What this PR makes true
1. Users with the poisoned mistralai 2.4.6 in their venv get a loud
detection banner with copy-pasteable remediation steps the moment
they run hermes (and on every gateway startup).
2. One quarantined / yanked PyPI package can no longer silently demote
a fresh install to 'core only' — the installer keeps every other
extra and tells the user which tier landed.
3. Future opt-in backends (Mistral, ElevenLabs, Honcho, etc.) can
lazy-install on first use under a strict allowlist, instead of
eagerly pulling everything at install time.
# Detection: hermes_cli/security_advisories.py
- ADVISORIES catalog (one entry currently: shai-hulud-2026-05 for
mistralai==2.4.6). Adding the next one is a single dataclass.
- detect_compromised() uses importlib.metadata.version() — no pip
dependency, works in uv venvs that lack pip.
- Banner cache (~/.hermes/cache/advisory_banner_seen) rate-limits
the startup banner to once per 24h per advisory.
- Acks persisted to security.acked_advisories in config.yaml; never
re-banner after ack.
- Wired into:
* hermes doctor — runs first, prints full remediation block
* hermes doctor --ack <id> — dismisses an advisory
* cli.py interactive run() and single-query branches — short
stderr banner pointing at hermes doctor
* gateway/run.py startup — operator-visible warning in gateway.log
# Lazy-install framework: tools/lazy_deps.py
- LAZY_DEPS allowlist maps namespaced feature keys (tts.elevenlabs,
memory.honcho, provider.bedrock, etc.) to pip specs.
- ensure(feature) installs missing deps in the active venv via the
uv → pip → ensurepip ladder (matches tools_config._pip_install).
- Strict spec safety regex rejects URLs, file paths, shell metas,
pip flag injection, control chars — only PyPI-by-name accepted.
- Gated on security.allow_lazy_installs (default true) plus the
HERMES_DISABLE_LAZY_INSTALLS env var for restricted/audited envs.
- Migrated three backends as proof of pattern:
* tools/tts_tool.py — _import_elevenlabs() calls ensure first
* plugins/memory/honcho/client.py — get_honcho_client lazy-installs
* tts.mistral / stt.mistral entries pre-registered for when PyPI
restores mistralai
# Installer fallback tiers
scripts/install.sh, scripts/install.ps1, setup-hermes.sh:
- Centralised _BROKEN_EXTRAS list (currently: mistral). Edit one
array when a transitive breaks; users keep every other extra.
- New 'all minus known-broken' tier between [all] and the existing
PyPI-only-extras tier. Only kicks in when [all] fails resolve.
- All three tiers explicit: every fallback announces which tier
landed and prints a re-run hint when not on Tier 1.
- install.ps1 and install.sh both regenerate their tier specs from
the same _BROKEN_EXTRAS array so updates stay in sync.
Side effect: install.ps1 Tier 2 spec previously hardcoded 'mistral'
in its extra list — bug fixed by the refactor (mistral is filtered
out).
# Config
hermes_cli/config.py — DEFAULT_CONFIG.security gains:
- acked_advisories: [] (advisory IDs the user has dismissed)
- allow_lazy_installs: True (security gate for ensure())
No config version bump needed — both keys nest under existing
security: block, and load_config's deep-merge picks up DEFAULT_CONFIG
defaults for users with older configs.
# Tests
tests/hermes_cli/test_security_advisories.py — 23 tests covering:
- detect_compromised matches/non-matches, wildcard frozenset
- ack persistence, idempotence, blank rejection, config-failure path
- banner cache rate limiting + 24h re-banner + ack-stops-banner
- short_banner_lines / full_remediation_text / render_doctor_section /
gateway_log_message
- shipped catalog well-formedness invariant
tests/tools/test_lazy_deps.py — 40 tests covering:
- spec safety: 11 safe parametrized + 18 unsafe parametrized
- allowlist: unknown-feature rejection, namespace.name shape,
every shipped spec passes the safety regex
- security gating: config flag, env var, default, fail-open
- ensure() happy/sad paths: already-satisfied, install success,
pip stderr surfaced on failure, install-succeeds-but-still-missing
- is_available, feature_install_command
Combined: 63 new tests, all passing under scripts/run_tests.sh.
# Validation
- scripts/run_tests.sh tests/hermes_cli/test_security_advisories.py
tests/tools/test_lazy_deps.py → 63/63 passing
- scripts/run_tests.sh tests/hermes_cli/test_doctor.py
tests/hermes_cli/test_doctor_command_install.py
tests/tools/test_tts_mistral.py tests/tools/test_transcription_tools.py
tests/tools/test_transcription_dotenv_fallback.py → 165/165 passing
- scripts/run_tests.sh tests/hermes_cli/ tests/tools/ →
9191 passed, 8 pre-existing failures (verified on origin/main
before this change)
- bash -n on install.sh and setup-hermes.sh → OK
- py_compile on all modified .py files → OK
- End-to-end smoke test of detect_compromised + render_doctor_section
+ gateway_log_message with mocked installed version → produces
copy-pasteable remediation output
# Community
Full advisory + remediation steps:
website/docs/community/security-advisories/shai-hulud-mistralai-2026-05.md
Short-form post drafts (Discord, GitHub pinned issue, README banner):
scripts/community-announcement-shai-hulud.md
Refs: PR #24205 (mistral disabled), Socket Security advisory
<https://socket.dev/blog/mini-shai-hulud-worm-pypi>
* build(deps): pin every direct dep to ==X.Y.Z (no ranges)
Companion to the supply-chain advisory work: replace every >=/</~= range
in pyproject.toml's [project.dependencies] and [project.optional-dependencies]
with an exact ==X.Y.Z pin sourced from uv.lock.
Why: ranges allow PyPI to ship a fresh version of any direct dep at any
time without a code review on our side. With ranges, the malicious
mistralai 2.4.6 release would have been pulled by every fresh
'pip install -e .[all]' for the hours between upload and PyPI's
quarantine — exactly the install window we got hit on. Exact pins close
that window: the only way a new package version reaches a user is via
an intentional update on our end.
What the user-facing change is: nothing, behavior-wise. Every package
resolves to the same version it was already resolving to via uv.lock —
the pins just remove the resolver's freedom to pick a different one.
Cost: any user installing Hermes alongside another package that requires
a newer pin gets a resolver conflict. Acceptable for our isolated-venv
install path; documented in the new comment block.
Build-system requires line (setuptools>=61.0) is intentionally left
as a range — pinning the build backend would block fresh pip from
bootstrapping the build on architectures where that exact wheel isn't
available.
mistral extra (mistralai==2.3.0) is pinned but stays out of [all]
(per PR #24205). 'uv lock' regeneration will fail until PyPI restores
mistralai; lockfile regeneration is gated behind that, NOT on every PR.
LAZY_DEPS in tools/lazy_deps.py also moved to exact pins so the lazy-
install pathway can never resolve a different version than the one
declared in pyproject.toml.
Validation:
- Cross-checked all 77 pinned direct deps in pyproject.toml against
uv.lock — every pin matches the resolved version exactly.
- Cross-checked all LAZY_DEPS specs against uv.lock — same.
- 'uv pip install -e .[all] --dry-run' resolves 205 packages cleanly.
- tests/tools/test_lazy_deps.py + tests/hermes_cli/test_security_advisories.py
→ 63/63 passing (every shipped spec passes the safety regex).
- Doctor + TTS + transcription targeted suite → 146/146 passing.
* build(deps): hash-verify transitives via uv.lock; remove unresolvable [mistral] extra
You asked: 'what about the dependencies the dependencies rely on?' —
correctly noting that exact-pinning direct deps in pyproject.toml does
NOT cover the transitive graph. `pip install` and `uv pip install` both
re-resolve transitives fresh from PyPI at install time, so a compromised
transitive (e.g. `httpcore` if it got worm-poisoned tomorrow) would
still hit our users even with every direct dep exact-pinned.
# What this commit fixes
1. **Both real installer scripts now prefer `uv sync --locked` as Tier 0.**
uv.lock records SHA256 hashes for every transitive — a compromised
package with a different hash gets REJECTED. Falls through to the
existing `uv pip install` cascade if the lockfile is missing or
stale, with a loud warning that the fallback path does NOT
hash-verify transitives. Previously only `setup-hermes.sh` (the dev
path) used the lockfile; `scripts/install.sh` and `scripts/install.ps1`
(the paths fresh users actually run) skipped it.
2. **Removed the `[mistral]` extra entirely.** The `mistralai` PyPI
project is fully quarantined right now — every version returns 404,
so any pin we wrote was unresolvable, which broke `uv lock --check`
in CI. Restoration is documented in pyproject.toml as a 5-step
checklist (verify, re-add extra, re-enable in 4 modules, regenerate
lock, optionally re-add to [all]).
3. **Regenerated uv.lock.** 262 packages, mistralai/eval-type-backport/
jsonpath-python pruned. `uv lock --check` now passes.
# Defense-in-depth view
| Layer | Where | Protects against |
|----------------------------|-------------------|-------------------------------------------|
| Exact pins in pyproject | direct deps | new mistralai 2.4.6-style direct compromise |
| uv.lock + `--locked` install | transitive graph | transitive worm injection |
| Tier-0 hash-verified path | install.sh / .ps1 | actually USE the lockfile in fresh installs |
| `uv lock --check` CI gate | every PR | drift between pyproject and lockfile |
| `hermes_cli/security_advisories.py` | runtime | cleanup for users who already got hit |
The exact pinning + hash verification together close the supply-chain
gap. Without the lockfile path, exact pins alone are theater.
# Validation
- `uv lock --check` → passes (262 packages resolved, no drift).
- `bash -n` on install.sh + setup-hermes.sh → OK.
- 209/209 tests passing across new + adjacent test files
(test_lazy_deps.py, test_security_advisories.py, test_doctor.py,
test_tts_mistral.py, test_transcription_tools.py).
- TOML parse OK.
* chore: remove community announcement drafts (PR body covers it)
* build(deps): lazy-install every opt-in backend (anthropic, search, terminal, platforms, dashboard)
Extends the lazy-install framework to cover everything that's not used by
every hermes session. Base install drops from ~60 packages to 45.
Moved out of core dependencies = []:
- anthropic (only when provider=anthropic native, not via aggregators)
- exa-py, firecrawl-py, parallel-web (search backends; only when picked)
- fal-client (image gen; only when picked)
- edge-tts (default TTS but still optional)
New extras in pyproject.toml: [anthropic] [exa] [firecrawl] [parallel-web]
[fal] [edge-tts]. All added to [all].
New LAZY_DEPS entries: provider.anthropic, search.{exa,firecrawl,parallel},
tts.edge, image.fal, memory.hindsight, platform.{telegram,discord,matrix},
terminal.{modal,daytona,vercel}, tool.dashboard.
Each import site now calls ensure() before importing the SDK. Where the
module had a top-level try/except (telegram, discord, fastapi), the
graceful-fallback pattern was extended to lazy-install on first
check_*_requirements() call and re-bind module globals.
Updated test_windows_native_support.py tzdata check from snapshot
(>=2023.3 literal) to invariant (any version + win32 marker).
Validation:
- Base install: 45 packages (was ~60); 6 newly-extracted packages absent
- uv lock --check: passes (262 packages, no drift)
- 209/209 lazy_deps + advisory + doctor + tts/transcription tests passing
- py_compile clean on all 12 modified modules
The `mistralai` PyPI package was quarantined on 2026-05-12 after a
malicious 2.4.6 release. Every fresh resolve (AUR makepkg, Docker build,
CI run, install.sh first-run) currently fails on
`mistralai>=2.3.0,<3` because PyPI returns zero candidates.
Existing users running `hermes update` mostly didn't notice — `hermes
update` falls back from `.[all]` to per-extra retries and silently
skips mistral with a warning that scrolls past. But fresh installs
hard-fail or lose every other extra.
Changes:
- pyproject.toml: drop `hermes-agent[mistral]` from `[all]` and
`[termux-all]`. The `mistral` extra itself is preserved so users
can opt back in once PyPI un-quarantines.
- hermes_cli/tools_config.py: hide Mistral Voxtral TTS from the
`hermes tools` provider picker until restored.
- hermes_cli/web_server.py: drop "mistral" from dashboard STT options.
- tools/transcription_tools.py: explicit `provider: mistral` returns
"none" with a clear status message; auto-detect skips mistral.
- tools/tts_tool.py: dispatcher returns a clear "temporarily disabled"
error before any SDK import attempt (avoids cached-stale-package
surprises).
- tests/tools/: update three test files to assert the new disabled
behavior. Each test docstring records why and points at the rollback
trigger (PyPI un-quarantines mistralai).
Restore plan: revert this commit once the package is available on PyPI
again. The behavior change is intentional and documented in code
comments + test docstrings to make the rollback trivial.
Validation:
- scripts/run_tests.sh tests/tools/ -k 'mistral or stt or tts' →
425/425 passing.
Refs: https://pypi.org/simple/mistralai/ (currently
"pypi:project-status: quarantined").
Handle MiniMax OAuth expiry values consistently across CLI and dashboard
flows, fix CLI status/add behavior, and force pooled OAuth runtime
requests through Anthropic Messages.
- web_server._minimax_poller: parse expired_in via the shared resolver
so unix-ms absolute timestamps stop landing as TTL seconds and crashing
with 'year 583911 is out of range' when a user connects MiniMax OAuth
from the dashboard.
- auth._minimax_oauth_login / _refresh_minimax_oauth_state: same fix on
the CLI login + refresh paths.
- auth.get_auth_status: dispatch minimax-oauth to its dedicated status
function instead of falling through.
- auth_commands.auth_add_command: 'hermes auth add minimax-oauth' now
starts the device-code login flow and persists a pool entry with the
access + refresh tokens, instead of requiring credentials to already
exist.
- runtime_provider._resolve_runtime_from_pool_entry: pin pooled
minimax-oauth credentials to anthropic_messages so a stale
model.api_mode: chat_completions can't send requests to
/anthropic/chat/completions and trigger MiniMax nginx 404s.
Co-authored-by: Cursor <cursoragent@cursor.com>
Qwen models on Nous Portal (e.g. qwen3.6-plus) now get the same envelope-layout
cache_control markers and long-lived (1h cross-session) cache treatment as
Portal Claude. Portal proxies to OpenRouter with identical wire-format and
cache_control semantics, but the prior policy left Portal Qwen falling through
to the alibaba-family branch (which only matches provider=opencode/alibaba),
serving 0% cache hits and re-billing the full prompt every turn.
Scope is narrow: Portal Claude OR Portal Qwen. Other models on Portal keep
their existing behavior.
- _anthropic_prompt_cache_policy: add (is_nous_portal and qwen) -> (True, False)
- _supports_long_lived_anthropic_cache: drop Claude-only gate for Portal so
Qwen also gets the validated 1h cross-session layout
- tests cover both functions, both bare and vendored qwen slug forms, and
the rejection of non-Claude non-Qwen Portal traffic
Free-tier users were seeing 'No free models currently available.' in the
`hermes model` and post-login pickers even though qwen/qwen3.6-plus is
free on the Portal right now. Three independent breakages compounded:
1. The docs-hosted catalog manifest at website/static/api/model-catalog.json
was not regenerated when _PROVIDER_MODELS['nous'] was updated, so users
fetching the manifest got a list that didn't include qwen/qwen3.6-plus.
2. _resolve_nous_pricing_credentials() returned ('', '') on any auth blip,
collapsing get_pricing_for_provider('nous') to {} and making every
curated model fall through the free-tier filter as 'paid'.
3. Even with healthy pricing, the picker only ever showed models from the
in-repo curated list intersected with live pricing — a Portal-flagged
free model not yet in the curated list could never appear.
Changes:
- hermes_cli/models.py: new union_with_portal_free_recommendations() that
augments the curated list with Portal freeRecommendedModels entries
(with synthetic free pricing so partition keeps them). The Portal's
/api/nous/recommended-models endpoint is now the source of truth for
free-tier surfacing — old Hermes builds will see new free models
without a CLI release.
- hermes_cli/models.py: _resolve_nous_pricing_credentials() falls back to
the public inference base URL when runtime cred resolution fails.
The /v1/models endpoint exposes pricing without auth, so silently
returning {} just because a refresh token expired was wrong.
- hermes_cli/auth.py + hermes_cli/main.py: both free-tier picker call
sites call union_with_portal_free_recommendations() before partition.
- tests/hermes_cli/test_models.py: 7 tests covering union behaviour
(prepend, dedup, end-to-end with stale pricing, empty/missing/error
payloads, invalid entries).
- tests/hermes_cli/test_model_catalog.py: drift guard
TestManifestMatchesInRepoLists fails CI when _PROVIDER_MODELS['nous']
or OPENROUTER_MODELS is edited without re-running
scripts/build_model_catalog.py. Verified empirically that removing a
manifest entry triggers an assertion with an actionable error message.
Validation:
- 133/133 targeted tests pass (test_models, test_model_catalog,
test_auth_nous_provider).
- Live E2E against the real Portal:
- Stale curated list ['claude-opus','claude-sonnet','gpt-5.4'] (no
qwen) → after union: ['qwen/qwen3.6-plus', ...] →
partition(free_tier=True): selectable=['qwen/qwen3.6-plus'].
- Simulated expired refresh token → anon fetch returns 403 pricing
entries including qwen/qwen3.6-plus -> {prompt:0, completion:0}.
- ruff: clean.
cua-driver was only installed once on toolset enable: `_run_post_setup` early-returns when the binary is already on PATH, so upstream fixes (e.g. v0.1.6 Safari window-focus fix) never reached existing users without manual reinstall.
Two refresh points now:
- `hermes update` re-runs the upstream installer at the end of the update if cua-driver is on PATH (macOS-only, no-op otherwise). Ties driver freshness to the user-controlled update cadence — no startup latency, no per-launch GitHub API call.
- `hermes computer-use install --upgrade` for manual force-refresh.
The upstream `install.sh` always pulls the latest release, so re-running is the canonical upgrade path. No version-comparison logic needed.
`hermes computer-use status` now shows the installed version, and points at `--upgrade` for refreshing.
Fixes#22832.
## Root cause
`hermes_cli/web_server.py:start_oauth_login` dispatched OAuth flows by
the catalog's `flow` field rather than provider id:
if catalog_entry["flow"] == "pkce":
return _start_anthropic_pkce()
The catalog had two `flow: "pkce"` entries — `anthropic` and
`minimax-oauth` — so clicking "Login" on MiniMax in the dashboard's
Keys tab unconditionally launched the Anthropic/Claude PKCE flow.
## Fix
Three changes in `hermes_cli/web_server.py`:
1. Catalog entry for `minimax-oauth` changed from `flow: "pkce"` to
`flow: "device_code"`. From a UX perspective MiniMax is a
verification-URI + user-code flow (open URL, enter code, backend
polls) — same shape as Nous's device-code flow. The PKCE bit
(verifier + challenge from `_minimax_pkce_pair`) is a security
extension that doesn't change the operator experience; the existing
dashboard modal already renders `device_code` correctly for this UX.
2. New MiniMax branch in `_start_device_code_flow`, mirroring the
existing Nous branch but calling MiniMax-specific helpers
(`_minimax_request_user_code`, `_minimax_pkce_pair`). Stashes
verifier + state in the session for the poller to consume. Handles
the overloaded `expired_in` field (could be unix-ms timestamp OR
seconds-from-now duration) the same way `_minimax_poll_token` does.
3. New `_minimax_poller` background thread mirroring `_nous_poller`.
Calls `_minimax_poll_token` → on success builds the same
`auth_state` dict the CLI flow (`_minimax_oauth_login`) builds, and
persists via `_minimax_save_auth_state` so the dashboard path leaves
the system in the same state as `hermes auth add minimax-oauth`.
Plus a dispatcher tightening to prevent regression: the `pkce` branch
now requires `provider_id == "anthropic"`, so any future PKCE provider
added without a proper start function gets a clean
`400 Unsupported flow` rather than silently launching Anthropic OAuth.
## Test
New `tests/hermes_cli/test_web_oauth_dispatch.py`:
- Regression test asserting MiniMax start does NOT return claude.ai
- Sanity test that Anthropic PKCE still works after the dispatcher
tightening
- Forward-looking test: a hypothetical pkce-flagged provider without
an explicit branch is rejected cleanly rather than misrouted
## Limitations
- The dashboard MiniMax path defaults to `region="global"`. CN-region
operators can still use the CLI flow which supports `--region cn`.
Adding a region toggle to the dashboard UI is a follow-up.
Follow-up to #23863 (CJK table alignment). The realigner was
correctly padding pipes to identical column offsets, but when a
table's natural width exceeds terminal cells it produced lines that
the terminal soft-wrapped mid-cell, destroying column alignment
visually even though the bytes were perfectly padded. Reported as
'columns are not aligned' on tables containing one long row alongside
several short rows.
Approach mirrors Claude Code's MarkdownTable.tsx narrow-terminal
fallback: when realign_markdown_tables is given an available_width
budget and the rebuilt horizontal table exceeds it, render each body
row as 'Header: value' lines separated by a thin ─ rule. Word-wraps
oversize values at the budget with a 2-space continuation indent.
- agent/markdown_tables.py: realign_markdown_tables(text, available_width=None);
threshold check at the top of _render_block flips into a new
_render_vertical fallback. Includes _wrap_to_width with hard-break
for tokens longer than the budget.
- cli.py: helper _terminal_width_for_streaming() returns
shutil.get_terminal_size().columns minus _STREAM_PAD and a 2-cell
safety margin; passed to all three realign call sites
(_render_final_assistant_content for strip+render Panel paths, and
the streaming flushers in _emit_stream_text / _flush_stream).
- tests/agent/test_markdown_tables.py: 4 new tests covering the
overflow-vertical fallback for ASCII + CJK content, the
'fits → keep horizontal' case, and the long-cell wrap with indent.
Live-verified: with COLUMNS=100, the user's reported 'long row in
ASCII table' case now renders as vertical key-value rows that all fit
the panel; the 6-column CJK comparison table still renders as an
aligned horizontal table because it fits inside 100 cols.
The old mtime-tracking staleness machinery (_tui_build_needed,
_hermes_ink_bundle_stale, _find_bundled_tui) tried to avoid rebuilding
by comparing source timestamps to dist/entry.js. This was fragile and
added ~100 lines of code. Replace with three clear paths:
1. HERMES_TUI_DIR set (prebuilt/nix): just node dist/entry.js, no build
2. --dev mode: tsx src/entry.tsx, no build, hot reload
3. Normal: always npm run build (esbuild is ~1s, correctness > caching)
Also error when HERMES_TUI_DIR is set with --dev (footgun: prebuilt
bundle has no source code to hot-reload).
Set HERMES_SESSION_ID using the existing session_context.py ContextVar
system for concurrency safety (multiple gateway sessions in one process
won't cross-talk). Also writes os.environ as fallback for CLI mode.
Touchpoints:
- gateway/session_context.py: Add _SESSION_ID ContextVar + _VAR_MAP entry
- run_agent.py: Set both ContextVar and os.environ at init and on
context-compression rotation
- tools/environments/local.py: Bridge ContextVars into subprocess env
in _make_run_env() (ContextVars don't propagate to child processes)
- tests/run_agent/test_session_id_env.py: 3 tests covering env, provided
ID, and ContextVar paths
execute_code subprocess already passes HERMES_* prefixed vars through
_scrub_child_env (line 82: _SAFE_ENV_PREFIXES includes 'HERMES_').
Primary use case: webhook-triggered agents that need to include a
`--resume <session_id>` takeover command in their output.
Cuts input cost for first-turn Claude requests by ~85-90% on subsequent
sessions within an hour. Tools array (~13k tokens for default toolset) +
stable system prefix (~5-8k tokens) get a 1h cache_control marker; the
volatile suffix (memory, USER profile, timestamp, session id) sits in a
separate non-cached block at the end so it doesn't poison the cross-session
prefix when it changes.
Provider gate: Claude on native Anthropic (incl. OAuth subscription),
OpenRouter, and Nous Portal (which proxies to OpenRouter). All other
providers keep today's system_and_3 layout unchanged.
Layout (4 cache_control breakpoints, Anthropic max):
1. tools[-1] -> 1h (cross-session)
2. system content[0] -> 1h (cross-session, stable prefix)
3. messages[-2] -> 5m (within-session rolling)
4. messages[-1] -> 5m (within-session rolling)
Within-session rolling shrinks from 3 messages to 2 to free the breakpoint
budget. On Claude with realistic tool loadouts the long-lived tier carries
the bulk of cross-session value anyway.
System prompt is now always assembled cache-friendly: stable identity /
guidance / skills / platform hints first, then session-stable context
files (AGENTS.md, .cursorrules), then per-call volatile content. Old
single-string callers see the same logical content (same join order),
just reordered so volatile lives at the end.
Config knobs (defaults shown):
prompt_caching:
cache_ttl: "5m" # rolling-window TTL (unchanged)
long_lived_prefix: true # opt-out switch
long_lived_ttl: "1h" # cross-session prefix TTL
Live E2E (tests/agent/test_prompt_caching_live.py, gated on
OPENROUTER_API_KEY) on anthropic/claude-haiku-4.5 with default toolset:
Call 1 (cold): cache_write=13,415 cache_read=0
Call 2 (NEW agent + msg): cache_write=391 cache_read=13,025
Cross-session reuse: 97.09%
Implementation:
* agent/prompt_caching.py: new apply_anthropic_cache_control_long_lived()
+ mark_tools_for_long_lived_cache(); existing apply_anthropic_cache_control()
preserved verbatim for the fallback path.
* agent/anthropic_adapter.py: convert_tools_to_anthropic() now forwards
cache_control onto each Anthropic-format tool dict.
* run_agent.py: _build_system_prompt_parts() returns the 3-tier dict;
_build_system_prompt() joins them (backward compatible).
_supports_long_lived_anthropic_cache() policy added next to the existing
_anthropic_prompt_cache_policy() (which now also recognises Nous Portal
Claude — pre-existing gap fixed in passing).
_build_api_kwargs() resolves tools_for_api once and propagates the
marker through all four build paths (anthropic_messages, bedrock,
codex_responses, profile/legacy chat completions).
Long-lived flag plumbed into the runtime snapshot/restore + model-switch
+ fallback-promotion paths.
Tests:
* tests/agent/test_prompt_caching.py: +8 tests (TestMarkToolsForLongLivedCache,
TestApplyAnthropicCacheControlLongLived).
* tests/run_agent/test_anthropic_prompt_cache_policy.py: +9 tests
(TestSupportsLongLivedAnthropicCache matrix across 8 endpoint classes
+ a fallback-target case).
* tests/agent/test_prompt_caching_live.py: new live E2E (skipif when
OPENROUTER_API_KEY is unset; runs outside the hermetic suite).
* Targeted suites: 327/327 pass (caching/adapter/policy/builder).
* tests/agent/ + tests/run_agent/: 3992 pass, 17 skip, 1 pre-existing
flake (test_async_httpx_del_neuter::test_same_key_replaces_stale_loop_entry,
verified failing on pristine origin/main).
#23482 fixed cache poisoning in the sync path: when a Codex auxiliary
timeout closes the underlying OpenAI client, _evict_cached_client_instance
walks CodexAuxiliaryClient wrappers via their _real_client attribute and
drops the cache entry so the next aux call rebuilds.
The cache key includes async_mode (see _client_cache_key), so the sync and
async clients for the same provider live in two distinct entries pointing
at the same underlying transport. The fix walked the sync wrapper's
_real_client correctly but the async wrappers
(AsyncCodexAuxiliaryClient, AsyncAnthropicAuxiliaryClient,
AsyncGeminiNativeClient) never exposed _real_client at all, so the async
entry survived eviction and kept handing out the poisoned client.
Effect on async aux callers: one timeout now poisons every subsequent
async aux call (compression, vision, session_search, title_generation)
with 'Connection error' until gateway restart -- even while the sync
route recovered as designed in #23482.
Mirror the sync wrapper's _real_client onto each async wrapper so the
existing eviction helper finds them. Three changes, one per wrapper:
- AsyncCodexAuxiliaryClient: self._real_client = sync_wrapper._real_client
(the underlying OpenAI client)
- AsyncAnthropicAuxiliaryClient: same shape
- AsyncGeminiNativeClient: self._real_client = sync_client (Gemini's
native facade is itself the leaf; no OpenAI client beneath it)
Update _evict_cached_client_instance docstring to reflect that it now
covers both sync and async wrappers via the same attribute walk.
Test: TestAuxiliaryClientPoisonedCacheEviction.test_evict_cached_client_instance_walks_async_wrapper
seeds both sync and async cache entries pointing at the same leaf and
asserts both are dropped on a single eviction call. Verified the test
fails without the wrapper changes ("async cache entry survived
eviction -- wrapper is missing _real_client") and passes with them.
Refs #23482, #23432
CJK and emoji glyphs render as two terminal cells but JS String#length
and the model's own padding count them as one, so any markdown table
with Chinese / Japanese / Korean cells drifts right per row when a
real terminal renders it. Both surfaces fix this with a display-cell
width measurement (wcswidth on the Python side, stringWidth on the
TUI side).
Changes:
- agent/markdown_tables.py: new helper. realign_markdown_tables(text)
detects markdown table blocks (header + |---| divider) and
rewrites the row padding using wcwidth.wcswidth so every pipe and
dash lines up across rows. No-op on text without tables.
- cli.py: hook the helper into _render_final_assistant_content for
strip / render modes (raw passes through untouched), and into the
streaming line emitter so live token-by-token rendering also
produces aligned tables. A small two-buffer state machine in
_emit_stream_text holds table rows until the block ends, then
flushes them through the realigner so all rows pad to a single
per-column width.
- ui-tui/src/components/markdown.tsx: renderTable now uses
stringWidth (Bun.stringWidth fast path + East-Asian-width-aware
fallback, already memoised in @hermes/ink) instead of UTF-16
String#length for both column-width measurement and per-cell
padding. Drops the comment that documented the bug as a deliberate
limitation.
Validation:
- New tests/agent/test_markdown_tables.py (11): every rebuilt block
shares pipe column offsets across rows for pure CJK, mixed
CJK+emoji, ragged-row, and multi-table inputs.
- Updated tests/cli/test_cli_markdown_rendering.py: the existing
strip-mode test asserted exact whitespace; rewritten to assert the
alignment contract (cell content survives + every rendered row
shares pipe offsets).
- New ui-tui markdown.test.ts case (1): rendered column-2 start
offset is identical for the header + every body row, including
the CJK row that drifted before the fix.
- Live: hermes chat -q with the user-reported screenshot prompt now
produces a perfectly aligned table on the wire (header, divider,
4 body rows including '通义千问', all pipes at identical columns).
The /model picker for Nous Portal users was returning the in-repo
_PROVIDER_MODELS["nous"] snapshot — which only updates on Hermes
releases — instead of the remote manifest published at
https://hermes-agent.nousresearch.com/docs/api/model-catalog.json.
OpenRouter already pulled from the manifest via fetch_openrouter_models;
"nous" was the only curated provider where the existing manifest
plumbing (get_curated_nous_model_ids → get_curated_nous_models) was
defined but not wired into the picker pipeline. Switch the curated
build in list_authenticated_providers to use it, with the same
graceful fallback to the in-repo snapshot when the manifest is
unreachable.
Test: tests/hermes_cli/test_model_catalog.py exercises the picker with
a patched manifest and asserts the manifest's nous list reaches
list_picker_providers. Falls-back-to-static path was already covered
by test_curated_nous_ids_falls_back_to_hardcoded_on_empty_catalog.
Follow-up to PR #23824. Adds two correctness fixes on top of the
contributor's salvaged commit:
1. Stale-dist fallback no longer gated on `fatal=False`. `cmd_dashboard`
passes `fatal=True` and is the primary scenario this fallback is for
(issue #23817 — Windows Scheduled Task at logon). The previous gate
meant the fallback never fired in the case it was designed for.
2. `--skip-build` now verifies the dist actually exists before starting
the server. Without this, a misconfigured pre-build would launch the
dashboard pointing at a missing dist and silently serve 404s. We now
exit 1 with a clear "pre-build first: cd web && npm run build"
message, and on success print which dist directory is being used.
Verified end-to-end on Linux:
- build fails + stale dist (fatal=True) -> fallback fires
- build fails + no dist (fatal=True) -> exit 1 with stderr surfaced
- build fails + stale dist (fatal=False) -> fallback fires
- --skip-build + missing dist -> exit 1 with clear guidance
- --skip-build + valid dist -> 'Skipping web UI build...'
On Windows systems using a Chinese GBK locale, `hermes update` could misreport the Web UI build as failed even when `npm run build` actually succeeded. The failure was caused by Python decoding captured npm output with the process locale inside a background subprocess reader thread. When npm emitted bytes such as `0x85`, decoding under GBK raised `UnicodeDecodeError`, and Hermes then surfaced a misleading "Web UI build failed" warning.
This change makes the npm install/npm ci path and the Web UI build step decode captured output explicitly as UTF-8 with `errors="replace"`. That keeps unexpected bytes from crashing output collection, preserves successful builds, and prevents false negatives during update on Windows.
The patch also adds regression tests that verify these subprocess calls always use explicit UTF-8 decoding with replacement semantics.
When the user's main provider is openai-codex on the ChatGPT-account
backend (https://chatgpt.com/backend-api/codex), sending a native image
attachment encodes it as data:image/...base64,... in the input_image
field. The OpenAI Responses API on the public endpoint accepts that, but
the ChatGPT-account variant rejects it with HTTP 400:
Invalid 'input[N].content[K].image_url'. Expected a valid URL, but got
a value with an invalid format.
Hermes' image-rejection phrase list didn't include this wording, so the
error escaped the strip-and-retry branch and fell through to the generic
recovery path: model fallback → context-too-large → compression cascade
→ auxiliary OpenRouter 402 spam (issue #23570).
Add a NARROW phrase keyed on the field-path apostrophe used by the Codex
Responses error format: "image_url'. expected". This matches the actual
error format without false-tripping on generic 'Expected a valid URL'
errors from unrelated tools (webhooks, redirect_uri, etc.). Once matched,
the existing branch strips images from history, sets _vision_supported=
False for the session, and retries text-only.
Refs #23570 (1 of 3 image-replay improvements; persistence rewrite to
store image PATHS instead of inlined base64 is a separate follow-up)
* Revert "fix(goals): force judge to use tool calls instead of JSON-text replies (#23547)"
This reverts commit a63a2b7c78.
* Revert "fix(goals): forward standing /goal state on auto-compression session rotation (#23530)"
This reverts commit 4a080b1d5a.
* Revert "feat(goals): /goal checklist + /subgoal user controls (#23456)"
This reverts commit 404640a2b7.
Adds the only #17873 category not covered by the in-flight PRs #17962
(briandevans, reverse shell + download-execute) and #7993 (SHL0MS,
credential reads + curl/wget exfiltration): sudo invocations that an
LLM-driven agent can drive without TTY interaction.
The agent has no TTY, so the sudo forms that succeed without human
involvement are those reading the password from stdin (`-S` / `--stdin`)
or via an askpass helper (`-A` / `--askpass`). The shell-launch (`-s`)
and list-privileges (`-a`) flags are also gated since they are
privilege-relevant invocations the agent can chain after acquiring the
password (e.g. read SUDO_PASSWORD from .env -> sudo -S -s -> root shell).
Plain `sudo cmd` (no flag) is TTY-bound and excluded.
Two patterns:
1. Direct flag: `\bsudo\b[^;|&\n]*?\s+(?:-s\b|--stdin\b|-a\b|--askpass\b)`
The lazy `[^;|&\n]*?` consumes flag-arguments without spanning
command separators, so `sudo -u root -S whoami` matches (a textbook
offensive form that a strict `(?:\s+-[^\s]+)*` "leading flags only"
pattern would have missed because `root` is a flag-value not a flag).
2. Combined short flags: `\bsudo\b[^;|&\n]*?\s+-[a-z]*[sa][a-z]*\b`
Catches packed forms like `sudo -nS id` where multiple flags share
a single `-X` token.
`_normalize_command_for_detection` lowercases input before pattern
matching (tools/approval.py:340), so case variants of S/s and A/a
collapse — both letter-pairs are gated since each is a privilege-
relevant invocation.
Tests: 21 new cases in TestDetectSudoStdin (12 positive covering all
flag-order permutations including herestring source and printf-piped
forms; 9 negative including TTY-bound `sudo whoami`, interactive
`sudo -i`, env-var reference `$SUDO_USER`, doc lookup `man sudo`,
package install, and the `pseudosudo` word-boundary edge case).
Empirical coverage: 11/11 attacks matched, 0/10 false positives.
Refs: #17873 category 4. Adjacent: #17962 (reverse shell + download-
execute), #7993 (credential reads + curl/wget exfiltration).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Fixes#9590: Block explicit sudo -S (stdin password mode) commands
when the SUDO_PASSWORD environment variable is not configured.
The attack vector: the LLM constructs 'echo guessedpass | sudo -S cmd'
to brute-force sudo passwords, iterates based on sudo's error output
('Sorry, try again'). The existing _transform_sudo_command only
injects -S when SUDO_PASSWORD exists; without it, the LLM's explicit
sudo -S must be treated as a guessing attempt.
Changes:
- Add _check_sudo_stdin_guard() in approval.py: detects sudo -S when
SUDO_PASSWORD is absent, anchored to command-start positions
(^ ; && || | etc.) to avoid false positives on literal text
- Integrate into check_all_command_guards() above yolo/mode=off so
the block is unconditional (like the hardline floor)
- Add 6 tests covering: detection, allow-list, SUDO_PASSWORD bypass,
integration with check_all_command_guards, yolo non-bypass,
container backend bypass
Adds a TestCheckSendMessage class with 7 focused tests pinning the
four passing conditions and the failure modes:
- HERMES_KANBAN_TASK grants access (the new branch)
- HERMES_KANBAN_TASK short-circuits before consulting
session_context or gateway.status (so workers don't depend on
those import paths being healthy)
- HERMES_SESSION_PLATFORM=telegram grants access
- HERMES_SESSION_PLATFORM=local falls through to gateway check
- is_gateway_running()=True grants access
- All signals absent → False
- gateway.status ImportError is swallowed → False
Pinning the short-circuit (test #2) is the load-bearing one — it
documents the contract that worker-side availability cannot regress
to depending on gateway-side state lookups.
When a kanban worker subprocess hits the iteration budget, the agent
loop strips tools and asks the model for a summary. The model cannot
call kanban_block itself at that point, so the process exits rc=0
without calling kanban_complete or kanban_block — a protocol violation
that the dispatcher detects as a fatal error, giving up after 1 failure
and stranding downstream tasks.
Fix: after _handle_max_iterations() returns, check HERMES_KANBAN_TASK
and call kanban_block with a reason describing the exhaustion. The
dispatcher then sees a clean block transition instead of a protocol
violation, and the task can be retried or escalated by a human.
Fixes [Bug] kanban-worker exits cleanly (rc=0) on iteration-budget
exhaustion without calling kanban_complete or kanban_block #23216
When an auxiliary provider returns HTTP 402 (credit / payment), every
subsequent compression / title-gen / session-search / vision call still
re-tried it as the FIRST entry in the chain — burning ~1 RTT to hit 402
again, then falling back. On a long Discord/LCM session that meant dozens
of doomed 402s per minute (issue #23570).
Add a per-process unhealthy-provider cache with a 10 min TTL. When any
caller observes a payment error against a provider, the label is marked
unhealthy and skipped by:
* _resolve_auto Step-1 (main provider use-as-aux path)
* _resolve_auto Step-2 (aggregator/fallback chain)
* _try_payment_fallback (used by call_llm/acall_llm on first 402)
Skip-logs are throttled to once per minute per label so a bursty session
doesn't spam agent.log. Entries auto-expire so a topped-up account
recovers without manual intervention. The cache is in-process only by
design — multi-profile users with different keys per profile must each
hit the 402 once.
Refs #23570
When the Discord typing API call fails (rate limit, network error, 403),
_typing_loop returns early but the stale task remains in _typing_tasks.
Subsequent send_typing calls see the stale entry and skip, leaving no
typing indicator for the rest of the agent invocation.
Add finally block to _typing_loop to always remove the task from
_typing_tasks on exit, whether from cancellation, error, or normal
completion. This allows send_typing to create a fresh task.
3 new tests in test_discord_send.py:
- Task removed after API error
- Typing restartable after failure
- stop_typing cleans up
A YAML parse error in ~/.hermes/config.yaml caused load_config() to print
one line to stdout (Warning: Failed to load config: ...) and silently fall
back to DEFAULT_CONFIG, dropping every user override (auxiliary providers,
fallback chain, model settings). Users only noticed when downstream
behavior misbehaved — see issue #23570 where a tab-indent error in the
auxiliary section caused aux fallback to use OpenRouter (depleted) instead
of the configured Codex/MiniMax chain.
Now: log at WARNING (so 'hermes logs' surfaces it), write a prominent line
to stderr, dedup on (path, mtime_ns, size) so concurrent loads don't spam,
and re-warn after the user edits the file. Both call sites (raw read +
merged load) route through the same helper.
Refs #23570
Salvages the three substantive low-severity fixes from Gutslabs' #1974
"misc bug fixes" bundle. The other 8 claims in that PR were either
already fixed on main with superior implementations (state lock,
firecrawl lazy import, fcntl/msvcrt guard, path normalization, schema
migrations) or did not survive review.
- run_agent: `_materialize_data_url_for_vision` uses
`NamedTemporaryFile(delete=False)`; if `base64.b64decode` raises on a
corrupt data URL the temp file would persist forever. Wrap the
write in try/except and `os.unlink` the temp on failure.
- gateway/session: `append_to_transcript` JSONL write had no error
handling, so disk-full / read-only-fs / permission errors crashed the
message handler. The SQLite write above is the primary store, so
swallow OSError on the JSONL fallback with a debug log.
- gateway/status: `_read_pid_record` reads `pid_path.read_text()` after
an `exists()` check; if the PID file is deleted between the two
calls (concurrent gateway restart) we hit an unhandled OSError.
Catch it and return None.
Adds a regression test for the tempfile cleanup; the other two paths
are defensive try/excepts on infrequent OSError that don't warrant
dedicated tests.
Co-authored-by: Teknium <127238744+teknium1@users.noreply.github.com>
- Implement tests for normalizing perpetual markets and DEXs.
- Validate JSON output for main commands including markets, candles, and review.
- Ensure environment variable resolution and dotenv file reading are covered.
- Test export functionality for market data with expected output structure.
agent.redact._REDACT_ENABLED is snapshotted at import time from
HERMES_REDACT_SECRETS env. Under xdist a prior test in the same worker
can flip it, so test_exec_command_output_is_redacted was order-dependent.
Pin it via monkeypatch like test_terminal_output_transform_still_runs_strip_and_redact does.
1. Quick command exec ran in the gateway process's full environment
without env sanitization or output redaction. A quick command like
"env" or "printenv" would leak all API keys, OAuth tokens, and
bot credentials to the messaging user.
Fix: apply _sanitize_subprocess_env() before exec and
redact_sensitive_text() on output before returning.
2. GatewayRunner._pending_messages was written on every interrupt
(lines 1331-1334) but never read or consumed anywhere. The actual
interrupt delivery uses adapter._pending_messages (a separate dict).
Removed the write-only accumulation to prevent unbounded growth.
Two new tests:
- tests/gateway/test_telegram_format.py
test_message_too_long_splits_into_continuations_not_silent_truncation:
asserts edit_message returns success=True with continuation_message_ids
populated and message_id pointing at the last continuation when
content exceeds MAX_MESSAGE_LENGTH (#19537). Replaces the original
fail-on-overflow assertion with the split-and-deliver contract.
- tests/gateway/test_stream_consumer.py
TestEditOverflowSplitAndDeliver.test_consumer_advances_message_id_on_split_and_deliver:
asserts the consumer side updates _message_id to the latest
continuation, clears _last_sent_text, and fires on_new_message when
the adapter reports a split-and-deliver result.
Surface ready tasks that nobody claims within a threshold (default
30 min) regardless of why. One identity-agnostic signal that catches:
- Operator typo'd the assignee
- Profile was deleted, leaving its tasks stranded
- External worker pool (Codex CLI lane, custom daemon) is down
- Dispatcher misconfigured (wrong board / wrong HERMES_HOME)
Today the dispatcher correctly skips these (no respawn loop, good)
but nothing surfaces the fact that operator-actionable work is
accumulating. The new `stranded_in_ready` rule does that without
requiring a manual lane registry — it reads the most recent ready-
transition event (`created` / `promoted` / `reclaimed` / `unblocked`)
and fires when (now - last_ready_ts) > threshold.
Severity escalates with age: warning at threshold, error at 2x,
critical at 6x. The cli_hint and reassign actions point operators
at the right next step.
Out of scope deliberately:
- Lane registry (#20157 closed) — this signal supersedes it.
- Pushing the diagnostic into messaging gateways — diagnostics
are pull-only via 'hermes kanban diagnostics' for now; gateway
push is a separate UX decision.
Tests: 10 new + 461 existing kanban tests pass. E2E verified end-
to-end via 'hermes kanban diagnostics --json' against a 2h-old
stranded task — surfaces as error severity with correct actions.
Live-tested on gemini-3-flash-preview the judge kept returning empty
or non-JSON content, tripping the consecutive-parse-failures auto-
pause. Free-form JSON output is hopeful; tool-call schemas are
enforced server-side by virtually every modern provider.
Two new tools the judge calls:
- submit_checklist(items) — Phase A, decompose
- update_checklist(updates, new_items, reason) — Phase B, evaluate
Both phases now call the auxiliary client with tool_choice forcing
the right tool. read_file remains for Phase B history inspection,
with the loop exiting only when update_checklist is called or the
read budget is exhausted (at which point read_file is dropped from
the toolbox and update_checklist is forced).
Robustness:
- _call_judge_with_tool_choice falls back tool_choice forced→required→
auto if the provider rejects a particular shape.
- If a fully-broken provider still returns content instead of a tool
call, the legacy JSON-text parsers stay around as a last-ditch
backstop so we never silently lose a checklist.
- _normalize_update_args replaces the JSON parser for the apply
layer; same 1-based→0-based conversion + terminal-status filter.
Live verification: same fizzbuzz goal that was hitting 'judge model
returned unparseable output 3 turns in a row' before now terminates
in 2 turns, all 11 items marked completed with item-specific
evidence, no auto-pause. Agent log shows
'produced 11 checklist items via tool call' instead of the JSON-
parse path.
Tests: 7 new cases for the tool-call path (Phase A success, Phase B
update only, Phase B read_file→update, JSON-content backstop,
empty-text item dropping, non-terminal status filter).
When run_agent's _compress_context fires mid-turn it ends the parent
session in SessionDB and creates a new continuation session with a
fresh session_id. The /goal state is keyed on session_id in
state_meta ("goal:<sid>"), so without forwarding the goal silently
disappears: _get_goal_manager() rebinds for the new session_id,
load_goal() returns None, mgr.is_active() is False, and the
continuation loop dies with no user-visible signal.
Fix: in the same SessionDB transaction block that creates the
continuation session, copy state_meta[goal:<old>] →
state_meta[goal:<new>] when present. No-op when the user has no
active goal. Logged at INFO so a stuck loop is debuggable.
Tests cover the round-trip via SessionDB and the no-op path.
Affects all three run-conversation surfaces (CLI, gateway, TUI
gateway) because _compress_context is the single rotation site.
Added tests/gateway/test_stream_consumer_draft.py with 11 tests
covering:
- Transport selection: auto+dm-supported -> draft; auto+group -> edit;
explicit edit; explicit draft on unsupported adapter -> edit;
MagicMock adapter -> edit (back-compat for the existing test suite).
- Happy path: DM stream animates draft frames with a single shared
draft_id, then finalizes via a regular adapter.send.
- Group fallback: drafts entirely skipped in non-DM chats.
- Failure fallback: send_draft returning success=False disables drafts
for the rest of the response.
- Draft_id lifecycle: consecutive responses use distinct ids; tool
boundaries bump the id so post-tool text animates fresh below the
tool-progress bubble (the openclaw #32535 leak guard).
- _already_sent contract: drafts must NOT set the flag so the gateway's
fallback final-send still fires (drafts have no message_id).
Updated website/docs/user-guide/messaging/telegram.md with a
'Streaming transport' section explaining auto|draft|edit|off, the
DM-only constraint, and the per-response fallback behaviour.
The existing _live_system_guard (PR #23397) blocked os.kill / os.killpg
and a narrow subset of subprocess invocations. Tests still SIGTERMed the
live gateway today (May 10) because the guard had structural holes.
Plug them all:
- subprocess: also wrap getoutput, getstatusoutput
- os.system, os.popen - completely unwrapped before
- pty.spawn - completely unwrapped before
- asyncio.create_subprocess_exec / create_subprocess_shell - bypassed
the subprocess module entirely; now wrapped
- Subprocess command inspection now looks at the WHOLE command string,
not just tokens[0]. Catches sudo systemctl, env systemctl, bash -c
'systemctl', setsid systemctl, /usr/bin/systemctl, etc.
- New process-killer block: pkill / killall / taskkill / fuser
targeting hermes/python patterns is now refused
- os.kill PID 0 (own group) allowed; PID -1 (every process we can
signal) refused
- subprocess.Popen wrapper preserves __class_getitem__ so third-party
packages that use Popen[bytes] as a type annotation still import
Coverage is locked in by tests/test_live_system_guard_self_test.py -
exercises every primitive against a guaranteed-foreign PID and asserts
the guard fires. Adding a new kill primitive without updating the guard
breaks CI.
scripts/run_tests.sh now also force-loads ~/.hermes/pytest_live_guard.py
when present (developer-machine convenience), so even worktrees that
predate this commit get the protection on subsequent test runs through
the canonical wrapper.
A Codex auxiliary timeout closes the underlying OpenAI client (so the
streaming hang doesn't sit until the user kills the session), but the
cached wrapper kept pointing at the now-dead transport. Subsequent
auxiliary calls (compression retry, memory flush, background review,
title generation routed via provider: main) reused that closed client
and failed fast with 'Connection error' until the gateway restarted —
even though the main agent route was healthy the whole time.
Sync `_get_cached_client` had no liveness check (async did, via loop
identity), and the connection-error fallback in `call_llm` only fired
on the auto provider path, so an explicit provider — including the
common `auxiliary.compression.provider: main` shape — never evicted.
Three fixes:
* New `_evict_cached_client_instance(target)` helper that drops the
cache entry whose stored client is target (or wraps it via
`_real_client`, for `CodexAuxiliaryClient`).
* `_CodexCompletionsAdapter._close_client_on_timeout` evicts the
wrapper after closing the inner OpenAI client.
* `call_llm` and `async_call_llm` evict on `_is_connection_error`
before re-raising, regardless of whether the provider is auto.
Net effect: one timeout costs one summary attempt + the existing 30s
compressor cooldown; the next compaction rebuilds the client and
works. Non-connection errors (4xx/5xx) do not evict, so cache hits
stay stable.
Closes#23432
Cherry-picked from PR #10371. Two-layer defense for the spurious-thread_id
issue (#3206):
1. _build_message_event filters DM thread_ids: only preserve thread_id
for real topic messages (is_topic_message=True). Telegram puts
message_thread_id on every DM that is a reply, but reply-chain ids
route to nonexistent threads on send.
2. _send_message_with_thread_fallback helper: control sends
(send_update_prompt, send_exec_approval / send_slash_confirm,
send_model_picker) retry once without message_thread_id when
Telegram returns BadRequest 'Message thread not found'. Mirrors
the pattern PR #3390 added for the streaming send path.
Salvage notes:
- Conflict 1 (line ~4099): merged the contributor's DM is_topic_message
filter with the existing forum General-topic default from #22423,
preserving both behaviors.
- Conflict 2 (line ~1664 / 1690): kept main's delete_message (PR #23416)
alongside the new helper. Tightened the helper's exception catch
from bare 'Exception' to use the existing _is_bad_request_error +
_is_thread_not_found_error helpers (line 484-496) for consistency
with the streaming send path.
- Widened the fix to send_update_prompt (was bare self._bot.send_message,
same bug class).
Authored by rahimsais via PR #10371 (re-attributed from donrhmexe@
local commit author).
* feat(goals): /goal checklist + /subgoal user controls
Two-phase judge for /goal — Phase A decomposes the goal into a detailed
checklist on first turn; Phase B evaluates each pending item harshly
against the agent's most recent response. The goal completes only when
every item is in a terminal status (completed or impossible). Adds
/subgoal so the user can append, complete, mark impossible, undo,
remove, or clear items the judge missed or got wrong.
Mechanics:
- GoalState gains `checklist` and `decomposed` fields, both backwards
compatible (old state_meta rows load unchanged).
- Phase A: aux call writes a harsh, exhaustive checklist; biased toward
more items not fewer. Falls through to legacy freeform judge when
decompose fails.
- Phase B: judge gets the checklist + last-response snippet + path to
a per-session conversation dump at <HERMES_HOME>/goals/<sid>.json.
A bounded read_file tool (max 5 calls per turn, restricted to that
one file) lets the judge inspect history when the snippet is
ambiguous. Stickiness in code: terminal items are frozen, only the
user can revert via /subgoal undo.
- Continuation prompt shows checklist progress when non-empty;
reverts to old prompt when empty.
- Status line shows M/N done counts.
CLI + gateway + TUI gateway all pass the agent reference into
evaluate_after_turn so the dump can be written. Gateway-side
/subgoal is allowed mid-run since it only modifies the checklist
the judge consults at turn boundaries.
Tests: 24 new cases — backcompat round-trip, Phase A decompose,
Phase B updates + new_items + stickiness, user override flows,
conversation dump (incl. unsafe-sid sanitization), judge read_file
restriction. Existing freeform-mode tests updated to patch the
renamed `judge_goal_freeform` and skip Phase A explicitly.
* fix(goals): off-by-one in judge index, message-list plumbing, prompt tuning
Three live-test findings from running /goal end-to-end against
gemini-3-flash-preview as the judge:
1. Off-by-one bug — the judge sees the checklist rendered with 1-based
indices ('1. [ ] foo, 2. [ ] bar') but the apply layer indexed
state.checklist as 0-based. Result: every judge update landed on
the wrong item, evidence got attached to neighbouring rows, and
the genuine 'first pending' item (usually #1) never got marked.
Fix: convert 1 → 0 in _parse_evaluate_response. Also tightened the
user prompt to call out the 1-based scheme explicitly. New tests
cover the parser conversion + an end-to-end fake-judge round-trip.
2. Conversation dump never happened — _extract_agent_messages tried
common AIAgent attribute names (.messages, .conversation_history,
etc.) but AIAgent doesn't expose the message list as an instance
attribute; it lives inside run_conversation()'s scope. Result: the
judge's read_file tool always saw history_path=unavailable. Fix:
added an explicit messages= kwarg to evaluate_after_turn that all
three call sites (CLI, gateway, TUI gateway) now pass directly.
Agent-attribute extraction kept as back-compat fallback.
3. Prompt was too harsh on simple goals. The original 'be HARSH,
default to leaving items pending' wording made the judge refuse
to mark 'file exists' completed even after the agent ran ls,
test -f, os.path.isfile, and find — burning the entire 8-turn
budget on a fizzbuzz task. Softened to 'strict but not absurd'
with explicit guidance on what counts as evidence and a directive
not to require re-proving items already established earlier.
Re-tested live with the same fizzbuzz goal: now terminates in 2
turns with all 8 checklist items correctly attributed to their
own evidence. /subgoal user-action flow (add / complete / undo /
impossible) verified live as well.
New TestUtf16OverflowDetection class covers two scenarios:
- test_emoji_text_exceeding_utf16_limit_triggers_overflow_split: feeds
2200 emoji codepoints (4400 UTF-16 units) — under Telegram's
codepoint-equivalent limit but over its UTF-16 limit. Asserts
truncate_message was called with len_fn=utf16_len, confirming the
consumer detected the overflow.
- test_codepoint_only_adapter_falls_back_to_len: documents that
adapters which don't subclass BasePlatformAdapter (or test MagicMocks)
fall back to plain len for backwards compat.
The contributor's PR shipped no tests for the UTF-16 path.
Slash commands (/clear, /new, /undo, /reload-mcp) are dispatched from the
process_loop daemon thread. prompt_toolkit.run_in_terminal returns a
coroutine that only the main-thread event loop can drive, so calling it
from a daemon thread orphans the coroutine — the input prompt never
renders and user keystrokes leak into the composer instead of the
confirmation prompt (issue #23185).
Mirror the thread-aware guard already in _run_curses_picker: when off the
main thread, fall back to a direct input() call. Also wrap
run_in_terminal in try/except so WSL / Warp / other emulators that
silently drop the scheduled coroutine fall back to input() too.
Tests: tests/cli/test_prompt_text_input_thread_safety.py covers main
thread (run_in_terminal path), daemon thread (direct input fallback),
no-app, run_in_terminal-raises, and EOF handling.
When kanban_complete rejects a created_cards list as hallucinated, the
task is intentionally left in-flight (the gate runs before the write
txn) so the worker can retry with a corrected list or pass
created_cards=[] to skip the check. The retry path already worked, but
the previous error wording read like a terminal failure and workers
were observed abandoning the run instead of trying again.
Spell out the recovery path explicitly in the tool_error response
("Your task is still in-flight ... Retry kanban_complete with ...") and
add regression coverage at both the kernel and tool layers so the
retry contract — and the wording the worker depends on to discover
it — is pinned.
Fixes#22923
Workers running slow models (e.g. kimi-k2.6) can spend longer than
DEFAULT_CLAIM_TTL_SECONDS inside a single tool-free LLM call, making
no tool calls and therefore not heartbeating. release_stale_claims
previously reclaimed these healthy workers, producing the
spawn-then-immediately-reclaim loop reported in #23025.
When a stale-by-TTL claim's host-local worker PID is still alive,
extend the claim (emit a claim_extended event) rather than killing
it. enforce_max_runtime / detect_crashed_workers remain the upper
bounds for genuinely wedged or dead workers. Reclaim events now also
record claim_expires, last_heartbeat_at, worker_pid, and host_local
so operators can see why a worker was killed.
xAI's Responses API returns HTTP 400 ("Model X does not support
parameter reasoningEffort") for grok-4, grok-4-0709, grok-4-fast-*,
grok-4-1-fast-*, grok-3, grok-4.20-0309-*, and grok-code-fast-1 — even
though those models reason natively. Hermes was unconditionally sending
`reasoning: {effort: 'medium'}` to xAI for every Grok model, breaking
direct `--provider xai` for the entire grok-4 line.
Add a substring allowlist predicate (verified live against api.x.ai
2026-05-10) covering the only Grok families that accept the effort dial:
grok-3-mini*, grok-4.20-multi-agent*, grok-4.3*. The Responses transport
omits the `reasoning` key entirely for everything else while still
including `reasoning.encrypted_content` so we capture native reasoning
tokens.
Verified end-to-end: `hermes chat -q hi --provider xai --model grok-4-0709`
went from HTTP 400 to a successful reply.
The contributor's regression test for Feishu fallback thread routing
asserted on attributes specific to the real lark SDK builder
(call_args.body, body.receive_id). In test environments without the
lark SDK installed, the in-tree fallback (gateway/platforms/feishu.py
_build_create_message_request) returns a SimpleNamespace using
.request_body instead of .body, causing AttributeError.
Now reads via getattr fallback and also verifies receive_id_type is
'thread_id' (not 'chat_id') as a stronger contract check.
When the first streamed message exceeds the platform length limit and
gets split into chunks, _send_new_chunk was called with self._message_id
(which is None on first send), dropping thread routing entirely.
Fallback to self._initial_reply_to_id so overflow chunks land in the
correct topic/thread.
Also fix a fragile test assertion that could be silently skipped.
Cherry-picked from PR #13077 commits:
- 5500c7d8 fix(gateway): stream consumer first message drops thread context
- e84403b9 test(gateway): add regression tests for stream consumer thread routing
Fixes: Streaming first message drops thread/topic context in Feishu group
topics, Slack threads, Telegram forum topics. Adds initial_reply_to_id
ctor arg to GatewayStreamConsumer, threaded through _send_or_edit and
_send_new_chunk. Also fixes Feishu _send_raw_message fallback path
(reply -> create) to use receive_id_type='thread_id' so the new message
lands in the correct topic instead of the main channel.
Authored by hrygo via PR #13077 (re-attributed from the bot-authored
salvage commit on the original branch).
The split-overflow path in _send_or_edit (gateway/stream_consumer.py) was
copying the cumulative _already_sent flag into _final_response_sent on the
done frame. _already_sent goes True on any successful prior edit (tool
progress) or on fallback-mode promotion when an edit fails — neither
proves the *current* chunked send delivered the final answer.
When the chunked send actually fails (network error, flood control), the
consumer would wrongly claim 'final delivered' and the gateway's
independent fallback delivery in run.py would be suppressed. User saw
only tool-progress bubbles and never got the answer.
Now we track per-chunk success locally: _send_new_chunk returns the new
message_id on success or returns the passed-in reply_to unchanged on
failure. If at least one returned id differs, chunks_delivered = True;
otherwise stays False, gateway fallback runs.
Adds two regression tests:
- test_split_overflow_failed_send_does_not_mark_final_sent — primes
_already_sent=True, then makes every send fail; asserts
_final_response_sent stays False.
- test_split_overflow_partial_send_marks_final_sent — happy path,
asserts _final_response_sent goes True.
Note: the companion bug at the CancelledError handler (issue cited
lines 417-418) was already fixed by 3b5572ded on 2026-04-16.
Closes#10748
Follow-up to the previous commit's notifier behavior change. Two test fixes:
1. `tests/gateway/test_kanban_notifier.py` gains
`test_notifier_redelivers_same_kind_on_dispatch_cycle` — pins the new
contract directly: a task that crashes, gets reclaimed, and crashes
again notifies the user BOTH times. Before #21398 the second crash
silently dropped because the subscription was already deleted.
2. `tests/hermes_cli/test_kanban_notify.py::
test_notifier_unsubs_after_abnormal_events[gave_up|crashed|timed_out]`
is flipped. Those tests were added in the salvage of #22941 and
asserted the OLD behavior (subscription deleted after gave_up /
crashed / timed_out). They're now obsolete — the new contract is
"subscription survives a non-final terminal event so retries reach
the user." Updated docstring + asserts; the cursor-advance check is
added to confirm the dedup mechanism still works.
The `test_notifier_unsubs_after_completed_event` test stays untouched
because `completed` IS still a terminal event that triggers unsub
(the task hits `done` status, which is handled by the `task_terminal`
branch in the notifier loop).
Follow-up to HuangYuChuh's #17384 cherry-pick:
- Use defensive getattr+logger.debug for delete_message lookup, mirroring
the sibling _try_send_fresh_final cleanup pattern at L820+. Platforms
that don't implement delete_message no longer raise AttributeError; the
failure path now logs at debug for diagnosability instead of silently
swallowing.
- Add three regression tests in tests/gateway/test_stream_consumer.py:
- delete_message awaited on happy-path exit with stale id
- delete_message NOT awaited when no fallback chunks reached the user
- no crash on adapters that lack delete_message (spec-restricted mock)
The shutdown forensics added in #23285 caught tests/hermes_cli/ pytest
runs sending SIGTERM to the developer's live gateway 5+ times in 3
days. Root cause: when a single test forgets to mock os.kill or
find_gateway_pids, the real call leaks past the hermetic HERMES_HOME
isolation — find_gateway_pids' psutil scan walks the whole machine and
returns the live gateway PID, then the unmocked os.kill delivers the
signal.
Rather than audit and patch ~30 tests across cmd_update, kill_gateway_processes,
and stop_profile_gateway code paths, install a single autouse guard in
tests/conftest.py that blocks the two primitives that actually cause
the damage:
- os.kill rejects any PID outside the test process subtree with a
hard RuntimeError so the offending test gets a stack trace instead
of silently murdering the real gateway.
- subprocess.run / Popen / call / check_call / check_output reject
any 'systemctl <verb> hermes-gateway' invocation that would mutate
the live unit. Read-only systemctl calls (status, show, list-units)
still pass through.
We intentionally do NOT stub find_gateway_pids / _scan_gateway_pids —
tests of those functions themselves need the real implementation.
Discovery without delivery is harmless; the os.kill + systemctl guards
catch the actual damage path.
Tests that legitimately need real signal delivery (e.g. PTY tests
signalling their own child) opt out via
@pytest.mark.live_system_guard_bypass.
Validation: tests/hermes_cli/ + tests/cli/ + tests/gateway/ produce
the same 17 failures with and without this guard (all pre-existing on
main, unrelated to gateway-kill leaks). The live gateway survives the
test run that previously SIGTERMed it.
Two follow-up improvements to the previous commit's notifier dedup work.
1. Add a regression test for the send-exception rewind path. The
contributor's PR included a test for the adapter-disconnect path
(test_kanban_notifier_rewinds_claim_if_adapter_disconnects, where
adapter is None at delivery time), but not for the "adapter is
connected, send() raises" path that fires inside the inner try/except
at gateway/run.py:4314. The new test
(test_kanban_notifier_rewinds_claim_on_send_exception) uses a
FailingAdapter that always raises and confirms (a) send was actually
attempted, (b) the claim was rewound, (c) the next call to
unseen_events_for_sub still returns the event for retry.
2. Drop the per-delivery success log from INFO to DEBUG. A busy board
on a multi-platform gateway can produce hundreds of these per day;
that's gateway.log noise that obscures real warnings. Failure paths
stay at WARNING (where you'd want to look when something's wrong)
so we don't lose visibility into transient send issues.
Builds on @kshitijk4poor's CLI handoff stub. The original PR's flow
deferred everything to whenever a real user happened to message the
target platform; this rewrites it so the gateway picks up handoffs
immediately and the destination chat just starts working.
State machine on sessions table replaces the boolean flag:
None -> 'pending' -> 'running' -> ('completed' | 'failed')
plus handoff_error for failure reasons. CLI request_handoff /
get_handoff_state / list_pending_handoffs / claim_handoff /
complete_handoff / fail_handoff helpers wrap the transitions.
CLI side (cli.py): /handoff <platform> validates the platform's home
channel via load_gateway_config, refuses if the agent is mid-turn,
flips the row to 'pending', and poll-blocks (60s) on terminal state.
On 'completed' it prints the /resume hint and exits the CLI like
/quit. On 'failed' or timeout it surfaces the reason and the CLI
session stays intact.
Gateway side (gateway/run.py): new _handoff_watcher background task
scans state.db every 2s, atomically claims pending rows, and runs
_process_handoff for each. _process_handoff:
1. Resolves the platform's home channel.
2. Asks the adapter for a fresh thread via the new
create_handoff_thread(parent_chat_id, name) capability so the
handed-off conversation gets its own scrollback. Adapters that
don't support threads (or fail) return None and the watcher
falls back to the home channel directly.
3. Constructs a SessionSource keyed as 'thread' when a thread was
created, 'dm' otherwise, then session_store.switch_session
re-binds the destination key to the CLI session_id. The full
role-aware transcript replays via load_transcript on the next
turn (no flat-text injection into context_prompt).
4. Forges a synthetic MessageEvent(internal=True) with the handoff
notice and dispatches through _handle_message; the agent runs
against the loaded transcript and adapter.send delivers the
reply.
5. Marks the row 'completed' on success, 'failed' (+error) on any
exception.
Adapter capability (gateway/platforms/base.py): create_handoff_thread
default returns None. Three overrides:
- Telegram (gateway/platforms/telegram.py): wraps _create_dm_topic
so DM topics (Bot API 9.4+) and forum supergroups both work.
- Discord (gateway/platforms/discord.py): parent.create_thread on
text channels with a seed-message + message.create_thread
fallback for permission edge cases. Skips DMs and other
non-thread-capable parents.
- Slack (gateway/platforms/slack.py): posts a seed message and
returns its ts as the thread anchor — Slack threads are
message-anchored.
In thread mode, build_session_key keys the destination without
user_id (thread_sessions_per_user defaults to False) so the synthetic
turn and any later real-user message in the thread share the same
session_key — seamless takeover without race.
CommandDef stays cli_only=True (handoff is initiated from the CLI;
gateway exposes /resume for the reverse direction).
Removed the original PR's _handle_message_with_agent handoff hook
(transcript-as-text injection into context_prompt) and the
send_message_tool notification — both replaced by the watcher path.
Tests rewritten around the new state machine: 13/13 pass.
E2E-validated thread + no-thread paths and the failure path against
real worktree imports with mocked adapters.
Adds /handoff <platform> CLI command that queues the current session for
resume on the configured home channel of any messaging platform.
CLI side:
- /handoff telegram — marks session in shared DB, sends summary to
the Telegram home channel via send_message
- /handoff discord — same for Discord
- Supports telegram, discord, slack, whatsapp, signal, matrix
Gateway side:
- On new session creation, checks for pending handoffs for the
incoming message's platform
- If found, loads the CLI session's full conversation history and
injects it into the context prompt as a handoff transcript
- Agent continues the conversation seamlessly
Files:
- hermes_state.py: handoff_pending, handoff_platform columns + helpers
- cli.py: _handle_handoff_command dispatch + handler
- hermes_cli/commands.py: CommandDef entry
- gateway/run.py: handoff detection in _handle_message_with_agent
- tests/hermes_cli/test_session_handoff.py: 8 tests
* feat(gateway): per-platform admin/user split for slash commands
Adds an opt-in two-list access control on top of the existing per-platform
`allow_from` allowlists, scoped to slash commands only:
- allow_admin_from — full slash command access
- user_allowed_commands — what non-admins may run
- group_allow_admin_from — same, group/channel scope
- group_user_allowed_commands
When `allow_admin_from` is unset for a scope, gating is disabled and every
allowed user keeps full access (backward compat). Plain chat is unaffected.
`/help` and `/whoami` are always reachable so users can see what they
can run.
Gate runs at the slash command dispatch site in gateway/run.py and uses
`is_gateway_known_command()`, so it covers built-in AND plugin-registered
commands through the live registry without per-feature wiring.
Adds `/whoami` showing platform, scope, tier, and runnable commands.
Salvage of PR #4443's permission tier work, scoped down. The full tier
system, tool filtering, audit log, usage tracking, rate limiting,
`/promote` flow, and persistent SQLite stores are not included here —
those can be re-expanded later if needed.
Co-authored-by: ReqX <mike@grossmann.at>
* fix(gateway): close running-agent fast-path bypass + add coverage and central docs
The slash command access gate was only applied at the cold dispatch site
(line ~5921). When an agent was already running, the running-agent
fast-path block (line ~5574) dispatched /restart, /stop, /new, /steer,
/model, /approve, /deny, /agents, /background, /kanban, /goal, /yolo,
/verbose, /footer, /help, /commands, /profile, /update directly
without going through the gate — letting non-admins bypass gating just
because an agent happens to be busy.
Refactored the gate into _check_slash_access() and called from BOTH
paths. /status remains intentionally pre-gate so users can always see
session state.
Also added 18 more dispatch tests covering:
- Running-agent fast-path: blocks non-admin, allows admin, /status
always works
- Alias canonicalization (gate uses canonical name, not user alias)
- Unknown / unregistered commands pass through (don't false-positive)
- DM admin scope-locked when group has its own admin list
- Multi-platform isolation (Discord gated, Telegram unrestricted)
Docs: added Slash Command Access Control section to the central
messaging index page + /whoami row in the chat commands table.
Co-authored-by: ReqX <mike@grossmann.at>
---------
Co-authored-by: ReqX <mike@grossmann.at>
When the gateway received SIGTERM, the shutdown_signal_handler ran a
synchronous 'ps aux' (3s timeout) inside the asyncio event loop, then
asyncio.create_task(runner.stop()). On a busy host that ate 1-3s of
the teardown budget before draining could even start, and the resulting
log line was a multi-line ps dump that didn't tell us who sent the
signal. The shutdown path itself logged 'Stopping gateway...' and then
nothing until 'Gateway stopped' — when systemd SIGKILLed mid-drain,
there was no way to see which phase wedged.
Changes:
- New gateway/shutdown_forensics.py:
* snapshot_shutdown_context(sig) — sub-millisecond /proc-only capture
of signal name, parent pid+name+cmdline, INVOCATION_ID (systemd
marker), loadavg_1m, TracerPid, takeover/planned-stop marker
presence + whether-it-names-self. Pure stdlib, never raises.
* spawn_async_diagnostic(log_path, sig) — detached subprocess with
its own 'timeout 5s', start_new_session=True, writes ps auxf +
pstree + dmesg to ~/.hermes/logs/gateway-shutdown-diag.log.
Returns immediately, can't block the event loop or the cgroup
teardown.
* check_systemd_timing_alignment(drain_timeout) — reads
/proc/self/cgroup for our unit, asks systemctl show for
TimeoutStopUSec, returns mismatch info when the unit's stop
timeout is smaller than restart_drain_timeout + 30s headroom
(the case where systemd SIGKILLs mid-drain).
* _parse_systemd_duration_to_us — covers '90s', '1min 30s',
'500ms', '1h' style values from systemctl show.
* format_context_for_log — single scannable key=value line, parent
cmdline last.
- gateway/run.py shutdown_signal_handler:
* Replaces synchronous ps aux + ad-hoc 'hermes-related lines' filter
with snapshot + detached spawn.
* Always logs 'Shutdown context: signal=... parent_pid=...
parent_cmdline=...' regardless of planned/unexpected so we can
correlate signal source even on planned restarts.
- gateway/run.py _stop_impl:
* Per-phase '+X.XXs' timing for notify_active_sessions, drain
(with drain_seconds, active_at_start, active_now, timed_out),
post-interrupt tool kill, each adapter disconnect (Xs),
all adapters disconnected, final-cleanup tool kill, SessionDB
close, total teardown.
- gateway/run.py start():
* Stale-unit warning at startup when the running systemd unit's
TimeoutStopSec is smaller than the configured drain timeout.
Points the user at 'hermes gateway service install --replace'
to regenerate, or at shortening agent.restart_drain_timeout.
Tests: 30 new in tests/gateway/test_shutdown_forensics.py — snapshot
speed bound, signal name resolution, marker detection self-vs-other,
async diag spawn doesn't block caller, systemd duration parser, and
alignment check returns None outside systemd. Wider tests/gateway/
suite: 5258 passing, 3 pre-existing TTS-routing failures unchanged
on main.
Follow-up to the previous commit's toolset-vs-skill validation.
The contributor's fix raises ValueError on the first toolset name found
in the skills list. That works for one mistake, but agents that confuse
skills with toolsets usually pass several at once
(`skills=["web", "browser", "terminal"]`) — and serial-correcting one
per failure round-trip wastes tokens. Collect all toolset-shaped
entries first, then raise once with the full list.
The error message is also slightly clearer:
'web', 'browser', 'terminal' are toolset names, not skill name(s).
Put toolsets in the assignee profile's `toolsets:` config instead of
per-task skills. Skills are named skill bundles (e.g. `kanban-worker`,
`blogwatcher`); toolsets are runtime capabilities (e.g. `web`,
`browser`, `terminal`).
vs. the previous "the assignee profile's toolsets" — explicitly naming
the YAML key (`toolsets:`) and giving concrete examples in both
categories closes the conceptual gap that produced the bug to begin
with.
Adds one regression test (test_create_task_skills_lists_all_toolset_typos)
covering the multi-name aggregation path. The single-typo test from
the original PR still passes (the loose `match="toolset name"` matches
both singular and plural forms).
Two follow-up improvements to Tranquil-Flow's metadata-panel restyle.
Both stay within the parent PR's "tone down the panel" scope.
1. Native <details>/<summary> collapse for verbose metadata.
The parent PR consciously deferred this ("adding native expand/collapse
would be the next step but requires UX agreement"). The default they
asked for is straightforward: collapsed when the rendered JSON exceeds
300 chars (the threshold where the max-height: 8.5rem cap actually
starts mattering), expanded otherwise. <details>/<summary> is the right
primitive — zero JS, browser-handled state, accessible by default
(keyboard-navigable, screen-reader announces the disclosure state),
and survives any react-state churn for free.
The OS-default disclosure marker is suppressed (list-style: none +
::-webkit-details-marker hidden) and replaced with a CSS ::before
chevron that rotates 90deg on the [open] attribute, so the look is
consistent across Firefox/WebKit/Blink without the double-marker
that would otherwise appear on the platforms that still render the
default triangle.
2. Skip rendering when metadata is an empty object.
`r.metadata && ...` truthy-checks, but `{}` is truthy in JS — so a
completed task with no actual metadata would render a "Metadata"
labeled disclosure block containing literal `{}`. Adds an
Object.keys(r.metadata).length > 0 guard so empty payloads render
nothing instead of an empty disclosure stub.
Tests: three new static-asset assertions covering the <details> shape,
the empty-object skip, and the suppress-default-marker + animated-chevron
CSS — all in `tests/plugins/test_kanban_dashboard_plugin.py`.
Hand-rebased onto current main from PR #19980; the original branch was stale
against main (~6 unrelated dashboard fixes had landed since), so applying
the PR's dist files directly would have silently reverted them.
The run-history panel in the task drawer rendered each completed run's
`metadata` field as a `<code class="hermes-kanban-run-meta">` containing
`JSON.stringify(r.metadata)` — a single unindented monoline. With
`white-space: pre-wrap` and a monospace font, a writer task's metadata
(changed_files paths, source URLs, generated-artifact details) wrapped
into a tall block of code-ish text that filled the parent run row. The
container's faint `--color-foreground 3%` background then made the whole
thing read like a crash dump even though the run completed normally.
Restyle and label, no interactivity changes:
- Wrap the meta payload in a `.hermes-kanban-run-meta-block` sub-block
with an explicit `Metadata` label (small, uppercase, muted) so the
panel reads as auxiliary detail at a glance.
- Pretty-print the JSON (`indent=2`) so the structure is scannable
instead of a wall of monoline text.
- Cap `.hermes-kanban-run-meta` at `max-height: 8.5rem; overflow: auto`
so a verbose blob scrolls inside its own pane rather than swamping
the run row.
- Sub-block uses a thin `border-left` rule and `background: transparent`
— distinct from the destructive-tinted treatment used by crashed /
timed_out / blocked / spawn_failed runs higher in the same file.
Tests: two new static-asset assertions in
`tests/plugins/test_kanban_dashboard_plugin.py` lock in the rendered
shape (the plugin ships built-only, no src/).
Adds CDPSupervisor.evaluate_runtime() and wires it into _browser_eval as a
fast path when a supervisor is alive for the current task_id. Replaces the
~180ms agent-browser subprocess fork+exec+Node-startup hop with a ~1ms
Runtime.evaluate over the supervisor's already-connected WebSocket.
Falls through to the existing agent-browser CLI path when no supervisor is
running (e.g. backends without CDP, or before the first browser_navigate
attaches one), so behaviour is unchanged where it can't apply.
JS-side exceptions surface directly without falling through to the
subprocess (the subprocess would just re-raise the same error, slower);
supervisor-side failures (loop down, no session) fall through cleanly.
Benchmark — 30 iterations of `1 + 1` against headless Chrome:
supervisor WS mean= 0.96ms median= 0.91ms
agent-browser subprocess mean=179.35ms median=167.73ms
→ 187x speedup mean
Tests: 14 unit tests (mocked supervisor + response-shape coverage), 5
real-Chrome e2e tests in test_browser_supervisor.py (gated on Chrome
being installed). Browser test suite: 355 passed, 1 skipped.
Follow-up to the previous commit's casing fix.
The original PR shipped the dist edits without test coverage. The
contributor's reasoning (UI-only attributes in a pre-built JS bundle,
nothing meaningful to unit-test) is fair, but a static-asset assertion
catches the most likely regression vector — a future rebuild of the
dist bundle that loses the attributes — at near-zero cost.
Adds two regression tests in tests/plugins/test_kanban_dashboard_plugin.py:
- test_dashboard_assignee_inputs_preserve_casing — reads dist/index.js
and asserts autoCapitalize="none", autoCorrect="off", spellCheck=false,
and textTransform="none" each appear at least twice (one per assignee
input — inline triage/lane create + task-edit panel).
- test_dashboard_lane_head_preserves_assignee_casing — reads dist/style.css
and asserts the .hermes-kanban-lane-head rule body does NOT contain
text-transform: uppercase. Locates the rule by marker so unrelated CSS
churn nearby doesn't flake the test.
Both follow the same shape as the existing test_dashboard_requests_default_board_explicitly
static-asset guard from PR #22940's salvage.
Also adds the AUTHOR_MAP entry for princepal9120's GitHub-noreply email
so release notes credit the right account.
Follow-up to the previous commit's safe-int task_age fix.
The original PR shipped without test coverage. This commit adds:
- test_safe_int_accepts_int_and_int_string — sanity for the well-typed
path so the helper itself can't quietly start swallowing valid values.
- test_safe_int_returns_none_on_corrupt_inputs — the failure modes
(None, '%s', 'abc', '', '1.5', random objects). Covers both the
ValueError and TypeError catch branches.
- test_task_age_handles_corrupt_created_at — the headline regression:
a task with created_at='%s' used to raise ValueError and turn
GET /api/plugins/kanban/board into a 500.
- test_task_age_handles_corrupt_started_and_completed — confirms the
safe-int treatment is consistent across all three timestamp fields.
- test_task_age_well_formed_task — regression that the safe path
doesn't change observable output for normal data.
- test_task_dict_survives_corrupt_created_at — defense in depth.
Writes a corrupt row directly via SQL, reads it back through the
ORM, and confirms task_age + the surrounding plugin_api guard
degrade gracefully instead of crashing.
Also adds the AUTHOR_MAP entry for the contributor's GitHub-noreply
email so release notes credit @baocin (the commit was authored locally
as `aoi <aoi@hino.local>` — re-attributed during salvage to the
github noreply form).
* feat(i18n): localize /model command output
Reported by @tianma8888: when Chinese users run /model, the labels
("Provider:", "Context:", "_session only_", etc.) are still English.
This routes the static prose through the existing i18n catalog so it
follows display.language / HERMES_LANGUAGE.
Changes:
- locales/{en,zh,ja,de,es,fr,tr,uk}.yaml: add 17 keys under
gateway.model.* covering switched/provider/context/max_output/cost/
capabilities/prompt_caching/warning/saved_global/session_only_hint/
current_label/current_tag/more_models_suffix/usage_*.
- gateway/run.py _handle_model_command: replace hardcoded f-strings in
the picker callback, the text-list fallback, and the direct-switch
confirmation block with t("gateway.model.<key>", ...).
What stays English:
- model IDs, provider slugs, capability strings, cost figures, and the
"[Note: model was just switched...]" prepended to the model's next
prompt (LLM-facing, not user-facing).
- The two slightly-different session-only hints unify on a single key
with the em-dash phrasing.
Validation: tests/agent/test_i18n.py 27/27 passing (parity contract
holds), tests/gateway/ -k 'model or i18n' 74/74 passing.
* feat(i18n): localize all gateway slash command outputs
Expands the i18n catalog from 7 strings to 234 keys across 35 gateway
slash command handlers, so non-English users see localized output for
\`/profile\`, \`/status\`, \`/help\`, \`/personality\`, \`/voice\`, \`/reset\`,
\`/agents\`, \`/restart\`, \`/commands\`, \`/goal\`, \`/retry\`, \`/undo\`,
\`/sethome\`, \`/title\`, \`/yolo\`, \`/background\`, \`/approve\`, \`/deny\`,
\`/insights\`, \`/debug\`, \`/rollback\`, \`/reasoning\`, \`/fast\`,
\`/verbose\`, \`/footer\`, \`/compress\`, \`/topic\`, \`/kanban\`,
\`/resume\`, \`/branch\`, \`/usage\`, \`/reload-mcp\`, \`/reload-skills\`,
\`/update\`, \`/stop\` (plus the \`/model\` block already added in the
previous commit).
Reported by @tianma8888 — Chinese users want command output prose in
their language, not just the labels we already had.
Translations are hand-written for all 8 supported locales (en, zh, ja,
de, es, fr, tr, uk), matching each catalog's existing style: full-width
punctuation in zh, em-dashes in zh/ja/uk, French spaced colons,
German noun capitalization, etc.
What stays English (unchanged):
- Identifiers/values: model IDs, file paths, profile names, session IDs,
command flag names like --global, URLs, config keys.
- Backtick code spans: \`/foo\`, \`config.yaml\`.
- Log messages (logger.info/warning/error).
- LLM-facing system notes prepended to next prompt (e.g. [Note: model
was just switched...]).
- Strings produced by external modules (gateway_help_lines,
format_gateway, manual_compression_feedback) — those have their
own surfaces.
New shared keys for cross-handler boilerplate:
- gateway.shared.session_db_unavailable (5 call sites: branch, title,
resume, topic, _disable_telegram_topic_mode_for_chat)
- gateway.shared.session_not_found (1 site)
- gateway.shared.warn_passthrough (2 sites in /title's f"⚠️ {e}" pattern)
YAML gotcha fixed: \`yolo.on\` and \`yolo.off\` were originally written
unquoted, which YAML 1.1 parses as boolean True/False keys. Renamed to
\`yolo.enabled\` / \`yolo.disabled\` for both safety and clarity.
Test fix: tests/agent/test_i18n.py::test_t_missing_key_in_non_english_falls_back_to_english
now resets the catalog cache on teardown, so the fake "foo: English Foo"
locale doesn't poison the module-level cache for subsequent tests in
the same xdist worker. (Without this, every gateway slash command test
that shares a worker with the i18n suite would see the fake catalog.)
Validation:
- tests/agent/test_i18n.py: 27/27 (parity contract — every key in every
locale, matching placeholder tokens).
- tests/gateway/: 5077 passed, 0 failed (full gateway suite).
- 180 t() call sites added across 35 handlers; 1872 catalog entries
total (234 keys × 8 locales).
* feat(i18n): add 8 new locales — af, ko, it, ga, zh-hant, pt, ru, hu
Expands the static-message catalog from 8 → 16 languages, each with full
270-key parity against the English source-of-truth. Every locale now
covers the same surface PR #22914 added: approval prompts plus all 35
gateway slash command outputs.
New locales:
- af Afrikaans (community ask in #21961 by @GodsBoy; PRs #21962, #21970)
- ko Korean (PRs #20297 by @tmdgusya, #22285 by @project820)
- it Italian (PR #20371 by @leprincep35700)
- ga Irish/Gaeilge (PR #20962 by @ryanmcc09-dot)
- zh-hant Traditional Chinese (PRs #20523 by @jackey8616, #13140 by @anomixer)
- pt Portuguese (PRs #20443 by @pedroborges, #15737 by @carloshenriquecarniatto, #22063 by @Magaav)
- ru Russian (PR #22770 by @DrMaks22)
- hu Hungarian (PR #22336 by @lunasec007)
Each locale uses native-quality translations matching the existing tone
and conventions of the older 8 locales:
- zh-hant uses 繁體 characters with TW/HK technical vocabulary (軟體
not 软件, 連線 not 连接, 設定 not 设置, 訊息 not 消息, 工作階段 not 会话, 程式
not 程序, 預設 not 默认, 伺服器 not 服务器), full-width punctuation 「：（）」.
- ko uses formal 합니다체 (습니다/합니다) register throughout.
- pt uses European Portuguese as baseline with neutral PT/BR vocabulary
where possible.
- ga uses standard An Caighdeán Oifigiúil; English loanwords retained
for tech terms without good Irish equivalents (gateway, API, JSON).
- All preserve {placeholder} tokens, backtick code spans, slash commands,
brand names (Hermes, MCP, TTS, YOLO, OpenAI, Telegram, etc.), and emoji.
Aliases added in agent/i18n.py:
- af-za, Afrikaans → af
- ko-kr, Korean, 한국어 → ko
- it-it, italiano → it
- ga-ie, Irish, Gaeilge → ga
- zh-tw, zh-hk, zh-mo, traditional-chinese → zh-hant (note: zh-tw used to
alias to zh; now aliases to its own zh-hant catalog)
- zh-cn, zh-hans, zh-sg → zh (unchanged from before)
- pt-pt, pt-br, brazilian, portuguese → pt
- ru-ru, Russian, русский → ru
- hu-hu, Magyar → hu
The zh-tw alias re-routing is intentional: previously typing 'zh-TW' got
the Simplified Chinese catalog (wrong vocabulary for Taiwan/HK users).
Now those users get the proper Traditional Chinese catalog.
Validation:
- tests/agent/test_i18n.py: 43/43 (parity contract holds for all 16
languages × 270 keys = 4320 catalog entries, with matching placeholder
tokens).
- E2E alias resolution verified for all 19 alias inputs (Afrikaans, ko-KR,
한국어, italiano, Gaeilge, zh-TW, zh-HK, traditional-chinese, pt-BR,
brazilian, Magyar, etc.).
- tests/gateway/: 5198 passed (3 pre-existing TTS routing failures
unrelated to i18n).
Credit to all contributors whose PRs surfaced these language requests.
Their original PRs may now be closed as superseded with credit.
* feat(dashboard-i18n): add 14 web dashboard locales matching the static catalog
Brings the React dashboard (web/src/) up to the same 16-language
coverage the static catalog already has after the previous commits in
this PR. The Translations interface is TypeScript-typed, so every new
locale must provide every key — tsc -b is the parity guard.
Languages added (each is a complete 429-line locale file):
- af Afrikaans
- ja Japanese (PR #22513 by @snuffxxx surfaced this)
- de German (PR #21749 by @mag1art)
- es Spanish (PR #21749)
- fr French (PRs #21749, #10310 by @foXaCe)
- tr Turkish
- uk Ukrainian
- ko Korean (PRs #21749, #18894 by @ovstng, #22285 by @project820)
- it Italian
- ga Irish (Gaeilge)
- zh-hant Traditional Chinese (PR #13140 by @anomixer)
- pt Portuguese (PRs #22063 by @Magaav, #22182 by @wesleysimplicio, #15737 by @carloshenriquecarniatto)
- ru Russian (PRs #21749, #22770 by @DrMaks22)
- hu Hungarian (PR #22336 by @lunasec007)
Each translation covers all 15 namespaces with full key parity vs en.ts,
preserves every {placeholder} token verbatim, keeps identifiers
untranslated (brand names, file paths, cron expressions, code spans),
translates the language.switchTo tooltip into the target language, and
matches existing tone conventions (zh-hant uses TW/HK vocab; ja uses
formal desu/masu; ko uses formal seumnida register; ga uses An
Caighdean Oifigiuil with English loanwords for tech vocab without good
Irish equivalents).
Plumbing:
- web/src/i18n/types.ts: Locale union expanded to all 16 codes.
- web/src/i18n/context.tsx: imports all 16 catalogs; exports
LOCALE_META (endonym + flag per locale); isLocale() type guard.
- web/src/i18n/index.ts: re-export LOCALE_META.
- web/src/components/LanguageSwitcher.tsx: replaced two-state EN-ZH
toggle with a click-to-open dropdown listing all 16 languages.
Note: zh-hant.ts exports zhHant (camelCase) since hyphen is invalid in
a JS identifier; the canonical 'zh-hant' string keys it in TRANSLATIONS.
Validation:
- npx tsc -b: 0 errors. Every locale satisfies Translations.
- npm run build (tsc + vite production): green, 2062 modules.
- Each locale file is exactly 429 lines.
Out of scope: plugin dashboards (kanban/achievements ship as prebuilt
bundles with no source in repo); Docusaurus docs (separate surface);
TUI (no i18n yet).
* feat(plugin-i18n): localize achievements + kanban plugin dashboards across all 16 locales
Brings the two shipped plugin dashboards (hermes-achievements, kanban)
under the same i18n umbrella as the core dashboard PR #22914 just
established. Both bundles now read user-facing strings from the host's
i18n catalog via SDK.useI18n() instead of hardcoded English.
## Approach
Plugin dashboards ship as prebuilt IIFE bundles in
plugins/<name>/dashboard/dist/index.js — no build step, no source in
repo (upstream-authored, vendored as compiled JS). Earlier contributor
PRs (#22594, #22595, #18747) tried direct edits but didn't actually
wire the bundles to read translations.
This change does the wiring properly:
1. Each bundle gets a useI18n shim at IIFE scope:
const useI18n = SDK.useI18n
|| function () { return { t: { kanban: null }, locale: "en" }; };
Older host SDKs without useI18n still load the bundle and render
English fallbacks.
2. A small tx(t, path, fallback, vars) helper resolves dotted keys
under the plugin's namespace (t.kanban.* or t.achievements.*) and
interpolates {placeholder} tokens.
3. Every React component starts with const { t } = useI18n() and
each user-visible string is wrapped in tx(t, "key", "English fallback").
Helpers called outside React components (window.prompt callers,
constants used during init) take t as a parameter.
4. Top-level constants that were English dictionaries (COLUMN_LABEL,
COLUMN_HELP, DESTRUCTIVE_TRANSITIONS, DIAGNOSTIC_EVENT_LABELS in
kanban) become getColumnLabel(t, status)-style functions backed by
FALLBACK_* dictionaries.
## Translations added
Two new top-level namespaces added to the dashboard's TypeScript-typed
Translations interface:
- achievements: ~70 keys covering the hero, scan banner, achievement
card, share dialog, stats, filters, and empty states.
- kanban: ~145 keys covering the board, columns (with nested
columnLabels and columnHelp sub-dicts), card detail panel,
bulk-actions toolbar, dependency editor, board switcher, and
diagnostic callouts.
Each key is provided across all 16 supported locales:
en, zh, zh-hant, ja, de, es, fr, tr, uk, af, ko, it, ga, pt, ru, hu.
Total new translation entries: ~3,440 (215 keys × 16 locales).
## What stays English (deliberate)
- API paths, CSS class names, data-* attributes, JSON keys, regex
strings, URLs, file paths (~/.hermes/kanban.db, boards/_archived/).
- State identifier strings used as lookup keys (triage / todo / ready /
running / blocked / done / archived) — labels translate, key strings
don't.
- The PNG share-card text rendered to canvas in the achievements
ShareDialog (HERMES AGENT watermark, UNLOCKED stamp, tier names) —
these become part of a globally-shared image and stay English.
- localStorage keys (hermes.kanban.selectedBoard).
- Brand names (Kanban, Hermes, WebSocket, Nous Research).
## Contributor credit
PR #22594 by @02356abc and PR #22595 by @02356abc supplied the
en + zh kanban namespace skeleton (145 keys); used as the en source-
of-truth in this commit and translated to the other 14 locales.
PR #18747 by @laolaoshiren first surfaced the achievements
localization request.
## Validation
- npx tsc -b: 0 errors. All 16 locale .ts files satisfy the
Translations type with full key parity.
- npm run build (tsc + vite production build): green, 2062 modules,
1.56MB JS / 95KB CSS, ~2.5s build.
- node --check on both plugin bundles: parse cleanly.
- 126 tx() call sites in kanban, 46 in achievements.
## Out of scope
- TUI (ui-tui/) has no i18n infrastructure yet.
- Docusaurus docs (website/i18n/) — already had zh-Hans; expanding
is a separate translation workstream (Thai / Korean / Hindi PRs).
Follow-up to the previous commit's contributor cherry-pick.
The cherry-picked change replaced the bare ``["hermes", ...]`` spawn with
``[sys.executable, "-m", "hermes", ...]``. The intent was right (avoid
PATH dependence — cron, systemd User= services, launchd jobs, and other
detached dispatcher invocations routinely run with a stripped $PATH that
doesn't include the venv's bin/, breaking the bare-shim spawn) but the
module name is wrong: there is no top-level ``hermes`` package. The
console-script entry point in pyproject.toml is
``hermes = "hermes_cli.main:main"``, and ``python -m hermes`` fails with
``No module named hermes``. The cherry-picked form would have replaced a
sometimes-broken spawn with an always-broken one.
This commit:
- Adds ``_resolve_hermes_argv()``, mirroring ``gateway.run._resolve_hermes_bin``.
Tries ``shutil.which("hermes")`` first (preferred — keeps existing ``ps``
output and log lines familiar in the common case) and falls back to
``[sys.executable, "-m", "hermes_cli.main"]`` when the shim is not on
PATH. The fallback goes through the running interpreter so it's
PATH-independent. Kept as a local helper rather than imported from
gateway because ``hermes_cli`` sits below ``gateway`` in the dependency
order.
- Switches the dispatcher's ``cmd`` list to use ``*_resolve_hermes_argv()``.
- Adds three regression tests:
* ``test_resolve_hermes_argv_prefers_path_shim`` — pins the PATH-first
branch so a future refactor doesn't silently flip the order.
* ``test_resolve_hermes_argv_falls_back_to_module_form_when_no_path_shim`` —
pins the correct module name (``hermes_cli.main``, NOT ``hermes``).
Direct regression guard for the form that shipped in the original PR.
* ``test_resolve_hermes_argv_module_actually_runs`` — runs the fallback
invocation as a real subprocess and asserts ``--version`` works, so
losing ``hermes_cli.main``'s ``__main__`` handling can't slip past the
string-match test.
Verified end-to-end: with the shim on PATH the resolver returns
``[/.../hermes]`` and ``--version`` works; with the shim removed the
resolver returns ``[python, -m, hermes_cli.main]`` and ``--version``
still works; the original PR's ``python -m hermes`` invocation fails as
expected (``No module named hermes``).
* feat(plugins): host-owned LLM access via ctx.llm
Plugins can now ask the host to run a one-shot chat or structured
completion against the user's active model and auth, without ever
seeing an OAuth token or API key. Closes the gap where plugins that
needed bounded structured inference (receipts, CRM extraction,
support classification) had to either bring their own provider keys
or register a tool the agent had to call.
New surface on PluginContext:
- ctx.llm.complete(messages, ...)
- ctx.llm.complete_structured(instructions, input, json_schema, ...)
- async siblings ctx.llm.acomplete / acomplete_structured
Backed by the existing auxiliary_client.call_llm pipeline — every
provider, fallback chain, vision routing, and timeout policy Hermes
already supports applies automatically.
Trust gate (fail-closed by default):
- plugins.entries.<id>.llm.allow_model_override
- plugins.entries.<id>.llm.allowed_models (allowlist; '*' = any)
- plugins.entries.<id>.llm.allow_agent_id_override
- plugins.entries.<id>.llm.allow_profile_override
Embedded model@profile shorthand goes through the same gate as
explicit profile=, so it can't bypass the auth-profile policy.
Conflicting explicit and embedded profiles fail closed.
Also lands:
- plugins/plugin-llm-example/ — reference plugin that registers
/receipt-extract, demonstrating image+text structured input,
jsonschema validation, and the trust-gate config.
- website/docs/developer-guide/plugin-llm-access.md — full API docs.
- 45 unit tests covering trust gates, JSON parsing, schema
validation, image encoding, async surface, and config loading.
Validation:
- 2628 tests pass in tests/agent/
- E2E: bundled plugin loaded with isolated HERMES_HOME, slash
command produced parsed JSON via stubbed call_llm
- response_format extra_body wired correctly for both json_object
and json_schema modes
* docs(plugin-llm): rewrite quickstart and framing
The quickstart now uses a meeting-notes-to-tasks example instead of
a receipt extractor, and the page leads with hook-time / gateway
pre-filter / scheduled-job framing rather than the OpenClaw
KB/support/CRM/finance/migration enumeration that the original
upstream PR used. Receipt example moved to a separate worked
example link so the docs page itself doesn't echo any of the
upstream framing.
Also clarifies where ctx.llm fits in the broader plugin surface
(table comparing register_tool / register_platform / register_hook
/ etc.) and what makes this lane different from auxiliary_client
internals.
No code change.
* docs(plugin-llm): reframe as any LLM call, not just structured output
The original draft leaned heavily on complete_structured() and made
the chat lane (complete() / acomplete()) feel like a footnote.
Restructure so:
- The page title and description say 'any LLM call.'
- The lead shows BOTH a plain chat call (error rewriter) AND a
structured call (triage scorer) up top.
- Quick start has two complete plugin examples — /tldr (chat) and
/paste-to-tasks (structured).
- New 'When to use which' table for choosing complete() vs
complete_structured() vs the async siblings.
- Trust-gate sections explicitly note 'all four methods,' and the
request-shaping list calls out chat-only fields (messages) and
structured-only fields (instructions, input, json_schema)
alongside each other.
- The 'Where this fits' section now says 'for any reason,
structured or not.'
The receipt-extractor reference plugin still exists under
plugins/plugin-llm-example/ — but the docs page no longer treats
it as the canonical surface example. It's now described as 'a third
worked example, this time with image input.'
No code change.
* feat(plugin-llm): split provider/model into independent explicit kwargs
The first cut accepted a single 'provider/model' slug on every method
and split it internally. That looked clean but broke under live test:
the model-override path tried to use the slug's vendor prefix as a
literal Hermes provider id, which silently switched the user off
their aggregator (e.g. plugin asks for 'openai/gpt-4o-mini' on a user
who routes through OpenRouter — host attempted to call the 'openai'
provider directly, failed because OPENAI_API_KEY wasn't set).
New shape mirrors the host's main config:
ctx.llm.complete(
messages=[...],
provider='openrouter', # gated, optional
model='openai/gpt-4o-mini', # gated, optional
profile='work', # gated, optional
...
)
Each is independently gated by its own allow_*_override flag.
Granting model-override does NOT auto-grant provider-override.
Allowlists are now per-axis (allowed_providers, allowed_models)
matched literally against whatever string the plugin sends.
Dropped 'model@profile' embedded-suffix shorthand entirely. Hermes
doesn't use that pattern anywhere else; profile= is its own kwarg.
Live E2E (against real OpenRouter via Teknium's config) confirms:
- zero-config call works
- default-deny blocks each override with a helpful error
- model-only override stays on user's active provider (the bug)
- provider+model override switches cleanly
- allowlist refuses non-listed entries
- structured output round-trip parses + schema-validates
Tests: 49 cases (up from 45); all green. Docs updated to match the
new shape, including a 'most plugins never need this section' callout
on the trust-gate config block.
* fix+cleanup(plugin-llm): real attribution, hook-mode coverage, move example out of core
Three integration fixes for the ctx.llm surface:
1. Attribution bug — result.provider and result.model now reflect
what call_llm actually used, not placeholder fallbacks ('auto',
'default'). New _resolve_attribution() helper:
- explicit overrides win (what the call targeted)
- response.model wins for the recorded model (provider
canonicalisation: 'gpt-4o' → 'gpt-4o-2024-08-06' etc.)
- falls back to _read_main_provider() / _read_main_model()
when no override is set, so audit logs reflect the user's
active main provider/model
- 'auto' / 'default' only when EVERYTHING is empty
Live verified: zero-config call now records
provider='openrouter', model='anthropic/claude-4.7-opus-20260416'
instead of provider='auto', model='default'.
2. Hook-mode coverage — TestHookMode confirms ctx.llm.complete
works from inside a registered post_tool_call callback. The
docs page promised hook integration; now there's a test that
exercises the lazy-import path through the real invoke_hook
machinery. Two cases: traceback-rewrite hook with conditional
ctx.llm.complete, and minimal hook regression for the
sync-hook + sync-llm path.
3. Reference plugin moved out of core. plugins/plugin-llm-example/
is gone from hermes-agent — it now lives in the new
NousResearch/hermes-example-plugins companion repo. The docs
page links there. Hermes' bundled plugins should be plugins
users actually run; reference / docs-companion plugins live
externally.
Test count: 56 (up from 49). Wider sweep on tests/hermes_cli/
+ tests/gateway/ + tests/tools/ + tests/agent/ shows 16770
passing; the 12 failures are all pre-existing on origin/main
(verified by stashing this branch's changes and re-running) —
kanban-boards, delegate-task, gateway-restart, tts-routing —
none touch the plugin_llm surface.
* chore(plugins): move all example plugins to companion repo
Reference / docs-companion plugins now live exclusively in
NousResearch/hermes-example-plugins, not bundled with the core repo:
- example-dashboard
- strike-freedom-cockpit
A new fourth example, plugin-llm-async-example, was added to that
repo demonstrating ctx.llm's async surface (acomplete()) with
asyncio.gather() — registers /translate <lang>: <text> which fires
forward translation + sentiment classifier in parallel, then a
back-translation for QA. Live-tested at 2.5s for three real
provider round-trips (would be ~5-6s sequential).
Docs updated:
- developer-guide/plugin-llm-access.md links both sync and async
examples in the Reference section
- user-guide/features/extending-the-dashboard.md repoints both demo
sections to the companion repo with corrected install paths
- user-guide/features/built-in-plugins.md drops the two demo rows
- AGENTS.md notes that example plugins live in the companion repo
Net: hermes-agent's plugins/ directory now contains only plugins
users actually run (memory providers, dashboard tabs that ship real
features, the disk-cleanup hook, platform adapters). All four
demo / reference plugins live externally where they can be cloned
on demand instead of inflating the core install.
Follow-up to the previous commit's middleware fix.
- plugins/kanban/dashboard/plugin_api.py: rewrite the "Security note"
docstring. The previous text said "/api/plugins/ is unauthenticated by
design" — that's now actively wrong and dangerously misleading. New
text explains that plugin routes flow through the same session-token
middleware as core API routes and that --host 0.0.0.0 is safe to use
on a LAN as a result.
- tests/hermes_cli/test_web_server.py: extend TestPluginAPIAuth to cover
the surfaces the original PR didn't pin:
* test_plugin_route_allows_auth now exercises a real plugin path
(/api/plugins/example/hello) instead of accepting 200 OR 404 from
a maybe-loaded kanban plugin — the assertion was effectively vacuous.
* test_plugin_patch_requires_auth + test_plugin_delete_requires_auth
cover non-GET mutation methods in case a future regression
whitelists them by accident.
* test_non_kanban_plugin_route_requires_auth proves the fix is
plugin-agnostic, not kanban-specific (hits hermes-achievements +
a non-existent plugin namespace; both 401 before route resolution).
* test_plugin_websocket_unaffected_by_http_middleware locks in that
the HTTP middleware change didn't accidentally start gating WS
upgrades — kanban /events still uses its own ?token= check.
Plus a cosmetic blank-line cleanup.
Remove the blanket /api/plugins/* exemption from auth_middleware so
plugin API routes (e.g. Kanban dashboard) require the same session
token as all other /api/ endpoints.
Fixes#19533
Surfaces the pin command at the moment users care about it: when a
consolidation just landed against their skill library and they're
looking at the umbrella name in the curator output. Previously `hermes
curator pin` existed but had no discovery surface — users only learned
it existed by reading docs or stumbling onto `hermes curator --help`.
The hint:
archived 3 skill(s):
• docx-extraction → document-tools
• pdf-extraction → document-tools
• old-stale — pruned (stale)
full report: hermes curator status
keep an umbrella stable: hermes curator pin document-tools
Gated on having at least one consolidation that produced an umbrella.
Pruned-only runs (nothing surviving to pin) skip the hint. When
multiple umbrellas were produced, picks alphabetically first as a
concrete example rather than listing them all.
3 new tests in tests/agent/test_curator_classification.py covering:
consolidation produces hint with real umbrella name, pruned-only run
omits it, multi-umbrella picks one example.
* feat(gateway): add LINE Messaging API platform plugin
Adds LINE as a bundled platform plugin under `plugins/platforms/line/`,
synthesized from the strongest pieces of seven open community PRs. The
adapter requires zero core edits — `Platform("line")` is auto-discovered
via the bundled-plugin scan in `gateway/config.py`, and all hooks
(setup, env-enablement, cron delivery, standalone send) are wired
through `register_platform()` kwargs the way IRC and Teams do it.
Highlights merged into one plugin:
- **Reply token preferred, Push fallback.** Try the free reply token
first (single-use, ~60s TTL); fall back to metered Push when the
token is absent, expired, or rejected. (PR #21023)
- **Slow-LLM Template Buttons postback.** When the LLM is still running
past `LINE_SLOW_RESPONSE_THRESHOLD` (default 45s), the adapter burns
the original reply token to send a "Get answer" button bubble. The
user taps it to fetch the cached answer via a fresh reply token —
also free. State machine: PENDING → READY → DELIVERED, ERROR for
cancelled runs (orphan resolves to `LINE_INTERRUPTED_TEXT` after
/stop). Set threshold to 0 to disable. (PR #18153)
- **Three-allowlist gating** — separate user / group / room allowlists
with `LINE_ALLOW_ALL_USERS=true` dev-only escape hatch. (PR #18153)
- **Markdown URL preservation.** Strip bold/italic/code-fence/heading
markers (LINE renders them literally) but keep `[label](url)` →
`label (url)` so URLs stay tappable. (PR #18153)
- **System-message bypass** for `⚡ Interrupting`, `⏳ Queued`, etc. —
busy-acks reach the user as visible bubbles instead of being
swallowed into the postback cache. (PR #18153)
- **Media via public HTTPS URLs.** LINE doesn't accept binary uploads;
images/audio/video must be HTTPS-reachable. The adapter serves
registered tempfiles under `/line/media/<token>/<filename>` from the
same aiohttp app. Allowed-roots traversal guard covers
`tempfile.gettempdir()`, `/tmp` (→ `/private/tmp` on macOS), and
`HERMES_HOME`. `LINE_PUBLIC_URL` overrides URL construction for
setups behind tunnels/proxies. (PR #8398)
- **5-message-per-call batching.** LINE rejects >5 messages per
Reply/Push; smart-chunker caps text at 4500 chars per bubble.
- **Inbound dedup** via `webhookEventId` LRU. (PR #21023)
- **Self-message filter** via `/v2/bot/info` userId lookup. (PR #21023)
- **Loading-animation indicator** wired to LINE's `chat/loading/start`
endpoint, DM-only (LINE rejects it for groups/rooms). (PR #21023)
- **Out-of-process cron delivery** via `_standalone_send`, so
`deliver: line` cron jobs work even when cron runs detached from
the gateway.
- **Webhook hardening** — 1 MiB body cap, constant-time HMAC-SHA256
signature verification, dedup, scoped lock so two profiles can't
bind the same channel.
Validation
----------
- `scripts/run_tests.sh tests/gateway/test_line_plugin.py` →
73 passed in 1.05s
- `scripts/run_tests.sh tests/gateway/test_line_plugin.py
tests/gateway/test_irc_adapter.py
tests/gateway/test_plugin_platform_interface.py
tests/gateway/test_platform_registry.py
tests/gateway/test_config.py` → 193 passed, 7 skipped
- E2E import + register + signature roundtrip + `Platform("line")`
bundled-plugin discovery verified against current `origin/main`.
Closes the seven open LINE PRs (#18153, #16832, #6676, #21023, #14942,
#14988, #8398) by superseding them with a single plugin-form
implementation that takes the best idea from each.
Co-authored-by: pwlee <32443648+leepoweii@users.noreply.github.com>
Co-authored-by: Jetha Chan <jetha@google.com>
Co-authored-by: Cattia <openclaw@liyangchen.me>
Co-authored-by: perng <charles@perng.com>
Co-authored-by: Soichiro Yoshimura <soichiro0111.dev@gmail.com>
Co-authored-by: David Zhou <77736378+David-0x221Eight@users.noreply.github.com>
Co-authored-by: Yu-ga <74749461+yuga-hashimoto@users.noreply.github.com>
* docs(platforms): document platform-specific slow-LLM UX pattern
Add a 'Platform-Specific Slow-LLM UX' section to the platform-adapter
developer guide covering the _keep_typing override pattern that LINE
uses for its Template Buttons postback flow.
Three subsections:
- Pattern: subclass _keep_typing to layer mid-flight UX (with code)
- Pattern: subclass send to route through a cache instead of sending
- When this pattern is appropriate (vs. always-Push fallback)
Plus a short pointer in gateway/platforms/ADDING_A_PLATFORM.md so
tree-readers find the prose walkthrough on the docsite.
Filed because the LINE plugin (PR #23197) was the first bundled
adapter to need this pattern — every prior plugin (irc, teams,
google_chat) handles slow responses with the default typing-loop and
a regular send_text. Documenting now while the rationale is fresh.
---------
Co-authored-by: pwlee <32443648+leepoweii@users.noreply.github.com>
Co-authored-by: Jetha Chan <jetha@google.com>
Co-authored-by: Cattia <openclaw@liyangchen.me>
Co-authored-by: perng <charles@perng.com>
Co-authored-by: Soichiro Yoshimura <soichiro0111.dev@gmail.com>
Co-authored-by: David Zhou <77736378+David-0x221Eight@users.noreply.github.com>
Co-authored-by: Yu-ga <74749461+yuga-hashimoto@users.noreply.github.com>
Adapted from PR #20568 commit ce3518578 (Eric Litovsky / @kallidean).
Adds two-tier gating for the kanban tool surface so dispatcher-spawned
workers see only task-lifecycle tools (show/complete/block/heartbeat/
comment/create/link) while orchestrator profiles with `toolsets: [kanban]`
also see board-routing tools (kanban_list, kanban_unblock).
Workers shouldn't be enumerating or unblocking the board — they should
close their own task via the lifecycle tools. Hiding board-routing tools
from worker schemas keeps the worker focused and the toolset-isolation
contract honest.
Plus inherited from the same upstream commit:
- 50/200 row bound on kanban_list with `truncated` + `next_limit` metadata.
- Belt-and-suspenders runtime guard `_require_orchestrator_tool()` inside
the orchestrator handlers in case a stale registration ever routes a
worker to one of them.
- Tests for the new gate, the stricter bound, and the fact that even a
worker with `toolsets: [kanban]` in config still doesn't see board
routing.
Co-authored-by: Eric Litovsky <elitovsky@zenproject.net>
Two follow-ups from self-review:
1. Add gpt-5.3-codex-spark to DEFAULT_CONTEXT_LENGTHS at 128k. The
primary resolution path for Spark goes through provider='openai-codex'
→ _CODEX_OAUTH_CONTEXT_FALLBACK (already correct). But if any future
code path resolves Spark's context with a different provider (custom
proxy, generic fallthrough), the longest-substring-first lookup in
step 8 would match 'gpt-5' and report 400k, which is wrong by ~3x.
Adding the explicit override is a cheap defensive correctness fix
matching how gpt-5.4-mini and gpt-5.4-nano already shadow the generic
gpt-5 entry.
2. Update test_openai_codex_model_validation_fallback.py docstring. The
bug it was originally written for (gpt-5.3-codex-spark missing from
listing) is now resolved by this PR's catalog restoration. The test
still validly exercises the soft-accept code path for any future
entitlement-gated Codex slug that ships before Hermes catalogs it,
but the framing was stale — clarified.
Two follow-ups from self-review:
1. Add unit test for _fetch_models_from_api covering the live HTTP path.
The salvaged PR #19530 dropped the supported_in_api:false filter in
both _fetch_models_from_api and _read_cache_models, but only the
cache path had a regression test. This adds the symmetric live-fetch
test (mocked httpx) so a future drive-by change to the HTTP path
can't silently re-introduce the filter.
2. Pin test_codex_picker_uses_live_codex_catalog to the cache fallback.
The test wrote a fake JWT and a CODEX_HOME cache, but provider_model_ids
('openai-codex') still issued a real 10s HTTP probe to
chatgpt.com/backend-api/codex/models before falling back to the cache.
That made the test slow and non-deterministic in restricted/CI
networks. Patch _fetch_models_from_api to return [] so we go straight
to the cache path the test actually means to exercise.
Closes#6051.
Reported failure mode: agent migrated to WSL2, browser launch failed
because Playwright wasn't installed yet. Background reviewer captured
the failure as a durable skill (`browser-tool-launch-issue`) and the
agent kept refusing the browser tool for weeks after Playwright was
installed and verified working. Negative claims also propagated into
unrelated skills ("browser tools do not work", "cannot use Y from
execute_code").
Root cause: `_SKILL_REVIEW_PROMPT` and `_COMBINED_REVIEW_PROMPT` both
lean hard on "be active, save things, a pass that does nothing is a
missed learning opportunity." Neither distinguished durable knowledge
from transient environment state. The reviewer was doing what it was
told.
Fix at the write site — both prompts now carry a "Do NOT capture"
section calling out:
• Environment-dependent failures (missing binaries, fresh-install
errors, post-migration path mismatches, 'command not found',
unconfigured credentials, uninstalled packages)
• Negative claims about tools or features ("X does not work")
that harden into self-cited refusals
• Session-specific transient errors that resolved before the
conversation ended
• One-off task narratives ("summarize today's market", "analyze
this PR") — also addresses the #12812 / #4538 family
Plus a positive-reframing line: when a tool fails because of setup
state, capture the FIX (install command, config step, env var)
under an existing setup/troubleshooting skill — never "this tool
doesn't work" as a standalone constraint.
Targeted tests: 24/24 passing in tests/run_agent/test_review_prompt_class_first.py
(2 new + all existing review-prompt assertions). Substring-based
checks so future prompt edits don't false-fail.
The previous PR (#22993) gave us a structured WARNING per stream drop
but the only diagnostic was 'error_type=APIError error=Network
connection lost.' — same nothing the user started with. To actually
diagnose why subagents drop streams disproportionately we need to know
WHERE the drop happened.
Adds three breadcrumbs to the agent.log WARNING:
1. Inner exception chain. openai SDK wraps httpx errors as
APIConnectionError / APIError so the catch site only sees the
wrapper. _flatten_exception_chain walks __cause__/__context__ up to
4 levels deep and renders 'Outer(msg) <- Inner(msg)' so we can
tell ConnectError vs RemoteProtocolError vs ReadError vs
ProxyError without enabling verbose mode.
2. Upstream HTTP headers. Snapshots cf-ray, x-openrouter-provider,
x-openrouter-model, x-openrouter-id, x-request-id, server, via,
etc. from stream.response immediately after open (so they survive
even when the stream dies before the first chunk). These answer
'is one CF edge / one downstream provider responsible, or random?'
3. Per-attempt counters. bytes streamed, chunk count, elapsed time on
the dying attempt, and time-to-first-byte. Distinguishes 'couldn't
connect at all' (0s, 0 bytes) from 'died after 30s mid-stream'
(very different root causes — first is auth/routing, second is
upstream idle-kill or proxy timeout).
Plumbing:
- _stream_diag_init / _stream_diag_capture_response live on AIAgent
and produce a per-attempt dict held on request_client_holder['diag']
for closure access from the retry block.
- _call_chat_completions and _call_anthropic both initialize the diag
and increment counters per chunk/event (best-effort, never raises in
the streaming hot path).
- _log_stream_retry / _emit_stream_drop accept an optional diag and
render the new fields. Final-exhaustion log goes through the same
helper so it gets the same diagnostic dump.
- UI status line gains a brief 'after Xs' suffix when timing is
available — distinguishes 'connect failed' from 'died mid-stream'
at a glance without grepping logs.
Sample WARNING after this change:
Stream drop mid tool-call on attempt 2/3 — retrying.
subagent_id=sa-2-cafef00d depth=1 provider=openrouter
base_url=https://openrouter.ai/api/v1
error_type=APIError error=Connection error.
chain=APIError(Connection error.) <- RemoteProtocolError(peer
closed connection without sending complete message body)
http_status=200 bytes=12400 chunks=47 elapsed=12.00s ttfb=0.83s
upstream=[cf-ray=8f1a2b3c4d5e6f7g-LAX
x-openrouter-provider=Anthropic
x-openrouter-id=gen-abc123 server=cloudflare]
Tests: 10 covering diag init, header capture (whitelist enforced for
PII), exception-chain walking + depth cap, log content with full diag,
log content without diag (placeholders), UI elapsed-suffix on/off.
Closes#21794.
`/kanban`, `/kanban help`, `/kanban --help`, and `/kanban <sub> -h`
all returned broken output to the gateway and interactive CLI. Three
underlying bugs in `hermes_cli.kanban.run_slash`:
1. argparse writes help to **stdout** but `run_slash` only captured
stderr at parse time, so `-h` text was silently swallowed and
replaced with the `(usage error: 0)` sentinel.
2. The wrapping parser used `prog="/"` and routed via a synthetic
"_top → kanban" subparser, producing `usage: / kanban …` (stray
space) and `usage: /kanban kanban …` (doubled token) in error text.
3. Bare `/kanban` and `/kanban help` dumped argparse's full ~3KB
usage tree, which reads as visual garbage in a chat bubble.
Fix: drive the kanban_parser directly (no double-wrap), rewrite prog
strings on every leaf subparser, capture stdout AND stderr around
parse_args, distinguish SystemExit(0) (help — return captured stdout)
from SystemExit(2) (error — return single-line ⚠-prefixed message),
and add an explicit chat-friendly short-help block returned for bare
invocation and the help aliases (`help`, `--help`, `-h`, `?`).
Added 5 regression tests covering bare invocation, every help alias,
subcommand help, unknown action, and missing required arg.
Affects every chat platform via gateway/run.py::_handle_kanban_command
and the interactive CLI via cli.py::_handle_kanban_command.
Co-Authored-By: Nagatha (Claude Opus 4.7) <noreply@anthropic.com>
Both `_kanban_notifier_watcher` and `_kanban_dispatcher_watcher`'s
`_tick_once_for_board` called `_kb.connect(board=slug)` immediately
followed by `_kb.init_db(board=slug)`. Since `connect()` already runs
the schema + idempotent migration on first open per process, the
explicit `init_db()` was redundant — and worse, `init_db()` deliberately
busts the per-process `_INITIALIZED_PATHS` cache and re-runs the migration
on a *second* connection that races the first.
On every cold gateway start against a legacy DB this surfaced as either
`sqlite3.OperationalError: duplicate column name: <col>` or intermittent
`database is locked` errors logged at the first tick. The duplicate-column
case is now tolerated by `_add_column_if_missing` (commit 78698381a), but
the wasted second migration plus the database-is-locked race remain
fixable by skipping the redundant call entirely.
Drops `_kb.init_db(board=slug)` at both call sites and adds a regression
test in `tests/hermes_cli/test_kanban_notify.py` that pins the absence
via source inspection plus a runtime spy.
Co-authored-by: Teknium <127238744+teknium1@users.noreply.github.com>
Subagent stream drops were spamming the parent terminal with two lines
per blip ('Connection dropped...' + 'Reconnected...') while leaving zero
breadcrumb in agent.log to debug them.
Two underlying bugs, fixed together:
1. quiet_mode raised the run_agent/tools/etc. loggers to ERROR, which
filters records before root-logger file handlers see them. The comment
claimed 'File handlers still capture everything' — that was wrong.
Removed in both run_agent.py and cli.py; console quietness already
comes from hermes_logging not installing a console StreamHandler in
non-verbose mode.
2. The stream-retry blocks emitted two _emit_status calls per drop
('⚠️ Connection dropped... Reconnecting...' + '🔄 Reconnected —
resuming…') with no provider name, so multi-provider sessions had to
dig through agent.log to attribute a drop. Replaced both call sites
with a single _emit_stream_drop helper that emits ONE line naming the
provider and error class, and always writes a structured WARNING to
agent.log with subagent_id, depth, provider, base_url, error_type.
Net UX change: 6 lines per triple-subagent drop → 3 lines, each
naming the provider. agent.log now has a structured breadcrumb per
retry that didn't exist before.
Tests: 6 new tests in tests/run_agent/test_stream_drop_logging.py
covering the logger-level guard, structured WARNING content, single
status line per drop (no Reconnected follow-up), and provider naming.
When the active main model has native vision and the provider supports
multimodal tool results (Anthropic, OpenAI Chat, Codex Responses, Gemini
3, OpenRouter, Nous), vision_analyze loads the image bytes and returns
them to the model as a multimodal tool-result envelope. The model then
sees the pixels directly on its next turn instead of receiving a lossy
text description from an auxiliary LLM.
Falls back to the legacy aux-LLM text path for non-vision models and
unverified providers.
Mirrors the architecture used in OpenCode, Claude Code, Codex CLI, and
Cline. All four converge on the same pattern: tool results carry image
content blocks for vision-capable provider/model combinations.
Changes
- tools/vision_tools.py: _vision_analyze_native fast path + provider
capability table (_supports_media_in_tool_results). Schema description
updated to reflect new behaviour.
- agent/codex_responses_adapter.py: function_call_output.output now
accepts the array form for multimodal tool results (was string-only).
Preflight validates input_text/input_image parts.
- agent/auxiliary_client.py: _RUNTIME_MAIN_PROVIDER/_MODEL globals so
tools see the live CLI/gateway override, not the stale config.yaml
default. set_runtime_main()/clear_runtime_main() helpers.
- run_agent.py: AIAgent.run_conversation calls set_runtime_main at turn
start so vision_analyze's fast-path check sees the actual runtime.
- tests/conftest.py: clear runtime-main override between tests.
Tests
- tests/tools/test_vision_native_fast_path.py: provider capability
table, envelope shape, fast-path gating (vision-capable model uses
fast path; non-vision model falls through to aux).
- tests/run_agent/test_codex_multimodal_tool_result.py: list tool
content becomes function_call_output.output array; preflight
preserves arrays and drops unknown part types.
Live verified
- Opus 4.6 + Sonnet 4.6 on OpenRouter: model calls vision_analyze on a
typed filepath, gets pixels back, reads exact text from images that
no aux description could capture (font color irony, multi-line
fruit-count list, etc.).
PR replaces the closed prior efforts (#16506 shipped the inbound user-
attached path; this PR closes the gap for tool-discovered images).
Adds test_notifier_second_blocked_delivers to cover the case where a
task is blocked, unblocked, then blocked again — the second blocked
event must still deliver a gateway notification.
Currently fails because blocked is treated as a terminal event kind,
causing the subscription to be dropped after the first block.
Linux's MAX_ARG_STRLEN caps any single argv element at 128 KB
(32 * PAGE_SIZE). The previous heredoc-in-the-command-string approach
in _write_to_sandbox put the entire tool result inside the 'bash -c'
arg, so any result over ~128 KB raised OSError [Errno 7] 'Argument
list too long' before the heredoc ever ran. The caller logged a
warning, but quiet_mode (CLI default) sets tools.* to ERROR — so the
warning never reached agent.log either, and the agent saw a 1.5 KB
preview tagged 'Full output could not be saved to sandbox'. Hits
delegate_task with 3+ subagent outputs routinely now.
Switch to passing content via env.execute(stdin_data=...). cmd is
now just 'mkdir -p X && cat > Y' (under 1 KB), and the heavyweight
payload travels through stdin where there is no argv-element limit.
E2E reproduced the user's exact 144,778-char delegate_task envelope:
old code OSError'd, new code round-trips cleanly to disk with all
three task summaries intact.
* feat(curator): show rename map (where skills went) in user-visible summary
The full data has always been on disk in REPORT.md, but the user-visible
curator summary (gateway 💾 line, CLI session-start panel,
`hermes curator status`) was counts-only — "consolidated 4 into 2
umbrellas" with no names. Users only discovered renames when something
they expected was gone.
New `_build_rename_summary()` formats the rename map and appends it to
`final_summary`:
auto: 1 marked stale; llm: consolidated 2 into 1, pruned 1
archived 3 skill(s):
• docx-extraction → document-tools
• pdf-extraction → document-tools
• old-stale-thing — pruned (stale)
full report: hermes curator status
Empty on no-op ticks (no archives), so most ticks add zero log noise.
Cap of 10 entries keeps agent.log readable when a 50-skill
consolidation lands; the full list is always in REPORT.md.
`hermes curator status` indents continuation lines so the multi-line
summary reads as one logical field.
5 new tests in tests/agent/test_curator_classification.py covering
empty / consolidation / pruning / cap / mixed cases.
* feat(curator): show recent run summary once on `hermes update`
The rename map is now visible from where users actually look — the
update flow they explicitly run, instead of just the live gateway log
or transient CLI session-start panel.
Behavior:
- After `hermes update`, if the most recent curator run produced a
rename map (multi-line summary) that the user hasn't seen yet, print
it once with a 'last run Xh ago' header and a one-time-message
footer.
- Stamp `last_run_summary_shown_at = last_run_at` after printing so
subsequent `hermes update` invocations are silent until a newer
curator run lands.
- Silent on no-op runs (single-line summary like 'auto: no changes;
llm: no change'). Still stamps shown so we don't reconsider on
every update.
- Silent when the curator has never run (the existing first-run
notice handles that case).
Output:
ℹ Skill curator — last run 4h ago
auto: 1 marked stale; llm: consolidated 2 into 1, pruned 1
archived 3 skill(s):
• docx-extraction → document-tools
• pdf-extraction → document-tools
• old-stale-thing — pruned (stale)
full report: hermes curator status
(This message shows once per curator run. View anytime: hermes curator status)
State migration:
- `_default_state()` gains `last_run_summary_shown_at: None`. Existing
state files lack the field; `.get()` returns None; the comparison
treats any prior run as 'not yet shown' and prints once on next
update. Self-healing.
Wiring:
- Both `hermes update` paths in main.py call the new
`_print_curator_recent_run_notice()` right after the existing
first-run notice. Best-effort try/except so a state-load bug
never breaks the update flow.
6 tests in tests/hermes_cli/test_curator_recent_run_notice.py:
no-run / single-line / multi-line / show-once / new-run-resets /
time-formatter buckets.
