Conversation
Salvage follow-up integrating PR NousResearch#30481 (@simplast) and PR NousResearch#57683 (@catbearlove1-lang) into the unified export surface: - --format html: standalone self-contained HTML transcript (single session or multi-session with sidebar), works with all shared filters and --redact; requires a file output path. - --only user-prompts: prompt-only export (jsonl records or md sections) via the shared session_export renderer; the separate export-prompts subcommand from the original PR is subsumed by this flag. - AUTHOR_MAP entries for both contributors; docs EN + zh-Hans.
Opt-in discord.approval_mentions (config.yaml, bridged to DISCORD_APPROVAL_MENTIONS) prepends <@id> mentions for numeric allowlist entries to exec-approval prompts, with a scoped AllowedMentions override (users only). Default off - no surprise pings. Reapplied onto the content-mirror layout from NousResearch#60245: mentions prepend to the visible content block and its truncation budget. Original implementation from PR NousResearch#39719; commits arrived bot-authored, re-attributed to the contributor.
…leaked into salvage)
`_save_anthropic_oauth_creds` wrote the Anthropic OAuth token file with `os.replace(tmp, path)` followed by a post-hoc `chmod(0o600)`. Between the rename and the chmod the token file existed at the default umask (0o644 on most hosts) — a window in which another local user could read the access/refresh tokens. Write via `utils.atomic_json_write(..., mode=0o600)`, which creates the temp with mode 0o600 *before* any content is written, fsyncs, atomically replaces, preserves the existing file's owner, and cleans up its temp on failure. This matches the `atomic_json_write(mode=0o600)` call already used elsewhere in this module for the credential-pool write, and NousResearch#56644's owner preservation. Tests updated for the new mechanism, plus a check that the write goes through `atomic_json_write(mode=0o600)` (mutation-verified).
The salvaged SelfHostedBackend made self-hosted servers reachable via mem0.json / MEM0_HOST, but the setup wizard still offered only Platform and OSS — exactly the gap users hit (Discord report: 'At memory setup there's only 2 options'). Adds a third wizard mode: - interactive picker: Platform / Self-hosted server / Open Source - non-interactive: hermes memory setup mem0 --mode selfhosted --host http://... [--api-key ...] [--dry-run] - host -> mem0.json (behavioral), API key -> .env as MEM0_API_KEY (secret), optional key for AUTH_DISABLED servers - best-effort reachability check against the server, non-fatal - README + memory-providers docs updated with the wizard path
…t trace' (NousResearch#60507) * feat(trace): upload sessions to HF Agent Trace Viewer Salvage trace upload as a smaller CLI-first feature: deterministic Claude Code JSONL export, fail-closed redaction, lazy Hugging Face dependency, and no gateway slash-command wiring. * chore(trace): drop external porting references from docstrings Describe the trace-upload design in Hermes' own terms. * feat(sessions): fold trace upload into 'sessions export --format trace' Integrates the HF Agent Trace Viewer exporter (PR NousResearch#36145) onto the unified export surface instead of a separate 'hermes trace' subcommand: - --format trace: Claude Code JSONL to stdout/file, or one <id>.trace.jsonl per session for filtered bulk export; defaults to the most recent session when no --session-id/filters given. - --upload pushes to the user's private HF traces dataset (--public to opt out of private); reads HF_TOKEN with guided setup when missing. - traces are secret-redacted by default (force mode); --no-redact opts out after review; redaction failure blocks export (fail closed). - hermes_cli/trace.py + subcommands/trace.py removed; agent/trace_upload.py is the single engine. Docs EN + zh-Hans; 4 new CLI tests.
…+ non-desktop picker opt-ins Follow-up on the NousResearch#56966 salvage: - is_provider_explicitly_configured(): an env-seeded credential-pool entry only counts as explicit while its env var still resolves to a usable secret. A stale auth.json entry left behind after the user deletes the var no longer keeps the provider in the picker forever (NousResearch#55790). - TUI modelPicker + dashboard ModelPickerDialog/api.getModelOptions pass include_unconfigured=true explicitly, preserving their full-universe setup-affordance behavior now that the backend defaults to the configured subset. - desktop lib/model-options.ts routes explicit_only through the shared requestModelOptions() helper (added on main after the PR branched). - regression tests for ambient (gh_cli) pool sources, explicit manual/ device-code sources, and stale vs live env-seeded entries.
…ion gate _run_approval_gate's gateway branch only queued via submit_pending, so plugin-escalated approvals never sent the interactive embed+buttons on Discord/Telegram/Slack (NousResearch#59413) - the user was never notified and the action stayed silently blocked. Mirror check_dangerous_command's path: when a session notify callback is registered, run the blocking _await_gateway_decision round-trip (redacted payload, once/session/ always persistence, deny/timeout produce definitive BLOCKED outcomes); fall back to submit_pending only when no callback exists. Fixes NousResearch#59413.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Keep-alive path when ?attach=<token> is present: PTY outlives the socket via PTY_REGISTRY, reattaches on reconnect. No token = unchanged legacy pump (_legacy_pump). detach (not close) on disconnect. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
ChatPage sends ?attach=<localStorage token> so /chat reattaches to its live PTY across refresh. onclose: 4410=process-exit (session ended), 4409=superseded (quiet), else transient -> auto-reconnect. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
When an MCP stdio subprocess fails to connect (token expiry, port contention, timeout), the run() reconnect loop retries with backoff. Each retry calls _run_stdio() which spawns a new process pair, but the previous failed pair was only detected as orphaned (added to _orphan_stdio_pids) — never actually killed. This caused rapid zombie accumulation: 5 failed attempts × 2 procs each = 10 orphans competing for the same port. Add a _kill_orphaned_mcp_children() call at the top of _run_stdio(), before the _snapshot_child_pids() baseline, so any orphans from prior failed attempts are reaped before a new subprocess is spawned. Fixes NousResearch#57355
Merge the two cherry-picked reap call sites into one unscoped sweep at the top of _run_stdio (the unscoped sweep is a superset of the per-server one), and run it via asyncio.to_thread so the 2s SIGTERM->SIGKILL escalation cannot stall the shared MCP event loop.
A stdio MCP server that never completes `initialize` (e.g. emits a non-JSON-RPC frame and then blocks on stdin) leaks a child process plus its stdio pipes/pidfd on every discovery-retry cycle — unbounded, until the gateway hits EMFILE and every new open()/spawn fails (NousResearch#59349). Root cause (confirmed by instrumenting the live repro, and different from the issue's own hypothesis): the spawned child IS captured in `new_pids`, so the report's "new_pids empty at finally" guess is not it. The real cause is that `session.initialize()` hangs forever on the garbage stream. `connect_timeout` only bounds the caller's `.result()` wait on the foreground thread — it does NOT cancel the `_run_stdio` coroutine on the background MCP loop. So the coroutine is stuck at `await session.initialize()` permanently, its cleanup `finally` never runs, the child is never reaped, and it stays invisible to the orphan-reaper (whose `_orphan_stdio_pids` set never gets populated). Fix: wrap `session.initialize()` in `asyncio.wait_for(..., connect_timeout)` so a stalled handshake fails instead of hanging. The TimeoutError unwinds through the SDK context managers (closing the child's stdin -> EOF -> exit) and lets the existing `finally` reap any straggler. Cross-platform — no signals/pgid/proc. Scope: stdio only. The HTTP path has the same `await session.initialize()` shape but spawns no subprocess (so it can't cause this leak) and already has httpx transport timeouts. Verified: the reporter's repro goes from unbounded growth to draining to zero; added a hermetic regression test (fake transport whose `initialize()` hangs, asserts the connect is bounded by connect_timeout) that fails on the pre-fix code and passes on the fix; 566 existing MCP tests pass; ruff clean. Repro confirmed on macOS (pipe FDs); the Linux-specific pidfd growth in the report should be equivalent — the reporter offered to validate on Linux. Closes NousResearch#59349
… + cancel abandoned start() task Sibling sites of the same bug class as the salvaged stdio fix: - SSE, streamable-HTTP (new + deprecated API) initialize() calls are now bounded by the same connect_timeout, so an endpoint that accepts the connection but never answers the handshake cannot park the run() task forever. - start() now cancels its ensure_future'd run() task when the caller's connect timeout cancels start() itself — the orphaned-task leak was the root mechanism behind NousResearch#59349, and this closes the class for any future pre-ready hang.
…onnect The gateway reconnect watcher forwards is_reconnect=True to every adapter.connect() call on every retry. Adapters whose signature omits the kwarg raise TypeError at every reconnect attempt and stay silently disconnected — the exact bug that shipped for QQAdapter and only surfaced after messages stopped flowing on the QQ channel for hours. This test statically parses every adapter.py under gateway/platforms/ and plugins/platforms/ (via AST, so third-party SDKs like slack_sdk, matrix-nio, aiohttp, telegram, etc. are NOT required in the test env) and asserts every *Adapter class with an async connect() accepts is_reconnect — either as a keyword-only argument or absorbed by **kwargs. Also fixes plugins/platforms/wecom/callback_adapter.py:WecomCallbackAdapter, which the new test caught as a second offender. Same class of bug: bare 'async def connect(self)' signature would die on the first reconnect. Companion to NousResearch#59429 (which fixed the original QQAdapter offender).
Addresses Copilot review on NousResearch#61348: the HTML-escaped role, while safe from injection (quotes are escaped), still contains whitespace when a crafted role is supplied, which splits the class attribute into several unintended CSS classes. Keep the escaped role for the display badge, and reduce the raw role to a single safe CSS token (alnum/-/_) for the class name. Real roles (user/assistant/system/tool) are unchanged, so the existing .message-<role> rules still match.
_load_context_cache() returned None when context_length_cache.yaml
contained 'context_lengths:' (no value) — YAML parses this as
{'context_lengths': None} and dict.get(key, default) only returns
the default when the key is absent, not when the value is None.
This caused AttributeError in every downstream caller (issue NousResearch#47135).
Fix: use 'or {}' instead of default= so both absent key and
None value return an empty dict.
Fixes NousResearch#47135
…ousResearch#61797) skills: null crashed with AttributeError, and a bare scalar disabled: my-skill was split into a set of characters. Both now normalize the same way agent.skill_utils._normalize_string_set does: null -> empty set, scalar -> single-item set. Non-dict skills sections are ignored. Closes NousResearch#13026.
…ributeError
When stt.local, tts.edge, or other config subsections are explicitly set
to null in config.yaml (which happens by default on a fresh --voice
setup), stt_config.get('local', {}) returns None instead of {} because
YAML null preserves the key. The chained .get('model') then crashes
with 'NoneType' object has no attribute 'get'.
Apply the defensive (x or {}) pattern to every place a config subsection
is read via .get('xxx', {}). Covers local, edge, openai, mistral, and
elevenlabs subsections in both transcription_tools.py and tts_tool.py.
Closes NousResearch#47318
Sibling sites of the salvaged NousResearch#47334 fix: xai/openai/elevenlabs/gemini/ mistral/piper/neutts subsection reads in transcription_tools.py and tts_tool.py used .get(key, {}) which passes a present-but-null value through as None. All provider-subsection reads now use .get(key) or {}. Providers without a DEFAULT_CONFIG entry (e.g. stt.xai) were still receiving None even after the load_config() deep-merge fix, since the merge can only fill sections that have defaults.
…les) (NousResearch#61816) * test: deflake CI and dev-machine flaky tests in bulk Fixes ten distinct flake sources found by mining recent CI failures and running the full suite on a dev machine with real user state: CI-observed races: - tests/conftest.py live-system guard: allow signal 0 (pure liveness probe) through _guarded_kill/_guarded_killpg. psutil.pid_exists() probes a just-killed grandchild reparented to init; the subtree check fails for it and the guard RuntimeError'd test_entire_tree_is_sigkilled_not_just_parent intermittently on unrelated PRs. Hermeticity flakes (fail on dev machines with real state, pass on CI): - agent/coding_context.py: _marker_root() now skips the shared temp root (tempfile.gettempdir()) like it skips $HOME — a stray /tmp/package.json flipped every tmp_path test into the coding posture (9 failures in test_coding_context.py). - test_agent_guardrails.py: pin MAX_CONCURRENT_CHILDREN=3 via autouse monkeypatch instead of freezing the user's real config value at import time (import-time vs call-time config mismatch). - test_web_tools_config.py: TestCheckWebApiKey now neutralizes the ddgs package probe and registry providers — the optional ddgs package in a dev venv lit up the fallback backend. - test_credential_pool.py: block claude_code/hermes-oauth credential autodiscovery in the two pool-merge tests that assert exact id lists (a real ~/.claude/.credentials.json seeded an extra entry). - test_modal_sandbox_fixes.py: clear _permanent_approved / _session_approved — the user's real command_allowlist silently approved the guard-escalation commands under test. - test_setup_irc.py: stub prompt_checklist to select only the IRC row; the non-TTY cancel fallback re-ran the real configured platforms' interactive setup_fn, which hit input() under captured stdin. - test_doctor.py: TestGitHubTokenCheck now patches the module-level HERMES_HOME constant (the file's established pattern) instead of only setenv — doctor was running PRAGMA integrity_check against the real multi-GB state.db and blowing the 300s per-file budget. Latent atexit-duplication (same _enter_buffered_busy class as NousResearch#34217): - test_undo_command.py: drop importlib.reload(tui_gateway.server) in fixture teardown; reload re-registers the module's atexit hooks. - test_session_platform_resolution.py: drop per-test reload of tui_gateway.server; every resolver reads env at call time. * test: sentinel model value in ignore-user-config fallback assertion With HERMES_IGNORE_USER_CONFIG=1, load_cli_config() falls back to the repo-root cli-config.yaml (untracked, gitignored). On a dev machine that file can legitimately set the same popular model the test hardcoded (anthropic/claude-sonnet-4.6), flipping the != assertion locally while CI (no cli-config.yaml) stayed green. Use an impossible sentinel model name instead.
`_load_web_config()` is typed `-> dict` but returned `load_config().get("web",
{})`, which is `None` when the config has a present-but-null `web:` section
(YAML `web:` with no body). Every caller then does
`_load_web_config().get(...)` and raises `AttributeError: 'NoneType' object
has no attribute 'get'` — this hits `_get_backend`, `check_web_api_key`, and
the extract-char-limit reader.
Separately, `check_web_api_key()` read the backend as
`.get("backend", "").lower()`; a null `web.backend` value yields `None` (the
`""` default only applies when the key is absent), so `None.lower()` raised.
`check_web_api_key` is the `check_fn` gate for `web_search`/`web_extract`, so
this surfaced as an exception during tool-availability checking.
- Make `_load_web_config()` honor its `-> dict` contract (`... or {}`), fixing
the null-`web:`-section crash at every call site.
- Guard the backend value in `check_web_api_key` with `or ""`, mirroring the
existing guard in `_get_backend`.
Adds regression tests for both the null-backend-value and null-web-section
cases.
When config.yaml has known_plugin_toolsets set to null (or any value mapped to None by the YAML loader), config.get returns None (dict.get only falls back to the default when the key is absent, not when its value is None). The subsequent set(known_map.get(platform, [])) then crashes with TypeError: NoneType object is not iterable and the gateway fails to start, even though no plugin toolsets are configured. Add or-empty-dict and or-empty-list guards so a null/None value is treated as empty instead of crashing the platform-tools resolver.
Sibling of the salvaged NousResearch#53196 read-path fix: setdefault() does not replace a present-but-null key, so saving platform tools with known_plugin_toolsets: null in config.yaml crashed on indexing None.
…p @mention delivery Without this UA tag the Feishu server does not push group @mention events over the WebSocket transport. The "channel" tag tells the server to use the Channel protocol which enables group-message routing in addition to P2P direct messages. Root cause: FeishuWSClient was created without any UA signaling tag, so the server defaulted to the basic DM-only push mode. Group @mention events were silently dropped before reaching Hermes. Fixes NousResearch#50656 Also adds a regression test verifying the UA tag is present in the FeishuWSClient constructor call.
* fix(agent): reject malformed tool call arguments * test(agent): expect malformed tool arguments to fail closed
dict.get(key, default) returns None (not the default) when the key EXISTS with value None. The default only applies when the key is ABSENT. Chained method calls (.strip(), .upper(), .count()) crash with AttributeError on NoneType. Fix two confirmed hits: - auxiliary_client.py: custom provider base_url/api_key (config null) - anthropic_adapter.py: text block content (API null response) Pattern: .get(key, "").method() → (.get(key) or "").method()
Sibling sites of the salvaged NousResearch#55997 fix, all reading user-editable config values through .get(key, '').method(): MoA slot provider/model labels, gateway quick-command alias targets (2 sites), gateway.proxy_url, and gateway.relay_url. Regression tests for the contributor's two sites plus the MoA labels.
…nai/omniroute path (ref NousResearch#10575) [carried] (cherry picked from commit fd5ac147e13d804be824f493ff5c2f5845250ddd)
…ry path [carried] (cherry picked from commit 207c60782f5f8f8cc97dd930fbcde54ad98e07b3)
…ght/doctor) [carried] (cherry picked from commit 707470ba781371999ea549f78e482ee191124b8f) (cherry picked from commit 20a77addbdc2221283f1cf44195ff2351744152a)
hermes plugins update <name> rejected any plugin installed via the operator-created cross-profile symlink pattern (~/.hermes/profiles/<profile>/plugins/<name> -> ~/.hermes/plugins/<name>) with 'resolves outside the plugins directory', because _sanitize_plugin_name() always followed symlinks via Path.resolve() before checking containment. Add an allow_symlink parameter that, when set, returns the symlink path itself instead of resolving through it. Scoped narrowly to read/update call sites (cmd_update, dashboard_update_user_plugin); install/create and remove paths are unchanged and still reject an escaping symlink, since those are exactly the operations where following a symlink would be a genuine escape/ambiguity risk. [carried] (cherry picked from commit 03c3154030f7dbfefa72915fbada794ffaaf71f9)
A verify-on-stop / pre_verify nudge can 'continue' the agent loop after
a valid no-tool-call final_response was already produced. If that
continue lands exactly when the iteration budget is exhausted, the
while-loop's own condition (not an explicit break) ends the turn, so
_turn_exit_reason is left at its 'unknown' initializer even though
final_response holds a real, complete answer.
turn_finalizer.finalize_turn only marks completed=True when
turn_exit_reason starts with 'text_response(' (or the turn ended
under max_iterations), so this falloff produced completed=False with
valid content. cron/scheduler.py then wrapped that valid content in
raise RuntimeError(final_response_text), reporting successful cron
runs to Discord as failures.
Concrete instance: the Daily Quant Platform Dev Agent cron job
(e099c871a5bf) reported a 'provider authentication error' on
2026-07-10, but had actually completed a full work cycle (arb-platform
PR NousResearch#48, an unauthenticated-trading-control-API security fix) -- the
RuntimeError just wrapped the successful report text. Same pattern
confirmed in at least 3 other runs (2026-07-03, 07-06, 07-07) via
cron output history.
Fix: right before finalize_turn is called, if _turn_exit_reason is
still 'unknown' and the turn wasn't failed/interrupted and
final_response has real usable content (not the empty sentinel),
relabel the exit reason as a normal text_response completion so it is
delivered as a real response instead of raised as an exception. Real
failure paths (budget_exhausted-with-no-content, interrupted, error,
empty_response_exhausted) are untouched since they either set failed,
leave final_response empty, or already claim a specific
_turn_exit_reason before this point runs.
trevornk
pushed a commit
that referenced
this pull request
Aug 26, 2026
fal's post-trained H3 variant — #1-ranked quality/prompt adherence/ aesthetics, 5s 768p video in under 3 seconds, $0.04/s launch pricing. - New minimax-h3-max family: minimax/h3-max/{text,image}-to-video - Inherits base-H3 wire quirks (integer duration, i2v drops aspect_ratio) but caps at 768P (480P/768P enums, no 2K/4K) and declares seed on both endpoints - New generic static_payload family flag: constant keys the endpoint requires on every request (H3 Max lists prompt_expansion_mode in its required array; sent as 'balanced') Payload asserted against the endpoint OpenAPI schema; 73/73 targeted tests green (surface matrix auto-covers the new family).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Bug (kanban t_da02e022)
The Daily Quant Platform Dev Agent cron job (
e099c871a5bf) reported a"provider authentication error" in #alerts-oracle on 2026-07-10, but the
job had actually completed a full, valuable work cycle (arb-platform PR NousResearch#48
— a critical security fix for an unauthenticated public trading-control API).
The RuntimeError was just wrapping the successful report text.
Confirmed the same false-failure pattern in at least 3 other historical runs
(2026-07-03, 2026-07-06, 2026-07-07) via
cron/output/e099c871a5bf/*.md—scope is real, not a one-off.
Root cause
verify-on-stop/pre_verifynudge cancontinuethe agent loopafter a valid no-tool-call
final_responsehas already been produced.continuelands exactly when the iteration budget is exhausted,the
whileloop's own condition (not an explicit in-bodybreak) endsthe turn — so
_turn_exit_reasonnever advances off its"unknown"initializer, even though
final_responseholds a real, complete answer.turn_finalizer.finalize_turnonly setscompleted=Truewhenturn_exit_reasonstarts with"text_response("(or exit happened undermax_iterations) — so this falloff producedcompleted=Falsewith validcontent.
cron/scheduler.pythen doesraise RuntimeError(final_response_text)for any
completed=Falseresult, so the real report gets delivered toDiscord dressed up as a failure.
Fix
Right before
finalize_turnis invoked inconversation_loop.py: if_turn_exit_reasonis still"unknown", the turn wasn'tfailed/interrupted, andfinal_responsehas real content (not the"(empty)"sentinel), relabel the exit reason as a normal
text_response(...)completion. Genuine failure paths (
budget_exhaustedwith no content,interrupted, APIerror,empty_response_exhausted) are untouched — theyeither set
failed=True, leavefinal_responseempty, or already claim aspecific
_turn_exit_reasonbefore this point runs.Verification
python3 -c "import ast; ast.parse(open('agent/conversation_loop.py').read())"— syntax OK_turn_exit_reasonto confirm thisfallback only fires on the previously-unhandled silent-falloff case, not on
any already-classified path.
Not touched
Does not change GitHub Actions billing block on trading-platform CI
(separate, tracked, expected to clear on its own).