e00297782d02a5b60aead2df1c94c6186315bf46
827
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
e5dad4ac57 |
fix(agent): propagate ContextVars to concurrent tool worker threads (#18123)
Propagates ContextVars (notably `tools.approval._approval_session_key`) into concurrent tool worker threads via `copy_context().run` — mirrors `asyncio.to_thread` semantics. Fixes approval-card cross-session misrouting in concurrent gateway traffic. Repro'd on Slack: session A's dangerous-command approval was delivered to channel B (@syahidfrd). Salvages #16660 — core 4-LOC fix preserved, unrelated `tests/eval_018/` scope contamination dropped. Adds 5 regression guards including an AST-level source check on the real call site. Closes #16660. Co-authored-by: firefly <promptsiren@gmail.com> Co-authored-by: banditburai <banditburai@users.noreply.github.com> |
||
|
Teknium
|
80a676658c |
fix(cli): surface self-improvement review summaries from bg thread
When the self-improvement background review fires after a turn, it runs in a bg thread and emits a ' 💾 <summary>' line to announce what it saved to memory or skills. Two problems made this invisible to users even when the review successfully modified a skill: 1. The print went through `_cprint` (prompt_toolkit's print_formatted_text) on a bg thread while the CLI's PromptSession was live. Direct print_formatted_text races with the input-area redraw and the line can land behind/above the prompt, scrolled off without the user seeing it. 2. The message said only '💾 Skill created.' / '💾 Memory updated' with no indication that the self-improvement loop was the one doing this. Users who did catch the line couldn't tell the background review from some other agent action. Fixes: - `_cprint` now detects when it's called from a non-app thread with a running prompt_toolkit Application, and routes through `run_in_terminal` via `loop.call_soon_threadsafe`. That pauses the input, prints the line above the prompt, and redraws — the normal prompt_toolkit contract for bg-thread output. Direct-print fallback preserved for the no-app / same-thread / import-error paths. Affects every bg-thread emission, not just the review summary (curator summaries and auxiliary failure prints benefit too). - The summary now reads ' 💾 Self-improvement review: <summary>' in both the CLI and the gateway `background_review_callback` path, so the origin is unambiguous. Tests: - New `tests/cli/test_cprint_bg_thread.py` covers all five routing branches (no app, app-not-running, cross-thread schedule, same-thread direct, app-loop-attribute-error, import-error). - New case in `tests/run_agent/test_background_review.py` asserts the attributed prefix shows up in both `_safe_print` and `background_review_callback`. Live E2E: exercised _cprint from a bg thread inside a real Application event loop; confirmed get_app_or_none() sees the app, call_soon_threadsafe schedules run_in_terminal, and the inner _pt_print runs. |
||
|
Tekniumandemozilla
|
c868425467 |
feat(kanban): durable multi-profile collaboration board (#17805)
Salvage of PR #16100 onto current main (after emozilla's #17514 fix that unblocks plugin Pydantic body validation). History preserved on the standing `feat/kanban-standing` branch; this squashes the 22 iterative commits into one clean landing. What this lands: - SQLite kernel (hermes_cli/kanban_db.py) — durable task board with tasks, task_links, task_runs, task_comments, task_events, kanban_notify_subs tables. WAL mode, atomic claim via CAS, tenant-namespaced, skills JSON array per task, max-runtime timeouts, worker heartbeats, idempotency keys, circuit breaker on repeated spawn failures, crash detection via /proc/<pid>/status, run history preserved across attempts. - Dispatcher — runs inside the gateway by default (`kanban.dispatch_in_gateway: true`). Ticks every 60s, reclaims stale claims, promotes ready tasks, spawns `hermes -p <assignee> chat -q "work kanban task <id>"` with HERMES_KANBAN_TASK + HERMES_KANBAN_WORKSPACE env. Auto-loads `--skills kanban-worker` plus any per-task skills. Health telemetry warns on stuck ready queue. - Structured tool surface (tools/kanban_tools.py) — 7 tools (kanban_show, kanban_complete, kanban_block, kanban_heartbeat, kanban_comment, kanban_create, kanban_link). Gated on HERMES_KANBAN_TASK via check_fn so zero schema footprint in normal sessions. - System-prompt guidance (agent/prompt_builder.py KANBAN_GUIDANCE) injected only when kanban tools are active. - Dashboard plugin (plugins/kanban/dashboard/) — Linear-style board UI: triage/todo/ready/running/blocked/done columns, drag-drop, inline create, task drawer with markdown, comments, run history, dependency editor, bulk ops, lanes-by-profile grouping, WS-driven live refresh. Matches active dashboard theme via CSS variables. - CLI — `hermes kanban init|create|list|show|assign|link|unlink| claim|comment|complete|block|unblock|archive|tail|dispatch|context| init|gc|watch|stats|notify|log|heartbeat|runs|assignees` + `/kanban` slash in-session. - Worker + orchestrator skills (skills/devops/kanban-worker + kanban-orchestrator) — pattern library for good summary/metadata shapes, retry diagnostics, block-reason examples, fan-out patterns. - Per-task force-loaded skills — `--skill <name>` (repeatable), stored as JSON, threaded through to dispatcher argv as one `--skills X` pair per skill alongside the built-in kanban-worker. Dashboard + CLI + tool parity. - Deprecation of standalone `hermes kanban daemon` — stub exits 2 with migration guidance; `--force` escape hatch for headless hosts. - Docs (website/docs/user-guide/features/kanban.md + kanban-tutorial.md) with 11 dashboard screenshots walking through four user stories (Solo Dev, Fleet Farming, Role Pipeline, Circuit Breaker). - Tests (251 passing): kernel schema + migration + CAS atomicity, dispatcher logic, circuit breaker, crash detection, max-runtime timeouts, claim lifecycle, tenant isolation, idempotency keys, per- task skills round-trip + validation + dispatcher argv, tool surface (7 tools × round-trip + error paths), dashboard REST (CRUD + bulk + links + warnings), gateway-embedded dispatcher (config gate, env override, graceful shutdown), CLI deprecation stub, migration from legacy schemas. Gateway integration: - GatewayRunner._kanban_dispatcher_watcher — new asyncio background task, symmetric with _kanban_notifier_watcher. Runs dispatch_once via asyncio.to_thread so SQLite WAL never blocks the loop. Sleeps in 1s slices for snappy shutdown. Respects HERMES_KANBAN_DISPATCH_IN_GATEWAY=0 env override for debugging. - Config: new `kanban` section in DEFAULT_CONFIG with `dispatch_in_gateway: true` (default) + `dispatch_interval_seconds: 60`. Additive — no \_config_version bump needed. Forward-compat: - workflow_template_id / current_step_key columns on tasks (v1 writes NULL; v2 will use them for routing). - task_runs holds claim machinery (claim_lock, claim_expires, worker_pid, last_heartbeat_at) so multi-attempt history is first- class from day one. Closes #16102. Co-authored-by: emozilla <emozilla@nousresearch.com> |
||
|
Tekniumandseason179
|
76edc40ab0 |
fix(agent): extend thinking-mode reasoning_content pad to Kimi/Moonshot
Builds on #16855 (@lsdsjy) which fixed DeepSeek v4 reasoning_content replay via model_extra fallback + capturing tool_calls at method entry. Kimi / Moonshot thinking mode enforces the same echo-back contract and hits the same 400 when a tool-call turn is persisted without reasoning_content. - _build_assistant_message: pad branch now uses _needs_thinking_reasoning_pad() (DeepSeek OR Kimi) instead of _needs_deepseek_tool_reasoning() alone. - Extract _needs_thinking_reasoning_pad() and reuse it in _copy_reasoning_content_for_api so both sites share one predicate. - tests/run_agent/test_deepseek_reasoning_content_echo.py: add TestBuildAssistantMessagePadsStrictProviders parametrized over DeepSeek (attr=None, attr-absent), Kimi (attr=None), Moonshot (via base_url), and an OpenRouter negative control that must NOT pad. Proven to fail 2/5 cases on Kimi/Moonshot without this change. - scripts/release.py: add AUTHOR_MAP entries for lsdsjy and season179. Refs #17400. Co-authored-by: season179 <season.saw@gmail.com> |
||
|
lsdsjy
|
b9b9ee3e6c | fix(deepseek): preserve v4 reasoning_content on replay | ||
|
Teknium
|
e8e5985ce6 |
fix(curator): seed defaults on update, create logs/curator dir, defer fire import (#17927)
Three fixes bundled for curator reliability on existing installs and broken/partial installs: 1. run_agent.py: defer `import fire` into the __main__ block. `fire` is only used by `fire.Fire(main)` when running run_agent.py directly as a CLI — it is NOT needed for library usage. Importing it at module top made `from run_agent import AIAgent` from a daemon thread (e.g. the curator's forked review agent) crash with ModuleNotFoundError on broken/partial installs where `fire` isn't present. 2. hermes_cli/config.py: add version 22 → 23 migration that writes the `curator` + `auxiliary.curator` sections to config.yaml with their defaults, only filling keys the user hasn't overridden. Existing configs from before PR #16049 / the April 2026 `auxiliary.curator` unification had neither section on disk, so users couldn't see or edit the settings in their config.yaml (runtime deep-merge papered over it at read time, but the file never reflected reality). 3. hermes_cli/config.py: `ensure_hermes_home()` now pre-creates `~/.hermes/logs/curator/` alongside cron/sessions/logs/memories on every CLI launch. Managed-mode (NixOS) variant mkdir's it defensively after the activation-script existence checks, since the activation script may not know about this subpath. 4. agent/curator.py: `_reports_root()` mkdir's the dir at call time as belt-and-suspenders for entry paths that bypass both ensure_hermes_home() and the v23 migration (gateway-only installs, bare library use). E2E validated in isolated HERMES_HOME: fresh install gets full defaults seeded; partial-override config keeps user's `enabled: false` and custom `interval_hours` while filling the missing keys; re-running the migration is a no-op. |
||
|
Sanjays2402
|
e0fa2cf972 |
fix(tools): isolate get_tool_definitions quiet_mode cache + dedup LCM injection (#17335)
Long-lived Gateway processes were sending duplicate tool names to providers that enforce uniqueness: - DeepSeek: 'Tool names must be unique.' - Xiaomi MiMo: 'tools contains duplicate names: lcm_expand' - Moonshot/Kimi: 'function name lcm_grep is duplicated' TUI was unaffected because TUI runs with quiet_mode=False and skips the cache entirely. Root cause (two layered bugs) - model_tools.get_tool_definitions(quiet_mode=True) memoizes its result in _tool_defs_cache. The cache-hit path returned list(cached) (safe), but the FIRST uncached call stored and returned the SAME object. run_agent.py mutates self.tools (memory + LCM context-engine schemas) in-place, so the very first agent init in a Gateway process poisoned the cache, and every subsequent init appended LCM schemas again on top of the already-polluted list. - run_agent.py's context-engine injection (lcm_grep / lcm_describe / lcm_expand) had no dedup, unlike the memory-tools injection right above it which already skips already-present names. Fix (defense in depth, per the issue's suggested fix) - model_tools.get_tool_definitions: on the uncached branch, cache the computed list but return list(result) to the caller. Same pattern as the cache-hit path. - run_agent.py: build _existing_tool_names from self.tools and skip schemas whose names are already present, mirroring the memory-tools block. This also defends against plugin paths that may register the same schemas via ctx.register_tool(). Tests (tests/test_get_tool_definitions_cache_isolation.py) - test_first_uncached_call_returns_fresh_list \u2014 pins the fix; without it, first-call alias caused all the symptoms. - test_cache_hit_returns_fresh_list \u2014 pre-existing behavior stays. - test_caller_mutation_does_not_poison_cache \u2014 simulates run_agent appending lcm_grep / lcm_expand to the returned list and asserts the next call doesn't see them. - test_repeated_caller_mutation_does_not_accumulate \u2014 reproduces the long-lived Gateway accumulation pattern across 5 agent inits. - test_non_quiet_mode_does_not_use_cache \u2014 sanity, explains why TUI was fine. 5/5 pass on the new file; 23/23 still pass on tests/test_model_tools.py. |
||
|
Rob Moen
|
0dd373ec43 |
fix(context): honor model.context_length for Ollama num_ctx and all display paths
When a user sets model.context_length in config.yaml, the value was only used for Hermes' internal compression decisions (context_compressor) but NOT for Ollama's num_ctx parameter. Ollama auto-detects context from GGUF metadata (often 256K+) and allocates that much VRAM regardless of the user's config — causing OOM on smaller GPUs like the P100 (16GB). Root cause: two separate context values existed independently: - context_compressor.context_length = config value (e.g. 65536) ✓ - _ollama_num_ctx = GGUF metadata value (e.g. 256000) ✗ ignored config Changes: 1. Cap Ollama num_ctx to config context_length (run_agent.py) When model.context_length is explicitly set and no explicit ollama_num_ctx override exists, cap the auto-detected GGUF value to the user's context_length. This is the core fix — it prevents Ollama from allocating more VRAM than the user budgeted. 2. Pass config_context_length through all secondary call sites Several paths called get_model_context_length() without the config override, falling through to the 256K default fallback: - cli.py: @-reference expansion and /model switch display - gateway/run.py: @-reference expansion and /model switch display - tui_gateway/server.py: @-reference expansion - hermes_cli/model_switch.py: resolve_display_context_length() 3. Normalize root-level context_length in config (hermes_cli/config.py) _normalize_root_model_keys() now migrates root-level context_length into the model section, matching existing behavior for provider and base_url. Users who wrote `context_length: 65536` at the YAML root instead of under `model:` had it silently ignored. 4. Fix misleading comments (agent/model_metadata.py) DEFAULT_FALLBACK_CONTEXT is 256K (CONTEXT_PROBE_TIERS[0]), not 128K as two comments stated. Tests: 3 new tests for root-level context_length normalization. All existing context_length tests pass (96 tests). |
||
|
Stephen Schoettler
|
f73364b1c4 |
fix(ci): stabilize main test suite regressions (#17660)
* fix: stabilize main test suite regressions * test(agent): update MiniMax normalization expectation * test: stabilize remaining CI assertions * test: harden config helper monkeypatching * test: harden CI-only assertions * fix(agent): propagate fast streaming interrupts |
||
|
Teknium
|
828d3a320b |
fix(anthropic): reactive recovery for OAuth 1M-context beta rejection (#17752)
Keep context-1m-2025-08-07 in OAuth requests by default so 1M-capable subscriptions retain full context. When Anthropic rejects a request with 400 'long context beta is not yet available for this subscription', disable the beta for the rest of the session, rebuild the client, and retry once. Addresses #17680 (thanks @JayGwod for the clean reproduction) without forcing every OAuth user off the 1M context window. Changes: - agent/error_classifier.py: new FailoverReason.oauth_long_context_beta_forbidden; pattern matches 400 + 'long context beta' + 'not yet available'. Narrow enough that the existing 429 tier-gate pattern keeps its own reason. - agent/anthropic_adapter.py: _common_betas_for_base_url, build_anthropic_client, build_anthropic_kwargs gain drop_context_1m_beta kwarg. Default=False (1M stays). OAuth OAUTH_ONLY_BETAS unchanged. - agent/transports/anthropic.py: build_kwargs forwards the flag. - run_agent.py: self._oauth_1m_beta_disabled flag, retry-once guard, recovery branch next to the image-shrink path. _rebuild_anthropic_client honors the flag. The main build_kwargs call site threads it through for fast-mode extra_headers. - hermes_cli/doctor.py, hermes_cli/models.py: sibling OAuth /v1/models probes get the same reactive retry — previously they'd falsely report the Anthropic API as unreachable for affected subscriptions. Tests: 2190 tests/agent/ + 94 adjacent integration tests pass. New unit tests cover the classifier pattern (including the collision guard against the 429 tier-gate) and the drop_context_1m_beta adapter behavior (default keeps 1M, flag strips only 1M while preserving every other beta). |
||
|
Teknium
|
71c8ca17dc |
chore(salvage): strip duplicated/merge-corrupted blocks from PR #17664
Removes drive-by duplication that accumulated during the contributor branch's multiple rebases. All runtime-benign (dict last-wins, redefinition last-wins) but left dead source that would confuse reviewers and maintainers. Surgical in-place de-duplication (kept PR's intentional additions, removed only the doubled copy): * hermes_cli/auth.py: duplicate "gmi" + "azure-foundry" ProviderConfig * hermes_cli/models.py: duplicate "gmi" entry in _PROVIDER_MODELS * hermes_cli/config.py: duplicate NOTION/LINEAR/AIRTABLE/TENOR skill env block + duplicate get_custom_provider_context_length definition * hermes_cli/gateway.py: duplicate _setup_yuanbao * gateway/platforms/base.py: duplicate is_host_excluded_by_no_proxy * gateway/platforms/telegram.py: duplicate delete_message * gateway/stream_consumer.py: duplicate _should_send_fresh_final and _try_fresh_final * gateway/run.py: duplicate _parse_reasoning_command_args / _resolve_session_reasoning_config / _set_session_reasoning_override, duplicate "Drain silently when interrupted" interrupt check * run_agent.py: duplicate HERMES_AGENT_HELP_GUIDANCE append, duplicate codex_message_items capture, duplicate custom_providers resolution * tools/approval.py: duplicate HARDLINE_PATTERNS section and duplicate hardline call in check_dangerous_command * tools/mcp_tool.py: duplicate _orphan_stdio_pids module-level decl * cron/scheduler.py: duplicate "not configured/enabled" check — kept the new early-rejection, removed the stale late-path copy Full-file resets to origin/main (all PR additions were duplicates of content already on main): * ui-tui/packages/hermes-ink/index.d.ts * ui-tui/packages/hermes-ink/src/entry-exports.ts * ui-tui/packages/hermes-ink/src/ink/selection.ts * ui-tui/src/app/interfaces.ts * ui-tui/src/app/slash/commands/core.ts * ui-tui/src/components/thinking.tsx * ui-tui/src/lib/memoryMonitor.ts * ui-tui/src/types.ts * ui-tui/src/types/hermes-ink.d.ts * tests/hermes_cli/test_doctor.py * tests/hermes_cli/test_api_key_providers.py * tests/hermes_cli/test_model_validation.py * tests/plugins/memory/test_hindsight_provider.py * tests/run_agent/test_run_agent.py * tests/gateway/test_email.py * tests/tools/test_dockerfile_pid1_reaping.py * hermes_cli/commands.py (slack_native_slashes block — full duplicate) |
||
|
Ari Lotter
|
868bc1c242 |
feat(irc): add interactive setup
feat(gateway): refine Platform._missing_ and platform-connected dispatch Restricts plugin-name acceptance to bundled plugin scan + registry (no arbitrary string -> enum-pollution), pulls per-platform connectivity checks into a _PLATFORM_CONNECTED_CHECKERS lambda map with a clean _is_platform_connected method, and adds tests covering the checker map, plugin platform interface, and IRC setup wizard. |
||
|
Teknium
|
e464cde58f |
feat: final platform plugin parity — webhook delivery, platform hints, docs
Closes remaining functional gaps and adds documentation.
webhook.py: Cross-platform delivery now checks the plugin registry
for unknown platform names instead of hardcoding 15 names in a tuple.
Plugin platforms can receive webhook-routed deliveries.
prompt_builder: Platform hints (system prompt LLM guidance) now fall
back to the plugin registry's platform_hint field. Plugin platforms
can tell the LLM 'you're on IRC, no markdown.'
PlatformEntry: Added platform_hint field for LLM guidance injection.
IRC adapter: Added acquire_scoped_lock/release_scoped_lock in
connect/disconnect to prevent two profiles from using the same IRC
identity. Added platform_hint for IRC-specific LLM guidance.
Removed dead token-empty-warning extension for plugin platforms
(plugin adapters handle their own env vars via check_fn).
website/docs/developer-guide/adding-platform-adapters.md:
- Added 'Plugin Path (Recommended)' section with full code examples,
PLUGIN.yaml template, config.yaml examples, and a table showing all
18 integration points the plugin system handles automatically
- Renamed built-in checklist to clarify it's for core contributors
gateway/platforms/ADDING_A_PLATFORM.md:
- Added Plugin Path section pointing to the reference implementation
and full docs guide
- Clarified built-in path is for core contributors only
|
||
|
Vlad RaandClaude Sonnet 4.6
|
a7fb79efb2 |
fix(agent): spawn OpenRouter pre-warm thread only once per process
Each AIAgent.__init__() was unconditionally starting a daemon thread to pre-warm the OpenRouter model metadata cache. In gateway mode a new AIAgent is created for every incoming message, so one OS thread leaked per request. After ~1 000 messages the process hit the Linux thread limit and raised RuntimeError: can't start new thread for all subsequent requests. Add a module-level threading.Event (_openrouter_prewarm_done) that is set before the thread is started. Subsequent AIAgent instantiations skip the spawn entirely; fetch_model_metadata() is cached for 1 hour so the single background call is sufficient. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
Nanako0129
|
2e991770fc | fix(gemini): pass base_url into chat transport | ||
|
刘昊
|
60c6b07128 | fix(cron): keep SOUL.md identity when workdir is unset | ||
|
Teknium
|
13683c0842 |
feat(memory): notify providers on mid-process session_id rotation (#17409)
Fixes #6672 Memory providers now receive on_session_switch() whenever AIAgent.session_id rotates mid-process — /resume, /branch, /reset, /new, and context compression. Before this, providers that cached per-session state in initialize() (Hindsight's _session_id, _document_id, accumulated _session_turns, _turn_counter) kept writing into the old session's record after the agent had moved on. MemoryProvider ABC ------------------ - New optional hook on_session_switch(new_session_id, *, parent_session_id='', reset=False, **kwargs) with no-op default for backward compat. reset=True signals /reset or /new — providers should flush accumulated per-session buffers. reset=False for /resume, /branch, compression where the logical conversation continues. MemoryManager ------------- - on_session_switch() fans the hook out to every registered provider. Isolated try/except per provider — one bad provider can't block others. - Empty/None new_session_id is a no-op to avoid corrupting provider state during shutdown paths. run_agent.py ------------ - _sync_external_memory_for_turn now passes session_id=self.session_id into sync_all() and queue_prefetch_all(). Providers with defensive session_id updates in sync_turn (Hindsight already had this at plugins/memory/hindsight/__init__.py:1199) now actually receive the current id. - Compression block at ~L8884 already notified the context engine of the rollover; now also calls _memory_manager.on_session_switch(reason='compression'). cli.py ------ - new_session() fires reset=True, reason='new_session' so providers flush buffers. - _handle_resume_command fires reset=False, reason='resume' with the previous session as parent_session_id. - _handle_branch_command fires reset=False, reason='branch' with the parent session_id already captured for the DB parent link. gateway/run.py -------------- - _handle_resume_command now evicts the cached AIAgent, mirroring /branch and /reset. The next message rebuilds a fresh agent whose memory provider initialize() runs with the correct session_id — matches the pattern the gateway already uses for provider state cross-session transitions. Hindsight reference implementation ---------------------------------- - plugins/memory/hindsight/__init__.py adds on_session_switch that: updates _session_id, mints a fresh _document_id (prevents vectorize-io/hindsight#1303 overwrite), and clears _session_turns / _turn_counter / _turn_index so in-flight batches don't flush under the new document id. parent_session_id only overwritten when provided (avoids clobbering on a bare switch). Tests ----- - tests/agent/test_memory_session_switch.py: new dedicated file. ABC default no-op, manager fan-out, failure isolation, empty-id no-op, session_id propagation through sync_all/queue_prefetch_all, Hindsight state transitions for every reset/non-reset case, parent preservation. - tests/cli/test_branch_command.py: new test verifying /branch fires the hook with correct parent_session_id + reset=False + reason. - tests/gateway/test_resume_command.py: new test verifying /resume evicts the cached agent. - tests/run_agent/test_memory_sync_interrupted.py: updated existing assertions to account for the session_id kwarg on sync_all and queue_prefetch_all. E2E verified (real imports, tmp HERMES_HOME): - /resume: session_id updates, doc_id fresh, buffers cleared, parent set - /branch: session_id forks, parent links to original - /new: reset=True clears accumulated state - compression: reason='compression' propagated, lineage preserved - Empty id: no-op, state preserved - Legacy provider without on_session_switch: no crash Reported by @nicoloboschi (Hindsight maintainer); related scope-widening comment by @kidonng extending coverage to compression. |
||
|
Teknium
|
df0e97a168 |
fix(minimax): enable Anthropic prompt caching for MiniMax's own models (#17425)
MiniMax's /anthropic endpoint documents cache_control support (0.1x read pricing, 5-min TTL) for MiniMax-M2.7, M2.5, M2.1, M2. PR #12846 gated third-party Anthropic-wire caching on 'claude' in model name, which left MiniMax's own model family re-paying full input tokens every turn. Opt in explicitly via provider id (minimax / minimax-cn) or host match (api.minimax.io / api.minimaxi.com). Narrow allowlist mirroring the existing Qwen/Alibaba branch below; leaves room for a capability-based surface (ProviderConfig.supports_anthropic_cache) if a third provider needs it. Closes #17332 |
||
|
Teknium
|
059980727a |
refactor(config): migrate remaining 33 cfg_get call sites (#17311)
Completes the cfg_get migration started in PR #17304. Covers the remaining hermes_cli/ and plugins/ config-access sites that the first PR intentionally left opportunistic. Migrated (33 sites across 14 files): hermes_cli/setup.py 13 sites (terminal.*, agent.*, display.*, compression.*, tts.*) hermes_cli/tools_config.py 7 sites (tts.*, browser.*, web.*, platform_toolsets.*) hermes_cli/plugins_cmd.py 3 sites (plugins.*, memory.*, context.*) plugins/memory/honcho/cli.py 3 sites (hosts.*) hermes_cli/web_server.py 1 site (dashboard.*) hermes_cli/skills_config.py 1 site (platform_disabled) hermes_cli/plugins.py 1 site (plugins.disabled) hermes_cli/status.py 1 site (terminal.backend) hermes_cli/mcp_config.py 1 site (mcp_servers.*) hermes_cli/webhook.py 1 site (platforms.webhook) plugins/memory/__init__.py 1 site (memory.provider) plugins/memory/hindsight/ 1 site (banks.hermes) plugins/memory/holographic/ 1 site (plugins.hermes-memory-store) run_agent.py 1 site (auxiliary.compression) The helper supports non-literal keys too, so e.g. cfg.get('hosts', {}).get(HOST, {}) becomes cfg_get(cfg, 'hosts', HOST, default={}) Migration bugs caught and fixed during this PR: 1. An AST-based batch rewrite naïvely captured the first word token in a chain, which corrupted 'self._config.get(...).get(...)' into 'self.cfg_get(_config, ...)' (dropping 'self.', creating a broken method call). Plugins/memory/hindsight caught it via its test suite. Fixed manually to 'cfg_get(self._config, ...)'. 2. Import-extension heuristic rewrote multi-line parenthesized imports ('from X import (\n A,\n B,\n)') as 'from X import cfg_get, (' — syntactically broken. Fixed by inserting cfg_get as the first name inside the parentheses. Combined with PR #17304, the cfg_get migration now covers: PR #17304 (first batch): 20 sites in tools/ + gateway/ PR #17317 (this one): 33 sites in hermes_cli/ + plugins/ + run_agent.py Total: 53 sites migrated. Remaining ~8 sites are either: - Function-call chains (e.g. '_load_stt_config().get(...).get(...)') that would need double-evaluation or a local binding to migrate cleanly — intentionally deferred. - JSON response-navigation (e.g. 'response_data.get('data',{}).get('web')) which is unrelated to config access and shouldn't use cfg_get. Verified: - 412/412 tests/plugins/ pass (including the hindsight test that caught the self.X regex bug before commit) - 3181/3189 tests/hermes_cli/ pass (8 pre-existing failures on main, verified by git-stash comparison) - Live 'hermes status' and 'hermes config' render correctly (exercise the migrated terminal.backend, tts.provider, browser.cloud_provider, compression.threshold, display.tool_progress sites) - Live 'hermes chat': 1 turn + /quit, zero errors in 11-line log window No semantic changes — cfg_get was already proven to be a 1:1 match for the original .get("X",{}).get("Y",default) pattern in PR #17304. |
||
|
Teknium
|
21676e80cc |
Revert "fix(anthropic): remove Claude Code fingerprinting from OAuth Messages API path (#16957)" (#17397)
This reverts commit
|
||
|
Tekniumandteknium1
|
1d4218be56 |
feat(review): active-update bias, loaded-skill-first, support-file variants (#17213)
The background skill-review prompts (_SKILL_REVIEW_PROMPT and the **Skills**
half of _COMBINED_REVIEW_PROMPT) steered the reviewer toward passive
behavior — most passes concluded 'Nothing to save.' even when the session
produced real lessons. User-preference corrections (style, format,
legibility, verbosity) were especially lost: they were read as memory
signals only, so skills never carried the fix.
This rewrite changes the stance:
- **Active-update bias.** The reviewer now treats inaction as a missed
learning opportunity. 'Nothing to save.' remains an explicit escape
but is no longer framed as the most-common outcome.
- **User-preference corrections are first-class skill signals.** Style,
tone, format, legibility, verbosity complaints — and the actual
phrasings users use ('stop doing X', 'this is too verbose', 'I hate
when you Y', 'remember this') — now warrant patching the skill that
governs the task, not just writing to memory.
- **Loaded-skill-first preference order.** When a skill was loaded via
/skill-name or skill_view during the session, the reviewer patches
THAT one first. It was in play; it's the right place.
- **Four-step ladder: patch-loaded → patch-umbrella → support-file →
create.** Support files are explicitly enumerated as three kinds:
* references/<topic>.md — session-specific detail OR condensed
knowledge banks (quoted research, API docs excerpts, domain notes)
* templates/<name>.<ext> — starter files to copy and modify
* scripts/<name>.<ext> — statically re-runnable actions
- **Name-veto for CREATE.** New skill names MUST be class-level — no PR
numbers, error strings, codenames, library-alone names, or session
artifacts ('fix-X / debug-Y / audit-Z-today'). If the proposed name
only fits today's task, fall back to one of the patch/support-file
options.
- **Memory scope clarified.** 'who the user is and what the current
situation and state of your operations are' — MEMORY.md is
situational/state, USER.md is identity/preferences.
- **Curator handoff.** Reviewer flags overlap; the background curator
handles consolidation at scale. Single-session reviewer doesn't
attempt umbrella-rebalancing.
Tests: tests/run_agent/test_review_prompt_class_first.py upgraded to
assert the new behavioral contracts (active bias, user-correction
signals, loaded-skill-first, support-file kinds, name-veto, memory
framing, curator handoff). 17 tests, all pass.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
|
||
|
kshitijk4poor
|
5d2f9b5d7d |
fix: follow-up for salvaged PR #17061
- Remove dead _lmstudio_loaded_context attribute from run_agent.py (set but never read — the loaded context is pushed to context_compressor.update_model which is the actual consumer) - Cache empty reasoning options with 60s TTL to avoid per-turn HTTP probe for non-reasoning LM Studio models. Non-empty results cached permanently. - Extract _lmstudio_server_root(), _lmstudio_request_headers(), and _lmstudio_fetch_raw_models() shared helpers in models.py — eliminates URL-strip + auth-header + HTTP-call duplication across probe_lmstudio_models, ensure_lmstudio_model_loaded, and lmstudio_model_reasoning_options - Revert runtime_provider.py base_url precedence change: preserve the established contract (saved config.base_url > env var > default) for all api_key providers - Remove unnecessary config version bump 22→23 - Fix TUI test: relax target_model assertion to avoid module-cache flake - AUTHOR_MAP: added rugved@lmstudio.ai → rugvedS07 |
||
|
Rugved Somwanshi
|
01ad0aacaf | fix(tui): show correct context length | ||
|
Rugved Somwanshi
|
214ca943ac | feat(agent): add lmstudio integration | ||
|
nfb0408
|
74c209534c |
fix(copilot-acp): disable streaming path for CopilotACPClient
CopilotACPClient communicates via subprocess stdio and returns a plain SimpleNamespace from _create_chat_completion(). The streaming path tries to iterate this as a stream, crashing with: TypeError: 'types.SimpleNamespace' object is not iterable Mirror the existing ACP exclusion pattern (used for Responses API upgrade) to disable streaming when provider is copilot-acp or base_url starts with acp:// or acp+tcp://. Based on PR #9428 by @ningfangbin and issue #16271 by @Joseph19820124. Fixes #16271 |
||
|
Tekniumandteknium1
|
b5128a751b |
perf(startup): lazy-import OpenAI, Anthropic, Firecrawl, account_usage (#17046)
* perf(startup): lazy-import OpenAI, Anthropic, Firecrawl, account_usage
Four heavy SDK/module imports are now deferred off the hot startup path.
Net savings on cold module imports:
cli 1200 → 958 ms (-242)
run_agent 1220 → 901 ms (-319)
tools.web_tools 711 → 423 ms (-288)
agent.anthropic_adapter 230 → 15 ms (-215)
agent.auxiliary_client 253 → 68 ms (-185)
Four independent changes in one PR since they all use the same pattern
and share the same risk profile (heavy SDK import → lazy proxy or
function-local import):
1. tools/web_tools.py:
'from firecrawl import Firecrawl' moved into _get_firecrawl_client(),
which is only called when backend='firecrawl'. Users on Exa/Tavily/
Parallel pay zero firecrawl cost.
2. cli.py + gateway/run.py:
'from agent.account_usage import ...' moved into the /limits handlers.
account_usage transitively pulls the OpenAI SDK chain; only needed
when the user runs /limits.
3. agent/anthropic_adapter.py:
'try: import anthropic as _anthropic_sdk' replaced with a cached
'_get_anthropic_sdk()' accessor. The three usage sites
(build_anthropic_client, build_anthropic_bedrock_client,
read_claude_code_credentials_from_keychain) now resolve via the
accessor. All pre-existing test patches of
'agent.anthropic_adapter._anthropic_sdk' keep working because the
accessor respects any value already in module globals.
4. agent/auxiliary_client.py AND run_agent.py:
'from openai import OpenAI' replaced with an '_OpenAIProxy()' module-
level object that looks like the OpenAI class but imports the SDK on
first call/isinstance check. This preserves:
- 15+ in-module OpenAI(...) construction sites in auxiliary_client
and the single site in run_agent's _create_openai_client (Python's
function-scope name lookup finds the proxy, forwards the call);
- 'patch("agent.auxiliary_client.OpenAI", ...)' and
'patch("run_agent.OpenAI", ...)' test patterns used by 28+ test
files (patch replaces the module attribute as usual).
Tried two alternatives first:
- 'from openai._client import OpenAI' — doesn't skip openai/__init__.py
(the audit's hypothesis here was wrong).
- Module-level __getattr__ — works for external access but Python
function-scope name resolution skips __getattr__, so in-module
OpenAI(...) calls NameError.
Note: 'openai' still loads on 'import cli' because
cli.py -> neuter_async_httpx_del() -> openai._base_client, and
run_agent.py -> code_execution_tool.py (module-level
build_execute_code_schema) -> _load_config() -> 'from cli import
CLI_CONFIG'. Deferring those is a separate, larger change — out of scope
for this PR. The savings above all come from avoiding the openai/*,
anthropic/*, and firecrawl/* top-level type-tree imports on paths that
don't need them.
Verified:
- 302/302 tests in tests/agent/{test_anthropic_adapter,
test_bedrock_1m_context, test_minimax_provider, test_anthropic_keychain}
pass. Two pre-existing failures on main unchanged.
- 106/106 tests/agent/test_auxiliary_client.py pass (1 pre-existing fail).
- 97/97 tests/run_agent/test_create_openai_client_kwargs_isolation.py,
test_plugin_context_engine_init.py, test_invalid_context_length_warning.py,
test_api_max_retries_config.py,
tests/hermes_cli/test_gemini_provider.py, test_ollama_cloud_provider.py
pass (1 pre-existing fail).
- Live hermes chat smoke: 2 turns + /model switch + tool calls, zero
errors in the 57-line agent.log window.
- Module-level import of run_agent + auxiliary_client + anthropic_adapter
no longer pulls 'anthropic' or 'firecrawl' at all.
* fix(gateway): restore top-level account_usage import for test-patch surface
CI caught two failures in tests/gateway/test_usage_command.py that I
missed locally:
AttributeError: 'module' object at gateway.run has no attribute 'fetch_account_usage'
The test uses monkeypatch.setattr('gateway.run.fetch_account_usage', ...)
to inject a fake account-fetch call. Moving the import inside the
handler deleted that module-level attribute, breaking the patch surface.
Restoring the top-level import in gateway/run.py gives up the ~230 ms
gateway-boot savings from that one lazy, but:
1. the gateway is a long-running daemon — boot cost is paid once per
install, not per turn;
2. the other four lazy-imports (firecrawl, openai, anthropic, cli's
account_usage) remain in place and still account for the bulk of
the savings reported in the PR body;
3. preserving the patch surface keeps the established
'gateway.run.fetch_account_usage' monkeypatch pattern working
without touching tests.
Verified: tests/gateway/test_usage_command.py — 8 passed, 0 failed.
Full targeted sweep (2336 tests across agent/gateway/hermes_cli/run_agent):
2332 passed, 4 failed — all 4 pre-existing on main.
---------
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
|
||
|
Tekniumandteknium1
|
6085d7a93e |
chore: remove unused imports and dead locals (ruff F401, F841) (#17010)
Mechanical cleanup across 43 files — removes 46 unused imports (F401) and 14 unused local variables (F841) detected by `ruff check --select F401,F841`. Net: -49 lines. Also fixes a latent NameError in rl_cli.py where `get_hermes_home()` was called at module line 32 before its import at line 65 — the module never imported successfully on main. The ruff audit surfaced this because it correctly saw the symbol as imported-but-unused (the call happened before the import ran); the fix moves the import to the top of the file alongside other stdlib imports. One `# noqa: F401` kept in hermes_cli/status.py for `subprocess`: tests monkeypatch `hermes_cli.status.subprocess` as a regression guard that systemctl isn't called on Termux, so the name must exist at module scope even though the module body doesn't reference it. Docstring explains the reason. Also fixes an invalid `# noqa:` directive in gateway/platforms/discord.py:308 that lacked a rule code. Co-authored-by: teknium1 <teknium@users.noreply.github.com> |
||
|
Nanako0129
|
dbbe2d1973 | fix(gemini): bridge reasoning_config into thinking_config for chat-completions routes | ||
|
Tekniumandteknium1
|
023f5c74b1 |
fix(anthropic): remove Claude Code fingerprinting from OAuth Messages API path (#16957)
* fix(anthropic): remove Claude Code fingerprinting from OAuth Messages API path
OAuth requests now identify as Hermes on the wire. Removed:
- "You are Claude Code, Anthropic's official CLI for Claude." system
prompt prepend
- Hermes Agent → Claude Code / Nous Research → Anthropic
system-prompt substitutions
- mcp_ tool-name prefix on outgoing tool schemas + message history
- Matching mcp_ strip on inbound tool_use blocks (strip_tool_prefix path
removed from AnthropicTransport.normalize_response, + all 5 call
sites in run_agent.py and auxiliary_client.py)
- user-agent: claude-cli/<v> (external, cli) and x-app: cli headers on
the Messages API client
Added:
- OAuth path strips context-1m-2025-08-07 — Anthropic rejects OAuth
requests carrying it with HTTP 400 'This authentication style is
incompatible with the long context beta header.'
Kept (auth plumbing, not identity spoofing):
- _is_oauth_token classifier and is_oauth flag threading
- Bearer vs x-api-key auth routing
- _OAUTH_ONLY_BETAS (claude-code-20250219, oauth-2025-04-20) — backend
requires these on the OAuth-gated Messages endpoint
- _OAUTH_CLIENT_ID (Claude Code's) — Anthropic doesn't issue OAuth
creds to third parties; this is the only way the login flow works
- claude-cli/<v> User-Agent on the OAuth token exchange + refresh
endpoints at platform.claude.com/v1/oauth/token — bare requests get
Cloudflare 1010 blocked
Verified live against api.anthropic.com with a fresh sk-ant-oat01-*
token:
- claude-haiku-4-5 simple message: HTTP 200, 'OK' response
- claude-haiku-4-5 tool call: HTTP 200, stop_reason=tool_use, tool
named 'terminal' (no mcp_ prefix) round-tripped correctly
- Outgoing wire: no user-agent, no x-app, real Hermes identity in
system prompt, real tool name in schema
Closes/supersedes #16820 (mcp_ PascalCase normalization patch — no longer
needed since the mcp_ round-trip is gone).
* fix(anthropic): resolve_anthropic_token() reads credential pool first
Close the gap where ~/.hermes/auth.json → credential_pool.anthropic
(where hermes login + dashboard PKCE flow write OAuth tokens) was not
in resolve_anthropic_token()'s source list.
Before: users who authed via hermes login got the token written into
the pool, but legacy fallback code paths (auxiliary_client, models
catalog fetch, explicit-runtime path) that call resolve_anthropic_token()
saw None and raised 'No Anthropic credentials found' — even though the
token was sitting in auth.json.
New priority 1: pool.select() with env-sourced entries skipped. Skipping
env:* entries preserves the existing env-var priority logic further
down the chain (static env OAuth → refreshable Claude Code upgrade via
_prefer_refreshable_claude_code_token).
Surfaced while writing the hermes-agent-dev skill playbook for
'finding a live OAuth token for an E2E test'.
---------
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
|
||
|
Tekniumandteknium1
|
2b728e1274 |
fix(agent): drop thinking-only assistant turns before provider call (#16959)
Adds a pre-call sanitizer that detects assistant messages containing only reasoning (reasoning / reasoning_content, no visible content, no tool_calls) and drops them from the API copy. Adjacent user messages left behind are merged so role alternation is preserved for the provider. Mirrors Claude Code's approach in src/utils/messages.ts (filterOrphanedThinkingOnlyMessages + mergeAdjacentUserMessages). We drop the whole turn rather than fabricate stub text (the '.' / '(continued)' pattern from contributor PRs #11098, #13010, #16842 that were rejected because they put words in the model's mouth). The stored conversation history (self.messages) is never mutated — only the per-call api_messages copy. Users still see the reasoning block in the CLI/gateway transcript; only the wire copy is cleaned. Session persistence keeps the full trace. Two call sites covered: - Main agent loop, after _sanitize_api_messages (catches every turn). - Iteration-limit-summary fallback path. Tests: tests/run_agent/test_thinking_only_sanitizer.py — 25 cases covering detection (string/list content, whitespace-only, tool_calls, reasoning_details list form), drop behavior, adjacent-user merge (string+string, list+list, mixed), non-mutation of input dicts, and system-message handling. E2E live-tested against 5 providers with a poisoned history (empty assistant message + reasoning_content): OpenRouter→Anthropic/OpenAI/ DeepSeek-R1/Qwen, native Gemini. All 5 accepted the cleaned request. Happy-path regression (5/5) confirms the sanitizer is a noop when no thinking-only turn exists. Related: #16823 (wontfix — stub-text approach rejected). Co-authored-by: teknium1 <teknium@users.noreply.github.com> |
||
|
simonweng
|
a6a6cf047d |
feat(providers): add tencent-tokenhub provider support
Registers tencent-tokenhub (https://tokenhub.tencentmaas.com/v1) as a new API-key provider with model tencent/hy3-preview (256K context). - PROVIDER_REGISTRY entry + TOKENHUB_API_KEY / TOKENHUB_BASE_URL env vars - Aliases: tencent, tokenhub, tencent-cloud, tencentmaas - openai_chat transport with is_tokenhub branch for top-level reasoning_effort (Hy3 is a reasoning model) - tencent/hy3-preview:free added to OpenRouter curated list - 60+ tests (provider registry, aliases, runtime resolution, credentials, model catalog, URL mapping, context length) - Docs: integrations/providers.md, environment-variables.md, model-catalog.json Author: simonweng <simonweng@tencent.com> Salvaged from PR #16860 onto current main (resolved conflicts with #16935 Azure Anthropic env-var hint tests and the --provider choices= list removal in chat_parser). |
||
|
Tekniumandteknium1
|
e63364b8df |
revert: computer-use cua-driver (PR #16919) (#16927)
Reverts PR #16919 (commits |
||
|
Teknium
|
afb9588298 |
fix(computer-use): harden image-rejection fallback + AUTHOR_MAP
Follow-up to #15328's vision-unsupported retry branch in run_agent.py. _strip_images_from_messages() previously deleted any message whose content was entirely images. That's fine for synthetic user messages injected for attachment delivery, but it breaks providers for tool-role messages — the paired tool_call_id on the preceding assistant message ends up unmatched, which OpenAI-compatible APIs reject with HTTP 400. Fix: tool-role messages whose content becomes empty are replaced with a plaintext placeholder that preserves the tool_call_id linkage. Only non-tool messages are dropped. Added 10 tests covering the role-alternation invariants + image-type coverage. Image-rejection detector: expanded phrase list (image content not supported / multimodal input / vision input / model does not support image) and gated on 4xx status so transient 5xx errors never get misinterpreted as 'server said no to images'. Detection is documented as best-effort English phrase matching. AUTHOR_MAP: mapped 3820588+ddupont808@users.noreply.github.com to ddupont808 so release notes attribute the salvage correctly. |
||
|
ddupont
|
b4a8031b2e |
fix(computer-use): unwrap _multimodal tool results to content list for non-Anthropic providers
Tool handlers (e.g. computer_use capture) return a _multimodal envelope
dict when a screenshot is attached. The tool-message builder was passing
this raw dict as the `content` field of role:tool messages, which is an
illegal format — OpenAI-compatible APIs expect a string or a content-parts
list, not a plain Python dict, and would reject it with a 400/422 error.
Fix: unwrap _multimodal results to their `content` list
([{type:text,...},{type:image_url,...}]) in both the parallel and
sequential tool-call paths. The Anthropic adapter already handles content
lists natively; vision-capable OpenAI-compatible servers (mlx-vlm,
GPT-4o, etc.) accept image_url parts in tool messages directly.
Also add a _vision_supported adaptive fallback: on first image-rejection
error ("Only 'text' content type is supported." etc.) the agent strips all
image parts from the message history and retries with text only, so
text-only endpoints degrade gracefully without crashing the session.
|
||
|
ddupont
|
413ee1a286 |
feat(computer-use): background focus-safe backend — set_value, structured windows, MIME detection
Extends the cua-driver computer-use backend to drive backgrounded macOS windows without stealing keyboard or mouse focus from the foreground app. All changes target the cua-driver MCP backend and the shared dispatcher. ## cua_backend.py **Window-aware capture**: capture() now calls list_windows + get_window_state instead of the removed capture tool. Prefers structuredContent.windows (MCP 2024-11-05+ cua-driver) for zero-parse window enumeration; falls back to regex-parsed text for older builds. Stores the selected (pid, window_id) as sticky context so subsequent action calls do not need a redundant round-trip. **Action routing**: click/scroll/type_text/key all carry the sticky pid (and window_id for element-indexed clicks). type_text routes through type_text_chars (individual key events) rather than AX attribute write -- WebKit AXTextFields reject attribute writes from backgrounded processes. **Key parsing**: _parse_key_combo splits cmd+s-style strings into (key, [modifiers]) and routes to hotkey (modifier present) or press_key (bare key) -- cua-driver actual tool names. **set_value method**: new set_value(value, element) calls the cua-driver set_value MCP tool. For AXPopUpButton / HTML select in a backgrounded Safari, AXPress opens the native macOS popup which closes immediately when the app is non-frontmost; set_value AX-presses the matching child option directly (no menu required, no focus steal). **focus_app**: reimplemented as a pure window-selector (enumerates list_windows, sets sticky pid/window_id) without ever raising the window or stealing focus. **list_apps**: fixed tool name from listApps to list_apps; handles plain-text response via regex when structured data is absent. **Structured-content extraction**: _extract_tool_result now surfaces structuredContent from MCP results, enabling the list_windows window array without text parsing. **Helpers**: _parse_windows_from_text, _parse_elements_from_tree, _split_tree_text, _parse_key_combo extracted as module-level functions. ## schema.py Added set_value to the action enum with a description explaining when to prefer it over click (select/popup elements, sliders, no focus steal). Added value field for set_value payloads. ## tool.py Routed set_value action through _dispatch to backend.set_value. Added set_value to _DESTRUCTIVE_ACTIONS (approval-gated). Fixed MIME-type detection in _capture_response: cua-driver may return JPEG; detect from base64 magic bytes (/9j/ -> image/jpeg, else image/png) rather than hardcoding image/png. ## agent/display.py + run_agent.py Guard _detect_tool_failure and result-preview logic against non-string function_result values: multimodal tool results (dicts with _multimodal=True) are not string-sliceable; treat them as successes and fall back to str() for length/preview. |
||
|
Teknium
|
dad10a78d0 |
feat(computer-use): cua-driver backend, universal any-model schema
Background macOS desktop control via cua-driver MCP — does NOT steal the user's cursor or keyboard focus, works with any tool-capable model. Replaces the Anthropic-native `computer_20251124` approach from the abandoned #4562 with a generic OpenAI function-calling schema plus SOM (set-of-mark) captures so Claude, GPT, Gemini, and open models can all drive the desktop via numbered element indices. - `tools/computer_use/` package — swappable ComputerUseBackend ABC + CuaDriverBackend (stdio MCP client to trycua/cua's cua-driver binary). - Universal `computer_use` tool with one schema for all providers. Actions: capture (som/vision/ax), click, double_click, right_click, middle_click, drag, scroll, type, key, wait, list_apps, focus_app. - Multimodal tool-result envelope (`_multimodal=True`, OpenAI-style `content: [text, image_url]` parts) that flows through handle_function_call into the tool message. Anthropic adapter converts into native `tool_result` image blocks; OpenAI-compatible providers get the parts list directly. - Image eviction in convert_messages_to_anthropic: only the 3 most recent screenshots carry real image data; older ones become text placeholders to cap per-turn token cost. - Context compressor image pruning: old multimodal tool results have their image parts stripped instead of being skipped. - Image-aware token estimation: each image counts as a flat 1500 tokens instead of its base64 char length (~1MB would have registered as ~250K tokens before). - COMPUTER_USE_GUIDANCE system-prompt block — injected when the toolset is active. - Session DB persistence strips base64 from multimodal tool messages. - Trajectory saver normalises multimodal messages to text-only. - `hermes tools` post-setup installs cua-driver via the upstream script and prints permission-grant instructions. - CLI approval callback wired so destructive computer_use actions go through the same prompt_toolkit approval dialog as terminal commands. - Hard safety guards at the tool level: blocked type patterns (curl|bash, sudo rm -rf, fork bomb), blocked key combos (empty trash, force delete, lock screen, log out). - Skill `apple/macos-computer-use/SKILL.md` — universal (model-agnostic) workflow guide. - Docs: `user-guide/features/computer-use.md` plus reference catalog entries. 44 new tests in tests/tools/test_computer_use.py covering schema shape (universal, not Anthropic-native), dispatch routing, safety guards, multimodal envelope, Anthropic adapter conversion, screenshot eviction, context compressor pruning, image-aware token estimation, run_agent helpers, and universality guarantees. 469/469 pass across tests/tools/test_computer_use.py + the affected agent/ test suites. - `model_tools.py` provider-gating: the tool is available to every provider. Providers without multi-part tool message support will see text-only tool results (graceful degradation via `text_summary`). - Anthropic server-side `clear_tool_uses_20250919` — deferred; client-side eviction + compressor pruning cover the same cost ceiling without a beta header. - macOS only. cua-driver uses private SkyLight SPIs (SLEventPostToPid, SLPSPostEventRecordTo, _AXObserverAddNotificationAndCheckRemote) that can break on any macOS update. Pin with HERMES_CUA_DRIVER_VERSION. - Requires Accessibility + Screen Recording permissions — the post-setup prints the Settings path. Supersedes PR #4562 (pyautogui/Quartz foreground backend, Anthropic- native schema). Credit @0xbyt4 for the original #3816 groundwork whose context/eviction/token design is preserved here in generic form. |
||
|
Teknium
|
d63abbc329 |
fix(agent): persist streamed reasoning_content on assistant turns (#16844) (#16892)
Streaming-only providers (glm, MiniMax, gpt-5.x via aigw, Anthropic via openai-compat shims) emit reasoning through delta.reasoning_content chunks that get accumulated into the local reasoning_text string — but never land on the assistant message object as a top-level attribute. The prior guard at _build_assistant_message only wrote reasoning_content when the SDK exposed hasattr(msg, 'reasoning_content'), so these providers persisted the chain-of-thought under the internal 'reasoning' key and omitted the protocol-standard field. The poison was silent until the user later switched to a DeepSeek-v4 or Kimi thinking model, at which point replay failed with HTTP 400: 'The reasoning_content in the thinking mode must be passed back to the API.' One reported session store accumulated 4,031 poisoned messages across 1,101 files (#16844). Fix: add an additive fallback that promotes the already-sanitized reasoning_text to reasoning_content when no earlier branch wrote it AND reasoning text was actually captured. Layered on top of the existing SDK-attr branch and DeepSeek ''-pad (#15250) rather than replacing them, so every existing behavior is preserved: - SDK-exposed reasoning_content (OpenAI/Moonshot/DeepSeek SDK) still wins. - DeepSeek tool-call ''-pad still fires when the SDK exposes the attr but the value is None. - Non-thinking turns with no reasoning leave the field absent, so _copy_reasoning_content_for_api's cross-provider leak guard (#15748), promote-from-'reasoning' tier, and thinking-pad tier remain live at replay time. - No empty '' gets eagerly written on every assistant turn (which would have bypassed the read-side ladder and triggered empty thinking-block insertion in the Anthropic adapter). Tests: three new TestBuildAssistantMessage cases covering the streaming promotion path, SDK precedence, and field-absent-when-no-reasoning invariant. Credit @Sanjays2402 for the original diagnosis and patch in #16884; this is a scoped rework that preserves the existing read-side compensation code as defense in depth. Refs #16844, #16884, #15250, #15353, #15748. |
||
|
Teknium
|
6ea5699e3f |
fix(compression): notify users when configured aux model fails even if main-model fallback recovers (#16775)
A misconfigured auxiliary.compression.model is a user-fixable problem that silent recovery would hide. The previous retry-on-main logic transparently swallowed aux-model failures whenever the fallback succeeded, leaving the user's broken config in place and racking up future failures.
Track the aux-model failure on the compressor alongside the existing fallback-placeholder fields:
- _last_aux_model_failure_model: str | None
- _last_aux_model_failure_error: str | None
Both are set at the moment the aux model errors (captured before summary_model is cleared for retry), regardless of whether the retry succeeds. Cleared at compress() start and on on_session_reset() so a clean run doesn't leak stale warnings.
Surface at three places:
- gateway hygiene auto-compress: ℹ note to the platform adapter (thread_id preserved)
- gateway /compress command: ℹ line appended to the reply
- CLI via _emit_warning: deduped on (model, error) so repeat compactions don't spam
Distinct from the existing ⚠️ dropped-turns warning — different severity, different emoji, explicit 'context is intact' reassurance.
|
||
|
Erosika
|
4a9ac5c355 |
fix(memory): drop scrub from interim commentary + final response
Same layering concern as the persisted-assistant scrub already removed: _emit_interim_assistant_message and the final_response return path were mutating model output broadly. Streaming scrubber covers real leaks delta-by-delta; these post-stream scrubs were redundant. |
||
|
Erosika
|
49e3a1d8ee | style: trim verbose comment blocks added by previous commit | ||
|
Erosika
|
e553f6f3e4 |
fix(memory): narrow scrub surface to known wrapper boundaries
Reviewer pushback on the original boundary-hardening commits — three overreach points pulled plugin-specific policy into shared core paths: 1. gateway/run.py hardcoded a '## Honcho Context' literal split for vision-LLM output. Plugin-format heading in framework code; could truncate legitimate output naturally containing that header. Drop the literal split; keep generic sanitize_context (the wrapper strip is plugin-agnostic). Plugin-specific cleanup belongs at the provider boundary, not the shared gateway path. 2. run_agent.run_conversation scrubbed user_message and persist_user_message before the conversation loop. User text is sacred — if a user types a literal <memory-context> tag we must not silently delete it. The producer (build_memory_context_block) is the only legitimate emitter; user input should never need the reverse op. 3. _build_assistant_message scrubbed model output before persistence. Same hazard: would silently mutate legitimate documentation/code the model emits containing the literal markers. The streaming scrubber catches real leaks delta-by-delta before content is concatenated; persist-time scrub was redundant belt-and-suspenders. 4. _fire_stream_delta stripped leading newlines from every delta unless a paragraph break flag was set. Mid-stream '\n' is legitimate markdown — lists, code fences, paragraph breaks — and chunk boundaries are arbitrary. Narrow lstrip to the very first delta of the stream only (so stale provider preamble still gets cleaned on turn start, but mid-stream formatting survives). Plus: build_memory_context_block now logs a warning when its defensive sanitize_context strips something — surfaces buggy providers returning pre-wrapped text instead of silently double-fencing. Net architectural change: scrub surface collapses from 8 sites to 3 (StreamingContextScrubber on output deltas, plugin→backend send, build_memory_context_block input-validation). Plugin-specific strings stay out of shared runtime paths. User input and persisted assistant output are no longer mutated. Tests: rescoped TestMemoryContextSanitization (helper-correctness only, no source-inspection of removed call sites), updated vision tests to drop '## Honcho Context' literal-split assertions, updated _build_assistant_message persistence test to assert preservation. Added: cross-turn scrubber reset, build_memory_context_block warn-on- violation, mid-stream newline preservation (plain + code fence). |
||
|
Erosika
|
5ce5b17a42 |
fix(honcho): buffer partial memory-context spans across stream deltas
sanitize_context() uses a non-greedy block regex that needs both <memory-context> open and close tags present in a single string. When a provider streams the fenced memory block across multiple deltas (typical for recalled-context leaks — the payload often arrives in 10+ 1-80 char chunks), the per-delta sanitize stripped the lone open/close tags via _FENCE_TAG_RE but let the payload in between flow straight to the UI. Adds StreamingContextScrubber: a small stateful scrubber that tracks open/close tag pairs across deltas, holds back partial-tag tails at chunk boundaries, and discards span contents wholesale (including the system-note line that fragments across deltas). Wired into _fire_stream_delta; reset per user turn; benign trailing partial-tag tails are flushed at the end of each model call. Mid-span interruption (provider drops closing tag) drops the orphaned content rather than leaking it — truncated answer > leaked memory. Follow-up to #13672 (@dontcallmejames). |
||
|
dontcallmejames
|
f1ba4014e1 | fix: harden memory-context leak boundaries | ||
|
dontcallmejames
|
39713ba2ae | fix: strip leaked memory context from commentary | ||
|
Teknium
|
628ca99d9b |
fix(compression): show main + aux model and provider in feasibility warning (#16619)
The auto-lowered-threshold warning only named the compression model, making it confusing when the main and aux models are configured with the same slug but end up with different resolved context lengths (e.g. OpenRouter's stepfun/step-3.5-flash catalog value vs. a main-model context_length override). Users couldn't tell whether the warning reflected two different models or a context-resolution mismatch. Now includes both 'model (provider)' labels. The aux provider falls back to the client's base_url hostname when the configured provider is 'auto', so users see where compression is actually being called. |
||
|
hermes-agent-dhabibianddhabibi
|
aa53fb661a |
fix(copilot): mark native image requests as vision
Co-authored-by: dhabibi <9087935+dhabibi@users.noreply.github.com> |
||
|
Teknium
|
008860a23f |
fix(approval): close remaining prompt_toolkit deadlock vectors (#15216)
PR #13734 fixed the concurrent-tool-executor vector (ThreadPoolExecutor
workers didn't inherit the CLI's TLS approval callback). Two vectors
remained that could still land in the deadlocking input() fallback:
1. _spawn_background_review spawns a raw threading.Thread with no
approval callback installed, so any dangerous-command guard the
review agent trips falls back to input() -> deadlock against the
parent's prompt_toolkit TUI (same class as delegate_task subagents,
fixed in
|
||
|
Andrew Ho
|
0046d170dc |
fix(agent): propagate approval callbacks to concurrent tool worker threads
When tools execute concurrently via ThreadPoolExecutor, worker threads could not see the thread-local approval/sudo callbacks registered by the CLI. This caused dangerous-command prompts to fall back to plain input(), which deadlocks against prompt_toolkit's raw terminal mode. Capture parent-thread callbacks before launching workers, register them locally in each _run_tool thread, and clear them on exit. Mirrors the existing fix pattern from cli.py run_agent() for the main agent worker thread (GHSA-qg5c-hvr5-hjgr / #13617). |
||
|
luyao618
|
8ad29a938a |
fix(agent): restrict background review agent to memory and skills toolsets
The background skill/memory review agent was created without toolset restrictions, inheriting the full default tool set. This allowed it to use terminal, send_message, delegate_task, and other tools outside its intended scope, potentially performing unrelated side effects after skill creation. Restrict the review agent to only memory and skills toolsets by passing enabled_toolsets=['memory', 'skills'] during AIAgent construction. Fixes #15204 |
||
|
Teknium
|
ec671c4154 |
feat(image-input): native multimodal routing based on model vision capability (#16506)
* feat(image-input): native multimodal routing based on model vision capability
Attach user-sent images as OpenAI-style content parts on the user turn when
the active model supports native vision, so vision-capable models see real
pixels instead of a lossy text description from vision_analyze.
Routing decision (agent/image_routing.py::decide_image_input_mode):
agent.image_input_mode = auto | native | text (default: auto)
In auto mode:
- If auxiliary.vision.provider/model is explicitly configured, keep the
text pipeline (user paid for a dedicated vision backend).
- Else if models.dev reports supports_vision=True for the active
provider/model, attach natively.
- Else fall back to text (current behaviour).
Call sites updated: gateway/run.py (all messaging platforms), tui_gateway
(dashboard/Ink), cli.py (interactive /attach + drag-drop).
run_agent.py changes:
- _prepare_anthropic_messages_for_api now passes image parts through
unchanged when the model supports vision — the Anthropic adapter
translates them to native image blocks. Previous behaviour
(vision_analyze → text) only runs for non-vision Anthropic models.
- New _prepare_messages_for_non_vision_model mirrors the same contract
for chat.completions and codex_responses paths, so non-vision models
on any provider get text-fallback instead of failing at the provider.
- New _model_supports_vision() helper reads models.dev caps.
vision_analyze description rewritten: positions it as a tool for images
NOT already visible in the conversation (URLs, tool output, deeper
inspection). Prevents the model from redundantly calling it on images
already attached natively.
Config default: agent.image_input_mode = auto.
Tests: 35 new (test_image_routing.py + test_vision_aware_preprocessing.py),
all existing tests that reference _prepare_anthropic_messages_for_api
still pass (198 targeted + new tests green).
* feat(image-input): size-cap + resize oversized images, charge image tokens in compressor
Two follow-ups that make the native image routing safer for long / heavy
sessions:
1) Oversize handling in build_native_content_parts:
- 20 MB ceiling per image (matches vision_tools._MAX_BASE64_BYTES,
the most restrictive provider — Gemini inline data).
- Delegates to vision_tools._resize_image_for_vision (Pillow-based,
already battle-tested) to downscale to 5 MB first-try.
- If Pillow is missing or resize still overshoots, the image is
dropped and reported back in skipped[]; caller falls back to text
enrichment for that image.
2) Image-token accounting in context_compressor:
- New _IMAGE_TOKEN_ESTIMATE = 1600 (matches Claude Code's constant;
within the realistic range for Anthropic/GPT-4o/Gemini billing).
- _content_length_for_budget() helper: sums text-part lengths and
charges _IMAGE_CHAR_EQUIVALENT (1600 * 4 chars) per image/image_url/
input_image part. Base64 payload inside image_url is NOT counted
as chars — dimensions don't matter, only image-presence.
- Both tail-cut sites (_prune_old_tool_results L527 and
_find_tail_cut_by_tokens L1126) now call the helper so multi-image
conversations don't slip past compression budget.
Tests: 9 new in test_image_routing.py (oversize triggers resize,
resize-fails-returns-None, oversize-skipped-reported), 11 new in
test_compressor_image_tokens.py (flat charge per image, multiple images,
Responses-API / Anthropic-native / OpenAI-chat shapes, no-inflation on
raw base64, bounds-check on the constant, integration test that an
image-heavy tail actually gets trimmed).
* fix(image-input): replace blanket 20MB ceiling with empirically-verified per-provider limits
The previous commit imposed a hardcoded 20 MB base64 ceiling on all
providers, triggering auto-resize on anything larger. This was wrong in
both directions:
* Too loose for Anthropic — actual limit is 5 MB (returns HTTP 400
'image exceeds 5 MB maximum' above that).
* Too strict for OpenAI / Codex / OpenRouter — accept 49 MB+ without
complaint (empirically verified April 2026 with progressive PNG
sizes).
New behaviour:
* _PROVIDER_BASE64_CEILING table: only anthropic and bedrock have a
ceiling (5 MB, since bedrock-on-Claude shares Anthropic's decoder).
* Providers NOT in the table get no ceiling — images attach at native
size and we trust the provider to return its own error if it
disagrees. A provider-specific 400 message is clearer than us
guessing wrong and silently degrading image quality.
* build_native_content_parts() gains a keyword-only provider arg;
gateway/CLI/TUI pass the active provider so Anthropic users get
auto-resize protection while OpenAI users don't pay it.
* Resize target dropped from 5 MB to 4 MB to slide safely under
Anthropic's boundary with header overhead.
Empirical measurements (direct API, no Hermes in the loop):
image b64 anthropic openrouter/gpt5.5 codex-oauth/gpt5.5
0.19 MB ✓ ✓ ✓
12.37 MB ✗ 400 5MB ✓ ✓
23.85 MB ✗ 400 5MB ✓ ✓
49.46 MB ✗ 413 ✓ ✓
Tests: rewrote TestOversizeHandling (5 tests): no-ceiling pass-through,
Anthropic resize fires, Anthropic skip on resize-fail, build_native_parts
routes ceiling by provider, unknown provider gets no ceiling. All 52
targeted tests pass.
* refactor(image-input): attempt native, shrink-and-retry on provider reject
Replace proactive per-provider size ceilings with a reactive shrink path
on the provider's actual rejection. All providers now attempt native
full-size attachment first; if the provider returns an image-too-large
error, the agent silently shrinks and retries once.
Why the previous design was wrong: hardcoding provider ceilings
(anthropic=5MB, others=unlimited) meant OpenAI users on a 10MB image
paid no tax, but Anthropic users lost quality on anything >5MB even
though the empirical behaviour at provider-reject time is the same
(shrink + retry). Baking the table into the routing layer also
requires updating Hermes every time a provider's limit changes.
Reactive design:
- image_routing.py: _file_to_data_url encodes native size, no ceiling.
build_native_content_parts drops its provider kwarg.
- error_classifier.py: new FailoverReason.image_too_large + pattern
match ("image exceeds", "image too large", etc.) checked BEFORE
context_overflow so Anthropic's 5MB rejection lands in the right
bucket.
- run_agent.py: new _try_shrink_image_parts_in_messages walks api
messages in-place, re-encodes oversized data: URL image parts
through vision_tools._resize_image_for_vision to fit under 4MB,
handles both chat.completions (dict image_url) and Responses
(string image_url) shapes, ignores http URLs (provider-fetched).
New image_shrink_retry_attempted flag in the retry loop fires the
shrink exactly once per turn after credential-pool recovery but
before auth retries.
E2E verified live against Anthropic claude-sonnet-4-6:
- 17.9MB PNG (23.9MB b64) attached at native size
- Anthropic returns 400 "image exceeds 5 MB maximum"
- Agent logs '📐 Image(s) exceeded provider size limit — shrank and
retrying...'
- Retry succeeds, correct response delivered in 6.8s total.
Tests: 12 new (8 shrink-helper shapes + 4 classifier signals),
replaces 5 proactive-ceiling tests with 3 simpler 'native attach works'
tests. 181 targeted tests pass. test_enum_members_exist in
test_error_classifier.py updated for the new enum value.
|