hermes-agent

Files

T

Teknium f6bd1633f7 fix(reasoning): GLM-5.3 on Nous/OpenRouter no longer 400s when thinking is disabled

Reasoning-mandatory routes answer reasoning: {enabled: false} with HTTP 400
"Reasoning is mandatory for this endpoint and cannot be disabled". Hermes
sends that disable for /reasoning none, agent.reasoning_effort: none, and the
one-shot thinking-exhaustion continuation override (which GLM-5.3-flash
triggers on its own). The Nous profile's catalog guard swallows the disable
only when its per-process capability cache already says mandatory; a gateway
that warmed the cache before the route flipped kept sending it, and the 400
was classified as a non-retryable format_error that aborted the turn.

- error_classifier: new reasoning_mandatory reason (retryable, no fallback,
  no compression), matched before the request-validation branch.
- conversation_loop: one-shot recovery — set agent._reasoning_disable_rejected,
  queue a catalog refresh for the provider, retry.
- chat_completion_helpers: _reasoning_config_for_wire drops every disable
  (configured or ephemeral) once the route has rejected one.
- hermes_cli/models: refresh_reasoning_caps_async(provider) forces a
  background re-fetch of the Nous/OpenRouter catalog.
- openrouter profile: omit a disable when the catalog marks the route
  mandatory (parity with the Nous profile).

Live: z-ai/glm-5.3-flash on the Portal with a poisoned mandatory:false cache.
Before: turn aborted with the 400. After: one retry, thinking stays on, turn
completes.

2026-09-03 05:20:11 -07:00

lsp

fix(lsp): share one pyright process across git worktrees via workspaceFolders

2026-09-03 02:32:15 -07:00

monitoring

feat(cron): acked failure signatures stop re-pinging — durable incidents + ack CLI (salvage #94692 ) (#95017 )

2026-08-25 14:02:40 -07:00

pet

feat(pet): gate Unicode placeholders to kitty and Ghostty

2026-08-28 23:38:59 -05:00

proxy_sources

fix(windows): sweep remaining unguarded text-mode subprocess sites codebase-wide

2026-07-24 11:45:57 -07:00

secret_sources

fix(update): avoid cryptography self-lock on Windows

2026-08-15 13:28:14 -07:00

transports

fix(agent): reasoning-off continuation reaches the wire on the legacy chat path; reset one-shot flag per turn

2026-09-02 00:55:42 -07:00

verify

Integrate verify subsystem with the existing verification stack

2026-08-07 10:11:05 -07:00

__init__.py

…

account_usage.py

fix(auth): detect upstream Codex quota resets and lift stale pool cooldowns (#69494 )

2026-07-22 10:58:22 -07:00

acp_openai_bridge.py

refactor(acp): share one OpenAI bridge between the ACP clients

2026-08-26 10:10:11 -07:00

agent_init.py

fix(terminal): scope terminal config per turn under profile multiplexing

2026-09-02 05:34:28 -07:00

agent_runtime_helpers.py

fix(agent): stream cut mid tool-call markup no longer persists as assistant prose (#101899 )

2026-09-03 03:42:15 -07:00

anthropic_adapter.py

fix(anthropic): track the current fast-mode model matrix (Opus 4.8 / Opus 5)

2026-09-02 05:33:13 -07:00

anthropic_credentials.py

fix(auth): never fork single-use OAuth grants across profiles (#100339 )

2026-09-02 00:58:29 -07:00

anthropic_endpoints.py

refactor(anthropic): split the adapter godfile into four modules

2026-08-29 18:34:35 -07:00

anthropic_message_convert.py

refactor(anthropic): split the adapter godfile into four modules

2026-08-29 18:34:35 -07:00

async_utils.py

refactor(gateway): dedupe detached-task consumer + reconnect backoff policy

2026-07-18 20:01:55 +05:30

aux_accounting.py

feat(analytics): record auxiliary model usage per task in session accounting (#65537 )

2026-07-16 04:23:12 -07:00

auxiliary_client.py

feat(opencode): send x-opencode-session on every OpenCode request for backend affinity

2026-09-02 21:46:36 -07:00

azure_identity_adapter.py

fix(secrets): scope-aware Azure credential presence reads in identity diagnostics

2026-08-02 10:02:33 -07:00

backend_identity.py

refactor(fallback): single owner for backend identity and failure-scoped skips

2026-07-26 23:41:54 -07:00

background_review.py

fix(agent): preserve foreground resources after background review

2026-09-01 16:27:13 +05:30

battery.py

feat(status-bar): add /battery toggle for a color-coded battery read-out

2026-07-21 13:54:11 -05:00

bedrock_adapter.py

fix(agent): preserve Bedrock redacted reasoning replay

2026-09-01 08:30:26 -07:00

billing_links.py

feat(billing): shared cross-surface out-of-credits signal

2026-07-22 18:08:59 -05:00

billing_usage.py

chore: remove unused imports and dead locals (ruff F401/F841 sweep)

2026-07-29 11:53:39 -07:00

billing_view.py

chore: remove unused imports and dead locals (ruff F401/F841 sweep)

2026-07-29 11:53:39 -07:00

bounded_response.py

fix(agents): bound streaming error-response body reads

2026-07-05 14:00:20 -07:00

browser_provider.py

feat(browser): integrate Browser Use CLI 3.0

2026-08-10 10:45:44 -07:00

browser_registry.py

fix(plugins): isolate ownership by profile

2026-08-12 19:13:32 -07:00

chat_completion_helpers.py

fix(reasoning): GLM-5.3 on Nous/OpenRouter no longer 400s when thinking is disabled

2026-09-03 05:20:11 -07:00

codex_headers.py

fix(cron): isolate lazy imports from stale modules

2026-08-31 09:58:51 -07:00

codex_responses_adapter.py

fix(codex): preserve assistant image slots in replay

2026-08-28 04:58:14 -07:00

codex_runtime.py

refactor(agent): clone the review snapshot once at the spawn chokepoint

2026-09-02 13:28:41 +05:30

coding_context.py

test: sweep sibling tests stale on the tool renames + deferral default

2026-08-29 18:23:07 -07:00

command_token_source.py

fix(auth): bound the no-TTL key_cmd token cache; docs for key_cmd

2026-08-15 03:16:21 -07:00

compaction_display.py

fix(clients): hide compaction carriers across surfaces

2026-08-21 21:53:11 +05:30

context_breakdown.py

fix(cli): context meter no longer sawtooths on reasoning models — show durable transcript, not last-request replay

2026-09-01 15:34:03 -07:00

context_compressor.py

test(compression): pin rearm-reset wiring through a public boundary

2026-09-03 12:26:22 +05:30

context_engine.py

Revert "fix: rewire DCP context engine to current main architecture"

2026-08-08 23:09:45 +05:30

context_references.py

fix(security): close GitSpawn RCE class — malicious repo .git/config no longer executes on context gathering (GHSA-7x36-8jrh-v4pw)

2026-09-02 10:33:43 -07:00

conversation_compression.py

test(compression): register the heartbeat in ROUTINE_COMPRESSION_STATUS_SAMPLES

2026-09-03 11:29:36 +05:30

conversation_loop.py

fix(reasoning): GLM-5.3 on Nous/OpenRouter no longer 400s when thinking is disabled

2026-09-03 05:20:11 -07:00

copilot_acp_client.py

feat(providers): let a provider profile supply its own client

2026-09-02 09:57:39 -07:00

credential_persistence.py

fix(auth): make the Anthropic refresh commit part of the transaction

2026-08-29 18:34:35 -07:00

credential_pool.py

fix(auth): concurrent Nous 401 recovery adopts a peer's refresh instead of re-rotating the shared grant

2026-09-02 09:33:05 -07:00

credential_sources.py

fix(auth): read .env as utf-8-sig in the dotenv-vs-shell detector

2026-08-08 12:32:23 -07:00

credits_tracker.py

refactor(nous): trim comments and drop an unused field

2026-08-28 15:39:23 -03:00

curator_backup.py

fix(curator): carry .git file pointers too and document the deleted-skill drop

2026-09-03 01:43:22 +05:30

curator.py

fix(curator): remove terminal from the consolidation fork (issue #96962 )

2026-08-31 10:08:13 -07:00

deadline.py

fix(terminal): bound env.execute wait so a wedged poll cannot disable every timer

2026-08-31 10:42:39 -07:00

delegation_context.py

fix(cron): don't let a cron job inherit a kanban worker's dispatcher identity

2026-08-06 03:16:26 +05:30

display.py

feat(tool-search): core-tool deferral — curated 19-tool set behind the bridge by default; renames todo_list/cronjob_manage/process_manage/gui_tour/show_tip with legacy aliases (13.4K -> 6.9K desktop schemas, -49%)

2026-08-29 08:26:24 -07:00

empty_response_guard.py

fix(agent): handle usage-less empty responses

2026-09-03 03:41:52 -07:00

error_classifier.py

fix(reasoning): GLM-5.3 on Nous/OpenRouter no longer 400s when thinking is disabled

2026-09-03 05:20:11 -07:00

error_surface.py

fix(desktop): error card honors the classifier's retry verdict + failing-session identity (review feedback)

2026-08-21 15:24:03 -07:00

errors.py

fix(moa): surface stale presets without retries

2026-07-17 13:49:12 -07:00

estop.py

refactor(estop): drop redundant isinstance branch, fix stale docstring

2026-09-01 00:35:29 +05:30

fast_mode.py

feat(fast): bounded /fast auto|cold windows behind one route-aware gate

2026-09-02 05:33:13 -07:00

file_safety.py

refactor(profiles): retire the cross-profile write guard — profiles are not isolated (maintainer decision); mirror lost-write guards (#32049 ) survive; patch/write_file schemas drop cross_profile (-83 tok/call) (#97165 )

2026-08-28 06:36:22 -07:00

gemini_native_adapter.py

feat(providers): let a provider profile supply its own client

2026-09-02 09:57:39 -07:00

gemini_schema.py

fix(gemini): preserve typed enum constraints as strings

2026-07-26 20:59:16 -07:00

i18n.py

perf: use load_config_readonly() at read-only call sites in agent/

2026-07-29 15:28:15 -07:00

image_gen_provider.py

feat(media): opt-in upscale pass for image_generate and video_generate across FAL and Krea

2026-08-08 14:49:28 -07:00

image_gen_registry.py

fix(tools): dispatch image/video FAL strictly on the stored hermes tools selection

2026-08-19 16:10:01 -07:00

image_routing.py

feat: local models — managed llama.cpp runtime with one-click desktop setup

2026-09-01 16:01:53 -04:00

insights.py

refactor(usage): simplify-pass follow-ups

2026-08-14 02:04:24 +05:30

interrupt_compat.py

fix(agent): separate cancellation diagnostics from tool output

2026-08-23 18:25:19 -07:00

iteration_budget.py

feat: raise default tool-calling iteration limit from 90 to 500

2026-07-26 12:54:45 -07:00

jiter_preload.py

…

kanban_stop.py

follow-up: integrate agent nudge + dispatcher retry docs and tests

2026-07-14 16:47:33 +05:30

learn_prompt.py

fix(learn): process large sources incrementally

2026-08-08 05:09:43 -07:00

learning_graph_render.py

chore: remove unused imports and dead locals (ruff F401/F841 sweep)

2026-07-29 11:53:39 -07:00

learning_graph.py

…

learning_mutations.py

…

lmstudio_reasoning.py

fix(lmstudio): clamp max/ultra reasoning effort to LM Studio's ceiling

2026-07-16 07:57:51 -07:00

manual_compression_feedback.py

fix(compression): /compress refusal no longer reports a successful rewrite

2026-08-19 22:41:05 -07:00

markdown_tables.py

…

memory_manager.py

fix(memory): tolerate bare-signature v2 providers when forwarding checkpoint requirement

2026-08-31 09:57:22 -07:00

memory_provider.py

refactor(memory): renumber checkpoint API — v1 is the implicit historical contract, v2 opts into fail-closed checkpoints

2026-08-25 03:55:55 -07:00

message_content.py

…

message_metadata.py

fix: create message_metadata module and update chat_completion_helpers

2026-08-15 01:04:19 -07:00

message_sanitization.py

fix(compression): route-aware stale-thinking charge parity between compaction trigger and tail walks (#84371 )

2026-08-30 20:40:43 -07:00

moa_loop.py

fix(prompt-caching): tool-using sessions no longer 400 behind LiteLLM Anthropic proxies (#89886 )

2026-08-29 12:06:48 +05:30

moa_trace.py

feat(langfuse): widen tracing to errors, sessions, subagents, and MoA fan-out

2026-08-13 23:10:16 +05:30

model_metadata.py

fix(context): resolve commandcode models via live /models

2026-09-03 00:58:16 -07:00

models_dev.py

fix(models_dev): alias opencode-free to the Zen "opencode" catalog; pin Muse Spark 1M invariant

2026-09-03 00:58:16 -07:00

moonshot_schema.py

fix(agent): inject empty required array on Moonshot object schemas

2026-07-20 11:05:52 -07:00

native_compaction.py

fix(gateway): preserve native compaction capability on resume

2026-08-30 05:16:10 -07:00

nous_rate_guard.py

fix: decode config and state files as UTF-8 on non-UTF-8 locales

2026-07-24 17:10:39 -07:00

onboarding.py

feat(surfaces): route busy-input corrections through active-turn redirect

2026-07-22 12:10:58 -05:00

oneshot.py

…

opencode_affinity.py

feat(opencode): send x-opencode-session on every OpenCode request for backend affinity

2026-09-02 21:46:36 -07:00

outbound_webhooks.py

feat(webhooks): stamp the emitting profile on outbound webhook payloads

2026-09-02 07:00:13 -07:00

periodic_scheduler.py

perf(agents): run per-child timers on one shared scheduler thread

2026-09-03 02:44:24 -07:00

plan_prompt.py

feat: /plan graduates from bundled skill to built-in command on every surface

2026-08-29 19:14:15 -07:00

plugin_llm.py

fix(plugins): complete task-routed LLM integration

2026-08-12 16:25:20 -07:00

plugin_stream_hooks.py

feat(plugins): add streaming output observer hooks

2026-08-12 18:38:25 -07:00

portal_tags.py

fix(cache): honor the host-declared conversation key on the affinity-key path

2026-09-01 02:14:35 -07:00

process_bootstrap.py

perf(agents): share one httpx transport pool across every agent's client

2026-09-03 02:35:21 -07:00

prompt_builder.py

fix(prompt): agent routes task-learned knowledge (incl. user preferences/corrections) to skills; memory is the every-session exception

2026-09-03 04:02:35 -07:00

prompt_cache_boundary.py

fix(caching): prevent whitespace-only text blocks in prompt cache prefix splits

2026-08-29 11:33:05 +05:30

prompt_cache_scope.py

fix(cache,tests): durable generation docstring + studio-bridge order (PR #98811 , refs #96811 )

2026-09-01 02:14:35 -07:00

prompt_caching.py

docs: note the MEASURED_1H_PROVIDERS exception in effective_cache_ttl's docstring

2026-08-29 12:23:41 +05:30

provider_projection.py

feat(agent): fold an agent-as-provider's own tool work back into the turn

2026-08-26 10:10:11 -07:00

rate_limit_tracker.py

…

reactions.py

feat(agent): core affection reaction detector + reaction_callback

2026-07-10 05:41:59 -05:00

reasoning_effort.py

fix(nebius): route effort through canonical clamp_effort — hand-rolled map inverted the ladder

2026-08-29 20:39:44 +05:30

reasoning_summaries.py

fix(reasoning): keep gpt-5.x summary parts as separate blocks on the chat wire

2026-08-06 22:02:37 -05:00

reasoning_timeouts.py

fix: follow-up for salvaged PRs #93250 + #96234

2026-08-27 03:24:20 -07:00

redact.py

fix(redaction): gate ambiguous assignment values

2026-09-01 12:07:16 -07:00

relay_llm.py

fix(relay): upgrade to 0.8.1

2026-08-28 08:28:21 -04:00

relay_runtime.py

fix(relay): upgrade to 0.8.1

2026-08-28 08:28:21 -04:00

relay_tools.py

fix(relay): upgrade to 0.8.1

2026-08-28 08:28:21 -04:00

repetition_guard.py

fix(agent+discord): guard truncated-response continuation loops and cap Discord split delivery (#86581 )

2026-08-16 01:55:51 -07:00

replay_cleanup.py

refactor: shared helpers for api_content sidecar pop/drop/extract

2026-07-19 08:25:35 +05:30

retry_utils.py

refactor: single shared Retry-After parser

2026-07-29 10:13:50 -07:00

review_engine.py

feat: every subagent's prompt embeds the workspace's project context files

2026-08-23 19:04:37 -07:00

review_idle_queue.py

feat: local models — managed llama.cpp runtime with one-click desktop setup

2026-09-01 16:01:53 -04:00

runtime_cwd.py

fix(terminal): scope terminal config per turn under profile multiplexing

2026-09-02 05:34:28 -07:00

search_policy.py

fix(search): prune heavy trees from zero-match probe

2026-09-03 04:56:59 +05:30

secret_scope.py

fix(gateway): classify relay routing stamps as process-global deployment config

2026-08-21 13:21:46 +10:00

session_activity.py

fix(gateway): split turn-hold expiry from idle-timeout failure path

2026-08-29 13:02:13 +05:30

shell_hooks.py

fix(gateway): scope force-reload hook re-registration to its own home

2026-09-02 07:00:13 -07:00

side_question.py

feat: /btw rides the background-review cache-parity fork for full-context answers

2026-08-29 08:23:47 -07:00

skill_bundles.py

feat(observability): add Relay skill metrics

2026-07-29 12:20:34 -07:00

skill_commands.py

fix(webhook): load URL-resolved profile's skills under multiplex

2026-09-02 07:00:13 -07:00

skill_preprocessing.py

perf: use load_config_readonly() at read-only call sites in agent/

2026-07-29 15:28:15 -07:00

skill_utils.py

fix(skills): stop syncing bookkeeping dirs to sandboxes

2026-09-03 01:33:18 +05:30

ssl_guard.py

fix(ssl_guard): tolerate truststore SSLContext.get_ca_certs() NotImplementedError on Windows

2026-08-08 15:10:24 +05:30

ssl_verify.py

perf(agents): share one httpx transport pool across every agent's client

2026-09-03 02:35:21 -07:00

stream_diag.py

…

stream_single_writer.py

fix(streaming): make the single-writer fence best-effort so a missing guard can't crash a turn (#66448 )

2026-07-17 18:31:09 +00:00

subagent_lifecycle.py

perf(delegation): finished delegate children no longer pin their transcripts in the parent heap

2026-09-03 02:35:37 -07:00

subdirectory_hints.py

fix(search): prune heavy trees from zero-match probe

2026-09-03 04:56:59 +05:30

subscription_view.py

feat(cli): plan catalog on Free + plan= deep link + top-up/auto-refill copy split (#68689 )

2026-07-22 08:11:09 +05:30

system_prompt.py

fix(prompt): skip bundled AGENTS.md for desktop launch cwd

2026-08-31 10:10:25 -07:00

terminal_env_provider.py

feat(terminal): pluggable terminal environment backends via plugin registry

2026-08-24 20:10:44 -07:00

terminal_env_registry.py

feat(terminal): pluggable terminal environment backends via plugin registry

2026-08-24 20:10:44 -07:00

think_scrubber.py

fix(agent): re-arm think scrubber boundary after stream flush

2026-07-16 01:07:29 +05:30

thinking_timeout_guidance.py

…

thread_scoped_output.py

fix(agent): stop thread output descriptor leaks

2026-08-15 00:33:01 -07:00

title_generator.py

Port from can1357/oh-my-pi#7306 : reject answer-shaped auto-title output

2026-08-16 22:10:02 -07:00

tool_dispatch_helpers.py

fix(tool-search): bridge batch barrier, listing truncation, source indexing (salvage #92693 , part 1)

2026-08-25 15:24:15 -07:00

tool_executor.py

Merge pull request #96633 from afourniernv/chore/relay-0.8.0

2026-09-02 22:03:27 -04:00

tool_guardrails.py

fix(guardrails): hard stops catch replays, never legitimate iteration

2026-09-02 00:26:57 -07:00

tool_result_classification.py

fix(agent): preserve none vs unknown tool effects (#61783 )

2026-07-11 05:41:58 -07:00

trace_upload.py

fix(state): close leaked SessionDB connections on exception paths (#83226 )

2026-08-14 21:41:26 -07:00

trajectory.py

…

transcript_repair.py

fix(desktop): preserve streamed assistant text and unify atomic persistence (#95514 )

2026-08-29 11:33:05 +05:30

transcription_provider.py

feat(plugins): add pre_transcription hook and STT prompt threading

2026-08-12 19:01:30 -07:00

transcription_registry.py

fix(plugins): isolate ownership by profile

2026-08-12 19:13:32 -07:00

tts_provider.py

feat(tts): speech toggles warm/release plugin and command TTS providers

2026-09-02 05:35:14 -07:00

tts_registry.py

fix(plugins): isolate ownership by profile

2026-08-12 19:13:32 -07:00

turn_context.py

fix(compaction): stop idle compaction re-summarising a transcript that has not grown

2026-09-03 03:07:33 +05:30

turn_finalizer.py

refactor(agent): clone the review snapshot once at the spawn chokepoint

2026-09-02 13:28:41 +05:30

turn_liveness.py

perf(agents): run per-child timers on one shared scheduler thread

2026-09-03 02:44:24 -07:00

turn_retry_state.py

fix(reasoning): GLM-5.3 on Nous/OpenRouter no longer 400s when thinking is disabled

2026-09-03 05:20:11 -07:00

turn_summary.py

2026-08-29 08:26:24 -07:00

usage_pricing.py

perf(usage): prefer bundled pricing before metadata fetch

2026-09-03 04:00:51 +05:30

verification_evidence.py

fix(agent): reject masked verification results

2026-08-16 00:14:58 -07:00

verification_stop.py

fix: make verify_on_stop opt-in everywhere (default False, not auto) (#84383 )

2026-08-12 01:15:25 -07:00

verify_hooks.py

…

vertex_adapter.py

refactor(vertex): fold _creds_cache_key into _sa_snapshot (simplify pass)

2026-08-29 12:33:44 +05:30

video_gen_provider.py

refactor(video_generate): capability-gated dynamic schema (~814 → 458/377 tok/call) (#97095 )

2026-08-28 05:10:33 -07:00

video_gen_registry.py

fix(tools): dispatch image/video FAL strictly on the stored hermes tools selection

2026-08-19 16:10:01 -07:00

web_search_provider.py

feat(web): add Tavily web search and extract provider

2026-09-01 10:56:49 -07:00

web_search_registry.py

feat(web): add Tavily web search and extract provider

2026-09-01 10:56:49 -07:00