Adds platforms.slack.extra.native_task_cards: when enabled, live tool
calls render as Slack-native plan/task cards via chat.startStream /
chat.appendStream (task_display_mode: plan, task_update chunks) instead
of text/edit progress bubbles. ID-bearing tool_start/tool_complete
callbacks correlate concurrent same-name tool calls correctly; any
native API failure falls back to one continuously edited text update.
The stream is stopped exactly once when the turn finalizes.
Salvaged from PR #29496 onto current main (TurnRunner/TurnContext seam);
closes#29483.
Adds a pre_transcription transform hook (prompt/language/model mutable,
file_path read-only, last-writer-wins per the transform_* convention)
fired before any STT backend, threads prompt to faster-whisper
(initial_prompt) and OpenAI/Groq/Mistral/DeepInfra (prompt), adds an
optional stt.prompt config key on the same plumbing, and keeps the
no-hook dispatch path byte-identical. Fixes#64168.
Documents the new surface for users: a "Transcription prompt
(vocabulary hints)" subsection in the configuration guide (composition
order, per-provider support matrix, length contract, privacy warning),
a pre_transcription entry in the hooks reference, and the mirrored row
in the plugins hook table.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AG6LyYMvHC2o6HbVUozmVR
Surface the existing planner/worker cost-split capability as an explicit
strategy in the docs:
- delegation.md: new 'Cost strategy: frontier planner, inexpensive workers'
subsection under Model Override, with a config.yaml snippet using the
verified delegation.model / delegation.provider keys, the resolution order
(base_url > provider > inherit parent; model applies in all cases, empty =
inherit), and a note that delegate_task has no per-task model parameter —
quality-sensitive tasks should use kanban's per-task override instead.
- kanban.md: matching 'Cost strategy: frontier orchestrator, inexpensive
workers' subsection using the verified per-profile config mechanism
(dispatcher injects profile-scoped HERMES_HOME at worker spawn) and the
existing per-task model_override (--model/--provider, set-model, dashboard).
- zh-Hans mirrors for both pages.
- cli-config.yaml.example: cost tip comment under the delegation section.
Config resolution was live-verified against tools/delegate_tool.py
(_load_config + _resolve_delegation_credentials) with a temp HERMES_HOME:
delegation.model pins children to the sentinel model; with no delegation
keys, children inherit the parent model and credentials.
Personality persistence used to be split per surface: the TUI/desktop wrote
the NAME to display.personality while the CLI/gateway wrote rendered TEXT
into agent.system_prompt (and their /personality none only blanked the
text, leaving the name behind). When #81946 made display.personality
authoritative everywhere, stale names written long ago resurrected
personalities users had turned off - kawaii defaulting on after updating.
- hermes_cli/personality.py: new single owner of personality state.
Built-in personality definitions, neutral-name normalization, rendering,
availability (built-ins overlaid by agent.personalities), overlay
resolution, and the ONLY sanctioned persistence path
(persist_personality -> display.personality; never agent.system_prompt).
- v34 config migration: one-time reset of display.personality to none
(announcing which personality was cleared and how to re-enable), plus a
scrub of agent.system_prompt when it verbatim-equals a known personality
render (machine-written by the old CLI/gateway). Hand-written manual
prompts are never touched.
- All surfaces rewired through the module: CLI /personality (incl. active
marker in the list), gateway /personality, TUI config.set + slash path
(which previously applied without persisting), TUI config.get (reports
the EFFECTIVE personality), completer, hermes config display, and the
tui_gateway health probe.
- cli.py/config duplicates removed: built-ins now defined once; the
desktop mirrors them from one lib module (src/lib/personalities.ts).
- Docs updated: selection lives in display.personality, built-ins always
available, one-time reset note.
Opt-in via compression.codex_responses_native (default: false). When enabled,
gpt-5.6-family models on the direct OpenAI API (api.openai.com) or a ChatGPT
Codex subscription send context_management=[{type: compaction,
compact_threshold: N}] on Responses requests. OpenAI compacts server-side and
returns an encrypted compaction output item; Hermes captures it into the
existing codex_reasoning_items sidecar and replays it on later turns in place
of the pruned history — inheriting persistence, session replay, the
cross-issuer guard, and the encrypted-replay kill switch with zero new state.
Scope is deliberately hard-gated (agent/native_compaction.py, re-checked per
request): gpt-5.6 family only — gpt-5.1/5.2 fail server-side on the field
(HTTP 500 / stream stall, no structured rejection; live-verified) — and
direct OpenAI/Codex routes only; xAI, GitHub/Copilot, OpenRouter, relays,
and local servers never see the field.
Hermes' local compression stays armed as the fallback owner: the native
threshold is clamped ~8K tokens below the local trigger so the server
compacts first, and a structured provider rejection of context_management
disables native compaction for the session and retries without it
(one-shot guard in TurnRetryState).
Live-verified E2E on api.openai.com/gpt-5.6: server compaction fired at a
4K threshold, checkpoints captured and replayed, recall preserved across
3 turns; gpt-5.1 with the flag enabled stays clean (field never sent).
Direction credit: PR #76950 by @laryhorb explored native Responses
compaction; this is a minimal reimplementation on current main.
The docs promised 'frees ~370MB RAM' — measured behavior on macOS/CPU
is that ctranslate2's allocator keeps the freed pages (RSS doesn't
visibly shrink); the concrete win is VRAM release on CUDA hosts and
process-internal reuse on CPU. Say exactly that instead.
The local faster-whisper model singleton (_local_model) is loaded once
and never released — the 'base' model holds ~370 MB of RAM/VRAM for
the entire lifetime of the process, even when no voice messages arrive
for hours or days. On long-running gateway processes (especially with
local LLMs competing for the same GPU) this is wasteful.
Add a config-driven idle unload: after stt.local.unload_after_idle_seconds
(default 0 = never) of no transcription activity, a lightweight daemon
thread sets _local_model = None so the Python GC can reclaim the
ctranslate2 objects. The next voice message reloads the model
transparently (the existing lazy-load path handles it).
The watcher:
- Checks every 30s whether idle time exceeds the configured threshold
- Acquires _local_model_lock before unloading (prevents races with
concurrent transcriptions that are mid-load)
- Exits immediately if the model is already None (unloaded by another
path, e.g. the CUDA fallback eviction)
- Is restarted by each transcription with the current config value,
so changing stt.local.unload_after_idle_seconds in config.yaml takes
effect on the next voice message without a process restart
Default is 0 (never unload) — zero behavior change for existing users.
Recommended value for gateway processes: 300 (5 minutes).
15 tests: config resolution (garbage/negative/None fallbacks), unload
safety (already-None, lock acquisition), touch timestamp, watcher
lifecycle (unload after timeout, no unload within timeout, exits when
model already None, stopped on new start). Existing STT test suite
unchanged.
The review-fold commit added the input-duration gate but the user-facing
docs and config example still implied every cloud clip gets trimmed.
One-line additions to both.
Local faster-whisper gets Silero VAD (bf8004e3a) so silence never
reaches the model. Cloud providers got no such protection: the raw
file uploads untouched, so every second of silence in a voice note is
paid for twice — upload time and per-audio-minute billing — and cloud
Whisper hallucinates junk tokens on silent stretches exactly like
local Whisper did before the VAD hardening. A 13s voice note with two
long pauses is billed as 13s of audio to transcribe ~6s of speech.
Close the gap client-side: before uploading to a built-in cloud
provider (groq/openai/mistral/xai/elevenlabs/deepinfra), collapse long
pauses with ffmpeg's silenceremove filter, keeping
stt.cloud_trim_keep_ms (default 300) of every pause so word boundaries
and natural pacing survive. Uses ffmpeg, already a dependency of this
exact path via _transcode_audio_for_stt — no new dependency.
The trim is strictly best-effort — ALL of these upload the original
untouched, transcription never fails because of the trim:
- stt.cloud_trim_silence: false
- ffmpeg/ffprobe missing, trim failure, or timeout
- trimmed result ~empty (mostly-silence clip: the provider, not a
client-side dB heuristic, decides whether it contains speech)
- trim saves <10% (re-encoding for nothing)
Command-type and plugin providers are deliberately NOT trimmed: they
may wrap local CLIs that want the original bytes or run their own VAD.
E2E (real ffmpeg + faster-whisper): 13.2s voice note with 7s pause ->
6.2s upload (-53%); transcript of trimmed audio matches the original
on both utterances. Dense-speech and all-silence WAVs correctly fall
back to the original. 22 unit+E2E tests; STT/voice suite failures
identical to upstream/main baseline (all pre-existing).
- website/docs/user-guide/configuration.md (en) and the zh-Hans
translation gain a 'Session Stall Watchdog' section: default 300,
0=disabled, notify-only semantics (never kills the turn — contrast
gateway_timeout), one notification per stall episode, and the exact
stall message text so it is greppable.
- cli-config.yaml.example: the two in-agent compression timeout keys
(compression.context_timeout_seconds /
compression.context_total_ceiling_seconds) are shown as commented
lines next to session_stall_timeout's example for discoverability.
Three mechanisms to detect and notify when gateway sessions stall silently:
1. Mid-turn activity heartbeats stamped to SessionDB so hermes sessions list
and hermes status show progress during long turns without new message rows.
2. Stall watchdog: when a busy session has pending inbound and the shared
activity clock is idle past agent.session_stall_timeout (default 300),
log a WARNING and notify the user once to try /new. Notify-only; does
not kill the turn.
3. Compaction timeout: fenceless compress_context callers get a progress-aware
host budget (compression.context_timeout_seconds default 120 idle,
compression.context_total_ceiling_seconds default 600 ceiling). On timeout,
cancel via commit fence, skip compaction without dropping messages, and
continue the turn.
Closes#72016 (slices 1-3; slice 4 cumulative SSE stream-retry deadline
remains a follow-up).
Cherry-picked from PR #72424 by @fangliquanflq.
database.wal_autocheckpoint / database.journal_size_limit are now real
schema keys (default None = SQLite defaults) so the dashboard config
schema doesn't produce a single-field 'database' category, and the two
pragmas apply_database_pragmas reads are discoverable/documented.
Use database.journal_mode as the sole non-secret operator setting, preserve the vulnerable-SQLite safety gate and existing WAL databases, validate explicit DELETE results, document the active config path, and cover real SQLite openers with behavioral tests.
Local faster-whisper called model.transcribe with bare {'beam_size': 5}:
no VAD, cross-window conditioning on, no confidence filtering. Pure
silence produced hallucinated tokens (E2E: 5s anullsrc WAV -> 'You',
no_speech_prob=0.705) and noisy clips could produce runs of junk, often
in other languages.
Three-layer class fix, one shared owner for every local-whisper call
site (build_local_transcribe_kwargs):
1. Silero VAD filter (bundled with faster-whisper) on by default —
silence never reaches the model. stt.local.vad: false restores the
raw behavior for music/ambient transcription.
stt.local.vad_min_silence_ms tunes chunk splitting (default 500).
2. condition_on_previous_text=False — one hallucinated token can no
longer seed a self-reinforcing run; negligible cost for
voice-note-length audio.
3. Segment confidence gate (_join_confident_segments): drop a segment
only when no_speech_prob > 0.6 AND avg_logprob < -1.0 (openai-whisper's
own heuristic shape; both must hit so quiet-but-real speech survives).
Config: stt.local.no_speech_prob_threshold / logprob_threshold.
The WHISPER_HALLUCINATIONS blocklist in voice_mode.py stays as
last-resort defense but should now almost never fire.
E2E (real faster-whisper 'base', CPU int8):
silence.wav before 'You' -> after ''
noise.wav before '' -> after ''
speech.wav before/after 'Hello World, this is a test of the
transcription system.' (unchanged)
Docs (EN + zh-Hans), DEFAULT_CONFIG, cli-config.yaml.example updated;
19 unit tests (kwargs contract, off-switch, confidence gate incl.
quiet-speech survival, _transcribe_local wiring), sabotage-verified.
Adds gpt-transcribe (OpenAI's new file-transcription model, $0.0045/min)
to the OpenAI STT provider:
- OPENAI_MODELS set: gpt-transcribe is recognized so provider
auto-correction keeps it on OpenAI and rejects it on Groq
- Language hint wiring: gpt-transcribe replaces the singular
'language' field with a 'languages' list; the API rejects the legacy
field, so the hint is sent via extra_body {languages: [..]}
- Config comment (DEFAULT_CONFIG), cli-config.yaml.example, desktop
settings enum, and docs (en + zh-Hans) updated
- Tests: model pass-through, languages-list hint shape, legacy singular
hint preserved for gpt-4o-transcribe, Groq auto-correction
gpt-live-transcribe (realtime WebSocket, $0.017/min) is NOT wired here:
the file-based STT pipeline has no realtime session path; it belongs in
a future realtime/voice-mode integration.
Whisper auto-detection frequently misidentifies short/accented clips,
which users experience as voice notes transcribed in the wrong language
(Teknium + CTO both hit this). The unified resolver from #73067 made a
global hint possible; this makes it the DEFAULT so stock installs stop
guessing. Non-English users set stt.language once; '' restores
auto-detect for multilingual use.
Deep-merge gives existing configs the new default automatically (no
_config_version bump needed); any explicit per-provider or global
language setting still wins.
Class-level fix for the 'STT transcribes the wrong language' issue family
(#55551, #50181 and siblings). Previously language handling was per-provider
chaos: local honoured stt.local.language, Groq/OpenAI/Mistral/DeepInfra sent
no language hint at all, xAI silently forced 'en', ElevenLabs used its own
language_code key, and there was no global setting.
- New _resolve_stt_language() helper: stt.<provider>.language >
stt.language (new global key) > HERMES_LOCAL_STT_LANGUAGE > auto-detect.
- Threaded through ALL providers: local, local_command, groq, openai,
mistral, xai, elevenlabs, deepinfra (shared OpenAI handler), command
providers, and plugin dispatch.
- xAI no longer forces English when nothing is configured (auto-detect).
- Mistral Voxtral now receives a language hint when configured.
- stt.groq.model is now honoured from config (previously env-only).
- DEFAULT_CONFIG gains stt.language, stt.groq, stt.xai, stt.mistral.language.
- Tests: tests/tools/test_stt_language_resolution.py (11 tests, sabotage-
verified) + full transcription suite green (236 passed).
Builds on cherry-picked contributor work from #19786 (@zombopanda),
#23161 (@materemias), #50684 (@BlackishGreen33).
- Normalize stt.groq.language: cast to str, strip, treat
empty/whitespace as unset (parity with xAI's str().strip()).
- Clarify "blank = auto-detect" inline comments in 4 docs/configs to
reflect the env-var fallback (HERMES_LOCAL_STT_LANGUAGE).
- Document that HERMES_LOCAL_STT_LANGUAGE also drives the local
faster-whisper provider, not just the CLI fallback.
- Add unit tests covering: omitted language when unset, config-supplied
language, env fallback, config-over-env precedence, whitespace
normalized to unset.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Read stt.groq.language from config.yaml (with HERMES_LOCAL_STT_LANGUAGE
env fallback) and forward it to the Groq Whisper API to skip
auto-detection on known-language audio. Omit when unset so Groq
auto-detects, preserving today's behavior. Bonus: swap xAI's hardcoded
env literal for the LOCAL_STT_LANGUAGE_ENV constant for consistency.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Add optional stt.openai.language config for OpenAI transcription. Forward non-empty hints to the API while preserving auto-detection when unset. Document the config-only setting, add its default, and cover configured and unset request arguments.
Follow-up on top of @waroffchange's alignment fix (#55673): the real
default changed from 90 to 500 in #72176, so bring the example value
and comment up to the current default.
Leg 2 of #63078: prompt.submit returns {"status":"streaming"} immediately and
runs _start_agent_build + _wait_agent(timeout=30s) behind it. The deferred
build (MCP discovery with per-server retry backoff, synchronous model-metadata
HTTP, skills scanning) routinely outlives 30s on cold starts; on timeout
run_after_agent_ready emitted an error EVENT and returned without ever calling
_run_prompt_submit — the user's first message was permanently discarded while
the build finished successfully in the background. The desktop's optimistic
row eventually cleared with no visible error: the blank first session.
New _wait_agent_for_prompt replaces the flat cliff for the deferred prompt
path only (_sess()'s RPC-blocking _wait_agent keeps its 30s contract):
- The pending prompt stays attached to the (already off-RPC) run thread and
is delivered the moment the still-running build completes — a slow build is
no longer message loss.
- The wait runs in 5s slices so a cancel (session.interrupt / churn) is
honored promptly; the cancelled path returns None and defers to the
caller's cancel branch (the #65567 emit) for user-visible messaging.
- Past 30s the client gets ONE keyed notification.show ('Still starting the
agent…', key=agent-build-slow, desktop toast / TUI status bar), cleared on
delivery — patient, never silent.
- Permanent failure only when the build itself fails: agent_error set at
ready, the build thread died without signalling ready (fail fast via the
new _agent_build_thread handle instead of sitting out the cap on a corpse),
or the bounded cap expired on a genuinely hung build. The cap defaults to
600s and is tunable via agent.build_wait_timeout in config.yaml (no new
env vars); the error message states the message was not sent.
Tests: slow-build delivery with zero error events; the keyed progress notice
shown once and cleared; build-failure surfacing exactly one error event with
the real reason; dead-thread fail-fast; cancel honored mid-wait; config
override + fallback semantics; cap expiry message. The compute-host fallback
test stubs the new waiter alongside _wait_agent.
Routine automatic compression stays silent-by-design on chat platforms
(default unchanged, byte-identical). New opt-in config key
compression.progress_notices (bool, default false) opens a gate on the
gateway noise filter (_prepare_gateway_status_message) that lets ROUTINE
compression progress statuses through to chat surfaces.
- Membership is derived from the #69550 status template constants in
agent/conversation_compression.py (compiled to a literal-escaped regex,
never re-inlined wording), so unrelated noisy statuses (aux failures,
provider retry/rate-limit chatter) stay suppressed even when enabled.
- The compaction completion notice (COMPACTION_DONE_STATUS, #69546
lifecycle 'compacted' edge) already flows through the status path and
passes the filter — no new emit site needed.
- Config wired everywhere: hermes_cli/config.py DEFAULT_CONFIG,
cli-config.yaml.example, gateway raw-YAML read (live, mtime-cached),
gateway hot-reload cache-busting key list, website configuration docs.
- Failure notices and manual /compress feedback remain always-visible;
VISIBLE_COMPRESSION_MESSAGES and emit sites untouched.
Design by @havok-training (issue #52995).
Follow-up fixes on top of the salvaged #22566 mechanism:
- N-collector now counts only REAL actionable user turns via
_is_actionable_user_turn + _is_synthetic_compression_user_turn —
the same filter pair _find_last_user_message_idx uses post-#69291.
The contributor's bare role=='user' + _is_context_summary_content
check let blank platform echoes and continuation/todo rows consume
N slots, silently degrading the guarantee.
- Default flipped 3 -> 1 (behavior-preserving): a default of 3 was
measured to change the tail cut on transcripts whose budget covers
only the last turn. min_tail_user_messages=1 delegates to the
existing single-user anchor; N>1 is opt-in, and the call site is
gated so the default path is byte-identical to main.
- Hardened config parse in agent_init (bool rejected, fractional
floats rejected, floor 1) matching the max_attempts parser shape.
- Wired the recurring external-PR config gaps: hermes_cli/config.py
DEFAULT_CONFIG + cli-config.yaml.example (PR only had cli.py).
- Regression tests: blank echoes / synthetic rows don't count toward
N; tool-call/result pairs never split by the N-boundary (no-orphan
both directions); N-guarantee wins over tail_token_budget and the
_MAX_TAIL_MESSAGE_FLOOR (floor is a minimum, not a cap); default
parity pin; DEFAULT_CONFIG pin.
Follow-ups on top of the cherry-picked #62644 mechanism, porting it to
current main and closing the salvage-review requirements:
- proactive_prune_min_reclaim_tokens (default 4096): a prune only COMMITS
when it reclaims a meaningful token batch, measured on the pruned output.
A committed prune rewrites already-sent history and invalidates the
provider prompt-cache prefix; this hysteresis gate keeps those breaks
episodic/amortized (like a compression boundary) instead of firing every
tool iteration. 0 disables the gate. (Design point credited to the
#62389 review cycle's prune_minimum_tokens.)
- Standard no-op caller contract: every skip path returns the INPUT list
object; the loop commits only on 'result is not messages' + non-zero count.
- Loop call is getattr+callable guarded (plugin engines predating the hook,
SimpleNamespace test doubles) and exception-swallowed at debug level.
- Config parse follows the compression.max_attempts hardened semantics:
booleans rejected, fractional floats rejected, integral floats/numeric
strings accepted; negative trigger = disabled.
- cli-config.yaml.example documented (all three keys) and gateway
_CACHE_BUSTING_CONFIG_KEYS extended so hot-reload rebuilds the agent.
- Tests: min-reclaim gate both directions, input-object no-op contract,
no-orphan tool_call_id pairing in BOTH directions (#69830 pin rule),
default-off zero-behavior-change pin, config parse seam, and behavioral
loop-wiring tests (consulted/commit/no-op/absent-method/raising).
Long-lived sessions (e.g. a Telegram thread resumed over hours/days)
accumulate a large context that the existing size-based threshold only
trims once it crosses `threshold × context_window`. Until then every
turn re-reads the full history, which on large-context models can mean
hundreds of K of cache-read tokens per call even across long idle gaps.
Add a time-based trigger that complements (does not replace) the size
threshold: when a session resumes after `compression.idle_compact_after_seconds`
of inactivity, compact the accumulated history up front, before the first
reply. Disabled by default (0), so existing behaviour is unchanged.
The trigger reuses `_last_activity_ts` (the last time the turn loop did
work) to measure the idle gap at turn start, gates the token estimate
behind a cheap gap pre-check, and skips compaction when the context is
already at/below the post-compression target (threshold × target_ratio)
so a short idle thread never pays for a summarization that saves nothing.
It also defers to an active compression-failure cooldown.
The decision is factored into a pure predicate, `_should_idle_compact`,
which is unit-tested without a live agent.
Follow-up for salvaged #24279:
- cli-config.yaml.example: document compression.threshold_tokens
(commented-out, default null = disabled)
- contributors/emails: map maly.dan@gmail.com -> DanielMaly
- tests: should_compress() fires at the absolute cap below the pct
threshold (first-fires-wins); DEFAULT_CONFIG ships None and 0/None
are behavior-neutral incl. across update_model(); the small-context
pct floor is unaffected by the cap and re-derives correctly on
model switch
Addresses teknium1 review feedback on PR #60781:
1. Gateway cache invalidation: added ('compression', 'model_thresholds')
to _CACHE_BUSTING_CONFIG_KEYS so a live config edit to the map
invalidates the cached compressor (previously kept stale thresholds).
2. Integrated resolver with small-context floor: per-model overrides are
resolved FIRST, then the existing 75% floor for <512K models is applied
on top. The floor is no longer replaced — it stacks. An override below
75% on a small-context model still gets floored to 75% (raise-only);
an override above 75% wins.
3. Clean rebase on upstream main — no unrelated deletions or anti-thrashing
changes. Only the per-model threshold feature is added.
Changes:
- resolve_model_threshold() module-level helper (longest substring match)
- ContextCompressor.__init__ accepts model_thresholds dict
- _base_threshold_percent stores the per-model resolved value
- _config_threshold_percent stores the raw config value (fallback base)
- update_model() re-resolves on /model switch, falls back to config value
- ContextEngine base class update_model() applies overrides for plugin engines
- agent_init.py reads compression.model_thresholds from config, passes to ctor
- gateway/run.py cache busting key added
- cli-config.yaml.example documents the feature
- 17 tests covering resolve helper, compressor init (large/small context,
override above/below floor), update_model (re-resolve, fallback), base class
Co-authored-by: Copilot <copilot@github.com>
Simon van Laak
Hans
Teknium
Eva
Jakub Wolniewicz
kshitij
texasich
Brooklyn Nicholson
konsisumer
fangliquanflq
Zeraphim
Jasmine Naderi
Carlos Diosdado
Alex Fournier
墨綠BG
Mate Remias
zombopanda
Jeffrey Quesnelle
Jeffrey Quesnelle
waroffchange
Muthuvel
Ben Kamholtz