stream_tts_to_speaker() drops its hardcoded ElevenLabs client for
resolve_streaming_provider() + SentenceChunker, so any provider speaks
sentence-by-sentence while the model is still generating. Markdown
stripping also drops emoji — providers stall on them or read them out
loud.
StreamingTTSProvider ABC + registry + resolve_streaming_provider() —
ElevenLabs (pcm_24000) and OpenAI (response_format=pcm) stream chunked
PCM; every other provider keeps its configured voice and falls back to
per-sentence sync synthesis. SentenceChunker is the one incremental
cutter every surface shares: sentence-boundary cuts on the delta
stream, <think> blocks stripped even when split across deltas, short
fragments merged forward so they never stall as tiny clips.
Live theme authoring's core loop — Hermes recolors the skin file it just
activated — repainted the TUI but not the GUI. The event path was fine
(post-#69533 the WS broadcast lands and ingestBackendSkin refreshes the
$backendThemes registry); the same-name apply guard also no-ops correctly
(it's what protects a manual desktop theme pick). The repaint was supposed
to come from the registry: the active theme IS that skin, its palette just
changed. But ThemeProvider memoized deriveTheme on [themeName, resolvedMode]
only, while deriveTheme reads the registry non-reactively via resolveTheme —
so the store update re-rendered the provider and handed back the stale
palette. Name switches repainted (themeName moves); recolors never did.
Add the theme stores (user/backend/registry) to the memo's deps — they are
deriveTheme's actual reactivity, same as the availableThemes memo directly
above. applyTheme is idempotent, and $backendThemes only publishes on a
real palette change, so no spurious repaints.
Tests: render ThemeProvider for real — activation applies; a same-name
recolor repaints (fails without the fix); an inactive-skin seed doesn't
touch the painted theme.
_emit and _broadcast_global_event were each building the JSON-RPC event
envelope — extract _event_frame and use it from both. Type the registry as
set[Transport] (protocol already imported), and cut comment bloat at the
call sites. No behavior change; suites stay green.
* chore(gitignore): ignore installer .install_method stamp
Salvage of #54855 by @drissman — rebased onto current main with root-scoped
rule and sister-marker comments alongside .update-incomplete.
Closes#66189
Root cause: scripts/install.sh writes <install>/.install_method but git
did not ignore it, so managed checkouts show ?? .install_method and
hermes update may autostash the untracked marker.
Fix: add /.install_method to .gitignore (repo-root only).
Verification: git check-ignore -v .install_method
* test(update): assert .install_method survives update autostash (#66189)
Add hermetic regression mirroring the .hermes-bootstrap-complete test:
adopt the real .gitignore, drop the installer .install_method stamp, run
the exact 'git stash push --include-untracked' the updater uses, and assert
the marker is neither swept nor reported dirty. Requested by hermes-sweeper
review on #67364.
Real-world failure from dogfooding the live-theme flow: display.skin was
already 'synthwave' in config, but the desktop never visibly applied it (the
activation event predated the WS transport fix / the connect). The desktop's
gateway.ready seed records the baseline WITHOUT painting (by design — never
stomp the persisted desktop theme on connect), so it believed it was synced.
Re-running 'hermes config set display.skin synthwave' then did nothing twice
over: the watcher signature (name, skin-file mtime) hadn't moved, so no
skin.changed fired; and even on an event, the desktop's name-equality guard
blocked the apply against the seeded baseline.
Two halves:
- hermes_cli: setting display.skin touches the named skin file so the
watcher signature always moves on an explicit set — a same-name re-affirm
now broadcasts skin.changed like any real move. Built-ins (no file) are
unaffected; a name switch already moves their signature.
- desktop: track whether the synced baseline was actually APPLIED vs merely
seeded at connect. A skin.changed matching a seed-only baseline is an
intentional apply and repaints; once applied, repeat same-name events stay
no-ops (protects a manual desktop-side theme switch from snap-back, incl.
across a reconnect re-seed).
When Codex returns 429 usage_limit_reached, Hermes persists the provider's
reset_at on the pool entry and freezes the credential until it elapses --
which can be days out for weekly windows. But the upstream window can
reopen EARLY: the user redeems a banked rate-limit reset (Codex CLI /
ChatGPT UI), upgrades their plan, or OpenAI resets the window. Hermes
never re-checked, so it kept erroring with 'Codex provider quota
exhausted (429); retry after Ns' until a manual re-auth rewrote the
tokens (issue #43747, externally-reset variant).
- hermes_cli/auth.py: add _probe_codex_quota_restored() -- a throttled
(5 min/token) GET of the Codex /usage endpoint; quota counts as
restored when every reported window is <100% used. Add
clear_codex_pool_quota_cooldowns() to lift 429/quota-shaped cooldowns
from persisted pool entries (DEAD and auth-shaped entries untouched).
- resolve_codex_runtime_credentials(): before surfacing a pool-only
cooldown as 'quota exhausted', probe upstream; on a positive probe
clear the cooldown and return the pool credential.
- agent/credential_pool.py: _available_entries() probes frozen
openai-codex entries (clear_expired path only) and unfreezes them when
upstream confirms the reset.
- agent/account_usage.py: a successful /usage reset redemption now
clears persisted pool cooldowns immediately.
Negative paths preserved: probe 429/exhausted/indeterminate keeps the
cooldown; read-only enumeration never probes; non-JWT tokens never
probe (no network in hermetic tests).
The cross-surface theme SDK's live-repaint relies on a gateway skin watcher
that polls config and emits skin.changed on any move. But that emit is
session-less and fires from a background thread, so write_json fell through
its (session-transport -> contextvar -> stdio) ladder to the module stdio
transport — which only reaches the stdio TUI (tee'd to the dashboard WS
publisher). WS clients (the desktop app, dashboard chat) never got it, so
'Hermes themes itself' repainted the CLI/TUI but not the GUI.
Add a live-transport registry (one entry per connected WS peer, maintained by
handle_ws) and a _broadcast_global_event primitive that fans session-less
announcements out to every connected client, falling back to write_json when
none are registered (stdio path unchanged). Route both skin.changed emits
(watcher + the /skin RPC) through it, so a skin switch from any surface
repaints all of them.
Backend-only; desktop already handles skin.changed and does not drop
session-less events.
Two narrow timing windows (reported by null-runner) silently downgraded a
mid-turn correction to a plain next-turn message on the desktop client:
- Turn-build window: a fresh turn flips running=True and builds the agent
asynchronously, so session["agent"] is briefly None. session.redirect
answered 4010 "unsupported", which the renderer's catch swallowed into a
lost follow-up. Queue the correction server-side instead and return
status="queued" — lossless, and honest about what happened.
- Stale runtime id after reconnect: session.redirect 404s on a sid the
gateway no longer maps. redirectPrompt now resumes the stored session and
retries once, mirroring stopPrompt, so a correction fired right after a
reconnect isn't dropped.
The desktop treats "queued" like "redirected": the correction reaches the
model either way, so it's recorded once as a real user message.
The zero-result fallback prefers messages_fts_cjk when built: exact
ranked token match for Latin runs unicode61 fused onto CJK, including
<3-char tokens the trigram leg can't recover.
A pure-Latin query (no CJK characters) routes to the unicode61
`messages_fts` table, whose tokenizer does not insert a boundary between
Latin letters and adjacent CJK characters. Content like "修改youer服务端" is
indexed as a single token, so `search_messages("youer")` returned zero
results even though the substring is present, and the Latin path had no
fallback.
Add a zero-result trigram fallback to the pure-Latin path: when the
unicode61 search misses, retry against the existing `messages_fts_trigram`
table, which matches substrings regardless of word boundaries. The fallback
is gated on `_trigram_available` and on every token being >=3 chars (the
trigram minimum), and only fires on a zero-result miss, so successful Latin
searches keep their unicode61 ranking unchanged.
The trigram query construction shared with the CJK path is extracted into a
`_run_trigram_search()` helper; the CJK branch is refactored to use it with
no behavior change.
Adds regression tests in tests/test_hermes_state.py::TestCJKSearchFallback.
A stray tsc run can emit foo.js next to foo.ts under apps/shared/src or
apps/desktop/src. .gitignore hides the artifact from git status, but Vite
resolves extensionless imports .js-before-.ts, so the renderer silently runs
the stale compiled copy.
tsc -b . --clean already knows the emit graph and deletes
matching outputs. Run it before vite in all dev scripts.
This bit for real: a Jul 16 artifact of websocket-url.js predated the #68250
getGatewayWsUrl contract change ({ ok, wsUrl } IPC result), so its old
'if (fresh) return fresh' handed the whole result object to new WebSocket(),
dialing ws://127.0.0.1:5174/[object%20Object] on every boot. The desktop app
could never connect, and the failure survived reboots and cache wipes because
the poison lived in src/.
JsonRpcGatewayClient.connect() now rejects non-ws:// URLs with a readable
error instead of letting new WebSocket() coerce an object into
[object%20Object], so any future contract skew fails diagnosably.
- Use the fork glyph for branch and a sine wave for read aloud (all one lib now)
- Extract compact "2h ago" into formatAgo() in lib/time.ts (+ ageDays locale string)
- Cover formatAgo with a unit test
Extract the open_preview emitter into a shared tools/desktop_ui bridge
(one gateway-injected sink, routed by HERMES_UI_SESSION_ID) and add a
second desktop-gated tool on top of it:
- focus_pane(chat|files|terminal|review|sessions) -> pane.reveal event.
The desktop runs each pane's own reveal path (revealDesktopPane table)
and only acts on the active window -- a background turn never moves the
user's focus (desktop AGENTS.md: offer, don't hijack).
open_preview now emits through the same bridge. Both tools are check_fn
on HERMES_DESKTOP (zero footprint elsewhere), sitting beside
read_terminal/close_terminal in _HERMES_CORE_TOOLS.
Deliberately not adding run_slash: letting the agent fire slash commands
mid-turn (/model, /new, /clear) fights prompt-cache + conversation
invariants.
Plain Enter (and the primary send button) while a turn is running now redirects
the live turn with the typed correction instead of queueing it — matching
Cursor's stop-and-correct. Removes the now-redundant steering-wheel button
(redirect is the default gesture) and teaches the primary button the `steer`
action. Attachments still queue; slash commands still run inline.
Update the CLI and messaging guides so the default `interrupt` mode reflects
the new behavior: a follow-up redirects the active turn (preserving displayed
reasoning and completed work, letting running tools finish at a safe boundary)
rather than hard-stopping it, with `/stop` still the explicit hard stop.
The default `busy_input_mode: interrupt` now redirects the live turn instead
of hard-stopping it and re-queuing a fresh turn, wired consistently across
every first-party surface via the shared core primitive.
- CLI, gateway (busy + PRIORITY paths), TUI (`_handle_busy_submit`), desktop
(`session.redirect` RPC), and ACP call `redirect()` when the agent advertises
`_supports_active_turn_redirect`, and fall back to the proven interrupt +
next-turn queue for older runtimes.
- Redirect is gated to plain text with no attachments: captioned or
attachment-bearing events (including adapters that classify unknown media as
`TEXT`) stay queued so media is never dropped.
- ACP `cancel()` records the interrupted prompt, sets its cancel event, and
hard-stops the agent while holding `runtime_lock`, closing the
cancel-then-correct ordering gap; connection I/O happens after the lock is
released.
- Desktop appends the correction as a real user transcript message so the live
view matches the durable history after reload.
- `/busy` help, onboarding hints, and the new `session.redirect` RPC describe
the redirect behavior; `/stop` remains the hard stop.
Add a desktop-gated open_preview tool so 'open cnn.com in the preview
pane' works. The tool (check_fn on HERMES_DESKTOP, zero footprint
elsewhere) emits a preview.open event through a gateway-injected emitter,
mirroring the close_terminal -> terminal.close bridge. The desktop
handles it in usePreviewRouting, normalizing the target and opening the
pane for the active session only -- a background turn never hijacks it.
Bare domains and localhost are coaxed into fetchable URLs (www.cnn.com ->
https://, localhost:3000 -> http://); file paths and schemes pass through
to the renderer's normalizer.
The Codex app-server runtime bypasses the main conversation loop and drives
its own subprocess turn, so it needs first-class hooks rather than the
OpenAI-loop interrupt path.
- `AIAgent.interrupt()` now forwards a hard stop to
`CodexAppServerSession.request_interrupt()`, and `redirect()` uses Codex's
native `turn/steer` protocol instead of cancelling the subprocess.
- `run_turn()` no longer clears an interrupt that arrived during
`ensure_started()`: a stop landing mid-startup is honored before `turn/start`,
and the interrupt event is cleared on every exit path.
- `run_codex_app_server_turn()` mirrors the loop finalizer's interrupt handoff
(surface `interrupted` / `interrupt_message`, then `clear_interrupt()`) on
both the normal and exception early-return paths, so a hard stop can't leave
`_interrupt_requested` stale for the next turn.
A follow-up sent while the model is still generating previously ended the
turn: Hermes kept only the visible partial text (reasoning was display-only),
cleared the loop, and replayed the message as a fresh next turn. If the
correction referred to something that only appeared in the thinking stream,
the model no longer had that context.
Add `AIAgent.redirect(text)`: a corrective interrupt distinct from a hard
stop. It cancels only the in-flight model request (not tool workers or child
agents), stashes the correction under a lock shared with `interrupt()` so a
concurrent `/stop` always wins, and lets the loop rebuild the same logical
iteration. `_apply_active_turn_redirect()` checkpoints the reasoning that was
actually shown to the user plus any visible partial text as an ordinary
assistant message, then appends the correction as a real user turn — never
replaying incomplete signed/encrypted provider reasoning, and keeping strict
role alternation and prompt-cache stability intact. During tool execution it
degrades to `steer()` so a running tool finishes at a safe boundary.
`_fire_reasoning_delta` now only records reasoning that a display callback
actually consumed, so `show_reasoning: false` never leaks hidden provider
thinking into the persisted transcript.
Since #65919 the live view seals each chunk of mid-turn assistant
commentary (message.interim) as its own finalized bubble. Every bubble
with visible text renders the hover action footer, so a tool-heavy turn
grew a copy/refresh bar under almost every paragraph — and the live
render didn't match rehydration, which merges the turn into one bubble.
Mark sealed interim bubbles with ChatMessage.interim, carry the flag
into the runtime message metadata (custom.interim), and skip the
AssistantFooter for them. The turn's final reply keeps the footer; a
previewed final that settles onto an interim bubble clears the mark so
the settled reply regains its actions. interim joins COMPARED_FIELDS /
chatMessagesEquivalent so flipping it repaints.
Also fix an id-collision flake this surfaced: stream/interim bubble ids
were Date.now()-only, so an interim seal and the next segment's first
delta in the same millisecond reused the id and the new segment appended
into the sealed bubble. Ids now include a monotonic sequence.
Follow-up for the salvaged #55800 idle-compaction commit:
- turn_context.py: treat a skipped _compress_context (per-session
compression lock held by another path, failure cooldown, anti-thrash
breaker, codex-native routing) as a strict no-op — only re-baseline
conversation_history and re-anchor current_turn_user_idx after a REAL
compaction. Also re-anchor the user-message index after idle compaction
(the PR predates the reanchor helper).
- hermes_cli/config.py: add idle_compact_after_seconds: 0 to
DEFAULT_CONFIG's compression block (the PR only had
cli-config.yaml.example).
- gateway/run.py: add the idle-compaction status wording to
_TELEGRAM_NOISY_STATUS_RE so the new 💤 message stays out of
human-facing chat surfaces (routine compaction is silent by design);
pin it in tests/gateway/test_telegram_noise_filter.py.
- docs: idle_compact_after_seconds in user-guide/configuration.md and
developer-guide/context-compression-and-caching.md parameter table.
- tests/agent/test_idle_compaction_lock_and_guards.py: end-to-end
coverage with a real AIAgent + SessionDB proving the idle path honors
the per-session compression lock (added after the PR), the persisted
failure cooldown, and the anti-thrash breaker, and that the lock is
released after an idle-triggered compaction.
Salvaged from #55800 by @iso2kx. Implements #27579.
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.
Composing #57835's multi-fossil summary scan with #47274's merged-handoff
unwrap: when the restart-decay path pulls a merged handoff into the
compression window, its genuine prior-tail user content must enter the
summarizer input (folded into the fresh summary) rather than being
dropped with the summary row. Standalone handoffs still drop. The
continuity test now pins the composed contract: recovered verbatim OR
via summarizer input, never silently deleted, never duplicated.
- Three '_previous_summary == "fresh summary"' exact pins and one
transcript-wide fossil-absence pin predated main's deterministic
task-snapshot grounding (761a0b124e), which prepends a
'## Historical Task Snapshot' section to stored summaries and may
quote a folded head turn inside the handoff. Re-pin the contracts
(fresh body present, fossil absent from non-summary messages)
instead of exact strings.
- Add test_restart_simulation_fresh_compressor_does_not_reprotect_head:
a fresh ContextCompressor over a transcript containing a persisted
handoff summary computes the same decayed protected-head boundary
(compress_start base) as a live already-compacted process, and the
first post-restart compaction does not preserve pre-restart head
fossils (#57814).
protect_first_n decay state (compression_count / _previous_summary) is
in-memory only, so a gateway restart re-protected the persisted handoff
summary and head fossils, growing the head unboundedly across
restart+compaction cycles (#57814).
_effective_protect_first_n now probes a bounded resumed-head window for
a persisted handoff summary (by metadata or content prefix) and decays
protection when one is found, before compress_start is computed. The
first post-restart compaction self-heals: stacked summary fossils are
folded into the next summary prompt instead of preserved verbatim,
rehydration is rolled back on abort, deterministic fallback carries a
bounded redacted previous-summary snapshot, and forced user-leading
merged summaries keep the live tail request after the summary end
marker so they stay rehydratable.
Squashed reapply of the 12-commit series from PR #57835 onto current
main (branch was 1210 commits behind; single add/add conflict with the
task-snapshot grounding helpers resolved by keeping both).
Fixes#57814.
- aux summary call on main intentionally omits max_tokens; use .get() in the
telemetry hook (and widen the param type) so the hook never breaks the call
- update test expectation: aux_output_reservation is None on main
- record no_progress failure_class in the no-progress boundary branch
Follow-up for salvaged PR #60444.
The summary_idx head-copy skip (from #69302) dropped the entire merged
handoff message, deleting the genuine prior-tail user content that
#47274's _strip_context_summary_handoff_message correctly unwraps.
Strip handles both shapes: standalone handoffs drop, merged handoffs
keep their real content. Caught by
test_recompression_of_current_merged_handoff_preserves_prior_tail_once
when both PRs landed together.
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
Add compression.threshold_tokens config option that sets an absolute
token cap for auto-compaction. When configured alongside the existing
ratio-based threshold, the effective trigger point is the lower of the
two, so compression never fires later than the user's preferred token
count regardless of which model is active.
This solves the problem where switching between models with different
context windows (e.g. 1M → 400K) shifts the absolute trigger point,
causing premature or delayed compression.
Rework from PR #24279 addressing sweeper feedback:
- The cap is now a first-class compressor configuration value
(threshold_tokens_cap parameter on ContextCompressor.__init__),
not a post-construction patch on the live instance.
- Applied in both __init__ and update_model() so it survives model
switches and fallback activations (the old approach was undone by
update_model() restoring _configured_threshold_percent).
- Clamped to the model's context length so a cap above the window is
a no-op (ratio-based threshold wins).
- Works with max_tokens output-token reservations.
- Added 9 tests covering cap-vs-ratio selection, model switch survival,
context-length clamping, max_tokens interaction, and invalid values.
- Updated user-facing configuration docs.
- Removed unrelated background-review/curator/Honcho changes (main
already contains background-review memory isolation in 973f27e95).
Config example:
compression:
threshold: 0.50
threshold_tokens: 200000 # never compress later than 200K tokens
Compaction summaries persist across sessions and re-enter every subsequent
summarizer prompt, but every redact_sensitive_text() call in
context_compressor.py used default mode: a no-op under
security.redact_secrets:false, and opaque OAuth-callback / URL-userinfo
credentials passed through even when enabled. The stored _previous_summary
also re-entered the iterative-update prompt unredacted.
Add _redact_compaction_text() — redact_sensitive_text(force=True,
redact_url_credentials=True) — and thread it through all compaction text
boundaries: serializer input (content + tool args), deterministic fallback
summary, summarizer LLM output, manual + auto focus topics, the latest-user
task snapshot, and _previous_summary re-entry.
Note: force=True at this boundary intentionally overrides
security.redact_secrets:false — that opt-out targets live tool output, not
persisted summaries.
Salvages the compaction half of #49556 (the redact.py strict-URL half
landed independently via 75af6dc57/62a00a739). Addresses #43666 item 2.
Co-authored-by: AndrewMoryakov <topazd2@gmail.com>
Integration layer for the cjk_unicode61 tokenizer, rebuilt on the v23
schema (the contributed integration in PR #65544 predated it):
- messages_fts_cjk: external-content FTS5 over a tool-row-excluding view
(same v23 storage discipline as the trigram index it supersedes — zero
inline text copies). Serves EVERY CJK query shape the legacy routing
split between trigram (>=3 chars/token) and LIKE full scans (1-2 char
tokens). Lone 1-char CJK runs and role_filter=['tool'] queries keep
their legacy routes.
- Dedicated marker pair (fts_cjk_rebuild_high_water/progress) gates the
id-scoped triggers, so a cjk-only backfill never gates the complete
messages_fts/trigram triggers.
- Transitions ride (the existing
throttled/resumable chunk engine): fresh DBs are born with the index;
legacy v22 DBs land on v23+cjk in one run; already-optimized v23 DBs
gaining the tokenizer get a marker-gated backfill; live writes are
indexed immediately in every case.
- Tokenizer-loss self-heal: a process that can't load the extension drops
the cjk triggers (writes keep working), leaves a stale breadcrumb, and
the index is rebuilt from scratch on the next optimize run — triggers
are never reinstalled over a gap (external-content 'delete' on an
unindexed rowid is the FTS5 corruption hazard the marker gating exists
to prevent).
- Capability classification: 'no such tokenizer: cjk_unicode61' joins the
degraded-runtime error class everywhere (read probe, write probe,
repair) so tokenizer absence is never misclassified as corruption.
- Config: sessions.cjk_fts (default on, inert without the .so) and
sessions.search_slow_ms in config.yaml, bridged to env by CLI + gateway
(startup + per-turn reload). build.sh falls back to vendored SQLite
headers so no libsqlite3-dev is needed.
Slow-query log path attribution updated: fts_cjk / fts5 / trigram /
like_scan. Tests: 14 lifecycle tests (fresh/legacy/stale/backfill paths,
tokenizer-loss round-trip) + 5 config-bridge tests + slow-log suite.
One INFO line per slow search naming the path taken (fts_cjk / fts5 /
trigram / like_scan), elapsed time, row count, and the query. The 2026-07
session_search investigation needed turn-trace archaeology plus workload
replay to discover that short-CJK queries were full-scanning the table —
with this line the next routing regression is a journalctl grep.
Threshold: sessions.search_slow_ms (default 1000ms; 0 logs every call),
bridged to HERMES_SEARCH_SLOW_MS.
Salvaged from PR #65544 (adapted to the v23 schema in follow-up commits).
