Symptom: Honcho logs show a dialectic answer was generated, but Hermes never
injects it — intermittently.
Root cause: the dialectic supplement that queue_prefetch() fires at the end of
turn N is stored pending (fired_at=N) for consumption by turn N+1's prefetch().
But prefetch()'s trivial-prompt guard returned early BEFORE the consumption
block. So when turn N+1's prompt was trivial ('ok', 'yes', 'continue', a slash
command), the ready result was never consumed, and a few turns later the
stale-discard guard dropped it. Generated by Honcho, never seen by the model.
The dependence on 'is the consuming turn trivial?' is why the loss looked random.
Fix: trivial turns now consume and inject a ready, non-stale pending result while
still spending no new work (no base-context fetch, no new dialectic fire). A
trivial ack shouldn't generate context, but it shouldn't destroy an answer
already computed for that exact turn. Extracted the pop+stale-check into a shared
_consume_pending_dialectic() used by both the trivial path and the normal path so
they age-check identically.
Preserved (covered by new tests): genuinely stale results are still discarded on
trivial turns; trivial turns still fire no new work; a trivial turn with nothing
pending still injects nothing.
Adds regression tests for inject-on-trivial and discard-stale-on-trivial.
A brand-new session injected no Honcho context on the user's first message —
the peer card/representation only showed up from turn 2 onward. The base-context
fetch was fired asynchronously and popped in the same synchronous pass, so it
always lost the race on turn 1 (a background thread can't finish inside one
pass), leaving the first response with zero recalled context.
Fetch the base layer (representation + card + summary) synchronously with a
bounded timeout on turn 1 so the peer card is injected immediately; subsequent
turns still consume the background-refreshed result primed by queue_prefetch().
The wait is bounded by _FIRST_TURN_BASE_TIMEOUT and tightened further by a small
configured request timeout (fail-fast deployments / tests).
Two related first-turn/dialectic reliability fixes ride along:
- first-turn dialectic no longer double-fires: if a prewarm .chat() thread is
already in flight from session init, turn 1 waits briefly for it instead of
firing a second (duplicate) call that also blocked the first response. The
first-turn wait is decoupled from a large host timeout (a 60s host timeout
must not block the first response for 60s) via _FIRST_TURN_DIALECTIC_CAP,
while still honoring a tight configured timeout.
- empty-pass propagation guard in multi-pass dialectic: at depth > 1 each pass
feeds the prior pass's output into the next prompt. If a pass returned empty
(e.g. a reasoning model that spent its whole budget thinking), the next prompt
carried a blank assessment (the "empty spot" seen in Honcho request logs). Now
only non-empty prior results feed dependent passes; if all priors are empty,
re-issue the base prompt instead of referencing nothing.
The five Honcho tool schemas had overlapping/misleading descriptions, making it
hard for the model to pick the right one, plus two concrete correctness bugs:
- honcho_context advertised an 'Optional focus query' parameter that the dispatch
never read. The model could pass query= expecting filtering that never happened.
Remove the dead parameter; honcho_context is an honest no-query snapshot. Focused
retrieval now lives in honcho_search (see prior commit).
- honcho_conclude's peer param was described as 'Peer to query' — wrong; it's the
peer the conclusion is ABOUT. Corrected.
Rewrite all five descriptions to give each tool a distinct mental model and
cross-reference siblings:
profile = read/write the compact card (cheapest, no query, no LLM)
search = find what was actually said, ranked, cross-session (cheap, no LLM)
reasoning= ask a question, get a synthesized answer (the only LLM tool; expensive)
context = a fixed session snapshot (no query, no LLM)
conclude = write a durable fact to the profile
Addresses the honcho_context query param half of #29402 (see PR notes for the
divergence from that issue's proposed wire-through approach).
honcho_search routed through search_context() -> peer.context(search_query=),
which returns the peer's standing representation + card. The search_query arg
does not turn that endpoint into a search, so results were effectively
query-independent: the same representation blob regardless of the query. Factual
lookups ('what medication', 'which value did we pick') returned noise.
Rewire search_context() to call the workspace message-search endpoint
(Honcho.search) with a peer_perspective filter: RRF-ranked (hybrid semantic +
full-text) raw message excerpts spanning every session the peer was a member of,
across all authors, membership-time-scoped. This is the cross-session factual
recall primitive.
peer_perspective is chosen over the alternatives because it is the only scope
that is simultaneously (a) cross-session, (b) inclusive of assistant-authored
facts about the peer (peer-author search drops these, and they are a large part
of what you want to recall about yourself), and (c) privacy-scoped to the peer's
own sessions (plain workspace search leaks other peers' sessions).
- snippets are labeled by author so the model can tell user-stated facts from
assistant-derived ones
- max_tokens is now an enforced budget (was accepted but meaningless)
- graceful fallback to peer-authored search if peer_perspective is unsupported
- query length clamped under the embedding input cap
Replaces 3 change-detector tests that asserted the old representation-dump
behavior with 4 that assert the message-search contract + fallback path.
auto_title_session runs as a bare daemon-thread target. Any exception
escaping it hits the default threading excepthook and sprays a raw
traceback into the user's terminal mid-session. The canonical trigger
is the post-'hermes update' stale-module window: the function's lazy
imports read NEW source from disk while already-imported modules
(agent.portal_tags) are still the OLD cached version, producing an
ImportError that repeats on every auto-title attempt until the
long-running process restarts (seen live after 9ce0e67f2 added
set_conversation_context).
The public entrypoint now wraps the body in a catch-all that logs one
WARNING naming the likely cause ('restart the running Hermes process'),
routes the exception through the existing failure_callback channel
(user-visible warning in CLI, debug-suppressed in gateway per #23246),
and never re-raises. This also makes the function honor its own
docstring contract ('silently skips if title generation fails').
react-router v7's HashRouter wraps every route state update in
React.startTransition() by default. In React 19's concurrent renderer,
transitions are non-urgent — React can yield mid-render and come back
later. When the app is under load (streaming token deltas, gateway
events, store updates from active sessions), those higher-priority
updates keep interrupting the transition, starving the route change commit.
This matches every symptom of the session-switch lag:
- Main thread is free (animations run, clicks work) — startTransition
defers, it does not block
- navigate() does not take effect for seconds — the transition keeps
getting interrupted by higher-priority updates
- Worse under load — more concurrent re-renders = more interruptions
- The whole UI (sidebar + main pane) does not update — the entire route
change is one transition, so nothing commits until it finishes
Pass useTransitions={false} to HashRouter so route state updates are
synchronous at default React priority instead of deferred transition
priority. navigate() now commits and paints immediately.
See: react-router v7 chunk-BIP66BKV.js HashRouter implementation.
Add the flag-gated compute-host supervisor, delta/control protocol, PPID orphan guard, inline fail-open path, synthetic GIL-heavy turn seam, and AC-4 certify harness.
Verified on current origin/main: 343 focused tests pass; Ruff and diff checks pass; 360s AC-4 run with six heavy lanes passes at 6.11ms serving p99 with zero stalls and valid load.
Co-authored-by: Kyzcreig <9063726+Kyzcreig@users.noreply.github.com>
Reassert the persisted webContents zoom after BrowserWindow moved, covering Windows monitor transitions where Chromium recalculates display scaling and drops the user-selected zoom.
Rebased onto current main, where the electron test harness migrated from
node:test to vitest (test:desktop:platforms = `vitest run --project electron`,
auto-discovering electron/*.test.ts). Swap the node:test import for vitest and
drop the .ts-extension import hack; the obsolete package.json node --test list
edit is dropped in the cherry-pick resolution since vitest auto-discovers.
Co-authored-by: Gille <4317663+helix4u@users.noreply.github.com>
Bare /reasoning and /fast now render a native one-tap picker on
picker-capable platforms, with automatic fallback to the text status
card everywhere else — parity with the /model picker UX.
- gateway/slash_commands.py: generic send_choice_picker capability gate
(detected on the adapter type, like send_model_picker); selection and
typed arguments flow through one shared application path so they can
never diverge; choices built from VALID_REASONING_EFFORTS so future
levels appear automatically
- telegram: flat inline-keyboard picker (cp:<idx> callbacks), authorized
users only (same gate as approval buttons)
- discord: ChoicePickerView select menu, auth mirrors ExecApprovalView,
2-minute timeout with expiry edit
- matrix: reaction-based picker; reaction set extended to 12 slots to
fit the full effort ladder + subcommands
- locales: picker_title + choice labels in all 16 languages
- docs: ADDING_A_PLATFORM.md capability table
Closes#61110.
selectModel in use-model-controls captured activeSessionId as a closure
prop, but the actions bag in wiring.tsx mutates in place to keep a stable
identity for memoized surfaces. The modelMenuContent useMemo captures
selectModel once when the gateway first opens (before any session is
active) and never re-evaluates, so clicking a model in an existing thread
goes through a stale closure with activeSessionId=null — the pick is
treated as UI-only, config.set is never sent, and the next session.info
event clobbers the optimistic update back to the session's real model.
Drop the activeSessionId prop entirely. All three callbacks now read
$activeSessionId.get() live from the store, matching the pattern
refreshCurrentModel already followed. This is the correct contract for
the actions bag's in-place mutation: callbacks read live state from the
store, not from captured props.
The salvaged choices list predates the max/ultra effort levels (#62650);
add them so the Discord dropdown matches the canonical ladder. Discord
caps choices at 25 — we're at 11, plenty of headroom.
The Discord /reasoning command declared a single free-text `effort`
parameter, so the native UI funneled every invocation into that one box
and never surfaced the reset / show / hide subcommands the gateway
handler already supports. Replace the free-text param with an explicit
choices dropdown covering the effort levels plus reset/show/hide,
mirroring the existing /tokens and /voice commands. --global persistence
stays reachable by typing the command as plain text.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
terminal_tool reads all settings from TERMINAL_* env vars, bridged from
config.yaml by the CLI, gateway, and TUI-PTY launchers. Processes that
skip every launcher bridge — hermes serve / the Desktop app backend's
in-process agents, the desktop cron ticker — saw an unset TERMINAL_ENV
and silently ran every command on the host even when config.yaml selects
terminal.backend: docker. A user who configured Docker isolation got
unsandboxed host execution with no warning.
Two layers:
- _ensure_terminal_env_bridged() in _get_env_config(): when TERMINAL_ENV
is unset, backfill TERMINAL_* from config.yaml via
apply_terminal_config_to_env(override=False). Explicit env always wins
(honor explicit choice; only fix the accidental fallback). One-shot,
fail-open to the historical local default.
- cmd_dashboard/serve: run the same bridge at startup so every consumer
in the backend process (in-process agents, desktop cron ticker,
tui_gateway cwd resolution) sees the bridged env directly.
Fixes#63141, #54449, #61115, #65696.
hermes update ran TWO separate pre-update backup mechanisms: the
config-gated full zip (updates.pre_update_backup, default off) and an
unconditional quick state snapshot added for #15733 that ignored the
user's setting entirely. On a large state.db (observed: 24 GB) the
'cheap' snapshot silently added ~60s to every update and ate 24 GB of
disk in state-snapshots/.
Now there is ONE mechanism, gated by updates.pre_update_backup with
three modes:
- quick (new default): state snapshot of critical small files (pairing
JSONs, cron jobs, config, auth, per-profile DBs). Files over 1 GiB
are skipped with a warning so a bloated state.db can never stall the
update again.
- full: the quick snapshot plus the HERMES_HOME zip (old 'true'
behavior; --backup forces it for one run).
- off: nothing runs — an explicit opt-out now disables the quick
snapshot too (--no-backup does the same per-run).
Legacy booleans are honored: true -> full, false -> off.
_run_pre_update_backup() now returns the quick-snapshot id so the
post-update cron-jobs restore safety net (#34600) keeps working; the
snapshot moved from the post-fetch site to the pre-mutation site,
which also covers the zip-fallback update path it previously missed.
Add current-main regression coverage for both the registered provider
profile and core GitHub Responses path while leaving live catalog loading
to the complementary catalog-resolution work in #51953.
The Copilot provider profile unconditionally mapped ``xhigh`` to ``high`` before
checking the model's catalog, so models that DO support ``xhigh`` (e.g. the
gpt-5.x family per the live /models catalog) were silently capped one level
down.
Honor the requested effort when the catalog lists it as supported, and only
downgrade when it does not, choosing the nearest weaker supported level
(xhigh->high, minimal->low, else medium, else the first supported level). This
matches the nearest-down clamp behavior used elsewhere for the ``max`` effort.
Adds tests/plugins/model_providers/test_copilot_profile.py covering forward,
downgrade, and fallback paths (catalog lookup stubbed).
The current code unconditionally downgrades 'xhigh' to 'high' whenever
'high' is in supported_efforts, even if 'xhigh' is also supported.
This prevents users from using extended thinking on providers like
Copilot that list 'xhigh' in their supported efforts.
Fix: only downgrade 'xhigh' to 'high' when 'xhigh' is NOT in the
provider's supported efforts list.
The desktop self-update rebuild (`hermes desktop --build-only`, driven by
the macOS in-app updater) runs `_run_npm_install_deterministic`, which used
plain `npm ci` / `npm install`. Those honor an inherited
`NODE_ENV=production` (or npm `omit=dev`) and silently omit devDependencies.
The desktop build toolchain — tsc, vite, electron-builder — are all
devDependencies, so under `NODE_ENV=production` the install completes (exit 0)
but `tsc` is never placed, and the very next step (`tsc -b && vite build`)
dies with `tsc: command not found` (exit 127). The user sees
"UPDATE DIDN'T FINISH / Rebuilding the desktop app failed (exit 127)" even
though the git/pip update applied cleanly. NODE_ENV=production can leak in
from a shell profile, a parent process, or a packaged-app launch context.
Force `--include=dev` on both the `npm ci` and `npm install` paths. The only
callers are frontend builds (desktop / TUI / web), which always need the dev
toolchain, so this is safe across the board.
Verified empirically: under NODE_ENV=production, `npm ci` leaves tsc MISSING
while `npm ci --include=dev` installs it. Added two regression tests
(test_npm_ci_forces_include_dev, test_npm_install_fallback_forces_include_dev)
— both confirmed to FAIL when the fix is reverted.
When no agent is active, '/queue <prompt>' previously fell through
dispatch with its raw text intact instead of being treated as a
normal prompt. Rewrite event.text to the bare payload (mirroring the
/steer no-active-agent path just below) and return a usage hint when
the payload is empty.
Salvaged from PR #29290 (queue half only — the /footer mid-run
dispatch half already landed on main via #65521).
Three follow-up fixes to the salvaged reasoning_effort support, all verified
live against ollama.com /v1/chat/completions + /api/show on deepseek-v4-pro,
gemma3, and qwen3-coder:
1. Capability-gate on /api/show 'thinking'. The original ignored the
supports_reasoning flag and emitted reasoning_effort for every model. Now
gated: only models whose native /api/show capabilities list contains
'thinking' (deepseek-v4 yes; gemma3 / qwen3-coder no) get reasoning_effort.
Mirrors the LM Studio pattern — capability resolved once per (model,
base_url) in run_agent._supports_reasoning_extra_body via a cached probe
(hermes_cli.models.ollama_model_supports_thinking), threaded into the
profile hook as supports_reasoning. No live HTTP in the per-request path.
2. Disable actually disables. Ollama Cloud defaults to thinking ON and IGNORES
the extra_body.thinking:{type:disabled} shape (verified: still returned
reasoning). The only working off switch is top-level reasoning_effort:'none'.
The salvaged code returned ({}, {}) for enabled:false / effort:none, leaving
thinking ON. Now emits {'reasoning_effort': 'none'}.
3. Omit unrecognized effort. The original forwarded any unknown string verbatim
including 'minimal' (a real Hermes effort level). Ollama Cloud rejects
unrecognized values with a hard HTTP 400 (accepted set: low/medium/high/
max/none), so forwarding 'minimal' would break the request. Now omitted.
Core touches (run_agent.py, hermes_cli/models.py) add the capability probe;
the plugin profile only consumes the resolved flag. 24/24 profile tests green;
194 provider/transport tests unaffected.
LM Studio's request vocabulary tops out at "xhigh", but Hermes' generic
effort ladder has since grown two stronger levels. "max" and "ultra" miss
the _LM_VALID_EFFORTS membership test, keep the initialized "medium"
default, and are thereby conflated with unparseable input -- so asking for
more reasoning yields less than "xhigh":
high -> 'high' xhigh -> 'xhigh'
max -> 'medium' ultra -> 'medium'
This is drift, not a design choice. The valid set was an exact mirror of
VALID_REASONING_EFFORTS when the file was authored; the ladder then grew
"max" and later "ultra", and the sweep that taught every other provider
about the new levels missed this module -- it has never been touched since
it was written.
Clamp the two stronger levels onto LM Studio's declared ceiling instead,
mirroring the ceiling clamp every other provider already applies. Widening
_LM_VALID_EFFORTS would instead assert that LM Studio accepts "max" on the
wire, which is a provider-side claim this repo cannot verify; clamping
consumes only the ceiling the file already declares for itself.
The clamp is kept separate from _LM_EFFORT_ALIASES because that mapping is
also applied to the model's published allowed_options, which must not be
rewritten. A clamped value stays subject to the allowed_options check, so a
model that does not publish "xhigh" still gets the field omitted and falls
back to its own default -- exactly how a directly-requested "xhigh" behaves.
The regression test asserts monotonicity over the canonical ladder rather
than the two values alone, so the next level added upstream cannot silently
reintroduce the inversion.
Replaces the salvaged tests' dict-config path (which required a
GatewayRunner.__init__ dict-coercion hack — dropped from this salvage;
the second commit on the PR branch existed only to support it) with the
established bare-runner test pattern. Also asserts full argument
passthrough to the inner task.
When multiplex_profiles is true, background tasks spawned by /background
command failed with UnscopedSecretError because _resolve_session_agent_runtime()
was called without a profile secret scope. This fix wraps the task in
_profile_runtime_scope, mirroring the pattern used by _run_agent.
Fixes#60726
PR #36019 documented the attachment tools in the kanban-worker skill,
but main removed that skill in #50473 and folded its content into the
KANBAN_GUIDANCE prompt block. Land the same guidance there instead so
every dispatcher-spawned worker sees it.
_download_url_with_cap called urlopen() after only a scheme check, so a
model-controlled URL could reach loopback services, RFC1918/CGNAT hosts,
or cloud metadata endpoints (169.254.169.254), and a public host could
302 to any of those unvalidated.
Route the fetch through the repo's canonical SSRF guard instead:
validate every hop with tools.url_safety.is_safe_url() and follow
redirects manually (httpx, follow_redirects=False, 5-hop limit) so each
Location target is re-checked before it is fetched — the same pattern
as tools/skills_hub._guarded_http_get. The streaming size cap is
unchanged. Local-fixture tests opt in via HERMES_ALLOW_PRIVATE_URLS
(the guard's documented escape hatch); new tests pin rejection of
loopback, cloud-metadata, and private-range URLs, a mocked
public→loopback redirect, and a mocked public happy path.
The salvaged attachment-toolset commit predated main centralizing the
25 MB cap as kanban_db.KANBAN_ATTACHMENT_MAX_BYTES and re-introduced a
private _MAX_ATTACHMENT_BYTES alias. Drop the duplicate: kanban_db's
store_attachment_bytes(), the dashboard upload endpoint, and the
kanban_attach_url tool all reference the one shared constant now, and
the tests monkeypatch that same name.
The kanban board has had full attachment storage and a dashboard HTTP
API (upload/list/download/delete) since #35338, but there was no agent
toolset tool and no `hermes kanban` CLI verb for attachments. Agents and
scripts that don't go through the dashboard server (or can't touch the DB
directly) had no way to create or read real attachments — only links in
comments.
Close that gap by mirroring the existing comment surface:
- `kanban_db.store_attachment_bytes()` — one shared write path (validate
name, enforce the 25 MB cap, write the blob under the per-task dir with
collision-free naming, insert the metadata row, clean up an orphan blob
if the insert fails). `_MAX_ATTACHMENT_BYTES`, `_safe_attachment_name`,
and a new `_collision_free_path` move here so the dashboard, the tool,
and the CLI all share one implementation and can't drift.
- Tools (`tools/kanban_tools.py`): `kanban_attach` (inline base64),
`kanban_attach_url` (server-side http/https fetch with the same cap),
`kanban_attachments` (list). Write tools respect worker task-ownership;
list is read-only. Registered in the `kanban` toolset.
- CLI (`hermes_cli/kanban.py`): `attach <id> <path>`, `attachments <id>`,
`attach-rm <attachment_id>`.
- Dashboard `upload_task_attachment` now imports the shared helpers and
uses `_collision_free_path` — behavior identical (still streams to disk
with the cap, still 413 on overflow).
- Docs (AGENTS.md, kanban-worker skill) and toolset membership updated.
Tests: tool round-trip + oversize + bad base64 + ownership; attach_url
against a local HTTP fixture incl. oversize-mid-stream and non-http
scheme rejection; CLI attach/attachments/attach-rm; shared-helper unit
tests; dashboard parity preserved.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The platform callback verifier can do blocking network I/O (e.g. the
google-chat adapter fetches Google signing certs on a cache miss), which
would stall the event loop if called inline. Run sync verifiers via
asyncio.to_thread (await coroutine verifiers directly), and treat a
crashing verifier as a 401 rather than a 500 through the dispatch path —
a broken verifier must never admit an event.
DeepSeek's own API (api.deepseek.com) reports context-cache hits as
top-level usage.prompt_cache_hit_tokens / prompt_cache_miss_tokens
(prompt_tokens = hit + miss), not the OpenAI nested
prompt_tokens_details.cached_tokens shape. Neither normalize_usage()
nor the chat_completions transport's extract_cache_stats() read those
fields, so direct DeepSeek sessions always showed 0 cache-hit tokens:
invisible in accounting, mis-billed at the full input rate, and 0%
cache display.
Both layers now fall back to prompt_cache_hit_tokens when the nested
shape is absent; the nested value wins when both are present (proxies).
Fixes#61871.
Server-side coverage for the critical-CSS shim (PR #36024 salvage):
- user theme → style block emitted with ONLY real bundle variable names
(--background-base/--midground-base from layerVars(),
--theme-font-sans/--theme-base-size from typographyVars()/index.css),
and an html,body rule expressed via those vars so runtime theme
switches never leave a stale canvas/font
- built-in / unknown / non-string active theme → no block
- malformed theme YAML and load_config() exceptions → no crash, index
still serves
- </style> breakout attempt in a theme value stays escaped
- mount_spa integration: block present in <head> for user themes,
absent for built-ins
Review fixes for the inline critical-CSS bootstrap (PR #36024):
1. Variable names now match what the bundle actually consumes.
--color-background, --color-midground, --font-sans and
--font-base-size appear nowhere in web/src; the real tokens are:
--background-base / --midground-base (layerVars(), context.tsx)
--theme-font-sans / --theme-base-size (typographyVars(), and
index.css html{font-family:var(--theme-font-sans);
font-size:var(--theme-base-size)})
2. Stale-rule bug: the injected html,body rule previously baked in
literal hex/font values. Because the <style> block sits after the
bundle's <link> at equal specificity and is never removed, switching
themes in the picker left the old canvas/font until reload. The rule
now references the same CSS variables instead of literals —
applyTheme() writes those vars as inline styles on documentElement,
which outrank this block in the cascade, so runtime theme switches
re-resolve the rule automatically. No frontend change needed.
