TCC keys permission grants to the app's code-signing requirement. Grants
made to pre-#73681 builds carry a cdhash-pinned requirement that no
longer matches the rebuilt bundle, so macOS re-prompts on every capture
even though the System Settings toggle shows ON — and the modern prompt
has no Allow button, so users cannot complete the one-time re-grant.
- hermes doctor: new check_macos_tcc_grants() reports the desktop
bundle's DR class (cdhash-pinned → grants reset on every update;
identifier-pinned → stable) and prints the exact stale-grant repair
(tccutil reset, toggle ON, fully quit & relaunch).
- hermes update: after a successful update on macOS with a desktop app
installed, print the one-line stale-grant guidance.
- docs: desktop.md no longer claims grants persist 'out of the box';
documents the one-time re-grant for pre-fix grants.
Closes#86385
Background processes started by subagents (task_id sa-*) route their
notify_on_complete / watch_pattern notifications to the parent
conversation (b95ec1cb5) because anything outliving the child needs a
durable consumer. In practice these 'npm ci finished' walls are noise
mid-conversation — the child's consolidated delegation result is the
deliverable.
- New config key delegation.surface_child_process_notifications
(default false = suppress). Flag true restores the previous behavior
exactly (delivery with subagent attribution line).
- drain_notifications drops (never requeues) completion/watch_match/
watch_disabled events whose task_id starts with 'sa-' when the flag
is false, logging at debug with session_id+task_id for diagnosis.
Requeueing would pin them forever — children never drain notifies.
- async_delegation events are NEVER suppressed (they ARE the result).
- watch_disabled emitters now carry task_id so sa- sessions' safety
events follow the same suppression as their other events.
- Config read errors fall back to the default (suppress) and never
crash the drain loop.
- Docs: delegation.md + configuration.md.
tool_search now takes queries: string[] (searched independently against
the same catalog, limit applies per query, default 5 / max 25) and
returns the split shape: per-query groups carry tool names only, one
shared tools map holds each matched tool's source, description (400-char
cap) and required parameter names once. When some queries miss, a single
top-level available_sources + hint block replaces the old per-response
fallback.
tool_describe now takes names: string[] and returns a map keyed by name;
unknown names collect in not_found (with the refresh hint) and
non-deferrable names keep their per-name spelling-check error in errors,
so one bad name no longer fails the whole call. Duplicates dedupe
silently.
The shared tokenizer now applies Snowball stemming (english, exact-pinned
snowballstemmer) at both index and query time, closing the measured
plural/singular miss where 'issues' failed to return create_issue. The
inline BM25 is unchanged. Stemmer instances are thread-local (they carry
mutable parse state and bridge dispatch can run on parallel tool-call
threads).
New config knobs under tools.tool_search: max_queries / max_describe_names
(default 10 each, floor 1, no upper clamp) bound the per-call array
inputs; over-cap calls error so the model repairs in one round-trip.
No backward compatibility with the single query/name shapes, by decision.
scripts/analyze_livetest.py renders both shapes since transcripts on disk
may predate this change.
Fixes the two live E2E blockers @ctaylor86 found on PR #77189 (macOS 26.3.1,
OpenSSL 3.6.3):
- retry the PKCS#12 export with -legacy when security import rejects the
OpenSSL 3 default format ('MAC verification failed during PKCS12 import')
- trust the self-signed root for the codeSign policy (security
add-trusted-cert -r trustRoot -p codeSign) — an imported-but-untrusted cert
is invisible to find-identity -v and unusable by codesign
- gate success on find-identity -v -p codesigning (postcondition), and use
the same -v probe for idempotency so an untrusted leftover cert is repaired
instead of reported as done
Tests rewritten as stateful fakes (valid only after import+trust), plus new
coverage for the -legacy retry, trust failure, postcondition gate, and the
untrusted-cert repair path; sabotage-verified (reverting to the name-in-output
probe fails 4 tests). Docs: manual fallback now includes the Trust step.
Adds a one-shot `hermes desktop --setup-tcc-identity` command that creates a
self-signed code-signing certificate in the login keychain (openssl +
security import), grants codesign access to it, writes
desktop.macos_signing_identity to config.yaml, and re-signs the packaged app
with a certificate-anchored Designated Requirement.
macOS persists permission grants (Full Disk Access, Accessibility, Files and
Folders, microphone) against the app's code-signing identity, not its path.
The default identifier-pinned ad-hoc signature is stable across rebuilds, but
a certificate-anchored identity is the strongest guarantee — the same
mechanism yabai/skhd rely on. Previously users had to create the certificate
manually in Keychain Access; this command automates the whole flow and is
idempotent (re-run after updates).
Docs: desktop.md TCC section now leads with the command, keeps manual steps.
Tests: 4 new — fresh cert creation path, idempotent reuse, non-macOS no-op,
cmd_gui early-exit before build.
Four fixes to the tool-search deferral layer, split from PR #92693 (the
availability-cache staleness fix ships separately):
1. The parallel batch planner now peels the tool_call bridge wrapper and
decides admission on the underlying tool — supports_parallel_tool_calls
works again when deferral is active. Unparseable wrappers stay
sequential barriers; bridged calls get exactly the admission the same
call gets direct. tool_search/tool_describe lookups batch concurrently.
2. _short_desc no longer truncates listing lines at 'e.g.', hostnames, or
version strings — a sentence terminator must be followed by whitespace.
3. BM25 indexes the source label (e.g. 'linear' for mcp-linear), so
service-name queries reach tools whose own name omits the service; the
dead 'mcp' prefix token is stripped.
4. Substring-fallback docstring corrected (token misses, not zero-IDF).
Salvaged from #92693 by @alt-glitch with authorship preserved.
Electron safeStorage parks a per-app key ('Hermes Key') in the macOS login
keychain; on machines with a locked/missing/corrupted default keychain that
turned every Hermes Desktop launch into a blocking 'Keychain Not Found' /
password dialog. Keychain-backed encryption is now an explicit opt-in:
- electron/secret-storage-policy.ts: standalone policy seam (default OFF,
strict === true coercion, one-shot migration flag) + unit tests
- default path never calls any safeStorage API (including
isEncryptionAvailable, which itself touches the keychain)
- one-shot legacy migration decrypts existing safeStorage blobs to plain
0600 files at first launch; undecryptable blobs are kept but read as
absent afterward (classify 'drop') so a dead keychain prompts at most once
- Settings -> Gateway toggle (all 5 locales) re-encodes every stored secret
store in place when flipped (v1 connection.json, v2 connections.json,
native-oauth-tokens.json)
- e2e: at-rest spec now covers both postures (opted-in unchanged contract,
default saves without secure storage, owner-only bits, restart round-trip)
- docs: multi-connection-desktop + desktop-native-signin updated
* feat(cron): durable failure incidents with signature dedup and ack
Introduce a durable cron incident store (cron_incidents in the shared
cron/executions.db) that groups "same job + same error signature" across
runs, so a known recurring failure stops re-pinging the operator every run
once it has been acknowledged.
- cron/incidents.py: lazily-created incident table (detected -> alerted ->
reviewed -> closed lifecycle; closed is per-signature terminal), sha256
signature dedup over job_id + normalized error, redacted/truncated error
storage, failure-type classification, and ack/list/get/count helpers.
- cron/scheduler.py: record an incident on the failure delivery path and
suppress the per-run failure ping when the exact signature is acked (both
the normal failure path and the processing-raised retry path). Best-effort:
an incident-store error never breaks the cron run or delivery. Streak nudge,
alert-once markers, and delivery-error behavior are untouched.
- hermes_cli: add `hermes cron incidents [--state ...]` and
`hermes cron incidents ack <id>`.
- tests/cron/test_cron_incidents.py: dedup, lifecycle, redaction,
classification, lazy-schema, scheduler gating, and CLI coverage.
Non-goals deferred to later slices: Discord buttons/review view, HMAC action
tokens, owner-agent review launch, approval-gated fixes, incident playbooks.
* refactor(cron): tighten incident lifecycle, wire alerted state and suppressed_acked outcome
Follow-ups on top of the salvaged #94692:
- Drop the dead 'reviewed' state and the SQLite CHECK (state validity
lives in INCIDENT_STATES so future slices can add states without a
table rebuild); lifecycle is detected -> alerted -> closed.
- Actually mark incidents 'alerted' after a failure ping reaches
delivery, on both the normal and exception delivery paths.
- Record ack-suppressed runs with a distinct 'suppressed_acked'
delivery outcome (registered in cron_health monitoring) instead of
the ambiguous generic 'suppressed'.
- Drift-skip alerts explicitly bypass the ack gate (they carry the
remediation command and alert once via drift_alerted already).
- Docs: failure-incidents section in the cron guide.
- Tests for the alerted transition + never-resurrect-closed.
---------
Co-authored-by: Laura López Real <113060513+laulopezreal@users.noreply.github.com>
Sites under active development but tested over the public internet
(Vercel previews, ngrok tunnels, staging domains) are public DNS, so
the local-dev never-cache rule can't catch them. web.cache_exempt_hosts
lists hosts whose pages are always fetched live: exact, "*.wildcard",
or domain-suffix matching (label-boundary aware — mysite.dev covers
preview.mysite.dev but never evilmysite.dev). Checked on both store
and lookup, so adding an exemption takes effect immediately even for
entries cached before the config change.
Dev servers, hot-reload builds, and chat-GUI artifact previews live on
localhost/private addresses and change on every save — a 20-minute
cached copy would show a stale build exactly when freshness is the
point of fetching. The extract cache now declines loopback, private,
link-local, *.local, *.localhost, and single-label LAN hostnames on
both put and get. Hostname heuristics only (no DNS) — this is a
freshness carveout, not a security boundary; SSRF enforcement is
unchanged in tools/url_safety.py.
Public URLs keep the full TTL.
Review fixes for #94618 (all three blockers reproduced by the reviewer
through the real web_extract_tool):
1. Cache lookup moved AFTER provider resolution and strict-selection
validation, and gated per-URL on the website blocklist policy — a
blocklist-blocked or misconfigured-backend call now behaves exactly
as it would without a cache instead of serving cached content.
2. Rescue-served extract batches are never cached (mirrors the search
memo's exclusion), keeping one-shot rescue one-shot.
3. Cache entries now get dedicated per-(url, format, provider) files
instead of sharing the URL-keyed truncate-store file — html and
markdown (or two backends') copies of one URL no longer overwrite
each other, and switching extract backends within the TTL never
serves the old backend's rendering.
Also from review: per-process index tmp filename (cross-process writers
can no longer truncate each other mid-write) and held flight locks are
never evicted from the bounded lock table (eviction could have allowed
a duplicate paid request).
New regression tests for formats/provider keying; E2E harness extended
with policy-block, strict-selection, rescue-two-call, and dual-format
scenarios — 6/6 pass; original 13/13 still pass.
Repeat searches (same normalized query + provider) within a 20-minute
TTL are served from an in-process memo, and concurrent identical
queries are single-flighted so a parallel subagent fan-out pays for
one vendor request instead of N. Requested limits bucket up to
10/20/50/100 so near-identical requests share an entry; callers get
their requested count sliced from the bucket.
Repeat extracts of the same URL are served from the existing
cache/web full-text store (previously written for read_file paging
but never read back), via a small JSON sidecar index. Disk-backed, so
CLI, gateway, cron, and subagents share it. Cached extracts re-run
the normal truncate pipeline, so per-call char_limit still works.
Both caches sit after every safety gate (secret-URL, SSRF, policy,
provider resolution) and directly around the paid vendor call — hits
skip only the network request. Only successful responses cache;
rescue-served responses are never cached (one-shot rescue must stay
one-shot). Config: web.cache_enabled (default on),
web.cache_ttl_minutes (default 20, clamped 1-1440).
Idea credit: query coalescing + num-bucketing pattern observed in
Apodex FrontierAgent (Apache-2.0).
The cloudflare entry's 3,320-endpoint surface is ~43% product families a
personal/dev account never touches (Zero Trust org-fleet suite, Magic
Transit/WAN, Cloudforce One, Radar analytics, API Shield, legacy
migration surfaces). Ship a 34-pattern curated exclude list in the
manifest: 3,320 -> 1,905 tools kept, and everything Cloudflare adds
later stays enabled by default.
Mechanism, two small extensions:
- tools/mcp_tool.py: tools.include/exclude entries containing glob
metacharacters now match via fnmatch (plain names stay exact-match),
so a product family is one pattern instead of hundreds of stale
literals.
- hermes_cli/mcp_catalog.py: manifests may declare
tools.default_excluded (mutually exclusive with default_enabled);
install writes it to tools.exclude and skips the probe/checklist —
a 3,320-row curses checklist is not a UX. Prior user include
selections still win on reinstall.
Verified by replaying the real filter functions over the live-probed
3,320-tool list: 1,415 excluded, zero overmatch against a per-product
target audit; DNS/Workers/R2/D1/tunnels/Access/AI kept.
Adds optional-mcps/cloudflare — Cloudflare's managed remote MCP server
(mcp.cloudflare.com/mcp) fronting the entire Cloudflare API (2,500+
endpoints across DNS, Workers, R2, KV, D1, Zero Trust, WAF, Pages)
through two Code Mode tools, search() and execute(), at a fixed ~1k-token
schema footprint. HTTP transport + native MCP OAuth 2.1 with DCR — no
install block, nothing to pin. post_install documents the scoped OAuth
grant, the bearer-token path for headless/CI, and Cloudflare's
product-specific servers for narrower surfaces.
Docs: mention Cloudflare in the hosted-OAuth MCP examples.
Review finding on #94633: _sanitize_label_value is lossy ('team/workspace'
and 'team_workspace' both sanitize to 'team_workspace'; >63-char keys
truncate identically), and container reuse is label-keyed — so two teams
with DIFFERENT shared keys could silently attach to one running container
(filesystem, processes, env) while their host sandboxes stayed separate.
Shared-key labels now carry a sha256 digest suffix of the raw key
(deterministic across processes; plain profile labels unchanged for
backward compat). Docs also state the first-creator-wins rule for image/
mounts on a shared container. Adds adversarial collision tests.
Independent review caught a compaction authority the gate missed:
post-turn micro-compaction (turn_finalizer -> _micro_compact) absorbs the
oldest exchanges into a rolling summary with no pre-compress checkpoint
hook in its path, and both compression.checkpoint_required and
compression.micro_compact could be enabled together — assistant evidence
could vanish into a summary the checkpoint filter later excludes, without
ever reaching the durable provider.
- agent_init: checkpoint_required forces micro-compaction off (warned),
mirroring the native-compaction suppression
- turn_finalizer: defense-in-depth guard at the call site (attribute is
plain mutable state a future path could flip on a live agent)
- behavioral regression test with a sabotage control (gate off proves the
harness reaches the call site; gate armed proves zero calls)
- docs + config example mention the suppression; stale v1 test header fixed
Per review: existing providers should not be retroactively re-versioned or
handed a changed payload. Version 1 is now the implicit historical
on_pre_compress() contract (best-effort, raw message list) that every
pre-existing provider is already on; the fail-closed checkpoint contract
becomes version 2. MemoryManager routes the raw transcript to v1 providers
unchanged and hands the host-normalized evidence list only to v2+ checkpoint
providers, so the plugin surface contract for shipped providers is
byte-identical with the gate off.
The fail-closed gate lived only in compress_context(), but two native
lossy owners compact without ever crossing it (review on #93996):
- codex app-server: in "native"/"off" auto-compaction mode (native is the
default) Hermes preflight is skipped and the codex agent compacts its
own thread inside run_turn() — the compress_context() rejection was
unreachable. init_agent now refuses checkpoint_required together with
api_mode=codex_app_server (BLOCKED_MISSING_PREREQUISITE, extracted as a
testable guard), and run_codex_app_server_turn() fails closed as
defense in depth before a turn can reach the codex-owned boundary.
- Responses server-side native compaction:
native_compaction_context_management() now returns None while the gate
is armed, so context_management never goes on the wire and the
checkpoint-aware Hermes compressor stays authoritative. The suppression
is logged once per process, not silently applied.
Regressions: checkpoint_required + app-server raises before run_turn()
(the session is never created); checkpoint_required keeps
context_management off the wire while the plain configuration still
produces it; the init guard refuses exactly the incompatible pair. Docs
and cli-config.yaml.example describe both bindings.
Refs #93986
Addresses the review on #93996:
- gateway: hygiene and manual /compress load the memory provider only when
compression.checkpoint_required is enabled (skip_memory=not required).
The historical fast path — no provider init, no best-effort hook — is
back for everyone who did not opt in, so default behavior is truly
unchanged.
- conversation_compression: assistant messages carrying both prose and
tool_calls keep their prose in the checkpoint evidence (the tool_calls
payload is stripped, the original message is not mutated); pure
tool-call wrappers without prose are still dropped.
- tests: legacy-database regression proving the _compressed_summary column
is added by the declarative _reconcile_columns() path on a plain reopen
(no version-gated migration needed — append_message works right after),
plus coverage for the prose-preserving filter.
- docs: providers must implement idempotent, content-keyed checkpoint
writes — a fail-closed block means the next attempt re-runs
on_pre_compress over largely the same transcript.
Refs #93986
Adds a 'Pre-Compress Checkpoints (fail-closed)' section to the memory
provider plugin guide: the versioned opt-in attribute, the operator-side
compression.checkpoint_required gate, fail-closed semantics, and the
normalized evidence contract including the persistent summary marker.
Refs #93986
Full-screen captures carry no element tree, so the CaptureResult now has a
'note' field surfaced in the tool summary telling the model to call
capture(app='<AppName>') or capture(app='desktop') when it needs to act on
what it sees. Schema description updated to distinguish app='screen'
(composited full-screen image) from app='desktop' (shell surface with
clickable elements); docs + regression tests (14, sabotage-verified) added.
web_extract stopped using an auxiliary LLM long ago (deterministic
truncate-and-store), but browser snapshots still routed oversized
accessibility trees through the auxiliary web_extract model, keeping a
dead-looking aux slot alive across every config/picker surface.
- tools/browser_tool.py: remove _extract_relevant_content and
_get_extraction_model; oversized snapshots always truncate at line
boundaries, store the full tree to cache/web, and append a read_file
pointer (element refs beyond the cut live in the file)
- tools/browser_camofox.py: same — no LLM path
- Remove auxiliary.web_extract slot: config_defaults (removal note, same
pattern as session_search/PR #27590), cli.py defaults + env bridge,
gateway/run.py bridged keys, hermes config display, hermes model picker,
dashboard REST slots, desktop + web AUX_TASKS, i18n labels (en/zh/
zh-hant/ja/ar)
- Docs: env-vars, configuration, fallback-providers, browser + zh-Hans
mirrors (web-search zh-Hans was stale on the old LLM pipeline — synced
to truncate-and-store truth)
- Tests updated: aux bridge uses approval slot, browser tests assert the
LLM path is gone and stored files are secret-redacted
Follow-up to lkz-de's adapter chunking commit: long Signal messages no
longer truncate on ANY delivery path.
- tools/send_message_tool.py: register Signal's 8000-char limit in
_MAX_LENGTHS (imported from the adapter module so the two paths can't
drift) so hermes send / cron standalone / MCP sends split via the
shared truncate_message() pass instead of signal-cli rejecting them.
Standalone-path idea credited to @5L-hermes01 (#67279).
- tests: regression test proving standalone Signal sends chunk at the
adapter limit with no truncation footer (fails on pre-fix main).
- docs: Long Messages section on the Signal page (en + zh-Hans).
Both fixes verified by sabotage A/B (tests fail with the respective
half reverted to origin/main) and a real-import E2E: 27k-char message
with emoji + cross-boundary bold + code blocks -> 4 chunks, all styles
in-range UTF-16, lossless reassembly.
The Dockerfile fix in #93757 only helps newly built images, and an
image upgrade (container recreate) resets the permission because
/opt/hermes lives in the image layer. The one stranded case is an old
image whose container was stopped and restarted after the lockout: it
keeps the 0700 install dir and runs code without the guard.
Document the one-line in-place recovery (chmod 0755 /opt/hermes as
root) in the Docker troubleshooting section.
Follow-up to #93757.
GSC page-level data shows configuration (171K impr, pos 5.3), quickstart
(135K, 5.3), providers (123K, 5.3), web-dashboard (68K, 6.5), docker
(37K, 6.3) and the desktop app page (98K, 3.9) all losing ranking
headroom because their title/H1 are bare nouns instead of the terms
people search.
- Frontmatter title + H1 now carry the query terms on all six pages
- Desktop docs page links back to the new marketing /desktop product
page, joining the two official properties Google sees for the query
Done by Hermes Agent (deepseek-v4-pro via nous), Nous Research.
Omarchy tiles the HUD like any other toplevel, so always-on-top and
xdg_toplevel.move never apply. Ask Hyprland to float+pin after map,
trying classic dispatch then Lua for 0.55+ configs.
A held port made 'hermes serve' print only uvicorn's bare
'ERROR: [Errno 98/10048] error while attempting to bind on address'
and exit 1 — indistinguishable from a broken backend for the desktop
spawn and wrapping scripts.
- Preflight bind probe (matching uvicorn's SO_REUSEADDR bind flags)
before uvicorn.Server; on conflict print machine-readable
'BACKEND_PORT_IN_USE port=<port>' + a human hint naming likely
holders, exit 75 (EX_TEMPFAIL — existing repo convention, see
gateway/restart.py, kanban_db.py).
- Probe-to-bind race covered: SystemExit(1) from uvicorn's own bind
failure is re-checked and translated on both POSIX and Windows
runner paths.
- --port 0 (ephemeral) short-circuits the probe: unchanged behavior.
- HERMES_BACKEND_READY contract untouched.
- Tests: real held-socket repro (sentinel + exit 75, sabotage-proven
to fail as bare exit 1 without the fix), free-port boot regression,
ephemeral-port regression, probe/classification units.
- Docs: port-conflict paragraph under 'hermes serve' in
reference/cli-commands.md.
The desktop pools per-profile backends and reaps them after ~10 idle minutes; a reaped profile took its cron ticker with it, so its jobs silently stopped until the user next opened that profile. The primary desktop backend (which outlives the pool) now ticks every local profile store, same as a multiplex gateway (#69377 desktop sibling). External cron providers keep single-store semantics (registries are not profile-scoped); enumeration failure fails open to the active profile. Per-store .tick.lock still dedupes against live pool backends.
Apply explicit per-model prompt_caching capabilities to custom
chat-completions routes, rather than limiting them to recognized providers,
hosts, or model families.
Keep undeclared routes conservative, derive the marker layout from the wire
transport, and leave Responses and Bedrock caching paths unchanged.
message_agent callers previously got provider prose (a raw 401
paragraph, a missing-provider essay) and could not branch on the
failure class. Now the #93091 item-1 reason enum rides the whole relay
roundtrip:
- Desktop relay drain forwards bot_relay.deliver's error.data.reason
into bot_relay.reply (and prefers it for the attention badge over
free-text re-parsing);
- write_reply already persisted reason / classified fallbacks;
- the sender-side waiter prints "[reason: <code>]" ahead of the free
text, so the completion notification the sending agent receives is
machine-branchable.
Additive everywhere: healthy replies unchanged, reasonless errors
classify to a code, old consumers keep working.
Maintainer ruling (2026-08-23): a retried bot turn never mints a fresh
session. retry_action() maps the #93091 item-1 reason enum to one of
resume / compress_then_resume / none:
- transient classes (runtime_offline, delivery_timeout, rate limit,
server error) re-run the same Bot Chat session once;
- context_overflow also re-runs the same session — the retried turn
goes through the pre-API compaction pass in conversation_loop.py,
which compacts the over-threshold transcript first (the one
sanctioned context mutation); no fresh-session escape hatch exists;
- auth/quota/config/model classes never auto-retry.
Wired at both delivery surfaces (fix the class, not one site):
bot_relay.deliver (relay handler) and _run_delivery (local
message_agent runner). Failed deliveries now carry the classified
reason in the structured error payload (error.data.reason).
Sabotage-verified: with the retry blocks removed, 3 consumer tests
fail; with them present, 22/22 pass.
Widened from /review to the class: _build_child_system_prompt now runs
the parent's resolved workspace_path through
agent.prompt_builder.build_context_files_prompt (same discovery/
priority/caps as the main system prompt: .hermes.md > AGENTS.md chain >
CLAUDE.md > .cursorrules; SOUL.md skipped) and embeds the result as
binding conventions. All delegate_task children get it — reviewer
included — since children are built with skip_context_files=True and
previously worked in repos without the repo's own conventions.
The review-engine-local load_workspace_context duplicate is removed;
the reviewer inherits the block via the shared child prompt path.
workspace_path comes only from explicit sources (_resolve_workspace_hint
— TERMINAL_CWD / agent cwd hints, never bare getcwd), so the #64590
install-tree-fallback guard concern doesn't apply.
Tests moved to pin the generalized path (real-filesystem AGENTS.md via
_build_child_system_prompt, empty/no-workspace negatives, reviewer E2E
through start_review). Docs: subagent-context section + /review flow
(en + zh-Hans).
load_workspace_context() resolves the parent's workspace via the same
_resolve_workspace_hint used for child prompts (explicit sources only —
TERMINAL_CWD / agent cwd hints, never a bare getcwd fallback, so the
#64590 install-tree-leak guard concern doesn't apply) and runs it
through agent.prompt_builder.build_context_files_prompt — the exact
discovery/priority/cap logic the main system prompt uses (.hermes.md >
AGENTS.md chain > CLAUDE.md > .cursorrules; SOUL.md skipped). The
result is embedded in the reviewer briefing as binding review
standards. Subagents are built with skip_context_files=True, so without
this the reviewer judged repo work without the repo's own conventions.
5 new tests incl. real-filesystem AGENTS.md discovery through the real
loader. Docs updated (en + zh-Hans).
The reviewer subagent now inherits the primary agent's working skill
context: collect_parent_loaded_skills() gathers launch-preloaded skills
(from the activation notes in ephemeral_system_prompt) and mid-session
skill_view loads (from assistant tool_calls in history), deduped and
capped at 8, and the briefing instructs the reviewer to skill_view each
and treat their conventions as binding for the assessment.
Reference-file reads (file_path=...) don't count as loads; full-skill
injection was rejected as too costly (a single dev skill can be 40KB+).
Docs: delegation.md /review flow updated (en + zh-Hans).
Follow-up to the #65422 salvage:
- startup_orphan_reap joins _RECOVERABLE_END_REASONS (kept distinct from
ws_orphan_reap for forensics): every recovery fence
(find_latest_gateway_session_for_peer, unarchive_recoverable_session,
promote_to_session_reset) now treats a startup-swept row as an
accidental end, so a sweep never makes a session unresumable.
- Config key moves from sessions.orphan_reaper to
dashboard.startup_orphan_sweep in DEFAULT_CONFIG, next to its siblings
ws_ping_interval / ws_ping_timeout / ws_orphan_reap_grace_s; the raw
loader in tui_gateway.server reads the new key (fail-open on missing).
cli-config.yaml.example and website/docs/user-guide/configuration.md
follow the dashboard.* documentation pattern.
- New regression test: a stranded 'active' row (ended_at NULL, no live
runtime) is swept AND still recoverable via peer-keyed lookup and fully
revivable via reopen_session afterward.
Close session rows left ended_at IS NULL when the in-process websocket
orphan timer dies with the process (#65194). Dual-clock staleness
(started_at AND newest message), desktop included, live in-memory
sessions excluded, scheduled once from both entry.main and the WS
sidecar so desktop/dashboard boots also run the sweep.
Follow-up to #93339: the auxiliary.review slot existed in config but was
missing from every model-picker surface, so users could only set the
review model by hand-editing config.yaml.
- hermes_cli/web_server.py: review in _AUX_TASK_SLOTS (REST allowlist,
stale-aux warning sweep)
- hermes_cli/main.py: review in _AUX_TASKS (hermes model aux picker)
- apps/desktop model-settings.tsx + all 5 i18n locales (en/ja/zh/
zh-hant/ar): review slot with label/hint
- web/src/pages/ModelsPage.tsx: review row in dashboard Models page
- tests: registry-sync test pinning review across DEFAULT_CONFIG,
_AUX_TASKS, and _AUX_TASK_SLOTS (curator pattern)
- docs: aux-task table in fallback-providers.md (en) + zh-Hans mirrors
of fallback-providers and the delegation /review section missed in
#93339
