Address teknium1 review on #64189:
- Re-pull gate now delegates to each source's is_enabled(cfg) via the
registry contract, so a plugin source with custom activation logic is
honored (previously only secrets.<name>.enabled was checked).
- Add BUILTIN_SOURCE_NAMES to the registry so plugin-vs-bundled is a
single source of truth instead of a hard-coded set at the call site.
- Reconcile docs: rewrite the timing :::note to describe both the
post-discovery re-pull and the remaining import-time limitation, and
cross-link the first-process bootstrap section.
- Tests: real SecretSource subclasses, custom is_enabled activation
(positive + negative), is_enabled-raises skip, builtin-only no-op,
and a discovery-registration end-to-end re-pull check.
After plugins register SecretSource backends, reset the env-loader cache
and re-run load_hermes_dotenv when an enabled plugin secret source is
configured. Closes the first-process bootstrap gap where import-time env
load stale-outs plugin vaults (tommck / Community ask). Fail-open, no-op
without plugin sources.
Docs: first-process bootstrap timing on secret-source plugin guide.
Tests: unit coverage for noop / enabled re-pull / discover hook.
Part of #64182 plugin-interface expansion.
* fix(windows): SSH ControlMaster gating + stop hijacking the user's python
Two Windows environment-integrity fixes:
1. tools/environments/ssh.py (#73927): Windows OpenSSH has no
Unix-domain-socket ControlMaster support, so unconditionally passing
ControlPath/ControlMaster/ControlPersist failed EVERY tool call on a
Windows-hosted ssh terminal backend with 'getsockname failed: Not a
socket'. Gate the three multiplexing options behind a module-level
_SSH_MULTIPLEX = (os.name != 'nt'); the scp upload path is gated the
same way. On Windows the backend now works without connection pooling
(each command a fresh connection); POSIX behavior is unchanged. The
teardown 'ssh -O exit' is naturally inert because the socket never
exists on Windows.
2. scripts/install.ps1 (#83797): the installer put the whole
venv\Scripts directory on the user PATH, which contains python.exe /
pythonw.exe / pip.exe and so silently hijacked the 'python' command in
every terminal on the machine — unrelated projects started resolving
python to Hermes' runtime interpreter. Now copy only the launchers
(hermes.exe, hermes-acp.exe) into a dedicated $InstallDir\bin and put
THAT on PATH. Existing installs are migrated: the legacy venv\Scripts
entry is stripped from the user PATH on the next install/update. The
new bin dir is under $InstallDir (…\hermes-agent), which the uninstall
PATH sweep already matches via its \hermes-agent marker.
Updated the stale hermes_cli/update_cmd.py docstring that described the
old venv\Scripts-on-PATH layout.
Tests: SSH ControlMaster gating pinned both directions (multiplex on →
flags present; off → absent but BatchMode/StrictHostKeyChecking retained).
install.ps1 parses clean via the PowerShell AST parser.
* docs: update windows-native install docs for the bin\ launcher layout
CI (test_windows_native_docs) pins the docs and installer to the same
PATH layout. The #83797 fix moved the PATH entry from venv\Scripts to a
dedicated $InstallDir\bin holding only the hermes launchers, so update
the Windows-native guide to match: PATH-after-install section, the
install-steps list, the directory-layout table, the Get-Command
verification line, and the 'command not found' pitfall. Test now asserts
the bin\ layout and guards against a regression back to venv\Scripts on
PATH.
* fix: keep install.ps1 pure ASCII (PowerShell 5.1 codepage safety)
The two comments I added in the #83797 PATH-hijack fix used em-dashes,
tripping tests/test_install_ps1_ascii_only.py — Windows PowerShell 5.1
reads a BOM-less .ps1 in the system ANSI codepage (not UTF-8), so a
non-ASCII byte can misdecode into a stray quote and desync the parser
(issues #66994/#67000). Replace the em-dashes with ASCII '--'.
Sweep of open Windows issues affecting day-to-day agent operation
(explicitly excluding install/setup and locale classes):
- hermes_cli/_subprocess_compat.py: new split_command_line() — Windows-
safe command-line tokenizer (posix=False + quote stripping) so
backslash paths survive. POSIX behavior unchanged (plain shlex.split).
- hermes_cli/console_engine.py (#83934): console commands like
'sessions export C:\Users\me\out.jsonl' no longer silently mangle the
path into a relative filename in the cwd.
- agent/shell_hooks.py (#78293): hook commands with backslash paths now
spawn, resolve their script path, and pass hooks doctor instead of
reporting 'not executable'. All three shlex sites routed through the
shared splitter.
- agent/prompt_builder.py (#51755): system prompt now reports
Windows (11) on Windows 11 — platform.release() returns 10 for both;
distinguish via sys.getwindowsversion().build >= 22000.
- hermes_cli/commands.py (#42016): @ autocomplete no longer crashes the
prompt_toolkit event loop when rg emits a path on a different mount
(device paths \.\nul, other drive letters) — relpath ValueError is
skipped per-entry.
- tools/browser_use_cli.py (#83884): screenshot-path detection now
matches Windows drive-letter paths (C:\... and C:/...) in addition to
POSIX; Browser Use screenshots attach on Windows.
- tools/skills_hub.py + tools/skills_guard.py (#62310): the two 'MUST
stay symmetric' skill content hashes actually agree on Windows now.
Bundle keys are normalized to POSIX separators before hashing, and the
disk digest sorts by rel-posix STRING (case-sensitive) instead of Path
objects (case-insensitive on Windows). Fixes permanent false-positive
update_available for every installed skill.
Tests: tests/tools/test_windows_agent_loop_papercuts.py — 16 cases
covering each fix, including a disk-vs-bundle hash symmetry check built
with native Windows separators and a mixed-case filename.
* fix: make verify_on_stop opt-in everywhere (default False, not auto)
The verify-on-stop nudge was already judged more noise than signal: the
v31 migration flips existing installs off, the v32 migration catches the
baked-in literal-true population, and the docs tell users to 'treat off
as the effective default and opt in explicitly'. But DEFAULT_CONFIG still
shipped the "auto" sentinel, so exactly one population kept getting the
nudges: fresh installs (and any config missing the key), where "auto"
resolves ON for CLI/TUI/desktop surfaces. Live symptom: repeated
'[System: You edited code ... run verification]' interruptions the user
never asked for and had to hunt down in source to disable.
- DEFAULT_CONFIG: agent.verify_on_stop "auto" -> False (opt-in).
- verify_on_stop_enabled(): missing/unrecognized value now falls back
OFF instead of surface-aware; explicit "auto" still selects the
legacy surface-aware behavior, explicit bools unchanged, and the
HERMES_VERIFY_ON_STOP env override is untouched.
- No migration needed: v31/v32 already normalized existing installs,
and this only changes the merged default for configs without the key.
- Docs updated; default-path E2E test now asserts OFF, plus a new
missing-value regression test. Also added the standard win32 skip
marker to the symlink-based temp-dir test (pre-existing Windows
failure, same class as tests/cron/test_cron_script.py).
* test: update config goldens — verify_on_stop=False is now stripped as default
With the DEFAULT_CONFIG flip to False, the migration-write invariant
(_persist_migration / save_config strip_defaults) no longer materialises
verify_on_stop: false to disk unless the user explicitly set the key:
- V20 floor fixture (agent: {} on disk): v31's write is stripped —
agent stays {} and load_config() supplies False at read time.
- V12 floor fixture (explicit verify_on_stop: true on disk): the key is
a user-set path, so the v32 flip stays materialised as false.
- Partial-write and _persist_migration regressions now assert the key is
absent from disk and (for the merge case) that the merged view still
resolves False.
Behavior verified with a one-shot migrate_config run against both
fixture shapes.
* fix(gateway): pass live adapters to cron fire webhook's fire_due
The Chronos fire webhook (/api/cron/fire) called
provider.fire_due(job_id, adapters=None, loop=loop), so every
externally-triggered fire delivered through the standalone path even
with a live gateway in-process. E2EE platforms and relay-fronted
logical platforms (whose ONLY send path is the live relay adapter — no
native credential exists on the box) failed every external fire with
"platform 'X' not configured/enabled", while the same job delivered
fine under the built-in ticker (gateway/run.py passes runner.adapters).
Resolve the runner (self.gateway_runner → app['gateway_runner'] →
_gateway_runner_ref(), the same chain the drain check uses) and forward
its adapters. No runner → adapters=None, preserving the historical
standalone path byte-identically.
Note: does not by itself fix Fly-hosted scale-to-zero deployments where
NAS's callback lands on the DASHBOARD process (internal_port 9119) —
_fire_cron_job_for_profile there has no gateway runner in-process. That
topology needs a separate fire handoff (design pending).
* fix(cron): dashboard forwards Chronos fires to the gateway (503 when unreachable)
The dashboard's /api/cron/fire executed cron jobs in the DASHBOARD
process via _fire_cron_job_for_profile with adapters=None. On hosted
deployments (Fly proxy exposes only the dashboard's port) that made
every managed-cron fire deliver through the standalone send path, which
cannot serve relay-fronted logical platforms (their only sender is the
live relay adapter in the gateway process — no native credential exists
on the box) or E2EE rooms. It also ran the whole agent turn inside the
dashboard: wrong process for memory/session ownership and fire-claim
attribution.
Restore the invariant that the GATEWAY owns cron execution:
- Dashboard route: after verifying the NAS JWT and resolving the job's
profile, FORWARD the fire to the gateway api_server's own
/api/cron/fire on loopback, NAS bearer preserved (the gateway
re-verifies the JWT — defense in depth, no new trust link), and pass
the gateway's response through. Gateway unreachable → 503 so NAS
retries per the Chronos contract (non-2xx = retryable; the store CAS
de-dupes the eventual double fire). Deliberately NO local-execution
fallback.
- Endpoint resolution mirrors gateway/config.py's api_server load order
per target profile (config.yaml extra.port → API_SERVER_PORT from
process env or the profile's .env → 8642), with /p/<profile>/ prefix
routing under multiplex.
- docker/stage2-hook.sh: generate a strong API_SERVER_KEY into .env on
first boot when absent (never overwrites an operator value), so the
loopback api_server passes its startup guard on hosted images. The
fire route itself is NAS-JWT-authed; the key gates the rest of the
api_server surface. The listener binds 127.0.0.1 by default and the
Fly service exposes only the dashboard port.
- _fire_cron_job_for_profile kept but deprecated (late-binding seam
compatibility); no route calls it.
- docs/chronos-managed-cron-contract.md: document the two-hop inbound
topology and the 503-retry semantics.
Depends on the previous commit (fire webhook passes live adapters to
fire_due) — together they make NAS→dashboard→gateway fires deliver over
relay end to end.
* fix(cron): read the profile api_server port via the canonical config loader
CI guard test_config_read_guard flagged the new _gateway_fire_endpoint
for a raw yaml.safe_load of the profile's config.yaml — the exact drift
class the guard exists to kill (raw reads miss the managed-scope
overlay, ${ENV_VAR} expansion, and root-model normalization).
Read through load_config() under a HERMES_HOME override scoped to the
target profile instead (the same pattern the deprecated
_fire_cron_job_for_profile uses for its store scope), and pull the port
with cfg_get. Test updated to stub load_config rather than write a raw
config.yaml.
* fix(gateway): only messaging platforms count for the scale-to-zero arm gate
The stage2 hook now generates API_SERVER_KEY for every Docker container,
and key presence force-enables the api_server platform. The scale-to-zero
arm gate counted every enabled platform, so the loopback api_server
listener made messaging_is_relay_only_or_absent False on every hosted
instance — silently disarming the feature (the not-armed log would show
enabled platforms=['relay','api_server']).
The arm gate and the not-armed logger now share one helper that filters
to enabled MESSAGING platforms, excluding LOCAL/API_SERVER/WEBHOOK —
the same non-messaging exclusion set _connect_platforms already uses.
A genuinely enabled direct-socket platform (Discord/Telegram) still
disarms. Two of the three new tests fail without this fix.
The Browser Use CLI became the default browser backend, but nothing
provisioned it: users without uv/uvx (field report from DongyangHe on
macOS) silently fell back to the built-in browser tools with no notice.
- install_cli() in tools/browser_use_cli.py: uv tool install browser-use
via the managed uv (bootstrapped on demand), linked into
$HERMES_HOME/bin (UV_TOOL_BIN_DIR)
- _find_cli() now also probes $HERMES_HOME/bin for browser-use/uvx —
Hermes' managed uv is not on the user's PATH
- hermes tools post_setup actually installs (Camofox standard) instead
of printing instructions
- install.sh / install.ps1 provision the CLI at install time
(best-effort, non-fatal, honors --skip-browser)
- CLI startup shows a one-line notice (24h rate-limited) when the
default backend downgraded to the built-in tools
The custom-endpoint REST handlers ran bare load_config/save_config, so
every add/activate/delete landed in the process-level default profile
regardless of which profile the desktop settings UI was targeting. A
provider added under a non-default profile silently went to default:
visible only in default-bound sessions, absent everywhere else, and
un-addable to another profile without hand-editing its config.yaml.
Scope all four handlers (list/upsert/activate/delete) to the requested
profile via _config_profile_scope, matching /api/config, and spread the
active profile into the four hermes.ts wrappers alongside their existing
validateCustomEndpoint sibling.
An unreadable profile dir made (entry / '.env').exists() raise
PermissionError out of the sidebar fallback, 500ing /api/profiles.
Found by hostile fixture during live E2E of the scandir conversion.
Two-part fix for the dashboard fd exhaustion reported in #81547:
1. Raise RLIMIT_NOFILE soft limit on startup (before uvicorn binds).
macOS defaults to 256 for LaunchAgent processes — too tight for the
dashboard which opens 3 fds (db+wal+shm) per SessionDB per request
across all profiles. After days of polling the soft limit exhausts
and every os.listdir/open raises OSError [Errno 24]. The helper raises
to the hard limit (or minimum 4096), matching the reporter's ulimit
workaround. No-op on Windows (no resource module).
2. Replace bare Path.iterdir() with context-managed os.scandir() in four
dashboard hot paths: _fallback_profile_dicts, file manager list,
checkpoint listing, and plugin discovery. iterdir() returns a
generator that holds an open directory fd until fully consumed; if
an exception interrupts iteration the fd leaks. os.scandir() is an
explicit context manager that guarantees close on exit, following
the same idiom already used in /api/fs/list.
Tests: 6 passed, 3 skipped (resource-module tests skip on Windows).
_spawn_gateway_restart() now calls _reap_unsupervised_gateway_orphans()
before spawning a new `hermes gateway restart` child. On desktop-app
restart the old serve exits but its gateway child gets reparented to
launchd (PPID=1) and keeps its platform connection alive. The new
serve then spawns a fresh gateway, resulting in two live gateways
racing the same connection.
The reap was already implemented for the CLI restart path (#75936) but
the dashboard's _spawn_gateway_restart path was not covered.
Fixes#77276
os.kill(pid, 0) sends CTRL_C_EVENT on Windows (bpo-14484). The reap path
is POSIX-only, but the blocking lint rejects the pattern repo-wide and
psutil is a core dependency.
On Desktop serve startup, reap orphan gateway processes (PPID=1) left
behind by a previous serve session that exited abnormally. This prevents
the old and new gateways from racing for the same QQ WebSocket
credential, which splits messages across parallel session trees (#77276).
Production incident: the orphan reap killed a legitimate SSH remote backend
started by another client machine. Its process sat at ppid 1 with the same
cmdline shape as a genuine orphan, and the exclusion list only covered THIS
app instance's children — ownership by OTHER clients was invisible.
The reap now treats every backend.lock.json under ~/.hermes/desktop-ssh/*/
as an ownership claim: lock payloads are schema-validated (mirroring
remote-lifecycle.ts) and their PIDs are excluded both before the scan and
re-checked after it (defense in depth against a lock written mid-scan).
Regression tests cover the exact incident shape: a lock-owned PID and a
genuine orphan with identical process shapes — only the orphan is reaped.
Also: fold the new single-field `runtime` config category into `agent`
(_CATEGORY_MERGE) and fix an env leak in the serve-startup test
(HERMES_SERVE_HEADLESS restored via monkeypatch) so the combined suites
run green in any order.
launchd starts children with soft nofile=256; hermes gateway start rewrites the plist and previously stripped any manually-added SoftResourceLimits, silently reintroducing EMFILE crashes under load. The plist generator now embeds the configured runtime.nofile_soft_limit so the persisted service definition and the in-process floor share one knob.
When Desktop exits uncleanly, leftover `hermes serve --host 127.0.0.1 --port 0`
processes can be reparented to pid 1 and keep full MCP trees alive. The next
boot then stacks another backend on top of the corpses until EMFILE kills
sidebar/session APIs and tabs disappear.
- Detect Desktop-local serve shape (loopback + ephemeral port 0)
- Only reap processes whose ppid is 0/1 (true orphans)
- Spare fixed-port remote serves (e.g. --port 9119) and HERMES_DESKTOP_CHILD_PID
- Run at Desktop backend start (HERMES_DESKTOP=1) before parent-death watchdog
Complements parent-death watchdog (prevents future orphans) and configurable
nofile soft limit (capacity floor). Together these stop the multi-backend
pile-up cascade observed on macOS Desktop SSH/local installs.
An unclean desktop exit (crash / SIGKILL / update handoff) stranded every
`hermes serve` profile backend as an orphan (ppid=1) still serving, each
holding its MCP child subtree — 31 orphans / ~1.3 GiB RSS on one install.
Root causes + fixes:
- serve had no parent-death watchdog: add _start_parent_death_watchdog() in
web_server.py (mirrors slash_worker.py), gated on HERMES_PARENT_PID; os._exit
cascades to MCP watchdogs. No-op for standalone `hermes serve`.
- desktop passes HERMES_PARENT_PID in both serve spawn env blocks (main.ts).
- POSIX teardown now group-kills (process.kill(-pid, ...)) so MCP grandchildren
die too (backend-child.ts + waitForBackendExit SIGKILL fallback).
Windows path unchanged (forceKillProcessTree). Tests updated + passing.
Shareable profile tarballs already drop auth.json/.env, but keys pasted
into skills, SOUL.md, or memories still shipped in plaintext. Force-run
the same redact_sensitive_text pass sessions export --redact uses on the
staged copy so the live profile is never rewritten.
Ancestor-reopen descendant invalidation previously lived only in the
dashboard plugin (_set_status_direct), so board semantics diverged by
surface and the retraction was silent: completed work snapped back to
todo and live workers were killed with no operator-visible signal.
Move it into kanban_db.invalidate_descendants_for_parent_reopen as THE
single domain implementation (recursive-CTE discovery and per-run
_retry_status_for_run handling preserved). It composes under a caller's
open transaction via write_txn(allow_nested=True) — the ancestor flip
and the descendant retractions must commit atomically — and opens its
own transaction standalone. The dashboard shim now delegates; the CLI
deliberately has no done-reopen verb (reopen-review is review-phase
only), so the DB-layer function being the single implementation is the
fix, documented in its docstring.
Non-silent: every invalidated descendant gets a descendant_invalidated
event ({ancestor, prior_status, new_status, resume_status}), the legacy
status event for existing live-feed consumers, and a task comment
naming the reopened ancestor. Running descendants keep the termination
behavior (a child building on a retracted premise is wasted spend), but
the events/comment are committed BEFORE the kill, which routes through
_terminate_reclaimed_worker — the same helper the reclaim paths use.
consecutive_failures resets to 0 on invalidated descendants: operator-
initiated invalidation is a deliberate fresh start, deliberately the
opposite of the review-loop rule (reopen_review_task preserves the
counter, #35072) so the autonomous review loop can't launder its own
failure streak.
Regression: DB-function reopen demotes done descendants with events +
comments; running descendant's audit trail is durable before its worker
dies; counter resets; dashboard and DB paths produce identical task
states, event kinds, and comment counts.
request_changes and reopen_review_task no longer reset
consecutive_failures (and last_failure_error) to 0 — review transitions
are neither success nor failure signals, so the circuit-breaker counter
is preserved (not incremented either), mirroring unblock_task (#35072).
Only complete_task's success path clears the counter.
Regression: counter=1 survives a full request_review -> request_changes
-> re-request cycle; a crash after request_changes accumulates to 2 and
trips a failure_limit=2 breaker; complete_task still resets to 0.
request_review on a running task under a live claim now requires the
caller to prove ownership (expected_run_id, the unchanged worker path)
or pass an explicit force=True override (CLI --force; dashboard human
actions pass force=True) instead of silently clearing claim_lock /
worker_pid of a live run.
Failures now carry distinct diagnostic reasons via with_reason=True
(mirroring request_changes' tuple pattern): live-claim refusal,
malformed re-review provenance, unsatisfied parents, unknown task, and
CAS miss. Tool/CLI handlers surface the specific reason instead of the
generic 'unknown id or not in running/ready'.
Regression tests: live-claim refusal + force/worker paths; malformed
provenance gets a distinct reason and explicit reviewer= recovers.
Thread lane= into check_respawn_guard. For review-lane dispatch the
active_pr and recent_success rules are skipped: a fresh PR URL comment
(and often a recent completed run) is the precondition of the canonical
review handoff, not a duplicate-work signal. Rate-limit cooldown and
the auth-blocker check still apply in every lane.
Regression: a review task with a <24h PR comment is spawned by dispatch
while a ready-lane task with the same comment stays deferred; a
rate_limited latest run still defers the review lane.
Plain write_txn raises loudly on nesting again (the historical main
invariant); composition primitives (create_task, add_comment) opt in
with allow_nested=True for savepoint semantics. create_swarm activates
the swarm root with an inline blocked->done CAS flip + synthesized run
+ event instead of nesting complete_task, so complete_task's post-commit
side effects (workspace cleanup, failure-counter clear, recompute_ready)
can no longer fire under an open outer transaction; recompute_ready now
runs after the outer commit. recompute_ready docstring corrected.
Regression: plain nesting raises; allow_nested composes and an outer
rollback discards inner work with no side effects fired.
Add a non-terminal "review" status so a worker that finished implementation
can hand off for human review without abusing kanban_block. The old
kanban_block(reason="review-required: ...") convention routed the handoff
through the unblock-loop breaker, so a normal review -> changes -> review
cycle was falsely escalated to triage.
- kanban_db: request_review (running/ready -> review, non-block, emits
review_requested), reopen_review_task (review -> ready/todo, review_reopened),
complete_task accepts review -> done, and a review_dispatch gate (default off,
shared by the dispatcher loop and the gateway health probe).
- kanban_request_review worker tool + `request-review` / `reopen-review` CLI
verbs; tool wired through toolsets, EXPOSED_TOOLS, _POLISHED_TOOLS.
- Gateway notifier wakes the origin subscriber on review_requested and
block_loop_detected; the subscription survives until done/archived, so every
review cycle re-notifies.
- Dashboard PATCH + bulk route the review transitions (request_review /
reopen_review_task) and render the review column.
- goals.py goal-loop and KANBAN_GUIDANCE recognize review as a terminator.
- Docs (reference tables, user guide, AGENTS.md, zh-Hans mirrors) + tests.
needs_input / failed are unchanged: they still route through kanban_block,
still count toward block_recurrences, and still escalate to triage.
An unset browser.backend ("") now resolves to Browser Use mode whenever
the browser-use CLI is runnable (installed binary or uvx); otherwise the
built-in browser tools are kept so browsing never silently breaks.
Camofox setups always keep the built-in tools (no CDP surface), and
backend: off (including YAML 1.1 bare off -> False) forces the built-in
stack. hermes tools row highlighting follows the same effective-mode
resolution, and tests/tools/ pins CLI discovery off so host uvx installs
can't flip built-in-browser tests.
The Hugging Face agent-harness registry matches standard-var values
EXACTLY against the harness id. Our registry id is 'hermes-agent'
(huggingface.js agent-harnesses.ts), so AI_AGENT=hermes was counted as
'unknown' — fixed at both entry points.
Remote terminal backends (Docker/SSH/Modal/Daytona/Singularity/Vercel)
never inherit the Hermes process env, and the cross-session leak guard
deliberately strips HERMES_SESSION_* from subprocess envs in engaged
multi-session hosts — so hf/huggingface_hub traffic from those shells was
unattributable. _wrap_command now exports AI_AGENT/HERMES_AGENT inside
every wrapped command with ${VAR:-default} semantics (outer harness is
never clobbered), and the snapshot dump excludes both names so a baked
value can never shadow a later outer harness.
E2E: verified against real huggingface_hub 1.27.0 detect_agent() with a
cached registry — 'hermes-agent' detected via AI_AGENT and via
HERMES_SESSION_ID; old 'hermes' value reproduced the 'unknown' bug.
CLI and gateway entry points now set AI_AGENT=hermes (the emerging
cross-agent standard read by e.g. huggingface_hub agent detection) and
HERMES_AGENT=true, via setdefault so an outer harness is never
clobbered.
Reframe (per review): browser.backend: browser-use is now a DRIVER over
whatever browser source is configured, not a competing backend choice.
- browser_exec resolves its CDP endpoint through the same chain the
built-in tools use: BU_* env override > BROWSER_CDP_URL/browser.cdp_url
(/browser connect) > the configured cloud provider via browser_tool's
_get_session_info() — sharing the per-task session cache, expiry
replacement, inactivity reaper, and atexit cleanup instead of
duplicating them. Live-validated against Browserbase (session created,
driven, reaped) and gateway-provisioned Browser Use cloud browsers.
- Direct-API Browser Use configs skip provider resolution (the CLI talks
to their cloud natively via BU_AUTOSPAWN); the Nous-gateway variant
resolves through the provider, so subscribers get CLI mode without a
raw BROWSER_USE_API_KEY.
- Camofox: only true fallback — Firefox-based, custom HTTP API, no CDP
surface (its own health probes fail on CDP-schema calls). Active
Camofox setups keep the built-in browser tools even with
backend: browser-use set.
- hermes tools picker: provider rows and the Browser Use row are no
longer mutually exclusive; selecting a provider keeps the driver
choice, and both rows highlight when composed.
- Docs updated for driver-over-source semantics.
Cold CLI time-to-banner was ~1.8s (hermes) / ~2.8s (hermes -w). The banner
path was paying for work the session doesn't need before first input:
- aux availability probes built REAL OpenAI/httpx clients (openai import
~0.3s + SSL context) just to answer check_fns. New aux_probe_mode()
returns a cache-excluded stub; resolution policy unchanged.
- tools/mcp_tool imported the mcp SDK (~260ms, mcp.types pydantic model
construction) at module import even with zero MCP servers configured.
SDK import is now lazy behind _ensure_mcp_sdk(); _MCP_AVAILABLE is a
find_spec probe so every existing gate/test keeps its semantics.
- banner blocked 500ms on the update-check prefetch; now waits 50ms and
defers the warning line to a daemon thread (prints above the prompt).
- banner recomputed get_tool_definitions + skills scan + git state every
launch; now snapshotted to ~/.hermes/cache/banner_snapshot.json keyed on
(config.yaml, .env, checkout rev, toolsets) and replayed on warm launches
with a background refresh. Agent tool list is still computed fresh.
- _resolve_active_context_length probed the Nous portal /models (~200ms
network) per launch; the tool-search gate now prefers the on-disk
context cache when present.
- schema reconciliation re-executed SCHEMA_SQL in a scratch SQLite DB
(~85ms) per SessionDB(); the reference parse is now disk-memoized by
DDL hash (live-DB diffing still runs every startup).
- bundled-skills sync (~120-170ms rglob/hash) moved off the startup path
to a daemon thread; plugin discovery starts in the background and every
synchronous consumer joins via discover_plugins().
- hermes_cli.auth imported httpx eagerly (~30ms); now a lazy proxy that
test monkeypatching still reaches (setattr forwards to the real module).
- fast chat launch: unambiguous 'hermes'/'hermes chat' invocations skip
building all ~40 subcommand parsers (bails to full dispatch on anything
else, incl. container mode).
- -w path: git worktree add runs with checkout.workers=8 (0.6s→0.2s) and
overlaps HermesCLI construction; --skills preload runs in the background
and is folded in at agent init (finalize_preloaded_skills, same
fail-loud contract for fully-unknown skill lists); stale-worktree prune
moved off the banner path.
Warm results (PTY time-to-banner, 5-run): hermes 1.80s → 0.38-0.40s;
hermes -w -s hermes-agent-dev --yolo 2.82s → 0.57-0.69s.
`projects.tree` answers for the backend's own profile, so the grouped
sidebar had nothing to draw once the user asked to see every profile.
Run the same authoritative builder once per profile against that
profile's state.db and merge the results by folder, so one checkout is
one group no matter how many profiles work in it, and the owning profile
rides on each session row where the badge and filter can read it.
Group totals are summed in SQL rather than over the loaded page — a
number that shrank as you scrolled would be worse than no number.
Scope the batched sidebar slices while we're here: cron and messaging
came back cross-profile unconditionally, which is why a concrete profile
showed another profile's Telegram threads and cronjobs.
Closes#65710Closes#42651Closes#70629
After a partial update (stash restore overwriting providers/base.py with
an older version), the NousProfile singleton was instantiated from a
ProviderProfile class that predates the supports_prompt_cache_key field
(added in f4fb23f3d). Accessing profile.supports_prompt_cache_key raised
AttributeError, crashing every API call with:
'NousProfile' object has no attribute 'supports_prompt_cache_key'
Use getattr(profile, 'supports_prompt_cache_key', False) so a stale
profile degrades to 'no prompt cache key' instead of crashing.
hermes update runs in the PRE-pull Python process. After git pull
updates the source files on disk, sys.modules still holds the OLD
hermes_cli.config and hermes_cli.config_migrations. Function-level
imports return the cached module, so DEFAULT_CONFIG["_config_version"]
is the OLD value and check_config_version() reports (33, 33) —
"up to date" — even though the freshly-pulled code has v34 with a
migration to run.
The personality reset migration (#81946) was silently skipped this
way: display.personality: kawaii stayed active after updates that
should have reset it. Every user who updated from a pre-v34 codebase
to a post-v34 codebase was affected.
Fix: _run_config_check_fresh and _run_migrate_config_fresh call
importlib.reload() on hermes_cli.config_defaults, hermes_cli.config,
and hermes_cli.config_migrations before calling check_config_version
and migrate_config. This forces the modules to be re-read from the
updated source files on disk.
When state.db's write path fails (corrupt FTS, or a crash landing between
routing publication and row creation), the live gateway conversation can end
up in a session row that never received its identity columns: session_key,
chat_id, chat_type and origin_json are all NULL. In-memory routing hides the
damage for as long as the gateway stays up. After a restart the chat is
resolved from the DB, and find_latest_gateway_session_for_peer cannot see
that row — both of its queries match on the very columns it lacks — so the
chat resumes the last keyed sibling instead, days older. The messages were
never lost, only unreachable.
Hardening the write side cannot reach a row that is already damaged, so add
the offline repair path the tracking issue asks for:
- SessionDB.find_orphaned_gateway_sessions() reports message-bearing rows
with no session_key, and names the predecessor each one continues only
when the evidence is unambiguous — a recorded parent_session_id
("lineage"), or exactly one keyed row of the same source and compatible
user_id that fell quiet within 15 minutes of the orphan's start
("contiguity"). Contested pairs are reported with a reason and left alone:
a wrong adoption would splice one person's conversation into another
person's chat. Branch, delegate and tool rows are excluded — they are
unkeyed by design, not by damage.
- SessionDB.adopt_orphaned_gateway_session() stamps the orphan from the
predecessor (never overwriting a column that already has a value), records
the lineage, and retires the predecessor under end_reason
'superseded_by_repair' — a reason recovery does not treat as resumable, so
the repaired row wins the chat from then on. The pair is re-verified inside
the write transaction, making a concurrent heal a no-op rather than a
conflicting write.
- `hermes sessions repair-routing` drives both. It reports without touching
the database; --apply confirms first and warns that a running gateway
still holds the old mapping in memory.
Refs #82616.
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.
The auto-resume restart-loop breaker (#30719, defense-3) pruned its boot
log against an absolute `window_seconds` (default 60s). That prune is
period-sensitive: a crash cycle slower than the window drops its own
history on every boot, so the counter never leaves 1 and the breaker can
never trip, no matter how long the loop runs.
The cycle reported in #81642 is ~150s — a wedged event loop, the liveness
watchdog hard-exiting at ~90s, a supervisor respawn, and auto-resume
replaying the same session that wedges it again. Structurally invisible to
a 60s window: `gateway/restart_loop.json` kept a single timestamp across 15
kills in one morning. Because every cycle leaves a gateway that cannot
process SIGTERM, `hermes update` has no drainable gateway to stop, which is
the reported hang.
Chain boots on the inter-boot GAP instead of an absolute window: two boots
belong to the same loop when they are no more than `max_gap_seconds` apart
(default 300s, floored by `window_seconds` so widening the window never
makes the breaker less sensitive). The verdict becomes period-agnostic —
the original ~10s respawn loop still trips in 3 boots, and so does a 150s
one — while a boot after real quiet resets the chain, so occasional
operator restarts still never accumulate. The persisted chain is capped at
50 entries.
- gateway/restart_loop_guard.py: gap-chained pruning (`_chain_ending_at`),
`DEFAULT_MAX_GAP_SECONDS`, `max_gap_seconds` kwarg on the three entry
points, clock-step tolerance, bounded state file
- gateway/run.py: `_restart_loop_guard_config` reads and returns
`max_gap_seconds`; the auto-resume call site passes it through
- hermes_cli/config_defaults.py: `gateway.restart_loop_guard.max_gap_seconds`
Tests: 7 new cases in TestRestartLoopGuard covering the slow cycle, chain
persistence, quiet-period reset, the #30719 fast loop, the config knob, the
window floor, and the disabled breaker. Verified RED before the fix (the
slow-cycle case asserted `[1300.0] == [1000.0, 1150.0, 1300.0]`, exactly
the single-timestamp state file from the report) and GREEN after.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
A session row can say whether its work is open, merged or closed, and link
to it. The join is the session's own repo + branch, asked of GitHub in one
batched GraphQL request per repo (branch aliases, not a `gh pr list` page
that a busy repo crowds ours out of), through the remote-aware git facade so
a desktop on a remote gateway asks the backend's `gh`.
Two ways a session's branch can't answer, both covered:
- It ran on trunk. Fork PRs share our branch namespace, so asking about
`main` badges a stranger's PR onto it — trunk is never asked about, and
cross-repository PRs are dropped server-side either way.
- It worked in a worktree, so the branch it recorded at start isn't where
the PR came from. Creating a PR from the review pane binds the session to
the branch it actually used, and for sessions that predate that, the PR is
recovered from the transcript: `gh pr create` prints a bare PR url and
nothing else, so a tool result whose whole output is one is a claim rather
than a mention. Scanned read-only across profiles, once per session ever.
The fast-model picker reads /v1/models to find the small model a provider
currently serves, and it asked anonymously. Most of those endpoints need a
key, so the fetch 401'd and the empty result read as "this provider has no
small model" — the picker fell back to its curated list and never noticed.
Worse, a failed fetch cached its empty result forever, so one bad moment
during startup disabled live model discovery for the life of the process,
and the processes that read this run for weeks. Give the failure an expiry
and pass the provider's credentials.
The bare family rungs (-mini, -flash, haiku) also picked whichever id
sorted first, which is the oldest generation a provider still serves:
gpt-3.5-mini over gpt-5.4-mini, claude-3-haiku over claude-haiku-4.5.
Compare the digit runs as numbers so the rung meant to keep us current
does.
Agent Plugins v1 packages with 'streamable-http' mcp.json entries now load
through Hermes' existing URL-based MCP client instead of being reported and
skipped. The stdio-only limitation was the agreed follow-up slice from
PR #81196.
Boundary rules from the v1 spec (§7.2.1) are enforced:
- URL must be absolute http(s), no user information, no fragment; plain
HTTP only for localhost/loopback hosts.
- Configured package headers are never forwarded across a cross-origin
redirect: translation marks entries strict_redirect_headers, and the
redirect hook in the native runtime strips those headers (plus
Authorization) whenever a redirect leaves the original origin. On mcp <
1.24.0, where the client cannot hook redirects, such servers fail closed
with an actionable upgrade message.
- Legacy 'sse' entries remain reported and skipped.
The redirect hook is extracted into a testable module-level factory
(_make_redirect_header_stripper); default behavior for native config
servers is unchanged (Authorization-only stripping).
Two cache-key correctness follow-ups to #82229 (review feedback):
1. Abbreviated commit pins are immutable too. The installer's
is_valid_commit() accepts 7-40 hex chars, but the Python refresh
exempted only exactly-40-hex names — an abbreviated pin like
install-4ce1994.ps1 could be overwritten with a branch script. The
predicate now mirrors the Rust rule (7-40 hex = immutable, never
rewritten), applied to the sanitized target ref.
2. Refresh only the update-target ref's cache key. The helper rewrote
EVERY mutable-ref entry with the active checkout's script: with
install-main.ps1 and install-bb_gui.ps1 coexisting, updating main
replaced both with main's script — cross-branch cache poisoning in
the other direction. It now computes the single cache key for the
branch being updated, using the installer's own ref sanitization
(sanitize_ref: non [A-Za-z0-9._-] -> '_', so bb/gui ->
install-bb_gui.ps1), and touches nothing else. Entries the
bootstrapper never wrote are not created.
The branch is threaded from the existing `branch =
_resolve_update_branch(args)` in both _cmd_update_impl call sites and
_update_via_zip (main-only by its own guard).
Regression tests lock down both invariants: abbreviated-SHA pin
untouched (including when passed as the branch), coexisting mutable
refs (main refresh leaves install-bb_gui.ps1 byte-identical),
sanitize_ref parity, and uncached-ref no-op.
E2E on the incident machine's real bootstrap-cache: planted a stale
install-main.ps1 + sibling install-bb_gui.ps1 + abbreviated pin
install-4ce1994.ps1; refresh("main") healed main byte-exact and left
both others untouched; refresh("4ce1994") was a no-op. The pre-existing
40-hex pin entry in the real cache was also untouched.
Pre-#67193 hermes-setup binaries (June 2026 and earlier, including the
newest published build) resolve bootstrap-cache/install-<branch>.ps1 by
"exists -> reuse forever": a branch-ref cache entry written at install
time is never re-downloaded, so every GUI update/repair executes a
months-stale install script. The binary has no self-update path, so no
amount of `hermes update` fixes it.
Live incident (2026-08-09, ryanc): install-main.ps1 cached June 4 lacked
the #81327 venv process-tree sweep; the bootstrap venv stage died with
"Cannot remove item venv\Scripts\python.exe: Access denied" on a
straggler backend pair, twice, despite every relevant fix already being
merged on main - the installer simply never ran that code.
Fix: `_refresh_bootstrap_cache_scripts()` runs at the end of every
update path (git, zip, already-up-to-date repair), overwriting mutable
branch-ref cache entries with the freshly pulled scripts/install.ps1 /
install.sh. The stale binary's unconditional reuse becomes a feature: it
"reuses" a file the update keeps permanently current. Post-#67193
installers re-download on every run anyway, so this is a harmless
pre-seed of identical bytes for them.
Scope guards: 40-hex commit-SHA entries are immutable pins and are never
touched; .ps1 gets the UTF-8 BOM to match the installer's cache format
(#67193); best-effort - a failed refresh never fails the update.
E2E on the incident machine: poisoned the real
bootstrap-cache/install-main.ps1 with a stub, ran the real function -
healed byte-exact to the checkout's script (BOM intact, #81327 tree-kill
sweep present).
Follow-up to #82179 addressing helix4u's review comment
(#82179 issuecomment-5229441571). Three parts:
1. Desktop teardown (salvaged from #77436, @4adwentures): the update
hand-off's releaseBackendLock() sent SIGTERM to the primary backend
BEFORE taskkill /T. If the launcher exits first, Windows can no longer
enumerate its descendants and they survive holding the venv — the
Electron path that creates the orphan #82179 then has to repair.
New stopBackendTreesForUpdate() tree-kills the live root first, with
the behavioral vitest from #77436. The scanner half of #77436 is
deliberately NOT taken (superseded by #82158's full-cmdline scan).
2. Tree-aware orphan classification: _orphaned_desktop_backend_pids()
previously refused the whole holder set when any holder had a live
parent. But the scanner legitimately returns an orphaned serve root
AND its descendants (the venv trampoline's uv-managed interpreter
worker — which carries the same backend argv — plus .hermes-runtime
children). Those have a live parent: the orphan root itself. Now
holders inside an accepted orphan root's tree fold into that root
(only roots are returned; taskkill /T reaps descendants), and
live-parent backends defer to the ancestry check instead of refusing
outright. Anything outside an orphan tree still refuses.
3. Tests for the mixed shapes: root+managed-runtime child,
grandchild depth, non-descendant stray alongside an orphan root
(still refuses), descendant exited mid-classify.
E2E on a real Windows box: spawned a detached backend-shaped orphan
that itself spawned children (3 python descendants); the scanner-shaped
mixed holder set classified to [root], taskkill /T reaped root and all
descendants. The live Desktop backend on the box still classified None
(refusal preserved). The first E2E attempt caught exactly the
trampoline/worker case the mocks missed — the live worker re-execs with
the same backend argv and a live parent — which is what part 2 fixes.
Co-Authored-By: 4adwentures <296413879+4adwentures@users.noreply.github.com>
The GUI-updater handoff race: the Desktop fires SIGTERM + app.quit() and
spawns hermes-setup, but its Python backend (`python.exe -m
hermes_cli.main serve`) can survive the teardown. The Desktop is gone --
nothing will respawn that backend -- yet the venv-holder guard refused on
it and the update dead-ended with "Hermes is still running" while the
user had zero windows open (observed twice on 2026-08-09, 01:59 and
02:17, bootstrap-installer.log).
New `_orphaned_desktop_backend_pids()` classifies remaining holders: a
serve/dashboard backend whose supervising parent is provably dead (PID
gone, or recycled -- parent created after the child) is a straggler safe
to reap. Any live-parent backend, non-backend holder, or unprovable case
keeps the refusal exactly as before. Reaping uses the new
`_stop_process_trees()` (taskkill /T /F), mirroring the Desktop's
forceKillProcessTree and install.ps1's venv sweep so the managed
.hermes-runtime interpreter child dies with its launcher (#70026).
Builds on #81327 (salvaged intact underneath): that fixed the same
parent-only-kill gap in install.ps1's venv sweep; this closes the
remaining dead-end in the `hermes update` guard itself.
E2E on a real Windows box: spawned a detached orphan with a
backend-shaped argv -> classifier returned its PID and the tree reap
killed it; a non-backend orphan and the live Desktop backend (parent
alive) both returned None (refusal preserved).
Extends the picker fix to the read that actually uses the key: switch_model's
user-provider credential resolution (the ${VAR} api_key expansion and the
key_env fallback at the resolve-credentials step) still read os.environ raw
and passed the result to resolve_runtime_provider as explicit_api_key — so
under multiplex_profiles the actual switch, not just the picker listing,
could adopt another profile's key. Same _scoped_key_env helper, same
fail-closed semantics; identical behavior when multiplexing is off.
Adds end-to-end switch_model tests pinning that an installed scope wins over
the process environment for both read shapes.
854007d1c routed the remaining main-agent fallback key reads through
agent.secret_scope so the multiplexed gateway's per-profile scope applies.
list_authenticated_providers - which gateway/slash_commands.py calls
directly for /model - still resolved custom-endpoint and fallback-entry
credentials with raw os.environ.get(key_env), so under multiplex_profiles
one profile's picker reads whatever key the process environment happens to
hold, i.e. another profile's.
no multiplexing : profileA-key (unchanged)
scope installed : profileB-key (was profileA-key)
Route both reads through a _scoped_key_env() helper over
secret_scope.get_secret(). get_secret is identical to os.getenv when
multiplexing is off, so single-profile deployments are byte-for-byte
unchanged; a fail-closed UnscopedSecretError is treated as "no credential
visible for this profile", which is how the picker already handles a
missing key.
Scope: only the two key_env credential reads. The other environment reads
in that function are provider-presence probes (AWS creds, LM_BASE_URL),
a separate concern.
_detect_venv_python_processes() returned cmdline_raw[:120]. Gateways
autostarted via the managed-runtime interpreter carry a >120-char exe path
(.hermes-runtime\python\generation-...\cpython-3.11-...), so the truncated
cmdline ended inside the exe path, before '-m hermes_cli.main gateway run'.
The Desktop preflight's pausable-gateway exemption
(_scan_venv_blockers._is_pausable_gateway) therefore never matched, the
gateway was reported as a blocker, and every Desktop update aborted with
'Update didn't finish' even with all windows closed — the updater's own
gateway pause never got a chance to run.
Fix: return the full cmdline from the detector and truncate only at
display time (_format_venv_python_holders_message and the scan's JSON
cmdline field, after redaction).
Reproduced live on Windows 11: scan reported blocked=true for
'...cpython-3.1' (truncated); after the fix the same gateway pair scans
clear with pausable_gateways=2.
An alias that family-matches multiple catalog models (/model opus) used to
silently pick one via _model_sort_key heuristics. The heuristics have
guessed wrong repeatedly — dated snapshots like claude-opus-4-20250514
parsed as version 20,250,514 and outranked claude-opus-4-8; suffix
tiebreaks landed on the cheapest tier — and every wrong guess silently
switches the user to a model they did not ask for.
resolve_alias now raises AmbiguousAliasError whenever more than one model
matches the alias family; switch_model catches it at all three call sites
(explicit-provider path, current-provider path, authenticated-provider
fallback) and returns a failure result listing the candidates
(best-guess-first ordering, capped at 10) with instructions to pick an
exact name. A single match still resolves automatically, and DIRECT_ALIASES
exact mappings are unaffected.
The date-stamp split from #67571 is kept, demoted from selection logic to
display ordering of the candidate list.
Supersedes the auto-pick approach of #67571; credit to @Sahaun and @GottZ
for the date-stamp parser analysis that this builds on.
_model_sort_key treated YYYYMMDD snapshot stamps (e.g.
claude-opus-4-20250514) as version components, so 20250514 > 8
and resolve_alias("opus", "anthropic") returned the wrong model.
Fix: split components ≥ 19_000_101 (smallest plausible date stamp)
out of the version tuple, keeping them as a trailing tiebreaker so
bare IDs sort before their dated snapshots and newer snapshots
before older ones. Shorter numeric components (mistral-large-2411,
gpt-4-0613) keep their current behavior. No models.dev dependency
in the sort path.
get_messages() only deserializes content and tool_calls; the structured
reasoning columns (reasoning_details, codex_reasoning_items,
codex_message_items) come back as the raw TEXT they were stored as.
Feeding those rows straight back into a write, which is exactly what
the POST /api/sessions/{id}/fork handler does by piping get_messages()
into replace_messages(), hit an unguarded json.dumps() and stored the
already-serialized string encoded a second time. On replay of the fork,
json.loads() then yields the inner string instead of a list, and every
consumer's isinstance(..., list) gate silently drops it: preserved
Anthropic thinking blocks, Codex encrypted-reasoning/message-item
replay, and OpenRouter multi-turn reasoning context are all lost after
a fork, with one more encoding layer added per fork.
The /branch copy loop had the same defect from the other side: it
forwarded reasoning but none of the structured columns, and both TUI
branch writers persisted role/content alone, dropping reasoning and
reasoning_content along with them.
Route the six dumps sites in append_message and _insert_message_rows
through a shared guard that keeps already-serialized strings as-is;
structured values from the live runtime are dumped exactly as before.
Forward the reasoning fields in all three branch writers, matching the
set gateway/slash_commands.py already forwards on its own /branch path.
Bundled backends/platforms/providers load without a plugins.enabled
entry ('must just work'), but plugins.manage reported them 'not
enabled' — clients rendered running plugins with an OFF switch.
Surface the truthful default; explicit disable still wins.
plugins.manage list rows now carry the canonical registry key and a
portable flag (Agent Plugins v1 plugin.json packages), and toggles
address the key — bare names collide across category dirs
(image_gen/fal vs video_gen/fal), so name-addressed toggles flipped
both. Portable packages' in-memory MCP servers also fold into
enabled_mcp_server_names(); without that their tools registered with
the MCP runtime but never reached the model's schema.
Titling fired on the first response, so a session sat unnamed for the whole
opening turn - p50 151s, p90 1212s across real sessions, because a turn is
tool calls, not one round-trip. A turn that failed or was interrupted never
got a title at all. Four surfaces each carried their own copy of the call.
Move it into the shared turn prologue and split it in two: a deterministic
title derived from the user's opening message, written inline before the
model runs, then one small-model call that upgrades it. The response is
constrained to a JSON object so there is no preamble to strip, and control
wrappers are stripped rather than refused, so a slash command titles as
what the user asked for instead of the command itself.
* fix(model-picker): serve cached custom-provider catalog on no-probe opens
#58183 stopped GUI picker opens from live-probing saved custom
OpenAI-compatible endpoints so a stopped local server could not stall the
picker. It gated the whole discovery block, not just the network call, so
`cached_fetch_api_models()` was skipped too — and with it the catalog an
earlier probe had already written to `provider_models_cache.json`.
A custom endpoint that is not the current provider therefore renders only
the models named in its config entry. A local server with 8 models loaded
shows the 1 model that was saved when the provider was first added, on
every picker open, while an explicit Refresh shows all 8.
Add `cache_only` to `cached_fetch_api_models()`: answer from disk within
the existing stale-serve window, never fetch, never revalidate off-thread,
return None on a miss. Split the three call sites in
`list_authenticated_providers()` into what the user's config permits
(`discover_models`, an explicit `models:` allowlist) and how we may obtain
it, so suppressing the probe now downgrades to a cached read instead of
skipping discovery outright. `discover_models: false` still pins, and a
cache hit no longer writes back to config since the probe that populated
it already did.
The latency win stands: a cold cache is a miss, so picker opens against
offline endpoints still make zero network calls.
* test(model-picker): pin the cached-catalog contract for no-probe opens
Cover both halves of the invariant, since fixing either one alone
reintroduces a bug the other guards against.
`cache_only` on `cached_fetch_api_models()`: a fresh entry and an entry
past its TTL but inside the stale-serve window both serve; an entry beyond
that window, an empty cache, rotated credentials, `force_refresh`, and a
missing base_url are all misses — and none of them fetch or spawn a
background revalidation.
`list_authenticated_providers()` on the GUI path: a non-current endpoint
with a warm cache reports its full catalog across all three provider
shapes (`custom_providers`, `providers:`, bare `provider: custom`) with no
live fetch attempted. A cold cache keeps the configured list and still
makes no network call, which is the #58183 guarantee. `discover_models:
false` keeps pinning, and a cache hit does not write back to config.
* fix: persist discovered custom-provider models in the hermes model flow
The `hermes model` named-custom-provider flow (_model_flow_named_custom)
probes the endpoint and shows the full catalog, but never persists it to the
entry's `models:` list. No-probe surfaces (dashboard, desktop, ACP) call
build_models_payload(..., probe_custom_providers=False) and only render the
configured `models:` list, so a provider added via `hermes model` collapses
to the single `model:` default everywhere except the CLI. OpenAI-compatible
providers added via a probing picker already benefit from
_save_discovered_models_to_config; the CLI flow did not.
Persist the live catalog after a successful probe, mirroring the picker path
in model_switch.py. A failed save is non-fatal.
* fix(model-picker): stop an auto-saved catalog pinning a keyless endpoint
The cached-catalog read added for no-probe picker opens still sat behind
the no-key discovery gate, so it never reached the shape that motivated
it: a keyless local model server.
`bool(api_key) or not has_explicit_models` is a network-cost gate. It
exists so Hermes does not probe an endpoint it cannot authenticate to
when that endpoint already declares its catalog (5f00f36ba, 1039e90b5).
Reading a catalog an earlier probe already paid for costs nothing, so
the gate belongs on the probe, not on discovery as a whole.
Left on the discovery side it re-pins the endpoint it was meant to
spare. A successful probe calls `_save_discovered_models_to_config()`,
which writes a plain list into `models:` — exactly the shape
`_models_config_is_allowlist()` reads back as an explicit user
allowlist. A keyless server therefore froze on the catalog of its first
probe and could never widen again, which is the "lineup changes after
config was written" case. f66319097 already carved the dict shape out of
this trap for the same reason; the list shape is the other door into it.
Move the clause to `_probe_live` at both custom-endpoint sites. Probe
suppression is unchanged — verified byte-identical to main across the
keyed/keyless x declared/undeclared matrix — and `discover_models: false`
remains the documented way to pin a catalog.
* test(model-picker): cover the keyless auto-save pinning trap
Three tests around the gate move, each failing on the code before it:
- a keyless endpoint carrying an auto-saved `models:` list still reads
its full cached catalog
- the same row, cold cache and probing enabled, still makes zero live
fetches — the network-cost gate the clause exists for
- an end-to-end round trip: persist a probe result via
`_save_discovered_models_to_config()`, reload it, and assert the shape
we wrote does not read back as a user pin
The round-trip test guards the whole chain rather than one branch, so a
future change that makes the saved shape look like an intentional
allowlist fails here even if the gate logic is refactored.
* fix(model-picker): key the custom-endpoint model cache by api_mode
`cached_fetch_api_models()` fingerprints entries with `api_mode`, but no
call site in `list_authenticated_providers()` passed it, so every custom
row resolved to the `api_mode=None` fingerprint. Two rows sharing a
base_url and credential but differing by `api_mode` are deliberately
distinct picker rows — it is part of `group_key` at both sites — yet they
collapsed onto one cache entry.
That was latent while probing was the only way to fill a row: a mismatched
entry was overwritten by the row's own live fetch. Serving that entry
without a probe makes it visible, so an `anthropic_messages` row could
render the catalog an OpenAI-mode row cached against the same URL. The
wire protocols differ (`x-api-key` + `anthropic-version` vs
`Authorization: Bearer`), so those catalogs are not interchangeable.
Persist `api_mode` on the group at both grouping sites — it is already
part of `group_key`, so it is constant across the group — and pass it
into the cache read. Section 3b (bare `provider: custom`) has no
`api_mode` in scope and already reads with the empty-credential
fingerprint, so it is unchanged.
Reported by Copilot review on #81973.
---------
Co-authored-by: xxxigm <tuancanhnguyen706@gmail.com>
Co-authored-by: Navlem <114683850+Navlem@users.noreply.github.com>
Widen of the PowerShell codepage cluster: the autostart registration
subprocess in tools_config.py was the last text=True capture in these
modules still decoding with the locale code page. Standardize on
encoding='utf-8', errors='replace' like the rest of the file (#53428).
A gate runs whatever command the operator configured, so its output is
arbitrary bytes. run_gate captured it with text=True and no encoding, which
decodes with locale.getpreferredencoding() under errors="strict".
One byte the decoder rejects — a test runner's checkmarks or CJK on a
non-UTF-8 Windows console, a stray binary byte anywhere in the stream — kills
subprocess's reader thread. proc.stdout comes back None, the `or ""` fallback
turns that into an empty tail, and an unhandled traceback is dumped to stderr.
The gate's pass/fail verdict still lands on the exit code, but the output tail
is exactly what the retry prompt feeds back so the agent can fix the failure.
With it empty the agent is told a gate failed and given nothing to act on, so
it burns every retry and the goal auto-pauses.
workspace_fingerprint has the same two calls; there a non-ASCII path in
`git status --porcelain` empties the fingerprint, silently disabling the
unchanged-gate skip that exists to stop a stalled agent re-running the same
red suite.
Decode as UTF-8 with errors="replace" — what git and modern toolchains emit,
and what 262 of the repo's 299 text-mode subprocess calls already do.
Complements the cherry-picked contributor fixes and closes out the
remaining sites of the 'missing explicit encoding' bug class, which is
now permanently gated by ruff PLW1514 (enabled repo-wide in
pyproject.toml and enforced by the blocking `ruff check .` step in
.github/workflows/lint.yml):
- tools/memory_tool.py: read MEMORY.md/USER.md via utf-8-sig so a
Notepad BOM never glues U+FEFF onto the first entry (issue #10878,
PR #10888 by @easyvibecoding — strict-decode contract of
_read_raw_checked preserved rather than errors="replace", so
undecodable files still refuse read-modify-write instead of being
lossily rewritten). Regression tests included.
- tools/skills_tool.py: SKILL.md and skill file reads pinned to
utf-8-sig + errors="replace" — deterministic across platforms instead
of the locale fallback proposed in PR #51701 (superseded: falling back
to cp1252/GBK makes the same skill render differently per host); .env
reader aligned with the canonical utf-8-sig dialect in hermes_cli/config.py.
- agent/shell_hooks.py, hermes_cli/main.py, gateway/slash_commands.py:
explicit utf-8 on the remaining fdopen/open text-mode sites flagged by
the AlexFucuson9 sweep series (#56033#56940#65565#66782#66791).
Co-authored-by: easyvibecoding <easyvibecoding@users.noreply.github.com>
Co-authored-by: AlexFucuson9 <AlexFucuson9@users.noreply.github.com>
Co-authored-by: flyingdoubleg <wangzhe00zju@gmail.com>
Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>
Follow-up to the auth.json UTF-8 read fix in this PR. A repo-wide scan for
the same bug class found three more callers that read ~/.hermes/auth.json
via Path.read_text() with no encoding — same Windows cp1252 hazard:
- agent/auxiliary_client.py _read_nous_auth: a non-ASCII byte raised
UnicodeDecodeError, the broad except swallowed it, and Nous silently
stopped being available as the auxiliary (vision/summarization) provider.
- tools/xai_http.py has_xai_credentials: same failure mode — xAI OAuth
silently looked absent on Windows.
- hermes_cli/main.py is_setup_complete: same; has a config.yaml fallback so
the impact is milder, but the read is still wrong.
All three now use read_text(encoding="utf-8-sig"), matching _save_auth_store's
write encoding. A repo-wide grep confirms there are no remaining
json.loads(...read_text()) reads of auth.json without an explicit encoding.
Tests: rewrote the Windows-encoding regression tests to actually exercise the
bug on POSIX too — a new windows_default_encoding fixture forces a no-encoding
read_text() to decode as cp1252 (the Windows default), and _write_utf8 now
emits real non-ASCII UTF-8 bytes (ensure_ascii=False) so the bytes actually
trip cp1252. Verified each test fails when its fix is reverted (including
the two new sibling-reader tests).
The auth store readers (_load_auth_store, _import_codex_cli_tokens, and the
shared Nous store reader) called Path.read_text() with no encoding, so bytes
were decoded with locale.getpreferredencoding() — cp1252 on Windows. The
stores are *written* as UTF-8 (os.fdopen(..., encoding="utf-8")), so any
non-ASCII byte (a CJK or emoji credential label, an accented display name in
OAuth state) raised UnicodeDecodeError on read.
Worst case: _load_auth_store's broad except then copied the file to .corrupt
and returned an empty store, silently wiping every provider credential on the
next launch. The sibling reader at line 2161 already used
read_text(encoding="utf-8"), confirming the omission was unintentional.
Use utf-8-sig (matching the .env handling in config.py) so a BOM from a
Notepad-edited file is tolerated too.
Adds regression tests covering the UTF-8 round-trip with a non-ASCII label,
BOM tolerance, no-corrupt-on-valid-load, and that the readers pass an explicit
encoding (guard against future regressions). Verified the tests fail when the
fix is reverted.
Closes no issue — found via cross-platform code audit (the bug is not in the
issue tracker).
send_cmd._load_hermes_env intentionally reimplements a minimal dotenv
load (no secret-source pulls, no sanitize rewrite, get_hermes_home path
resolution incl. Windows/profile override), so the shared-loader BOM fix
is mirrored in place: utf-8-sig primary read, BOM strip before the
latin-1 stream fallback.
Claude-Session: https://claude.ai/code/session_01JPmJz5u1Bvtw4cCRvRWnYr
utf-8-sig only covers the primary decode. BOM + invalid UTF-8 (e.g.
PowerShell BOM + cp1252 body) forced latin-1, which kept EF BB BF as
part of the first key name and dropped the canonical name. Strip the
BOM before latin-1 decode and load via stream so override= is preserved.
PowerShell 5.1 Set-Content -Encoding UTF8 and Windows Notepad write a
UTF-8 BOM. load_dotenv(encoding="utf-8") kept U+FEFF on the first key
name, so the canonical name was absent from os.environ and Hermes looked
unconfigured with no error. utf-8-sig strips the BOM and is a no-op for
BOM-less UTF-8; latin-1 fallback unchanged.
Prevent UnicodeEncodeError when model text contains U+D800-range
surrogates by sanitizing to U+FFFD before writing to UTF-8 stdout.
Co-authored-by: Cursor <cursoragent@cursor.com>
Ports #68497 forward onto current main per teknium1's review.
input() can raise UnicodeDecodeError when the terminal encoding
cannot decode the byte sequence (e.g. a non-UTF-8 locale, or an
embedded terminal). The prior port targeted hermes_cli/main.py, the
pre-refactor location -- the update pipeline moved to
hermes_cli/update_cmd.py in 927463efcc.
Per review, fixed all three interactive update prompts that call
input() directly, not just the one this originally targeted:
1. Config-migration prompt (update_cmd.py:~3989): extends the existing
except EOFError to also catch UnicodeDecodeError, prints an
actionable 'hermes config migrate' hint, and falls through to the
skip branch (response=n).
2. Stash-restore prompt (_restore_stashed_changes, ~line 971): the raw
input() call here had NO exception guard at all -- not even for
EOFError. Added a try/except covering both EOFError and
UnicodeDecodeError, falling back to the existing skip-restore path
(changes remain safely in git stash, restorable manually).
3. Upstream-remote prompt (_sync_with_upstream_if_needed, ~line 1274):
already caught (EOFError, KeyboardInterrupt) but not
UnicodeDecodeError -- added it to the existing tuple.
Also dropped the incorrect #12884 reference (a TUI sticky-scroll
report, unrelated to this update-encoding issue, per the review).
4 new tests pass covering all three call sites (config-migration prompt
via cmd_update end to end, stash-restore and upstream-remote prompts
via direct unit tests against their own functions), plus an EOFError
sanity test confirming the stash-restore fix doesn't regress that case
either (it had no guard before). 6/6 in the full
tests/hermes_cli/test_update_yes_flag.py file (no regression).
Persist display.personality only; apply rendered text as an in-session
overlay across CLI, TUI config.set, and gateway /personality.
Co-authored-by: kyssta-exe <kyssta-exe@users.noreply.github.com>
Co-authored-by: EMT5320 <1908937833@qq.com>
Keep agent.system_prompt user-owned; named personalities resolve as an
ephemeral overlay via display.personality.
Co-authored-by: kyssta-exe <kyssta-exe@users.noreply.github.com>
Co-authored-by: EMT5320 <1908937833@qq.com>
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.
Fixes 13 issues found in PR #20774 review:
1. Wiring: engine selection moved from run_agent.py to agent/agent_init.py
(where init_agent lives on current main). Transform hook moved from
run_agent.py to agent/conversation_loop.py (where run_conversation lives).
2. Prompt caching: replace copy.deepcopy with copy-on-write (shallow list
copy + clone only messages that are mutated). Use last_prompt_tokens
from update_from_response instead of re-estimating tokens every call.
System extension injection is idempotent (one-time cache break).
3. Signature mismatch: _message_signature renamed to _content_signature
and now excludes tool_calls/tool_call_id from the hash. This prevents
mismatches when _canonicalize_api_tool_calls re-serializes argument
JSON with sort_keys=True on the API copy.
4. update_model: accepts api_mode parameter (required by agent_init.py).
5. Reconciled with select_context: transform_api_messages is a separate
hook that runs AFTER select_context and sanitization, before
prompt-cache marker placement. Both hooks coexist with clear ordering.
6. Dedup/purge: kept as DCP-specific strategies (different semantics from
ContextCompressor._prune_old_tool_results — DCP deduplicates by
tool+args signature, not by content hash).
7. Removed copy.deepcopy: replaced with shallow list copy + copy-on-write
via _clone_if_needed. Only messages that are actually mutated get
cloned.
8. Removed redundant _ensure_refs call: _match_api_messages_to_refs no
longer calls _ensure_refs (the caller already called it).
9. _message_key still uses index (needed for positional ref assignment),
but _content_signature is cached per id(msg) to avoid re-hashing.
10. _inject_nudge: only injects into user messages, never falls back to
non-user messages (prevents role semantics violations).
11. Memory: _evict_inactive_blocks bounds blocks_by_id to
_MAX_INACTIVE_BLOCKS (50) deactivated blocks.
12. Merged _range_tool_schema and _message_tool_schema into a single
_compress_tool_schema. Merged _handle_range_compress and
_handle_message_compress into _handle_compress.
13. Dropped DCP_CONTEXT_ENGINE_PR_SPEC.md (temporary file, not for tree).
Config defaults kept minimal in hermes_cli/config_defaults.py (only
the keys the engine actually reads, not the full DCP-compatible surface).
Closes#20717
Salvage of PR #17973 by @TKCen (Sebastian Hänisch), re-implemented on
current main to preserve speed/instructions/provider params,
prepare_spoken_text normalization, OPUS_VOICE_PLATFORMS, is_write_denied
path security, microsecond timestamps, and the streaming-TTS gate.
- Split long TTS text into provider-safe chunks instead of truncating
- Pack generated audio against platform upload limits (Discord 10MB,
Telegram 50MB, configurable via tts.delivery_profiles)
- Combine chunks with ffmpeg (OGG/Opus re-encoded, MP3 stream-copied)
- Multi-file delivery when combination fails or would exceed limits
- Remove hard [:4000] truncation from all callers (cli.py, voice.py,
gateway/run.py, gateway/platforms/base.py)
- Gemini TTS raises ValueError instead of silently truncating when
composed prompt exceeds the provider limit
Simplify-code fixes: removed dead all_touched_paths set, added
try/finally for scratch file cleanup on exception, clean error response
on chunk failure instead of leaking stale file_path.
Four fix-forwards from the adversarial post-merge audit of the Aug 7
unreviewed merge batch:
- estop (#81148): is_engaged() now fails SAFE (engaged) on stat errors;
the gateway estop gate lets recognized slash commands and replies owned
by in-flight work (update prompts, clarify, slash-confirm, tool
approvals, running sessions) through instead of consuming them; new
gateway /pause [reason|off] command gives messaging-only operators an
in-band engage/resume path (busy_policy=dispatch so it works mid-run).
- cron monitor mode (#81138): execution-mode invariants (monitor x
no_agent, monitor_script x monitor_url, no_agent-requires-script) now
have ONE owner (_validate_job_mode_invariants) called from BOTH
create_job and update_job, so the create-time invariant can no longer
be silently violated through the update door.
- cron notepad (#81139): remove_job now clears the job's notepad rows
(clear_notepad was dead code -> orphaned KV state forever); clear is
best-effort and no-ops without creating notepad.db.
- delegation batch gate (#81141): template-marker regex narrowed to
multi-word placeholder shapes only (<feature name>, {file_path}) so
generics (Vec<T>), HTML tags, JSON snippets, glob braces and f-string
style no longer reject legitimate batches; duplicate-goal rejection
removed (best-of-N fan-outs are legitimate).
--resume latest resolves the most recent session through the same
workspace-scoped MRU lookup as -c (TUI source first under --tui, with
classic-CLI fallback). --in DIR chdirs before session resolution so the
lookup keys off DIR's workspace, and pins the session there by skipping
the recorded-cwd restore.
Requested by @Jeff9James: hermes --tui --resume latest --in ./dir
- Migrate the missed 6th inline formatter (update_cmd.py backup-size
display) to the shared helper.
- checkpoints._fmt_bytes: plain alias instead of a None-guard wrapper —
every caller feeds ints from checkpoint_manager (all size fields
initialize to 0), so the None path was dead defensive code.
- Drop the fallback= kwarg (zero production callers; '?' default is the
real inherited contract and stays).
- curator_backup + context_references: call format_bytes directly (single
internal call site each, zero external importers — alias was churn
avoidance with nothing to avoid). backup/_format_size and
doctor/_human_bytes keep their aliases (claw.py + tests pin the former;
three call sites use the latter).
- Reshape the loop so the trailing TB return is reachable (no dead line).
- Tests: replace alias-identity assertions (ossified the delegation
mechanism) with behavior-contract equality over a value sweep;
mutation-checked red-green.
- update_cmd parity: byte-identical B-GB vs the old inline loop; gains
the TB tier.
Five modules each carried a private near-identical human-readable byte
formatter (backup._format_size, checkpoints._fmt_bytes,
doctor._human_bytes, context_references._human_bytes,
curator_backup.format_size). Three of them silently topped out at GB and
rendered a 1 TiB value as '1024.0 GB'. All five now alias one shared
format_bytes in hermes_cli/sizefmt.py (sibling of timefmt.py, same
zero-dependency rationale), keeping each module's established local name
so no caller churns.
Deliberately NOT migrated (behavior differs on purpose):
- session_recovery._format_bytes: binary suffixes (KiB/MiB/GiB)
- qqbot chunked_upload.format_size: '100.0 B' one-decimal style, pinned
by its protocol tests
Net -33 production LOC before the new module; parity verified over a
16-value corpus against all five verbatim originals (only divergence:
the TB tier fix). Contract tests mutation-checked red-green.
_format_db_size reimplemented human-readable size formatting two
imports away from backup._format_size, which doctor already leans on
for _QUICK_STATE_FILES. Delegate and keep only the stat-failure wrap.
Sizes now scale units (KB/GB) instead of pinning everything to MB.
hermes doctor already warns when the linked SQLite carries the WAL-reset
bug, but it never said which databases are actually exposed. A database
already in WAL mode on a vulnerable runtime can still corrupt; one on a
rollback journal cannot. Doctor now lists each Hermes-managed database
with its journal mode next to the SQLite version line and marks the WAL
ones as exposed when the runtime is vulnerable.
The probe reads the 20-byte file header and checks byte 18 (2 = WAL,
1 = rollback journal). It deliberately avoids the SQLite engine: even a
read-only open creates -wal/-shm sidecars next to a WAL database, needs
directory write access, and can wait on locks. The header read does none
of that. It cannot tell delete from truncate/persist, so doctor reports
'rollback journal mode' rather than an exact mode name. Missing files
are skipped; empty, unreadable, or corrupt files are reported as
unreadable without failing doctor.
The database list reuses backup.py's _QUICK_STATE_FILES plus per-board
kanban databases. Exposure uses hermes_state.is_sqlite_wal_reset_vulnerable,
so the 3.50.7 and 3.44.6 backports count as fixed.
OpenCode Go serves GPT 5.6 Luna only via the Responses API per its
published endpoint table (https://opencode.ai/docs/go/#endpoints), but
opencode_model_api_mode() had no gpt- case in the Go branch, sending
Luna to /v1/chat/completions. The relay's shim streams full text but
never emits a finish_reason chunk, so every complete answer is
classified as a mid-stream drop and each turn fails with 'Response
remained truncated after 4 continuation attempts'.
Mirror the Zen branch: gpt- on Go -> codex_responses. Base URL needs
no change (normalize_opencode_base_url already keeps /v1 for
codex_responses). Extend test_opencode_go_api_modes_match_docs with
the Luna assertions.
- Move classify_persistence_error into hermes_state beside is_disk_full_error
and delegate the disk bucket to it (fixes 'ENOSPC writing state.db' and
'not enough space' classifying as unknown). run_agent keeps a thin lazy
delegating wrapper so the documented import path and fast import survive.
- Classify CompressionSessionBusyError (and its RPC-wrapped message forms)
as 'locked': the motivating #81227 failure mode stringifies to 'is being
compressed by another writer', which the substring heuristic missed.
- Export PERSISTENCE_ERROR_CAUSES and iterate it in the cron explainer
suppression instead of a hardcoded tuple, so a future cause bucket cannot
silently desynchronize cron delivery.
- Hedge the gateway locked/unknown recovery wording ('should already be
saved' instead of 'was recorded') to match the explainer - the early
turn-start persist may also have failed.
- Drop STATE_DB_WAL_WARN_BYTES (speculative dead constant with no consumer;
the pre-existing 50 MB doctor WAL check covers the warning).
- Tests: compression-busy classification, is_disk_full_error delegation,
causes-tuple coverage; mutation-checked red-green.
Review follow-ups from the pre-push falsification pass:
- collect_state_db_stats now routes through _connect_tracked_db so the
module's byte-probe guard sees the read-only connection (consistency
with the module's own ro-connection precedent; prevents a raw header
probe from cancelling this reader's locks in multi-threaded callers).
- Drop the new >256 MiB WAL warning from the stats renderer: doctor's
pre-existing 50 MB WAL check (with --fix checkpoint) already covers
WAL runaway, and two warnings for one condition is noise. The test now
locks in the dedup decision.
- Locked-cause explainer says the message 'should already be saved'
rather than overclaiming when the early turn-start persist also failed.
Operators had no Hermes surface showing state.db size, WAL health, index
family shape, or how many processes hold the database — all of which were
needed to diagnose a lock-contention incident on a 4.5 GB multi-writer
install.
Adds collect_state_db_stats() (strictly read-only URI connection, no
SessionDB instantiation, per-field best-effort) and a /proc-based
count_db_holders() to hermes_state, and wires a stats block into hermes
doctor's state.db section: logical size, pages/freelist, WAL size,
message/session counts, journal mode, holder count, FTS table presence
and deferred-rebuild status. Advisory warnings at >1 GiB (suggest
sessions.auto_prune and, when the v23 rebuild is pending or the legacy
trigram shape is detected, an offline 'hermes sessions optimize-storage')
and >256 MiB WAL (checkpoint health). Any stats failure degrades to a
single info line.
Two claim-failure diagnostic paths (cronjob_tools.py:629,921) still used
the old inline 'not enabled or state==paused' check. After get_job()
normalizes via effective_job_state, a half-paused record has
state='scheduled' and enabled=True, so the inline check returned False —
mislabeling the job as 'already being fired' instead of 'paused/disabled'.
Also hoists effective_job_state/is_job_runnable to the top-level import in
cronjob_tools.py (was function-local) and updates console_engine.py's
_format_job to use effective_job_state instead of the old inline
state-or-enabled derivation — a fourth display path the original PR missed.
Follow-up to PR #81287.
pause_job already sets enabled=false atomically with state/paused_at, but
get_due_jobs only checked enabled — so a contradictory record
(enabled=true + paused_at/state=paused) still fired. That was the 07-30
outage failure mode: list looked frozen, fleet kept merging.
- is_job_runnable / effective_job_state: pause markers gate fire; display
derives from the scheduler-honoured enabled flag so half-paused never
renders as [paused]
- get_due_jobs self-heals enabled=false + logs error on contradiction
- claim_job_for_fire uses is_job_runnable (paused_at counts too)
- list/format paths use effective_job_state
- behavioural tests: pause blocks due fire; half-pause self-disables
SessionResumeTooLargeError said 'across its lineage' even when the CLI
mid-setup path counted only the tip segment; the exception now takes a
scope phrase.
OFFSET paging made the streaming export O(n^2) on huge transcripts;
after_id keyset paging keeps each page seek O(1). Adds after_id to
SessionDB.get_messages (ascending-only, guarded against latest/offset
combos).
The mid-setup CLI resume path loads only the tip session's rows, so
gate it with a tip-only count instead of the full-lineage count (which
over-rejected heavily-compressed sessions). Transient guard failures
(locked DB, adaptor stores) now log and proceed instead of blocking
resume with a new error.
sessions.max_resume_messages / sessions.max_export_messages (default
20000, 0 disables) replace the hardcoded hard-rejects, and the CLI
'sessions export' guard becomes per-session instead of cumulative so
full-DB backups of many small sessions keep working. Error guidance now
points at the config override instead of the (corruption-only) repair
command.
Two follow-ups to the off-loop move, from external review (both verified,
the second larger than reported):
- Config read-modify-write handlers moved to worker threads could now
interleave — _CONFIG_LOCK covers each load/save individually, never the
span between them; the event loop used to serialize these accidentally.
New _CONFIG_MUTATION_LOCK (worker-threads only, so it can never block
the loop) held across the whole load→mutate→save span in all seven RMW
handlers. update_config_raw skipped: it's a full-document replace with
no server-side read, so a lock cannot close its client-side window.
- The review flagged two skills routes still taking _SKILLS_PROFILE_LOCK
on the event loop; a systematic audit of hermes_cli/web_routers/ found
24 on-loop routes (skills 5, mcp 9, tools 10, cron 1). All moved to the
same inner-_run + asyncio.to_thread pattern, mutating ones under the
mutation lock, uniform lock order (_SKILLS_PROFILE_LOCK →
_CONFIG_MUTATION_LOCK). Await-safe _config_profile_scope routes, plain
def routes, and already-threaded routes unchanged.
Regression tests: concurrent theme+font updates both survive (fails with
the lock nulled: "theme write lost to a concurrent font write"); event
loop stays responsive while the profile lock is held during GET
/api/skills. 214 tests passing across the touched suites.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The diagnostics loop watchdog caught GET /api/config freezing the gateway
event loop for >1s, stack-sampled blocking on _SKILLS_PROFILE_LOCK inside
_profile_scope. Any async handler that entered _profile_scope (process-wide
threading lock) or called load_config()/save_config() on-loop could stall
every chat and WebSocket at once while a slow lock-holder ran.
Move 28 such handlers to the existing inner-_run + asyncio.to_thread
pattern (contextvar-safe: the whole scope enter/body/exit stays inside one
worker thread). Handlers using the await-safe _config_profile_scope, plain
def endpoints (FastAPI threadpool), and tui_gateway's contextvar-only
decorator are unaffected and unchanged.
Regression test holds _SKILLS_PROFILE_LOCK in a thread while calling
GET /api/config and asserts an event-loop heartbeat keeps ticking; it fails
against the pre-fix code.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Surfaced during the post-merge review pass on our own #81113 follow-up:
cached_fetch_api_models gained _cache_entry_valid (numeric-'at'
validation) but its sibling cached_provider_model_ids still did
float(entry.get('at', 0)), which raises ValueError/TypeError on a
hand-edited or corrupted provider_models_cache.json row and propagates
uncaught into the /model picker call sites. Same fix, same helper:
corrupt rows are now a cache miss (live fetch), never an exception.
Both wrappers now share the identical validity predicate, closing the
divergence the 'mirrors' docstring promised away.
Also two test nits from the same review: unused OrderedDict import
dropped and the drain-order assertion strengthened to pin LRU-first
FIFO order in tests/gateway/test_agent_cache_pressure.py.
Mutation-checked: restoring the raising float() form makes the new
corrupt-at tests fail.
Rescope: hermes verify fills only the runtime-smoke gap and plugs into
the pieces Hermes already has instead of standing beside them.
- agent/verification_evidence.py: record_verify_run() — explicit ledger
write for hermes verify results (shared _insert_evidence factored out
of record_terminal_result). Passing runs mark the workspace passed
like scripts/run_tests.sh; failures are recorded; --phase/--skip-start
runs are recorded as targeted scope.
- hermes_cli/verify_cmd.py: record results into the ledger on completion
(fail-silent, HERMES_SESSION_ID attribution); on the detect path merge
detect_project_facts verify commands the recipe missed into the
recipe's test list (never applied to a saved manifest).
- agent/verification_stop.py: recipe-aware nudge — when the workspace
has a runnable recipe (start command or .hermes/environment.json),
suggest hermes verify --json as the preferred full check; cheap,
try/except-guarded detection that can never break the nudge path.
- agent/verify/recipes.py: document layer ownership (coding_context =
cheap prompt facts; verify/recipes = deep runtime recipe).
- tests/verify/test_ledger_and_nudge_integration.py: 17 tests covering
ledger pass/fail recording, the closed edit->nudge->verify->satisfied
loop, recipe-aware nudge wording + fail-silence, and the facts merge.
Connection-class infrastructure failures on remote terminal backends (SSH
host unreachable/timed out, Docker daemon down or missing, remote file
sync failing on a dead link) previously surfaced to the model as raised
RuntimeError tracebacks. The model got a stack blob with no guidance and
the failure was indistinguishable from a tool bug.
Now:
- New EnvironmentConnectionError(RuntimeError) in tools/environments/base.py
carrying a reason + retry_hint. Subclassing RuntimeError keeps every
existing catcher working.
- ssh.py classifies connect-refused, connect-timeout, scp, remote mkdir,
bulk upload/download, and remote rm failures as connection errors.
- docker.py classifies all four _ensure_docker_available() failure paths
(missing exe, non-executable exe, daemon timeout, `docker version`
failure).
- terminal_tool catches EnvironmentConnectionError and returns a
structured tool result the model can act on:
{"status": "degraded", "reason": ..., "retry_hint": ..., "exit_code": -1}
The failed backend is evicted from the environment cache so a later
call retries from scratch — recovery is automatic once the backend is
reachable again.
- Config gate terminal.degraded_mode: warn|fail (default warn) in
config.yaml, bridged as TERMINAL_DEGRADED_MODE across all four bridge
sites (cli.py env_mappings, gateway/run.py _terminal_env_map,
TERMINAL_CONFIG_ENV_MAP, DEFAULT_CONFIG). "fail" preserves the
historical error+traceback tool result.
- Command failures (nonzero exit, command-not-found) are NOT touched —
only infrastructure failures classify as degraded.
Tests: tests/tools/test_terminal_degraded_mode.py (15 tests) covering
exception classification for ssh+docker, structured degraded results,
no-caching of degraded envs, recovery after the backend returns,
nonzero-exit results unaffected, fail-mode preservation, invalid-mode
fallback to warn, and the four-site config bridge invariant.
Inspired by: Claude Cowork degraded-backend behavior (idea-level,
docs-only evidence).
Adds a bounded, read-only health probe per CONFIGURED tool backend, run
only when the user explicitly passes `--live` (real network calls):
- Firecrawl: credit-usage metadata GET (auth check, no scrape spend)
- FAL: models metadata GET (never a generation)
- Browser: headless launch + about:blank + close (full cleanup)
- MCP: initialize + tools/list per configured server (reuses the
`hermes mcp test` machinery in mcp_config._probe_single_server)
- TTS/STT: provider models/voices list GET (openai/groq/elevenlabs);
local providers (edge/piper/faster-whisper/...) skipped
Invariants:
- Opt-in only: zero probes without --live (default False)
- Bounded: sequential, per-probe timeout (doctor.live_probe_timeout,
default 10s, config.yaml knob)
- Never mutates state; unconfigured backends skip with a note
- Failure isolation: every probe wrapped in a catch-all; a probe crash
can never break the doctor run; failures append to the issues summary
New: hermes_cli/doctor_live.py, tests/hermes_cli/test_doctor_live.py
(23 tests, probes mocked at the HTTP/client seam).
Wired: --live flag in subcommands/doctor.py; run_doctor calls
maybe_run_live_checks after all static checks.
Coordination: PR #70124 (--probe-routes) probes LLM routes; this flag
probes TOOL backends — different surface, no code-region collision
(the run_doctor hook here sits at the end-of-run summary, not the
API Connectivity section #70124 extends).
Inspired by: paradigmxyz/centaur tool-health-smoke (MIT/Apache-2.0);
sibling: #70124 (LLM route probes — different surface)
write_file/patch targeting AGENTS.md, CLAUDE.md, SOUL.md, .cursorrules, or a
project-local .hermes config dir now ALWAYS prompt the human for approval —
even under --yolo/auto-approve — and fail closed when no human channel
exists. These files steer future agent behavior, so an injected write to
them is a prompt-injection persistence vector.
Design:
- New _check_protected_instruction_write() in tools/file_tools.py, a
sibling of _check_sensitive_path that returns approval-required rather
than a hard error. It realpaths before matching (symlink lesson from
#41351), matches basenames case-insensitively in ANY directory, rejects
'./x/../AGENTS.md' traversal via normpath, and gates files whose
immediate parent dir is `.hermes` (project-local config) while exempting
the authoritative ~/.hermes home (governed by its own guards).
- Approval is ONE-OPERATION only: no session/permanent persistence, no
yolo bypass — intentionally does not route through _run_approval_gate.
Gateway sessions get the button round-trip with allow_permanent and
allow_session both False; CLI uses the per-thread approval callback;
no channel at all = BLOCKED (fail closed).
- Multi-file V4A patches: ONE protected file gates the ENTIRE patch (a
single prompt lists all protected targets; deny applies nothing).
- Config: security.protected_instruction_files (default true) and
security.protected_instruction_extra_patterns (fnmatch on basename).
Config read failure keeps the gate ON.
Tests: 22 new cases in tests/tools/test_file_write_safety.py covering the
adversarial checklist — deny/approve/yolo-bypass attempt, symlink at a
protected target, case variants, relative traversal, arbitrary-directory
basenames, project-local .hermes, checkout-nested-under-~/.hermes
non-gating, patch replace + V4A multi-file atomicity, gateway round-trip,
fail-closed with no human, config off/extra patterns.
Ported from: RooCodeInc/Roo-Code RooProtectedController (Apache-2.0);
companion: #58631 (terminal vector), symlink lesson from #41351.
Two small config-gated features:
1. Kanban orphaned-card reconciliation (kanban.reconcile_orphans, default
true, config.yaml): a running card with broken claim bookkeeping
(claim_lock or claim_expires NULL — crash mid-claim, manual SQL, DB
restore) is invisible to all existing recovery paths
(release_stale_claims requires claim_expires NOT NULL,
detect_crashed_workers requires host-local lock + pid,
detect_stale_running is config-disabled by default) and shows Running
forever. New reconcile_orphaned_running() pass in kanban_db.py runs
each dispatch_once tick: requeues orphans to ready with an explanatory
comment, closes any leaked run, emits a 'reconciled' event, and defers
when the recorded PID is still alive on this host (never requeue
beside a live worker). Surfaced via DispatchResult.reconciled_orphans.
2. Per-server MCP identity header (mcp_servers.<name>.identity_header,
config.yaml): optional {name, value_from: static|profile, value}
mapping; the header is attached to that server's HTTP/SSE transport
requests. 'static' sends the config value; 'profile' resolves the
active Hermes profile name once at connect time (no per-call
mutation). Explicit per-server headers of the same name (any casing)
win. Invalid blocks warn-and-ignore; stdio servers warn-and-ignore.
Tests: tests/gateway/test_kanban_reconcile_orphans.py (9),
tests/tools/test_mcp_identity_header.py (13), all written first (RED)
then implemented (GREEN). No new HERMES_* env vars.
Inspired by: openai/symphony tracker reconciliation (Apache-2.0) +
Poke per-user MCP identity (idea-level).
Resumable ESTOP sentinel at $HERMES_HOME/ESTOP that halts NEW work only:
- agent/estop.py: sentinel engage/disengage/is_engaged (single stat, no
caching), optional reason + timestamp stored as JSON, paused_reply()
notice, check_paused() log-once-per-engagement helper. Corrupt/empty
sentinel still pauses (fail safe); a `touch ~/.hermes/ESTOP` works.
- cron/scheduler.py: tick() skips dispatch while engaged (logged once per
engagement, not per tick). Due jobs simply wait for the next tick after
resume — in-flight runs are never touched.
- gateway/kanban_watchers.py: dispatcher skips auto-decompose and worker
spawning while engaged; zombie reaping still runs and running workers
finish naturally.
- gateway/run.py: new gateway turns (post-auth, non-internal) get a brief
"Hermes is paused" reply instead of an agent run. Internal events
(in-flight background completions) bypass the gate.
- hermes_cli/subcommands/pause.py: `hermes pause [--reason]` and
`hermes resume`, wired into main() and _BUILTIN_SUBCOMMANDS.
- hermes_cli/status.py: `hermes status` shows a PAUSED banner (one stat).
- tests/test_estop.py: 20 tests — sentinel lifecycle, reason surfacing,
log-once, cron skip + resume, kanban gate, gateway paused reply +
internal bypass, CLI idempotence, builtin-set parity, status line.
Never kills in-flight work; resumable with no restart. Footprint ladder:
CLI command only, no new model tool, no new env vars.
Ported from: gastownhall/gastown estop.go (MIT); related prior art:
#26778 (/panic — kill/exit semantics, deliberately different: ours is a
resumable pause), #44617 (interrupt in-flight cron — out of scope here).
Validate a job's configuration BEFORE any agent machinery is constructed:
- missing provider API key (AuthError from a read-only
resolve_runtime_provider probe; skipped when a fallback_providers chain
is configured, since auth-fallback may rescue the run)
- attached skill not ready (skill_view readiness_status=setup_needed —
missing required env vars / commands / credential files)
- delivery platform unknown or unconnected (deliver=local/origin/all are
never checked; gateway-config load failures fail open)
On a failing check run_job returns a [blocked_config]-marked error without
constructing AIAgent/MCP/etc, so a misconfigured job never burns an LLM
call. run_one_job records last_status='blocked_config' and delivers the
alert exactly ONCE across ticks (persisted preflight_alerted bit — the
alert-once shape from the #73506 dead-pin auto-pause); the next healthy
run clears the marker so a future break re-alerts. Every preflight check
fails open: only an affirmative misconfiguration verdict blocks.
Config: cron.preflight (default true); `cron.preflight: false` restores
the old fail-during-run behavior. Documented in the cron user guide and
config defaults.
mark_job_run gains an optional status= override (unblocked call shape
unchanged) and drops preflight_alerted on any successful run.
Tests: tests/cron/test_preflight_config.py (blocked_config + no agent +
single alert across two ticks, healthy job unaffected, recovery clears
dedup, fallback-chain rescue, opt-out restores old behavior, skill
readiness miss, unknown delivery platform, deliver=local never loads
gateway config). Full tests/cron/ + cronjob tool suite green (525 tests).
Ported from: paperclipai/paperclip execution-semantics §5 (MIT);
in-repo precedent: #27948, #73506
- cron/notepad.py: SQLite-backed cron_notepad(job_id, key, value,
updated_at) store in its own profile-local db (cron/notepad.db),
following the executions.py connection/transaction pattern. APIs:
set_note/get_note/delete_note/list_notes/clear_notepad +
render_notepad_section. Documented size caps: 16KB per value,
128-char keys, 64KB per job total; oversized writes raise ValueError.
- cron/scheduler.py: inject non-empty notepads into the job prompt at
the context_from data-injection seam as a clearly-labeled
"Job notepad (persistent across runs)" section that also documents
the CLI write path. Empty notepad renders "" — byte-stable prompts
for jobs that never use the feature.
- hermes_cli/cron.py + hermes_cli/subcommands/cron.py:
`hermes cron notepad <job_id> [get|set|delete|list]` under the
existing cron subcommand tree (no new top-level command, no new
model tool — the agent writes via terminal + CLI).
- tests/cron/test_notepad.py: CRUD, durability, cap enforcement,
prompt injection, byte-stable empty case, read-failure resilience,
CLI handler + dispatch (TDD; watched fail first).
Inspired by: Amp (Sourcegraph) cron notepad (idea-level, proprietary —
zero code).
Add monitor-mode cron jobs: a cheap monitor source (monitor_script or
monitor_url) runs on every tick BEFORE any agent machinery is built.
Its output is hashed as exact bytes and compared to the hash stored
from the last agent-triggering tick:
- unchanged -> agent run suppressed entirely (no LLM, no delivery);
the tick is recorded as a silent no_change run visible in the
executions ledger doc
- changed -> a MONITOR CHANGE DETECTED block (capped unified diff of
previous vs current output + the new output) is injected into the
prompt via the existing extra_prompt seam, then a normal agent run
- first run -> always runs the agent with a baseline block
- source failure -> delivered as an ERROR alert, never treated as a
change; the stored hash is untouched so recovery to prior output
still suppresses
Implementation:
- cron/monitor.py (new): hash/diff/URL-fetch/state persistence.
monitor_script reuses _run_job_script (same ~/.hermes/scripts/
containment + interpreter rules); monitor_url is a bounded GET
(30s, 256KB, http/https only). Output is exact bytes by design —
scripts should emit stable output (documented).
- cron/jobs.py: additive job fields monitor_script / monitor_url /
monitor_state {last_output_hash, last_changed_at}. JSON job records
need no migration. create-time validation: sources are mutually
exclusive and incompatible with no_agent=True.
- cron/scheduler.py: one tight monitor gate in run_job between the
no_agent short-circuit and the LLM path (outside sibling-lane
regions). State persists in jobs.json + a per-job snapshot file, so
suppression survives scheduler restarts.
- tools/cronjob_tools.py: additive optional monitor_script/monitor_url
params on the cronjob tool (create + update, empty string clears),
path containment validated at the API boundary, surfaced in
_format_job.
- hermes_cli: --monitor-script/--monitor-url on `hermes cron create`
and `hermes cron edit`; `hermes cron list` shows the monitor source
and last-changed time.
Tests (tests/cron/test_monitor_kind.py, TDD): unchanged suppresses,
changed injects diff, first run always runs, hash persists across
module reload (restart), script failure is error-not-change with hash
untouched, create/update validation, tool wiring + path-escape reject.
Inspired by: ChatGPT Work monitor tasks (idea-level, docs-only);
enabler: #80774
Answers "what would the approval system do with this command?" without
executing it, prompting anyone, or persisting anything. Composes the
REAL runtime evaluators from tools/approval.py in the same order as
check_all_command_guards: container-skip gate, hardline blocklist,
sudo-stdin guard, user approvals.deny rules, yolo/mode-off bypass,
permanent command_allowlist, dangerous-pattern detection. Because the
same functions run — including _command_detection_variants's
normalization/de-obfuscation path — an obfuscated command gets exactly
the verdict its plain form would get at runtime, and the output shows
the normalized-variant trace the detectors actually evaluated.
- hermes_cli/approvals_test.py: evaluate_command() + text/JSON output.
Script-friendly exit codes: 0 allow, 1 usage, 2 ask-approval, 3 deny
(hardline / sudo-stdin / user deny rule).
- hermes_cli/subcommands/approvals.py: `test` subparser with --env-type
(default local), --json, and a REMAINDER command (dest command_words —
NOT "command", which main.py's startup path reads as the top-level
subcommand name).
- hermes_cli/approvals_suggest.py: dispatch `test` and mention it in the
bare-`hermes approvals` usage text.
- tests/hermes_cli/test_approvals_test.py: verdict matrix (benign /
hardline / dangerous / user-deny from config / container skip /
mode=off vs hardline), obfuscated==plain verdict parity with
normalized trace, spy proof that the real runtime detectors are the
ones invoked, read-only invariants (nothing executed; prompt and
persistence paths rigged to explode), JSON shape, dispatcher and
parser wiring.
Read-only by construction: only detection/matching functions are
called; the approval gate, prompts, gateway notify, and allowlist
writers are never reached.
Inspired by: Amp `permissions test` (idea-level, proprietary — zero code)
- Give cached_fetch_api_models the same stale-while-revalidate tier as
cached_provider_model_ids: TTL-expired entries within the 7d window are
served instantly while a background refresh rewrites the cache —
without this, every /model open an hour into the session re-blocked on
the live probe (#72762's stall class, deferred).
- Generalize _spawn_swr_refresh(cache_key, refresh_fn) so non-slug
custom:<base_url> keys reuse the same inflight-dedupe scaffolding;
slug behavior unchanged (default refresh_fn preserved).
- Convert the missed sibling site: acp_adapter/server.py
_named_custom_provider_catalogs() live-probed every custom_providers
row's /v1/models per ACP catalog build.
- Extract _cache_entry_valid() (the fp/models predicate existed 4x) and
validate 'at' is numeric so hand-edited/corrupt cache JSON degrades to
a live fetch instead of raising through the picker's blanket except.
- Flatten the dead api_mode conditional (fetch_api_models declares
api_mode=None; branch was behaviorally inert).
- Tests: 4 new guards (stale-serve, stale-window cutoff, generalized SWR
write-through, corrupt-at degradation) — stale-serve and corrupt-at
mutation-checked; 2 existing tests updated for the new behavior.
Custom OpenAI-compatible endpoints (named custom_providers rows, bare
provider: custom, and per-endpoint-map entries) called fetch_api_models()
directly at three call sites in model_switch.py, with no disk cache — unlike
first-class providers, which go through cached_provider_model_ids(). Every
plain /model open live-probed the active custom endpoint's /v1/models,
regardless of how recently it had already been probed.
Adds cached_fetch_api_models() in hermes_cli/models.py: a TTL disk-cache
wrapper keyed on custom:<base_url> (custom endpoints have no
PROVIDER_REGISTRY slug to key on) and fingerprinted on api_key/api_mode/
headers, with the same stale-beats-nothing fallback policy as
cached_provider_model_ids(). Routes all three probe call sites through it.
Since prewarm_picker_cache_async() already calls list_authenticated_providers()
with probe_custom_providers defaulting True, this also fixes the endpoint
being warmed on boot (populating the disk cache) instead of that work being
discarded on every open — any custom endpoint (an LLM gateway, a
self-hosted vLLM/SGLang server, etc.), not just one specific provider.
Fixes#72762. Salvaged from #72810 per review feedback: extracts just the
verified custom-endpoint cache fix with real cache-contract test coverage
(hit/stale/rotation/refresh/fallback), leaving the credential-pool and
Copilot-token-exchange costs described in the issue for separate follow-up.
The per-session agent cache is capped at 128 entries with a 1h idle TTL, and
neither bound knows how many bytes it holds. Each cached agent pins
_session_messages -- the full transcript including tool output, tens of MB on
a session with 100+ tool calls -- so a gateway serving many chats keeps every
warm transcript resident: agents that took a turn inside the TTL are never
idle-swept, and the idle sweep additionally defers finalizable sessions until
they expire. RSS climbs until the cgroup throttles and SIGTERM can no longer
flush inside systemd's stop timeout.
Add the missing bound. Each session-expiry watcher tick compares the process's
anonymous RSS against a budget and, when over, sheds LRU agents through the
same soft-eviction path the cap enforcer uses, then runs malloc_trim so the
freed arenas actually return to the OS. Evicted sessions rebuild their
transcript from the persisted session on the next turn.
Three classes of session are never shed: agents mid-turn, the most recently
used ones, and any session whose transcript has not finished reaching disk
(_last_flushed_db_idx vs len(_session_messages) -- the same divergence the FTS
write-corruption guard reacts to when it preserves live history).
memory_high_mb defaults to "auto", deriving the budget from the cgroup limit
the gateway runs under, so a MemoryHigh/MemoryMax on the unit is respected
without a second number to keep in sync. The two existing bounds become
configurable alongside it under agent.agent_cache.
protect_recent is clamped to half the cache: a couple of sessions can exhaust
the budget on their own, and a fixed MRU guard would then protect everything
and leave the gateway climbing with nothing it would shed.
Fixes#80764
When the Nous Portal returns paid_service_access.allowed=false with
reason=member_spend_cap_exceeded, Hermes was falling through to the
generic 'no active subscription or usable credits' message — even
though the user has ample purchased credits and the real blocker is
an org-level per-member spend cap.
This adds a dedicated branch that surfaces the actual cause: names the
spend cap, shows the cap/spend amounts, and tells the user to ask their
org admin to raise it. Also adds member_spend_cap_exceeded to the
billing error code set so the error classifier and auth error formatter
route it through the Nous entitlement message path.
Follow-ups on top of the salvaged #80696 fix (review findings):
- Sibling sites: rollback.restore, gateway /retry, CLI /retry and /undo N,
and both CLI resume turn counters now use is_user_originated_turn so
legacy-persisted standalone handoffs (durable role=user, no display_kind)
can never be truncation targets or counted as user turns (#80622
suggested regression 4, dispatcher-wide).
- Site-1 guard: hoist the api_call_count decrement + iteration-budget
refund above the break so a skipped turn no longer leaks a budget unit
and finalize_turn logs the true call count (matches the ollama early-exit
and the site-2 sibling).
- Site-2 guard: run the handoff guard BEFORE reanchoring so a restored
user ask is what the anchor lands on, not a stale pre-restore index.
- SUMMARY_PREFIX: add the mid-tool-loop carve-out the code-side guard
already implements, so a literal-minded model doesn't halt an in-flight
exchange after in-place compaction.
- Skip path returns a short compaction status instead of replaying the
previous turn's answer (finalize_turn would append it as a fresh
assistant row — duplicate prose in transcript and delivery).
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.
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).
Follow-up to the salvaged registration contract:
- share one _raise_if_cron_registration_error() helper for the two
byte-identical dashboard 424 except-blocks (web_server + cron router,
via the existing late() seam)
- add endpoint-level 424 coverage for /api/cron/blueprints/instantiate
(previously only the sync worker was tested)
- give chat/CLI surfaces a human-facing user_message() (job name, no
exception class name) and add a recovery hint (pause/resume or update
re-registers via provider reconcile) to the model/REST message
- consolidate five inline provider test doubles into one ABC-subclassing
make_cron_provider conftest factory; the web_server test double now
subclasses CronScheduler so an ABC rename fails loudly
- narrow the wrapper facade to keyword-only (**kwargs) and route the
tool's partial-failure return through tool_error()
- gateway/config.py: rewrite the stale enablement-pass header comment that
still described check_fn as 'the single source of truth for are-my-env-
vars-set' / 'lazy-installs it' — both false under the new contract.
- teams: check_requirements docstring wrongly claimed credential checks
(body checks only SDK/aiohttp presence); derive install_hint from the
canonical LAZY_DEPS pins + sys.executable instead of hardcoding
'~/.hermes/hermes-agent/venv/bin/pip' and version pins (wrong under
HERMES_HOME overrides / profile installs; pins go stale on CVE bumps);
connect() fatal-error hints now point at the venv pip instead of bare
system pip (the PEP 668 trap the docs warn about).
- teams docs: drop exact version pins from the two manual-install commands
(LAZY_DEPS is the source of truth; unpinned installs still work and the
text can't go stale).
- hermes_cli/status.py: per-entry exception guard around check_fn so one
raising probe can't abort the listing of all remaining plugin platforms
(aligns with the other three call sites).
- tests: rename test_register_check_fn_is_active_lazy_installer ->
test_register_splits_passive_probe_from_active_installer (name said the
opposite of what it verifies).
PlatformEntry.check_fn served three contradictory roles: adapter-creation
gate, config auto-enablement gate, and status display. Plugins had to pick
one function for all three:
- Active installer as check_fn (discord/slack/telegram/matrix/dingtalk/
feishu): every status display could pip-install SDKs as a side effect
(the desktop 94% boot-loop class).
- Passive probe as check_fn (teams, wecom_callback): create_adapter()
returned None before connect() could lazy-install, so the SDK never
installed (#79812 deadlock; wecom_callback's platform.wecom_callback
LAZY_DEPS entry was dead code).
The split makes both call sites correct by construction:
- check_fn is now contractually PASSIVE (probe only, never installs).
- New optional PlatformEntry.ensure_deps_fn is the ACTIVE installer;
create_adapter() runs it exactly when check_fn is False — the platform
is enabled+configured and the gateway is about to connect it.
- Config enablement keeps a configured platform whose deps are missing
but installable; the install itself is deferred to create_adapter().
- Status surfaces (_platform_status, hermes status) read only the
passive probe and can never trigger pip.
Migrated all lazy-installable platform plugins to the split; platforms
with no optional deps (irc/ntfy/buzz/simplex/line/a2a/...) are unchanged
— no ensure_deps_fn means a False check_fn stays a hard block.
wecom_callback gains a working installer for the first time.
Builds on @xxxigm's #79812 (both commits cherry-picked with authorship
preserved), reworking the check_fn swap into the two-field split so the
Teams fix doesn't reintroduce install-on-status.
After `hermes update`, the desktop sidebar showed "No sessions yet" until
the user's first message. #72424 added sessions.last_activity_at, which
list_sessions_rich now selects — but column adds only land through
_reconcile_columns() in the writable _init_schema, and read-only opens
skip that by design. Every sidebar read path opens state.db read-only, so
each poll raised "no such column: s.last_activity_at" until the first
prompt's lazy session-row persist forced a writable open and reconciled.
A heal for exactly this class already existed (_open_session_db_for_profile
probes the read-only handle and does a one-time writable reopen on
staleness), but its probe was a hand-written four-column list that never
learned last_activity_at — it went stale three days after shipping. And the
batched sidebar route (/api/profiles/sessions/sidebar) bypassed the helper
entirely, swallowing per-profile failures into an errors array the desktop
never surfaces, so the incident produced an empty sidebar with clean logs.
The fix removes the maintenance burden instead of paying it once more:
- hermes_state_schema.schema_read_probe_statements() derives one
`SELECT <every declared column> FROM <table> LIMIT 0` per table from
SCHEMA_SQL via the existing _parse_schema_columns() — the same source of
truth the writable reconciler diffs against, so any future ADD COLUMN is
probed with no list to update. Column references are table-qualified:
an unqualified double-quoted identifier that fails to resolve silently
degrades to a string literal (SQLite's double-quoted-string misfeature)
and would make the probe pass on exactly the store it exists to catch.
- web_server splits the heal into a path-level _open_session_db_at_path
(semantics unchanged) so the cross-profile session routes can share it;
both profiles.py loops and _count_status_active_sessions (the remaining
raw read-only sibling) now open through it. The heal stays a helper
rather than a SessionDB classmethod on purpose: escalation-to-writable
must remain an explicit caller decision — update_cmd.py opens read-only
mid-update and must never write.
- Exhaustion guard: if the writable heal SUCCEEDS and the re-probe still
fails (a schema problem ADD COLUMN cannot express), the store is marked
exhausted — warn once, skip the probe, serve reads probe-less — instead
of re-running the full writable init on every poll against a possibly
live DB. A FAILED writable open (transient lock) is deliberately not
recorded, so the next poll retries the heal.
- The per-profile swallow sites in profiles.py now also log a deduplicated
warning, so a persistent read failure is loud in errors.log even though
the response errors array stays invisible to the sidebar.
Tests: probe/SCHEMA_SQL coverage invariants (tests/test_schema_read_probe.py),
last_activity_at added to the /api/sessions heal parametrize, a sidebar-route
heal test reproducing the shipped symptom (errors == [] and the session
returned against a store missing the column), and an exhaustion test pinning
exactly one writable open. The sidebar and last_activity_at tests fail on
main.
Review follow-ups on the salvage:
- The helper script's success check accepted any "PID" line, including
the "PID" = -1 a recently-crashed job reports — while the in-process
path's _parse_launchd_pid_from_list_output rejects non-positive PIDs.
Both bash sites now require a positive PID (grep -qE '"PID" = [0-9]+;')
so the two paths enforce the same supervised-PID standard.
- _graceful_restart_via_sigusr1's drain-wait tail was a duplicate of the
new _wait_for_pid_exit — now delegates to it.
- Stale comments: the ancestry-detection framing at the top of the reload
block, and the exhaustion log's '(refresh ran outside gateway process
tree)' which is false on the new helper-spawn-failure fallback path
(now '(in-process fallback path)').
The reload retry loop treated `launchctl list <label>` exit 0 as success,
but exit 0 also covers a registered-but-not-running definition (macOS 26+
`state = not running`) — the same trap _probe_launchd_service_running
already guards against. Require a PID so success means launchd is
supervising a live process, in both the Python loop and the shell helper.
Verified against live launchd: a RunAtLoad=false job reports exit 0 with
no PID, which the old check accepted and the new one rejects.
Note this is NOT what distinguishes a draining instance — measured, the
label deregisters within ~1s of bootout while the old process drains on.
Waiting for the old PID to exit is what covers that.
Reload chose the in-process bootout/bootstrap path based on POSIX
ancestry, but bootout tears down the job's process coalition, and
coalition membership is inherited at spawn and survives reparenting.
A gateway-spawned process reparented to PID 1 is no longer an ancestor
yet still dies with the coalition, so the retry loop was killed
mid-bootstrap and nothing re-registered the label (KeepAlive can't
revive a job launchd no longer knows about).
- always prefer the detached transient-job helper; it's also correct
when genuinely outside the coalition, just asynchronous
- wait for the old gateway PID to exit before bootstrapping; bootout
only sends SIGTERM and every bootstrap during the drain fails EIO
- fall through to the in-process path when the helper can't spawn
instead of leaving the plist rewritten but never reloaded
/refine [focus] fires the existing background review fork
(AIAgent._spawn_background_review) immediately instead of waiting for
the automatic 10-turn memory / 10-iteration skill nudge counters.
Optional focus instructions are appended to the review prompt so the
fork prioritizes what the user asked for (e.g. '/refine save the
deploy workflow as a skill').
- New optional focus parameter threaded through
_spawn_background_review -> spawn_background_review_thread.
Automatic post-turn reviews pass None and their prompts are
byte-identical to before.
- CLI handler snapshots conversation_history; gateway handler pulls
the idle session's cached AIAgent from _agent_cache (rejected while
the agent is running).
- Review runs in a daemon thread against the snapshot — live
conversation, message alternation, and prompt cache untouched.
- Slack stays under the 50-slash cap via /hermes refine.
Adapted from the /refine concept in Prime Intellect's Prime-Agent
(Continual Harness); Hermes' equivalent durable state is the
memory + skill stores, so the review fork is the natural target.
/heartbeat every <interval> <prompt> gives the current session one
recurring instruction. When the session is idle and the interval has
elapsed, the prompt is injected as a plain user turn — same
conversation, same context, prompt cache and role alternation
untouched.
- CLI: idle-poll watchdog thread (wake-word watchdog pattern) feeding
_pending_input; gateway: single gateway-wide async poller injecting
through the adapter FIFO. Busy sessions coalesce their tick to the
next idle poll.
- Missed ticks coalesce (anchor resets on fire) — a busy hour yields
ONE heartbeat turn, never a backlog. Real user messages always win.
- 60s interval floor; injected prompt carries a don't-invent-work
guard so idle heartbeats don't generate busywork.
- State persists in SessionDB.state_meta (heartbeat:<session_id>),
survives /resume, migrates across compression session rotations
alongside /goal state.
- Session-scoped and in-process by design — durable cross-process
schedules remain the cron subsystem's job (docs draw the boundary).
- Slack stays under the 50-slash cap via /hermes heartbeat; ghost-text
suggester now prefers the shortest prefix match so /he still
suggests /help.
Adapted from the session-heartbeat concept in Prime Intellect's
Prime-Agent (/heartbeat).
/goal gate add <command> attaches shell commands to the active goal.
Gates run at turn boundary BEFORE the LLM judge: a failing gate skips
the judge entirely and feeds its exit code + bounded output tail back
as the continuation prompt, so the agent iterates against concrete
evidence instead of a prose verdict.
- Unchanged-workspace skip: a gate that failed on an identical
workspace (git HEAD + status fingerprint) is not re-run — the
recorded failure replays and the attempt count advances.
- Bounded retries (default 3) + per-gate timeout (default 300s);
exhaustion auto-pauses the goal like the turn budget does.
- Gates persist in SessionDB.state_meta with the goal (survive
/resume and compression rotation); pre-gate goal rows load
unchanged.
- /goal gate [list|add|remove|clear] on CLI + gateway; 'gate' added
to the mid-run control-verb whitelist (gates only run at turn
boundary, so editing the list mid-run is safe).
Adapted from the quality-gate concept in Prime Intellect's Prime-Agent
(--autonomous-gate).
Bartok9
rob-maron
Teknium
cmoiccool
Ben Barclay
fangliquanflq
x7peeps
Trevin Chow
Brooklyn Nicholson
Math
Michael Gannotti
Quark Assistant
RelaxJonh
cadezhou
Leon Phull
XiaoZAZA
Eva
Jakub Wolniewicz
Nikita Barkov
ethernet
Laith Weinberger
kshitij
joaomarcos
Drexuxux
Sohom Sahaun
cryptoyasenka
Austin Pickett
Nolan
Paulo Nascimento
rainbowgits
ygd58
Erosika
Axmr1
Victor Kyriazakos
rjvandeve
kinsolee
Royalaid
Gille
GodsBoy
Prashant Jain
HexLab98
kshitij
texasich
emozilla
Rob Hilgefort