Commit Graph

32252 Commits

Author SHA1 Message Date
Teknium 0d8a1575c5 refactor(mcp): keep the passive status RPC, drop the SDK contract and reason codes
mcp.servers.status now rides the shared _mcp_rpc decorator (profile scope, 4064,
5024 with the real message) instead of a hand-rolled try/finally with a blanket
except. Drop the _MCPConnectErrorText str subclass and reason taxonomy: the
existing status/error fields already carry the state, and a whitelist on the RPC
keeps error text out of the wire. The Desktop connections.health contribution
contract is held back until its consumer plugin is public. Tests trimmed to the
scope invariants (per-profile runtime visibility, scoped shutdown clears only its
own status, launch runtime never leaks into another profile).
2026-09-06 13:18:19 -07:00
Joey a6699d60f4 feat(mcp): expose profile-scoped cached connection health 2026-09-06 13:18:19 -07:00
Teknium b167e81750 fix: legacy Bot Mode section in SOUL.md no longer taxes every session or shadows the live roster
Older desktop builds appended a frozen "## Messaging other agents" section (roster
included) to SOUL.md. Since the server started injecting the live section into Bot Chat
sessions, that copy did two wrong things: every CLI/TUI/messenger session paid ~600 tok
for a bot-only protocol, and in Bot Chat itself the probe went silent when SOUL carried
the heading, so bots saw the stale roster instead of the live one.

- load_soul_md strips the legacy section at read time (covers un-migrated profiles and
  the ambient-home edge cases the same way the SOUL isolation fix does)
- bot_mode_probe drops the SOUL-carries-heading suppression; a SOUL-era stored Bot Chat
  prompt now counts as legacy and is upgraded once (stamped, so it cannot loop)
- config migration v41 rewrites SOUL.md across the default + every profile once
2026-09-06 13:08:31 -07:00
Teknium dec1e87833 Merge pull request #103553 from NousResearch/fix/goal-set-no-repaste
fix(goal): /goal <text> kicks with a pointer when the last user message already carries the goal (11-call replay turn in one run)
2026-09-06 13:03:01 -07:00
Teknium 7551168262 ci: redispatch after zero-job run on the main merge 2026-09-06 12:57:21 -07:00
Teknium 6b2d4faf36 Merge pull request #103549 from NousResearch/fix/async-batch-task-failure-notice
feat(delegation): a failed child of a running detached fan-out is surfaced immediately, as a non-durable notice (66 min dead wave; review-found final-result loss closed)
2026-09-06 12:44:28 -07:00
kshitijk4poor 8b9a9f8c23 refactor(desktop): one sessionBucketId for the filter rule and the overview overlay; shorter resolver header 2026-09-07 01:09:00 +05:30
kshitijk4poor 758e33c28c chore: map contributor emails for the #96269/#102465 salvage 2026-09-07 01:09:00 +05:30
kshitijk4poor 88d0a740c9 refactor(desktop): one live-filter resolver; keep the Home row rule from #102465
#96269 and #102465 fixed the same blank-sidebar symptom with the same
"narrow the persisted filter to ids the live tree names" mechanism.
resolveLiveProjectFilter (the earlier PR) is the single resolver; the
duplicate sanitizeProjectFilter is removed. What #102465 adds beyond it stays:
detached rows file under NO_PROJECT_ID, so filtering to Home keeps Home's rows.
2026-09-07 01:09:00 +05:30
finn763 28c508cce0 fix(desktop): restore sidebar sessions Closes #97762 2026-09-07 01:09:00 +05:30
liuhao1024 fd54282678 fix(desktop): a cross-profile or stale project filter no longer empties the sidebar (#96246)
The sidebar's persisted project filter is a membership whitelist over tree node
ids. Ids that the active profile's tree does not resolve (picked in another
profile, or left over after a project was deleted / an update rebuilt the tree)
used to filter every row out — headers rendered, zero sessions, until Local
Storage was cleared. Narrow the persisted filter to ids the live tree resolves;
dead ids are inert, never fatal. Memo-only, never written back.

Salvage of #96269 (three commits: fix + two lint passes, folded).
2026-09-07 01:09:00 +05:30
Teknium c6bf8fd95c chore: retrigger CI (zero-job dispatch failure, auto-heal) 2026-09-06 12:37:59 -07:00
kshitijk4poor d86627a7f3 docs(desktop): trim the ssh token comments to the WHY 2026-09-07 00:58:49 +05:30
joaomarcos 690bd8af09 fix(desktop): keep the ssh session token in the v2 connection registry (#103795)
`persistSshConnectionToken()` writes the per-serve session token adopted for
an SSH connection onto its v2 registry entry, but the registry never read it
back: `normalizeRegistry()` rebuilt an `kind === 'ssh'` entry from
`normalizeSshConfig()` alone, which describes only the DIAL (host, user, port,
keyPath, remoteHermesPath, remoteProfile). The sibling remote/cloud branch
preserves `entry.token`; the ssh branch did not.

The token therefore survived only in the mtime-keyed in-process cache. On the
next cold read — an app restart, or any process that re-parses
connections.json — it was silently dropped, so `resolveRemoteBackend()`
decrypted an empty value and dialed with `reuseToken = ''`. That fails the
`Boolean(reuseToken)` clause of remote-lifecycle's `reusable` gate, so a
HEALTHY owned backend was classified not-reusable, reaped by `cleanupStale()`
and respawned on a new port behind a new tunnel — while the renderer kept
dialing its cached `wsUrl?token=` at the old credential and got 403 forever.

`normalizeConnectionInput()` had the same omission: `saveRegistryConnection()`
resolves the surviving envelope via `resolvePersistedRemoteToken()` and passes
it in, but the ssh branch dropped it, so a plain label rename wiped the live
backend's reuse credential and re-armed the same loop.

Both branches now carry the token exactly the way the remote branch does.
There is no auth-mode choice on an ssh entry that could invalidate the
envelope, so no drop condition is needed.

Fixes #103795
2026-09-07 00:58:49 +05:30
kshitijk4poor df4c786279 docs(gateway): say WHY the replay sidecar survives a timestamp-only render 2026-09-07 00:53:06 +05:30
3ASiC 08f269fa13 fix(gateway): preserve exact API content through timestamp replay 2026-09-07 00:53:06 +05:30
hermes-seaeye[bot] cb9546c055 fmt(js): npm run fix on merge (#104539)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2026-09-06 19:22:04 +00:00
Teknium 339034b56a chore: retrigger CI (zero-job dispatch failure, auto-heal) 2026-09-06 12:20:59 -07:00
Teknium 211b3635e3 chore: retrigger CI (zero-job dispatch failure, auto-heal) 2026-09-06 12:17:45 -07:00
kshitijk4poor 644d00b960 refactor(desktop): keep the codex_message_items hydration fallback; drop the placeholder half
- The placeholder ("assistant response not persisted") is removed: it turned a
  wholly-empty persisted row into TEXT, which in reconcileResumeMessages could
  replace a text-only live stream row at the same ordinal until the turn
  settled. The sidecar fallback alone covers the #68321 field repro.
- Phase filter matches the backend (codex_responses_adapter _OutputScan._message):
  commentary AND analysis are reasoning-channel narration, not the reply.
- Tests trimmed to the two contracts that are red on main; six that passed on
  main (pre-existing reasoning-part behaviour) are gone. File renamed for what
  it now covers.
2026-09-07 00:45:11 +05:30
salch-cred 9e8adb10bb lint: fix import ordering in chat-messages.reasoning-survival.test.ts
Add blank line between @/ alias imports and relative imports per perfectionist/sort-imports convention.
2026-09-07 00:45:11 +05:30
sal 4a5ee5510e style: separate vitest import from local imports (perfectionist/sort-imports) 2026-09-07 00:45:11 +05:30
sal 0b87e89d40 fix(desktop): assistant rows whose text persisted to sidecars no longer vanish on rehydrate (#68321)
Field-level reproduction (2026-09-02, v0.21.0, in the issue thread): an
assistant row with content length 0 whose user-visible response exists
only in reasoning / reasoning_content / codex_message_items renders
live, then disappears from the transcript after a session/profile
switch-back. DB intact - the row is still there on every re-read; only
the rehydrated render loses it. Six independent confirmations across
macOS and Windows since 2026-07-22; all prior fixes (#68329 envelope
normalization, closed implemented_on_main; #77644 mid-turn reconcile;
#101470 compaction-display projections) addressed adjacent producers,
not this one.

Two producers in toChatMessages hydration, both pinned by the new
chat-messages.reasoning-survival.test.ts (fails 9/9 on current main):

1. codex_message_items never read. Responses-API turns can persist with
   `content` empty while the reply the user saw lives only in the
   message-items sidecar ({type:'message', role:'assistant', phase,
   content:[{type:'output_text', text}]}). The live stream painted that
   text; hydration ignored the sidecar, so the rehydrated bubble came
   back blank - and the blank chatMessageText at the same role-ordinal
   then made reconcileResumeMessages drop the cached row's parts
   (sameText/extension/isLiveTailRow all fail), erasing the reply on
   every switch-back. Fix: codexMessageItemText() extracts
   non-commentary assistant output_text as the bubble's text when
   content and reasoning produced no parts. Persisted content still
   wins when present; commentary narration is never promoted.

2. the zero-parts drop. An assistant row hydrating to no parts at all
   returned early and vanished from the transcript entirely - the
   "all assistant messages gone; user messages remain" shape. Fix: a
   wholly empty assistant row (display_kind != 'hidden') paints a
   _(assistant response not persisted)_ placeholder instead of
   disappearing. Hidden scaffolding rows keep dropping as designed
   (pinned by a test).

Also adds codex_message_items to the SessionMessage type (the gateway
has shipped it since the branch-copy lane; the type never declared it).

Verification (native Windows, node 24.17):
- new file: 9 passed (fails 9/9 without the hydration changes)
- src/lib full dir: 1243 passed
- reconcile suites (utils + resume-structural-parts): 115 passed
- streaming/timeline reasoning-part suites: 25 passed
- tsc --build tsconfig.json: clean

Fixes #68321
2026-09-07 00:45:11 +05:30
Teknium 9db6c8b200 chore: retrigger CI (zero-job dispatch failure, auto-heal) 2026-09-06 12:12:27 -07:00
kshitijk4poor 4f6ef8806f refactor(auth): positive store-identity check for the clone strip; drop the save kwarg
The alias check re-implemented most of _is_same_auth_store (#101356) inline, but
that helper answers False on a samefile() OSError — on the strip path that would
fail OPEN. Resolve identity positively (same resolved path, or samefile says so)
and treat any error as "refuse"; three lines instead of the inline stat dance.
The `preserve_symlinks=False` save path (raw os.replace) bypassed atomic_replace's
EXDEV/Windows fallback to defend against a path swap no concurrent writer performs
on a directory this process just created — removed with its mock-injected test.
Tests kept: shared-store invariant [symlink|hardlink] and two fail-closed variants.
2026-09-07 00:42:18 +05:30
kshitijk4poor fee38b03cd chore: map GuardianZ71 contributor email for #104095 salvage 2026-09-07 00:42:18 +05:30
GuardianZ71 5e108489a0 fix(auth): preserve shared store during clone cleanup 2026-09-07 00:42:18 +05:30
Teknium 8f2167342f evals(postmortem): notice probes target a grouped unit (per-group split on main; ungrouped tasks already report individually) 2026-09-06 12:12:09 -07:00
kshitijk4poor 3ac671dbba refactor(agent): drop the write-only agent-level codex watchdog timestamps
With a request-local watchdog state on every codex request, agent._codex_stream_last_event_ts / _last_progress_ts had no remaining reader; the state-None snapshot only runs for non-codex requests where no watchdog consults it.
2026-09-07 00:41:09 +05:30
kshitijk4poor 1ad8b5dd4a refactor(agent): trim the watchdog phase split to what the tests pin
- Explicit-vs-implicit idle timeout detection uses env_float with a sentinel
  instead of a hand-rolled parse (unset and unparseable both mean implicit).
- _on_event writes the agent-level timestamps only when there is no
  request-local watchdog state; with state present they were dual bookkeeping
  nobody read (the snapshot prefers the state).
- _abort_request keeps main's close-then-retire order: the reorder had no
  test teeth and is a separate concern from #90449.
2026-09-07 00:41:09 +05:30
kshitijk4poor 8b07d809c4 chore: map PeaceMaker-best contributor email for #103710 salvage 2026-09-07 00:41:09 +05:30
PeaceMaker-best 463d4bcd15 fix(agent): defer codex idle watchdog until progress
Signed-off-by: PeaceMaker-best <221849497+PeaceMaker-best@users.noreply.github.com>
2026-09-07 00:41:09 +05:30
Teknium 14c3101256 merge main: notice rides the per-group unit (unit_id, n_here); drop the detached kwarg main removed 2026-09-06 12:09:49 -07:00
kshitijk4poor 193f05dec5 refactor(cron): one FIRE_CLAIM_TTL_SECONDS for claiming, one-shot re-arm, and stale-error recovery
The TTL was three copies of the literal 300 (claim_job_for_fire default,
rearm_oneshot, and the new stale-error guard). Hoisted so the three lanes
cannot drift; incident narrative in the guard comment cut to the WHY.
2026-09-07 00:39:44 +05:30
kshitijk4poor 37a0c1b95f chore: map r3x443 contributor email for #103740 salvage 2026-09-07 00:39:44 +05:30
r3x443 eb40bf060f fix(cron): skip stale-error re-arm while another process holds a live fire_claim
Multi-process schedulers sharing one jobs store (gateway + Desktop serve tabs)
re-armed a job every tick while a long run in another process was still
heartbeating its fire_claim, producing claim-fight churn and killing the live
run (brain, 2026-09-02). Treat a fresh fire_claim as 'running elsewhere'.
2026-09-07 00:39:44 +05:30
kshitijk4poor 5f87ac74d7 refactor(gateway): verdict helpers live in run_shutdown; keep the early failure return; dedupe test setup
- _exit_with_failure_verdict / _resolve_gateway_exit_verdict move out of the
  run.py facade into run_shutdown.py, which already owns _restart_via_service
  and GATEWAY_SERVICE_RESTART_EXIT_CODE (no alias import needed).
- The running-shutdown tail keeps its early `return False` on a failure verdict,
  as on main, so a failure exit does not first drain cron/MCP; the helper still
  re-checks it for the startup-abort path.
- The three start_gateway tests share one _patch_aborted_startup helper.
2026-09-07 00:38:37 +05:30
kshitijk4poor 57238b8507 chore: map YuYigeng contributor email for #103208 salvage 2026-09-07 00:38:37 +05:30
YuYigeng e24047d8bd fix(gateway): unify shutdown exit verdicts
Adapt the shared exit-verdict resolver and service-restart fallback from JoaoMarcos44’s implementation in f77586ef7683c17d5890e63e38604a68d5ea11ce (#103248) for the earlier #103208 branch.

Co-authored-by: joaomarcos <joaomarcosdias444@gmail.com>
2026-09-07 00:38:37 +05:30
YuYigeng 51ddff0bb1 fix(gateway): restart after startup SIGTERM 2026-09-07 00:38:37 +05:30
Teknium d0090a147c Merge remote-tracking branch 'origin/main' into fix/async-batch-task-failure-notice
# Conflicts:
#	tools/delegate_tool_dispatch.py
2026-09-06 12:07:50 -07:00
Teknium 28747b4034 Merge remote-tracking branch 'origin/main' into fix/goal-set-no-repaste
# Conflicts:
#	hermes_cli/goals.py
2026-09-06 12:06:39 -07:00
Teknium 6d9c166455 Merge pull request #103529 from NousResearch/fix/terminal-auto-background
fix(terminal): an over-cap foreground timeout runs as a tracked background process instead of being refused (454 refusals in one run)
2026-09-06 12:06:04 -07:00
Teknium fdd140557b Merge pull request #103551 from NousResearch/fix/tool-output-caps
feat(file_tools): write_file flags a whole-file rewrite that mostly re-sends what is on disk (661 such writes, ≈$155, in one run)
2026-09-06 12:05:53 -07:00
Teknium cd658b6a46 Merge pull request #103492 from NousResearch/fix/approval-scanner-quoted-subshell
fix(approval): a grep inside "$(...)" no longer trips the hardline malformed block, and a quoted substitution body keeps its command boundaries (546 false blocks; review-found bypass closed)
2026-09-06 12:03:29 -07:00
Teknium 634109b7aa Merge pull request #103534 from NousResearch/fix/goal-judge-wait-on-subagents
fix(goal): the judge can WAIT on delegated subagents (4 of 5 nudges re-poked a waiting orchestrator; live 3/3 CONTINUE → 3/3 WAIT)
2026-09-06 12:03:15 -07:00
Teknium afb4e080f6 Merge pull request #103496 from NousResearch/fix/goal-judge-own-processes-only
fix(goal): the judge sees only its own session's background processes; pid/session waits expire after 30 min (parked 3h22m on a grandchild's poller)
2026-09-06 12:03:05 -07:00
Teknium d97f318717 Merge pull request #103526 from NousResearch/fix/nous-auth-stampede
fix(nous): adopt a same-account fresh key before expiry and start the keepalive in every process (620 hourly 401s → 0; review-found account takeover closed)
2026-09-06 12:02:58 -07:00
Teknium e5f8420be8 Merge pull request #103513 from NousResearch/fix/subagent-context-cap
fix(delegation): compression_threshold_tokens is opt-in (default off, children keep the 500K ratio trigger); validate the value
2026-09-06 12:02:49 -07:00
Teknium 3d5831fa59 Merge pull request #103486 from NousResearch/fix/nested-delegate-deadline-and-summary-budget
fix(delegate): nested orchestrators get their workers' results back — delegate_task exempt from the 420 s tool deadline; summary budget uses current prompt, not the session sum
2026-09-06 12:02:43 -07:00