Commit Graph

1059 Commits

Author SHA1 Message Date
Teknium 67de93862c fix(tui-gateway): gate the ws-orphan interrupt of running turns on activity staleness
The 20s ws-orphan grace (14b50f5edd) interrupts a RUNNING turn whenever
the client is absent past the grace window — killing healthy long turns
on deliberate client absence (desktop closed, PC asleep, mobile
backgrounded, Electron tab-switch throttling, desktop update/relaunch).

The reaper now interrupts a detached running turn ONLY when BOTH the
client is absent past the grace AND the turn's activity clock is stale
(seconds_since_activity >= dashboard.ws_orphan_activity_stale_s,
default 600s — matching agent.turn_liveness.timeout_s semantics from
PR #99758). A detached-but-actively-producing turn keeps running to
completion (the sentinel transport already buffers detached emits);
a detached AND activity-stale turn is interrupted/reaped as today.
Non-running orphaned sessions keep current behavior. Reuses the
existing AIAgent.get_activity_summary() clock — no parallel tracker
(rejected in PR #4864).

Fixes #98028
Fixes #100325
2026-09-01 10:52:23 -07:00
kshitijk4poor db339f0051 fix(state): consolidate gateway SessionDB writers via process-wide shared registry
A gateway process opened state.db from ~12 call sites, each minting its
own writer connection, self._lock, close-time WAL checkpoint, and
token-writer thread. With N independent writers on one WAL file, one
connection's close-time checkpoint could race another's growth — the
lost/reordered-page-write signature across 11+ incidents (#90837).

Adds hermes_state_registry.py: a process-wide, per-path, refcounted
shared registry owning the writer boundary.

- acquire(path): same resolved path returns the same instance (one
  writer connection, one lock, one token-writer thread) for every
  long-lived in-process caller (gateway runner, SessionStore, per-agent
  lazy recall, cron per-job, mirror, channel_directory, slash_commands,
  shutdown_flush, session_search, react_to_message, delegate, mcp_serve,
  auto_archive, tui_gateway).
- close() on a shared instance is a NO-OP — the registry owns the
  lifecycle, so one caller's close can never tear down a writer other
  callers still hold.
- Generation-aware retirement on inode change: a replaced state.db
  RETIRES the live generation (never lent again) but keeps it alive for
  existing holders; release is object-keyed so holders of the old
  generation drain it independently of the new one. The old
  generation's own write path still fails with the typed
  StateDbReplacedError (existing protection, unchanged).
- Replacement-open failure leaves NO registry entry for the path —
  the next acquire retries fresh, never hands out a closed stale object.
- All teardown runs OUTSIDE the registry lock: a final release's WAL
  checkpoint can never stall acquisition for every state.db.
- close_shared_session_dbs() at gateway shutdown drains every
  generation (live + retired) as the final safety net.

CLI one-shots, recovery flows, and read-only cross-profile opens keep
using SessionDB() directly with their own close() — only long-lived
in-process sites route through the registry.

References #90837 (root-cause tracker stays open: the #10 EOF signature
and the WAL-lifecycle A/B verdict remain under investigation there).
2026-09-01 20:55:35 +05:30
Brooklyn Nicholson d0e41cda69 fix(gateway): let config.set write the desktop's Appearance switches
config.set matches an explicit key list and answers 4002 for anything
else, so a renderer mirroring an unlisted key wrote nothing at all. The
reactions toggle shipped that way: every write was rejected into a
swallowed .catch(), and react_to_message stayed dark no matter what the
user picked.

Adds the display booleans as a recognized group so the toggle reaches
the config of whichever gateway the app is actually talking to, which is
the only place a check_fn can read it.
2026-08-31 21:11:11 -05:00
Brooklyn Nicholson 5c3bfb6da8 fix(tui_gateway): retire recovery marker on local stop
A confirmed Desktop Stop left the crash-recovery marker on disk until the
run thread finished. If the backend exited in that window, resume treated
the leftover as a crash and auto-continued the turn the user had stopped.

Co-authored-by: Jaime Chieng <164842890+buddhaholic420@users.noreply.github.com>
2026-08-31 20:50:39 -05:00
Brooklyn Nicholson adb23c13cb fix(bot-mode): keep Bot Chat resume on a proven compression tip
Desktop opens the registry id, then session.resume walked the legacy
unmarked-child fallback, so Open Chat still landed in a side chat after
the title lookup was already strict. Recoverable-archive resurrection
uses the same helper.

Co-authored-by: Gille <4317663+helix4u@users.noreply.github.com>
2026-08-31 20:47:53 -05:00
Gille bb28056efd fix(bot-mode): keep canonical lookup on compression lineage 2026-08-31 20:47:53 -05:00
Brooklyn Nicholson 0e7eebc266 fix(desktop): scope remote model catalog and primary-label REST to the focused profile
A shared dashboard's launch HERMES_HOME is not the selected profile. model.options now runs under @_profile_scoped, and global-remote REST keeps ?profile= even for the primary label.

Co-authored-by: fangliquanflq <fangliquan@qq.com>
2026-08-31 20:40:09 -05:00
Futahua a5f0fbb262 fix(sessions): per-session exclusivity is correctness, not a capacity policy
Cherry-picked from PR #94595 (author: Futahua) onto current main, with the
maintainer-review revision points folded in during the rebase:

- the lease engages UNCONDITIONALLY: try_acquire_active_session no longer
  returns a disabled no-op lease when max_concurrent_sessions is unset;
  the concurrency cap stays an orthogonal, optional policy checked second
- ownership uncertainty fails CLOSED (SESSION_COORDINATION_UNAVAILABLE)
  instead of degrading to an untracked go-ahead: a corrupt/unreadable
  registry must not be collapsed into 'no owner exists' (review blocker 2)
- the ownership admission sits at the _run_prompt_submit chokepoint that
  EVERY fresh turn source crosses, and crash auto-continue acquires (or
  bails) BEFORE emitting message.start — closing the #94778 bypass where
  backend B's auto-continue ran a duplicate turn while backend A was live
  (review blocker 1)
- the TUI gateway claim helper fails closed on claim exceptions for every
  surface, not just desktop
- CLI and messaging-gateway call sites pass live_session_id metadata so
  the (pid, live id) re-entrancy identity protects them from self-fencing
  on a leaked lease

Co-authored-by: teknium1 <teknium1@users.noreply.github.com>
2026-08-31 12:36:33 -07:00
Teknium 4396253aed fix(gateway): gate compute-host interrupt forward on hosted activity
Follow-up to the salvaged #98571: forward the interrupt to the compute
host whenever the parent 'running' mirror is stale, but only for
sessions that actually have hosted activity — HostSupervisor.interrupt()
calls start(), so an unconditional forward would spawn a compute-host
child just to deliver an interrupt for an idle lazy session.

Adds a regression test asserting the idle-lazy-session no-spawn path.

Refs #92916
2026-08-31 12:18:00 -07:00
konsisumer 3ae74119c9 fix(gateway): relay compute-host clarify state 2026-08-31 12:18:00 -07:00
fangliquanflq da090aa4ba fix(prompt): preserve resumed workspace provenance 2026-08-31 10:10:25 -07:00
fangliquanflq c6ee4e0809 fix(prompt): skip bundled AGENTS.md for desktop launch cwd 2026-08-31 10:10:25 -07:00
HexLab98 3a542bbef4 fix(tui): show status while idle/auto compaction runs
Idle and preflight compaction arrived as lifecycle status without the
"Compacting context" marker, so TUI never entered a compacting state.
Re-tag those lines and freeze the busy FaceTicker on "compacting" for
the whole pause instead of restoring "running…" after 4s.
2026-08-31 09:57:04 -07:00
Teknium 037a73fa23 fix(tui): fail prompt.submit loud only on a real store-open failure
The salvaged #98948 change returned False for every db=None, which also fired in deliberately store-less/degraded contexts (no _db_error), regressing six prompt.submit tests. Gate the loud failure on _db_error being set — the actual #98924 symptom — and keep the pinned best-effort contract otherwise.
2026-08-31 09:56:43 -07:00
Alvin T. Veroy e17fd0a708 fix(state): decode errors now reach the heal path and fail loud in TUI (residual #98924 surfaces)
Companion to #98935, which fixes _fts_table_probe itself. This covers the
surfaces that PR does not touch:

- web_server._open_session_db_at_path: the one-writable-open heal only
  caught sqlite3.DatabaseError; a raw UnicodeDecodeError (pysqlite failing
  to decode SQLite's own error message over corrupt file bytes) bypassed
  it, so the heal documented for malformed schema never fired (#98924
  Failure 1). Both catches widened; decode errors dispatch to the heal.
- SessionSchemaMixin._recover_stale_fts_locked: drop-and-recreate skipped
  vtables whose probe raised UnicodeDecodeError, the same too-narrow
  catch the issue identified in the probe.
- TUI gateway: _ensure_session_db_row returned silently when the store
  could not open, so prompt.submit streamed the turn while persisting
  nothing (#98924 Failure 2). It now returns False and prompt.submit
  fails the RPC with code 5072 so desktop maps it to a toast, mirroring
  the disk-full/5070 convention. session.create stays silent per its
  pinned degraded-mode contract.
2026-08-31 09:56:43 -07:00
Teknium 6874b99d49 fix(sessions): stamp launch-profile name on new session rows instead of NULL
Sessions created on the launch/default profile were persisted with
profile_name = NULL by all three writers (run_agent._ensure_db_session
None'd out 'default'; the desktop backend's _ensure_session_db_row and
session.branch passed None when no profile_home override was set).

NULL used to mean 'launch profile' by convention, but the desktop now
keys sessions by (profile, id), filters the sidebar by profile scope,
and resolves @session:<profile>/<id> deep links by profile match — a
NULL row matches nothing, so sessions created around a profile switch
vanished from the sidebar and their deep links could not be opened
(#99222). The #94724 one-shot legacy-owner backfill stamps literal
'default' onto old NULL rows, so writers minting NEW NULL rows after
that backfill ran recreated the exact state it exists to repair.

Stamp the real profile name at creation time in all three writers.
E2E-verified against a temp HERMES_HOME: both the desktop create path
and the agent path now persist profile_name='default'.

Fixes #99222
2026-08-31 05:56:18 -07:00
StanleyStetson fa2dd28029 fix(tui_gateway): scope config.get/set RPC to params.profile
config.get and config.set ignored the focused profile on a shared
app-global backend, so reads and persistent writes used the launch
config.yaml. Bind the existing @_profile_scoped decorator and write
_save_cfg through the request home override.

Fixes #95760
2026-08-31 04:33:20 -07:00
David Dudok de Wit e7433910e9 feat(bot-mode): add scoped cross-gateway Group Chat transport 2026-08-31 01:04:11 -07:00
Teknium 5a3edc7467 fix(bot-mode): cancel re-routes on worker races instead of failing disband
Follow-ups on the salvaged #97744 runner:

- tui_gateway/hosted_room_driver.py: HostedRoomRuntime.cancel() treated its
  initial status read as truth, so a task transitioning queued->running (or
  settling) between the read and the state call surfaced a transient
  'running work requires acknowledged two-phase cancellation' /
  StaleTaskError to the caller and failed groups.disband. Deterministic
  repro on the PR head: test_client_event_id_cannot_squat_disband_receipt
  failed 5/5 locally. cancel() now re-reads and re-routes on every
  race-shaped failure (bounded retries), returns already-cancelled tasks
  idempotently, and rejects truly terminal states honestly.
- methods_groups conflict resolution keeps both method sets: the replication
  surface from #99047 (groups.replicate/replica_state/promote/demote) and
  the runner surface from this layer (groups.stop/retry/approve).
- test_groups_replication_methods.py updated to the runner's stricter
  create contract (2-6 profile-backed members, live worker service).
2026-08-30 22:19:06 -07:00
David Dudok de Wit 93c7089f70 feat(bot-mode): run same-gateway Group Chats without Desktop 2026-08-30 22:19:06 -07:00
Teknium e730deedd1 feat(bot-mode): Group Chats survive the authority gateway dying — log replication and fenced takeover
Every participant gateway can now keep a durable copy of a hosted room's
ordered log and continue the room when its authority host is gone:

- gateway/hosted_room_replicas.py: replica store in root state.db.
  ingest_page() persists authority-stamped groups.log pages idempotently,
  refusing sequence gaps and authority-epoch regressions. promote_replica()
  continues the room locally at epoch+1 with a lineage-proving
  authority.claimed event; the stale owner is fenced everywhere the claim
  replicates. demote_room() lets a returning stale authority fence itself
  (authority.lost) upon observing a newer epoch, killing split-brain writes.
- tui_gateway/methods_groups.py: groups.replicate / groups.replica_state /
  groups.promote / groups.demote RPC surface. Promotion requires
  confirm=true — storage decides HOW takeover is atomic and provable, the
  caller (user action now, lease/quorum driver later) decides WHEN it is
  safe, matching the boundary blessed on #97681.

Validation: 20 new tests incl. a full failover round-trip (A hosts, B
replicates incrementally, A dies, B promotes with complete history, A
returns demoted and fenced); 69 total across the hosted-rooms area; E2E
with two real gateway stores and real install identities.
2026-08-30 20:39:58 -07:00
Teknium 6101f52ba4 Merge remote-tracking branch 'origin/main' into core-tool-deferral 2026-08-30 19:47:30 -07:00
David Dudok de Wit cbc67b939f feat(bot-mode): add durable Group Chat authority and replay 2026-08-30 19:46:14 -07:00
imsuperseller 77f5de6272 fix(compression): hot-apply native compaction settings 2026-08-30 05:16:19 -07:00
Stephen Chin 48a4201f40 fix(compaction): preserve switch compatibility fixtures
Keep model-switch callers compatible with result objects created before runtime_capabilities was added, and do not roll back minimal agents that lack optional LM Studio helpers. Preserve rollback for real helper failures.
2026-08-30 05:16:10 -07:00
Stephen Chin 08c7879ca1 fix(compaction): preserve native capability across runtime switches
Stage destination native-compaction capabilities until the complete runtime and context setup succeeds, and restore them with primary and fallback runtimes. Keep native compaction default-deny across live switches and session reconstruction.\n\nVerification: uv run --with pytest --with pyyaml python -m pytest tests/run_agent/test_switch_model_context.py tests/run_agent/test_native_compaction.py tests/run_agent/test_native_compaction_switch_capabilities.py tests/run_agent/test_switch_model_rollback.py tests/run_agent/test_fallback_reasoning_override.py tests/run_agent/test_primary_runtime_restore.py tests/run_agent/test_provider_fallback.py -q -o 'addopts='; uv run --with ruff ruff check <touched files>; git diff --check
2026-08-30 05:16:10 -07:00
Adolanium 58523f284c fix(todo): unversioned tool.start still merges after resume
Resume was attaching an unused store as {todos: [], revision: 0} and the desktop rejected tool.start updates that have no revision. A merge:true start after reconnect never patched the list until complete.

Skip unused empty snapshots. Apply unversioned updates without moving the watermark so a later todo.updated can still win.
2026-08-29 20:46:14 -07:00
Teknium 0f5dd5c46e feat(mcp-oauth): Desktop MCP OAuth now completes against remote backends (client-side callback relay)
The gateway's session-backed MCP OAuth flow (mcp.servers.oauth.start) binds
its browser-callback listener on the BACKEND machine's 127.0.0.1. When the
Desktop app connects to a remote backend (SSH/Tailscale), the user's browser
resolves that loopback to the user's machine, the redirect dies, and every
OAuth catalog server (ClickUp, Hospitable, ...) fails in-app with no working
path — the exact topology from the 'MCP Recurring erros' support thread.

Fix mirrors the Desktop's native gateway login (native-oauth-login.ts):

- gateway: mcp.servers.oauth.start accepts client_redirect_uri (loopback-only,
  RFC 8252-style validation); when supplied no gateway listener is bound and
  the OAuth redirect_uri pins to the client's listener.
- gateway: new mcp.servers.oauth.callback RPC relays the client-captured
  code/state into the flow; state verification stays in
  DashboardOAuthFlow.deliver_callback (constant-time compare, replay-safe).
- desktop: mcp-oauth-callback-ipc.ts hosts a one-shot 127.0.0.1 listener in
  the main process (hermes:mcp-oauth:listen/wait/cancel via preload bridge).
- desktop: hermes-bots mcp-setup.tsx prefers the client listener for local
  AND remote backends, falling back to the legacy gateway-listener flow on
  older gateways (feature-detect via start rejection).
- docs: remote-host MCP OAuth section documents the automatic Desktop path.

Validation: 19 new gateway tests (validator allowlist, listener skip, relay
accept/reject/replay) — sabotage-verified; 5 new desktop tests against a real
ephemeral listener; E2E through the real session registry + flow bridge with
a stubbed provider probe; tsc electron+renderer builds clean.
2026-08-29 19:18:01 -07:00
Teknium 0f3fcacd3f feat: /plan graduates from bundled skill to built-in command on every surface
The bundled plan skill's auto-generated slash command fell off the capped
Telegram/Discord command menus for most installs (skills are the only tier
trimmed at the platform caps, alphabetically — 'plan' sat past the cutoff at
index 57 of 82 bundled skills). Converting it to a first-class CommandDef
gives it a guaranteed core-tier menu slot on every platform.

- agent/plan_prompt.py: build_plan_prompt() — plan-mode rules + authoring
  craft distilled from the retired skill; prompt-injection pattern like
  /learn and /init (no engine, no model-tool footprint, cache-safe).
- CLI: _handle_plan_command mixin handler (pending-input injection).
- Gateway: /plan branch rewrites event.text and falls through (role
  alternation preserved).
- TUI: command.dispatch branch ('plan' was already in
  _PENDING_INPUT_COMMANDS).
- Removed skills/software-development/plan/ + docs pages (EN + zh-Hans),
  catalog rows, sidebar entry, related_skills references.
- PROTECTED_BUILTIN_SKILLS is now empty (mechanism kept); dependent
  curator/usage tests moved to monkeypatched sentinels.

Salvages #67292 by @webtecnica (credit: first /plan command submission,
issue #67264); reworked from inline planning prompt to the prompt-injection
pattern with workspace-saved plans. Closes #67264, closes #36821 (empty
/plan infers task from conversation context).
2026-08-29 19:14:15 -07:00
Teknium 86a2fdc634 feat(tui): status rule shows cache-hit %, latency, t/s and honors display.status_bar.fields
Extends PR #98250's classic-CLI status-bar upgrades to the Ink TUI:
- tui_gateway/server.py _get_usage() now emits cache_hit_pct,
  avg_latency_s, avg_tps (reads the same per-call deque history from
  agent/conversation_loop.py; keys omitted when no data — Codex
  app-server has no latency, zero cache reads show no %)
- StatusRule renders the three read-outs as width-budgeted tail
  segments (breakpoints 96/104/110 cols, lowest priority — they shed
  first on narrow terminals)
- display.status_bar.fields (the SAME key the classic CLI honors)
  filters TUI segments too: cache_hit, latency, tps, duration,
  compressions, bg_tasks, bg_subagents, voice, battery, title,
  context_pct, context_detail
- values ride the existing usage payload/ticker; constants between
  events so the usage==last dedup keeps suppressing repaints
- 3 new server tests, 5 new TUI tests; full ui-tui suite 1727 green
2026-08-29 19:12:24 -07:00
Teknium 7b3c9f86ed Merge origin/main — resolve todo-state seam onto the todo_list rename (accept legacy alias) 2026-08-29 18:55:29 -07:00
Teknium c0875ba503 fix(tui): derive resume todo snapshots from already-loaded history
The eager _read_persisted_todo_state(db, target) added a second
get_messages_as_conversation call on every resume, breaking the
one-lineage-SELECT contract pinned by
test_session_resume_uses_parent_lineage_for_display. Derive the
snapshot from the history each resume path already loaded instead;
deferred (defer_history) resumes cache it in the hydration worker once
the transcript arrives.
2026-08-29 18:40:51 -07:00
itsflownium 393af4a310 fix(todo): live task state via revisioned snapshots and a dedicated todo.updated event
Salvaged from PR #97815 by @itsflownium, slimmed to the schema-free core:
- TodoStore gains a monotonic in-memory revision; the todo tool result
  returns it so clients can reject stale updates
- tui_gateway emits a dedicated todo.updated full-snapshot event that
  bypasses optional tool-progress display settings
- session resume/activate responses attach the authoritative todo
  snapshot; renderer restores it with revision arbitration
- desktop store tracks per-session revisions and rejects regressions

The session_todo_state DB table from the original PR is intentionally
dropped: canonical todo tool results already persist in conversation
history, so resume paths derive the snapshot from the stored transcript
instead of a parallel store.
2026-08-29 18:40:51 -07:00
Teknium e05c91ac71 fix(cli): slow /handoff transfers no longer misreported as "gateway not running"
Live-reproduced on main: /handoff poll-waited a flat 60s for a TERMINAL
state, but the gateway's dispatch is a full synthetic agent turn (whole
transcript replay + delivery) that routinely exceeds 60s on long sessions.
The CLI then printed "Timed out waiting for the gateway. Is `hermes
gateway` running?" (false diagnosis), called fail_handoff() on the RUNNING
row (stomping the gateway's claim), and promised "Your CLI session is
intact" after switch_session had already re-pointed the session. The
watcher later overwrote failed -> completed: split-brain.

- hermes_state.fail_handoff gains only_states CAS; waiters can only fail
  rows still pending. Owner (gateway watcher) keeps the unconditional form.
- CLI wait loop is two-phase: 60s for the CLAIM (pending) — a timeout
  there really does mean no gateway — then up to 15 min for the claimed
  dispatch with 30s heartbeats; a running row is never failed by the CLI.
- Desktop handoff.fail RPC now CAS-fails pending rows only; a running row
  returns {failed: false, state: running} instead of stomping the claim.

Repro (real _handoff_watcher, real state.db, CLI as separate process,
75s dispatch): before — CLI timeout @60s + false message + row stomped;
after — pending->running@5s->completed@80s, clean CLI exit.
2026-08-29 18:08:55 -07:00
Teknium e16ad33a9d feat(tool-search): core-tool deferral — curated 19-tool set behind the bridge by default; renames todo_list/cronjob_manage/process_manage/gui_tour/show_tip with legacy aliases (13.4K -> 6.9K desktop schemas, -49%) 2026-08-29 08:26:24 -07:00
Teknium 578f85cfb0 feat: /btw rides the background-review cache-parity fork for full-context answers
The initial /btw implementation (#97937) answered from a rendered
plain-text transcript digest — truncated context, cold-written tokens on
every question. Teknium's call: reuse the self-improvement review fork
instead, which keeps the entire prompt cache stable for the fork and
gives it the complete conversation for very cheap.

- agent/background_review.py: extract the review-fork construction into
  build_cache_parity_fork() — same runtime/credentials as the parent,
  byte-identical system prompt / tools[] / reasoning config on the
  same-model path, shared session_id for prefix warmth, full persistence
  detachment (no state.db writes, no rotation, no external memory,
  in-place-only compaction). The review thread now calls the helper;
  behavior unchanged (full review test suite green).
- agent/side_question.py: /btw prefers the fork when a live parent
  AIAgent exists — replays the untruncated snapshot as warm cache reads,
  denies every tool at dispatch via an empty thread whitelist (tools[]
  stays byte-identical for cache parity), attributes usage to the parent,
  and trims a mid-turn snapshot tail so role alternation holds. The
  one-shot digest remains as fallback (no live agent = cold cache anyway,
  and any fork failure degrades gracefully).
- CLI passes self.agent, TUI passes the session agent, gateway looks up
  the chat's cached agent (parity with how turns reuse it).

Live-verified: /btw on the worktree runs the fork path (agent.log shows
the side question as a forked conversation turn on the parent session_id
with the full history replayed), answers correctly from context.
2026-08-29 08:23:47 -07:00
Teknium 74a95a3ddf feat: /btw now answers side questions with conversation context; /background renamed to /bg
/bg (formerly /background, which is retired) keeps the existing semantics:
spawn a fresh, independent agent session in the background.

/btw is now its own command matching the convention other harnesses use:
ask a quick side question ABOUT the current conversation without
interrupting it. A one-shot auxiliary LLM call (main model by default,
overridable via auxiliary.side_question.* in config.yaml) answers from a
read-only transcript snapshot — the live session's history, role
alternation, and prompt cache are untouched, and the current turn keeps
running.

Surfaces wired: CLI (inline mid-run dispatch), gateway (all messengers,
busy-dispatch table + idle dispatch, i18n across all 17 locales), TUI
(prompt.btw RPC + btw.complete event), Discord native slash, relay
command manifest, desktop exec routing, docs (EN + zh-Hans).
2026-08-29 07:25:17 -07:00
Inimitable Mind 4e860c093a fix(tui): harden failed build recovery handoff 2026-08-28 04:58:28 -07:00
Inimitable Mind 258d0283b0 fix(tui): close failed resume recovery races 2026-08-28 04:58:28 -07:00
Inimitable Mind dbb9854591 fix(tui): recover model switch after failed resume 2026-08-28 04:58:28 -07:00
ahrazzle 9ddc6fb23a fix(gateway): drop stale model/provider keys in session model_config
_runtime_model_config merges the agent's current identity onto the row's
existing model_config JSON. For model and provider it only SET the key
when the agent attribute was truthy, while base_url/api_mode/
reasoning_config/service_tier already deleted stale values when falsy.
When an agent rebuilt with an empty provider (inheriting the profile
default) was persisted, the previous provider/endpoint survived in
model_config while _persist_live_session_runtime updated the model
column separately. Resume then read the fresh model from the column but
the STALE provider from model_config, silently routing the resumed chat
to the wrong endpoint (e.g. a VeniceAI/empero route under a model that
should run on the profile default).

Apply the same delete-on-falsy rule to model and provider, mirroring the
or-None deletion the CLI path (_persist_model_switch_to_session) already
uses, so a stale session state can never survive into a resume override.
Existing desynced rows self-heal on the next live metadata persist.

Adds regression tests: merge drops stale provider/model when the agent
attribute is falsy, a truthy provider overwrites the stale value, resume
overrides fall back to the billing provider instead of the stale
endpoint, a real-DB round trip heals an already-desynced row, and a
first write (existing=None) reflects only the agent's current identity.
2026-08-28 04:57:49 -07:00
Teknium af53d02920 fix(bot-mode): backfill follow-profile contract for legacy canonical Bot Chats
Bot Chats created before the follow_profile_config marker existed carry no
contract in model_config, so they would stay pinned to a stale stored
provider until deleted — the exact shape of the live reports (#89497,
#94818). Mirror the plugin's own identity rule (the profile's session
titled exactly 'Bot Chat') as a legacy fallback in
_stored_session_runtime_overrides, matching the room-plumbing legacy
'Group:' title fallback.

Follow-up to the salvaged #90343 (@curator8888) and #96111 (@lorzl).
2026-08-28 02:59:17 -07:00
David Tyler 84e17db0bd fix(bot-mode): canonical bot DMs always follow the profile's current config
Bot-Mode canonical chats (the ONE forever DM per bot) and room plumbing
sessions are plugin-owned scratch conversations. They are now created with
an explicit follow_profile_config contract, persisted in the session row's
model_config, so session.resume rebuilds from the member profile's CURRENT
config instead of restoring the stored model/provider pin from an old row.

That stale pin is what left bot DMs stuck on a dead provider (e.g. 'out of
Nous credits' after the profile was switched to ollama-cloud) while the
same bot worked fine in rooms — the mirror image of the room-plumbing bug
(#89497 class). Normal 1:1 user chats keep the stored-runtime restore:
opening an older chat must show the model it actually used.

- tui_gateway/methods_session.py: accept follow_profile_config on session.create
- tui_gateway/server.py: persist the marker in the row; skip stored-runtime
  overrides on resume when present
- apps/desktop/src/plugins/hermes-bots/plugin.js: send the contract from
  createCanonicalChat and ensureGroupChatSession
- tests: backend override + row-persist coverage; desktop source-contract
  coverage for both session kinds
2026-08-28 02:59:17 -07:00
David Tyler 316e51ae72 fix(bot-mode): room plumbing sessions always follow the profile's current config
Room member sessions in Bot Mode are per-member scratch conversations
inside a group chat. session.resume restored their stored model/provider
pin from the row's model_config, so a room bot stayed stuck on whatever
provider was pinned when the row was first written — even after the
profile was switched. Every room message then failed on the stale
provider (e.g. 'out of Nous credits' after switching a profile from
Nous to ollama-cloud) while the same bot worked fine in DMs.

Add an explicit room_plumbing contract:
- session.create accepts room_plumbing: true, persisted in model_config
- _stored_session_runtime_overrides() returns {} for marked rows, so a
  room session always rebuilds from the member profile's CURRENT config
- hidden + 'Group:' title shape is kept as a legacy fallback for rows
  created by older desktop builds that never sent the marker; hidden
  non-room chats keep the stored-runtime restore
- Desktop Bot Mode sends room_plumbing: true when creating the hidden
  per-member room sessions

Fixes #89497
2026-08-28 02:59:17 -07:00
lorzl 99a6852019 fix(tui-gateway): heal or fall back when a resumed session's provider is stale
A session row persists the provider identity a chat actually used. When that
provider is later renamed or removed (e.g. a custom_providers:/providers:
entry deleted, or a provider renamed oldone->newone), Desktop/TUI resume
restores the stale name into agent init and dies with:

  agent init failed: Unknown provider '<name>'

while the CLI resumes the same session fine with the configured default.

- runtime_provider: add is_routable_provider() (full resolution chain:
  built-in -> providers: -> custom_providers: -> models.dev)
- _stored_session_runtime_overrides: heal a non-routable provider via
  canonical_custom_identity (base_url -> model -> configured provider),
  drop to the configured default when unrecoverable, and clear the stale
  base_url after healing so a dead endpoint cannot override the registry URL
- _start_agent_build: gate deferred-resume overrides on provider routability;
  when the stored provider is gone, prefer the model the user picked for THIS
  session, else the configured default
- tests: is_routable_provider cases, heal/fallback round-trips, gate checks

Refs #75128
2026-08-28 02:59:17 -07:00
Brooklyn Nicholson 595ee92289 fix(commands): put desktop slash metadata on the CommandDef
Inference is now any args_hint without subcommands → text. Mixed is the
only remaining hint-token path. desktop= and the few argument_mode
overrides live on the registry entry; the side tables are gone. Catalog
aliases get their own dict copy. Composer tests seed the catalog so
/goal stays mixed without an overlay row.
2026-08-27 22:05:40 -05:00
Brooklyn Nicholson b61408e95e feat(commands): attach desktop slash metadata to the registry
New commands and plugins declare argument_mode and desktop availability
on CommandDef / register_command. commands.catalog ships that map so
desktop does not need a second command list.
2026-08-27 22:05:40 -05:00
Brooklyn Nicholson 39f1e1881a fix(tui-gateway): spare durable rows while a sibling backend holds them
Automatic Desktop ends (ws_orphan_reap, disconnect, idle, LRU, shutdown)
now drop the local runtime but keep the state.db row and durable-key
delegations when another live lease still owns the session.

Co-authored-by: metamindedu <metamind@kakao.com>
2026-08-27 11:50:05 -05:00
Finn763 cae58be1f5 fix(state.db): cross-backend heartbeat gates orphan sweep
A live sibling serve sharing state.db is no longer treated as a dead process by the startup orphan sweep.

Covers the sweep half of #94895. The launchd Errno 48 KeepAlive loop is not addressed here.

Credit: @Finn763
2026-08-27 11:31:59 -05:00
konsisumer c760143935 fix(tui-gateway): claim disconnect sessions before teardown 2026-08-27 07:51:22 -07:00