Commit Graph

15423 Commits

Author SHA1 Message Date
Franci Penov c50bf92f44 fix(gateway): flush spoken acknowledgments at tool boundaries 2026-09-09 10:59:52 -07:00
Teknium ac087e6ada fix(console): cancel/timeout interrupts the command's agent and waits for the worker
Hermes Console ran each command on a ThreadPoolExecutor and cancelled only
the asyncio waiter. A command that forks an AIAgent (`curator run
--consolidate`) kept its worker thread and its in-flight provider request
alive after the prompt said "cancelled" — a llama.cpp generation kept
decoding for 30+ minutes and held the inference slot (#106179).

Root cause: the host owning the thread never knew about the agent created
deep inside the synchronous command, so it could not call the existing
cooperative `interrupt()` path that closes the request sockets.

Fix: `agent/interrupt_scope.py` gives the host an `InterruptScope`; the
console binds it around the worker (ContextVar), and every
`AIAgent.run_conversation()` registers itself with the bound scope for the
turn. On cancel, timeout and disconnect the console calls `scope.cancel()`
(hard-interrupts every registered agent; an agent registering after the
cancel is interrupted on entry so the cancel cannot lose the race with a
turn that has not started) and awaits the worker Future with a 10s bound
before reporting cancelled/timeout. Queued-but-unstarted work is dropped via
`Future.cancel()` alone.

Live repro (fake OpenAI-compatible provider blocking like llama.cpp, real
/api/console, real curator dispatch, real AIAgent + direct request path):
origin/main at the "cancelled" frame -> request_exited=false,
worker_exited=false; with this change -> both true, provider saw the peer
close, prompt reported cancelled 0.27s after the frame.

Salvage of #106197 by @kyssta-exe (executor-future handle, cancel/timeout/
disconnect propagation) and #106320 by @Xixiartemis (deterministic
lifecycle regression: terminal(cancelled) => no owned request or worker
remains live; interrupt-on-late-registration). Both rebuilt slimmer: #106197 keyed its fallback on Future.cancel()
returning False, but the handle it held was run_in_executor's asyncio
wrapper, whose cancel() returns True while the thread keeps running, so its
thread-name abort registry was never consulted; #106320's command-scoped
ownership model is folded into one small module hooked at the turn facade
instead of a per-caller `bind_agent`.

Co-authored-by: kyssta-exe <218078013+kyssta-exe@users.noreply.github.com>
Co-authored-by: Xixiartemis <182932319+Xixiartemis@users.noreply.github.com>
2026-09-09 10:58:16 -07:00
Teknium 6530eb41ad test: verify API Runs continuation consumers over loopback HTTP 2026-09-09 10:55:32 -07:00
Teknium d5926b2494 fix: persist API delegation units once without waking the model 2026-09-09 10:55:32 -07:00
liuhao1024 705bcdcf37 fix(gateway): adopt compression tip for explicit-header chat continuations (#98619)
An explicit X-Hermes-Session-Id client re-sending a pre-rotation id read
the closed parent's stale history slice, bound the turn and the wake
target to the closed parent, and — once the detached delivery writer
adopted the live tip — could no longer consume a late delegation delivery
row persisted on the tip, while still being granted wake_capable="1".

Resolve the client-addressed id through the same canonical
resolve_resume_session_id resolution the delivery writer (gateway/wake.py)
and /v1/runs use, before loading history: the read, the turn, and the wake
binding all select the live continuation tip. Response headers (SSE and
JSON) keep echoing the client-provided id, so the external identity stays
stable across rotations regardless of when a turn rotates relative to
prepared response headers.

Compression-tip read/write routing and the stable-echo identity contract
originate from #13437 (manuelschipper), ported onto the post-refactor
route owner with real-SessionDB regressions (JSON and streaming).

Reported-and-investigated-by: shojikumaru (Sho + Alpha) via #98619
Co-authored-by: manuelschipper <11737902+manuelschipper@users.noreply.github.com>
2026-09-09 10:55:32 -07:00
liuhao1024 71818aaf52 fix(gateway): deny wake authority for caller-supplied conversation_history
#98619 review follow-up: an explicit session_id plus non-empty
caller-supplied conversation_history skipped the SessionDB load yet was
still marked wake-capable ('not previous_response_id' alone). Such a
turn is authoritative on the caller snapshot and never consumes the
SessionDB delivery row a detached completion persists, so wake is now
fixed before the history load can overwrite the variable and denied on
the same default-deny contract as previous_response_id continuations.

Adds an HTTP regression proving the binder receives wake_capable=""
and _conversation_history_for_session stays uncalled on that branch.
2026-09-09 10:55:32 -07:00
liuhao1024 0efb525420 fix(gateway): adopt live compression continuation for /v1/runs delivery
Address the compression-rotation blocker from the follow-up review of #98619:

The parent run can compress/rotate before a detached delegate completes.
The captured origin session id is then a closed parent: the delivery
append is rejected with CompressionSessionClosedError forever (the
watcher retries the same stale id), and no read surface exposes the row.

- persist_delegation_delivery now resolves the live continuation tip via
  the canonical resolve_resume_session_id (the same resolution
  /api/sessions/{id}/messages reads use) before appending, failing open
  to the original id.
- /v1/runs adopts the resolved tip for a client-addressed session id
  (body id or declared key): history loads from it, the turn and wake
  binding target it, so the run no longer writes into the closed parent.

End-to-end regression: parent compresses, detached delivery persists to
the stale id, and the next same-id run loads the delivery row from the
live tip and binds it.
2026-09-09 10:55:32 -07:00
liuhao1024 3db45bab6e fix(gateway): load declared-key history and deny wake for response-chain runs
Address the two /v1/runs blockers from re-review of #98619:

- P1: resolve the session identity (body id > response chain > declared
  X-Hermes-Session-Key > run_id fallback) BEFORE loading history, so a
  header-only declared-key run now loads its selected session's SessionDB
  history. A persisted async-delegation delivery row therefore reaches the
  next same-key run's context, which is what the wake opt-in promises.
- P1: a previous_response_id continuation consumes its ResponseStore
  snapshot and can never see a SessionDB delivery row (async completion
  persists to SessionDB only), so it is no longer granted wake_capable;
  delegate_task keeps its synchronous fallback on that branch until a
  merge contract exists for the chain.

Regressions: declared-key history load (delivery row consumed), no-row
declared key stays fresh, response-chain continuation denied wake with
snapshot history preserved, plain run still granted wake.
2026-09-09 10:55:32 -07:00
liuhao1024 dffc0fa2d5 fix(gateway): require wake-capable session provenance for background delegate_task (#98619)
Rebuilt against the post-refactor owners: the chat-completions route now
lives in gateway/platforms/api_server_openai_routes.py, the wake gate in
tools/delegate_tool_dispatch.py, and session_context.py was reshaped —
the original patch aimed at code main no longer has.

Header-less OpenAI-compatible clients get a fingerprint-derived session
id bound as the api_server chat_id. delegate_task's background gate
treated ANY bound session id as wake-capable and dispatched detached
subagents, but for derived ids the wake self-post lands in a session
whose history the client never reloads — the result is undeliverable by
construction.

Bind a wake_capable provenance flag at session-bind time, DEFAULT-DENY
at the central boundary (set_session_vars and _bind_api_server_session
both treat an omitted declaration as denied; a binder that says nothing
grants no wake authority): "1" only from audited producers whose client
can address the id again (explicit X-Hermes-Session-Id — 403-gated on
API_SERVER_KEY — native /api/sessions/{id} routes, /v1/runs); "" for
fingerprint-derived ids. The delegate gate requires the flag (fail-closed,
captured pre-child-construction alongside origin_wake_sid) and keeps the
forced-sync fallback with its honest note.

Reported-and-investigated-by: shojikumaru (Sho + Alpha) via #98619
2026-09-09 10:55:32 -07:00
Teknium 179790df6f test: reproduce API delegation provenance and replay loss 2026-09-09 10:55:32 -07:00
teknium1 322905e91b feat(memory): make the mem0 sync char cap configurable via mem0.json
A flat 450-char cap fits 512-token embedders (bge-small-zh-v1.5,
all-minilm) but stores only ~5% of the window on 8192-token models
(text-embedding-3-small, jina-embeddings-v3, bge-m3), degrading memory
quality for users those models served fine before truncation existed.

Read `sync_max_chars` from mem0.json once in initialize() (450 default)
and pass it to _truncate_for_sync(). Config over auto-detection: the
Ollama /api/show probe + known-model table proposed in #37427 adds a
network call and a curated list for a number the operator already knows
from their embedder choice; the setup wizard's mem0.json is the plugin's
behavioral-settings surface (no new HERMES_* env var). Documented in the
plugin README and the memory-providers docs page.

Dynamic-cap requirement and measurements (450 OK / 600 -> HTTP 500 on
bge-small-zh-v1.5:f16) by @szicely in #106235.

Refs #37421 #106235
Co-authored-by: szicely <140148567+szicely@users.noreply.github.com>
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
2026-09-09 10:55:02 -07:00
liuhao1024 040742d06b fix(memory): truncate oversized mem0 sync messages at the source
sync_turn() sent the whole turn to backend.add() untruncated. OSS
embedding models with small context windows (Ollama bge-small-zh-v1.5:
512 tokens) reject the request with HTTP 500, and hosted APIs answer
INPUT_TOKEN_LIMIT_EXCEEDED — in both cases _try() only logs, silently
dropping the turn's memory extraction after long conversations.

Cap each synced message at its last sentence boundary within 450 chars
before ingestion: short turns pass through unchanged, long turns keep a
coherent statement for fact extraction. This replaces the previous
retry-on-error approach, which could not match Ollama's HTTP 500 shape.

Salvaged from #37427 with the test suite trimmed to the one invariant
(oversized turn still reaches a small-context backend, short text
untouched, no breaker failure).

Refs #37421 #106235
Co-authored-by: szicely <140148567+szicely@users.noreply.github.com>
2026-09-09 10:55:02 -07:00
liuhao1024 77ca949b90 fix(cli): stop dpaste.com fallback from leaking debug logs for 7 days
The dpaste.com fallback path kept pastes for 7 days (vs the promised
6-hour auto-delete), could not be deleted by `hermes debug delete`
(anonymous pastes have no owner token), and the pending-paste sweep
skipped dpaste URLs entirely — while the share output still claimed
pastes auto-delete in 6 hours.

- Default the dpaste.com fallback retention to 1 day (dpaste's minimum)
  across --expire, upload_to_pastebin, and build_debug_share so the
  dashboard endpoint benefits too
- Print an accurate warning when uploads fall back to dpaste.com
  (retention window + no delete path) instead of the 6-hour promise
- Mention the fallback retention in the CLI and gateway privacy notices
  before the user consents to uploading
- Explain in `hermes debug delete` errors why dpaste.com pastes cannot
  be deleted and that they expire on their own

Refs #106164

[salvage: trimmed to 2 invariant tests (dpaste delete error, dpaste fallback notice);
5 duplicative default-value tests dropped]
2026-09-09 10:54:34 -07:00
chelsealong 21d5df4100 fix(session-state): keep the canonical Bot Chat hidden when pinned
set_session_pinned's unconditional hidden-clear (0be7f931) also
unhides the canonical Bot Chat, which the desktop contract requires
to stay hidden and reachable only through the bot row. Exposing it
breaks the sidebar and disables the rename guard that protects its
identity title.

Skip the unhide when the pinned row is hidden and carries the exact
canonical title; ordinary hidden sessions are unaffected.
2026-09-09 10:52:21 -07:00
chelsealong c59aa2d041 fix(session-state): clear hidden flag when a session is pinned
A bot-mode session is created with hidden=true. Pinning it only wrote
pinned=1 and left hidden=1, so the row was filtered out of both the
default listing (`s.hidden = 0`) and the pinned back-fill (which reuses
the same WHERE), making a pinned session vanish from the sidebar
entirely. set_session_pinned now clears hidden across the session's
compression lineage whenever pinned is set to true.

Fixes #106171
2026-09-09 10:52:21 -07:00
KeyArgo 070128f056 test(agent): provider-neutral name for 429 server-overload regression test 2026-09-09 10:47:49 -07:00
KeyArgo 43ecad8fe6 fix(agent): classify Novita 'server overload' 429 as overloaded
Novita returns HTTP 429 with message 'server overload, please try again
later' and error type 'server_overload' when its server is genuinely busy.
Neither phrase was in _OVERLOADED_PATTERNS, so the 429 fell through to
_V_RATE_LIMIT and set should_fallback=True + should_rotate_credential=True —
rotating the credential / falling back early instead of retrying the same
key. Add 'server overload' and 'server_overload' to the overload tuple so
this reaches the existing _V_OVERLOADED verdict (retryable, no rotation).
Closes #106205
2026-09-09 10:47:49 -07:00
Teknium e22e04692a test(matrix): trim LaTeX salvage to two invariant tests, tidy _markdown_to_html
Keep the two tests that fail without the fix: inline + display math reach
formatted_body as data-mx-maths markup with the TeX HTML-escaped while the
plain body keeps the raw TeX; unpaired dollars and text colliding with the
sentinel format pass through unchanged (no IndexError). The 17 unit tests
from #106452 are dropped per the salvage bar (≤ 2 invariant tests).

Also drop the dead `_tex_store = []` pre-assignment and the `_fb`/`html`
temporaries in `_markdown_to_html` — pure tidy, no behaviour change.
2026-09-09 10:43:58 -07:00
romanovzky 199f4d5b96 feat(matrix): render LaTeX math via Element data-mx-maths markup
Element (feature_latex_maths) typesets <div|span data-mx-maths="TEX">
elements at display time, but the outbound HTML sanitizer allowlists tags
and attributes, so data-mx-maths markup sent by the gateway never reaches
Element intact - messages containing $...$ render as raw dollars.

Convert $...$ (inline) and $$...$$ (display) to opaque sentinel tokens
before Markdown conversion and expand them to data-mx-maths markup after
sanitization. Tokens are printable text with no HTML/Markdown meaning, so
neither the converter nor the sanitizer touches the TeX. Unpaired dollars
(prices, literals) are untouched, and adversarial text colliding with the
sentinel format passes through verbatim (index-checked expansion).

(cherry picked from commit eb73aafe0e08502c54e63dbd03e99796c3b7fee3)
2026-09-09 10:43:58 -07:00
Teknium 1a500a43a7 fix(gateway): keep launchd_stop's bootout quiet too; prove the fd-2 invariant with a fake launchctl
Widens #106272 to the one remaining sibling: `launchd_stop()` boots out with check=True and
already handles exit 3/113/125 (job unloaded) and 5/125 (domain unmanageable) by falling through
to the PID kill, yet inherited stderr — so `hermes gateway stop` against an unloaded job printed
"Boot-out failed: 3: No such process" next to "✓ Service stopped". Same `_CAPTURE_TEXT` kwargs as
the sibling calls; an unexpected exit still raises with `e.stderr` populated.

Replaces the contributor's two kwarg-assertion tests (`capture_output is True` on a mocked
`subprocess.run`) with two invariant tests that run a real fake `launchctl` on PATH and read fd 2
through `capfd`: restart-on-unloaded prints only its ↻/✓ lines and drives
kickstart→bootout→bootstrap→kickstart; stop-on-unloaded is silent, while a real bootout failure
(exit 1) still raises with the captured stderr. Both red on origin/main, green here.
2026-09-09 10:42:32 -07:00
teknium1 79d73e8f63 test(telegram): trim bots_require_mention coverage to the two invariants
Keep the loop-breaker test (bot quote-reply processed on main, dropped with the
flag, explicit @mention still passes) and the human quote-reply test (unaffected
with the flag on). Drop the defaults-off snapshot, the /cmd@botname variant, the
plain-chatter duplicate and the own-echo helper test: they re-cover paths
(_message_mentions_bot, _is_own_message) already pinned elsewhere in this file.
2026-09-09 10:37:37 -07:00
Konstantin Khlopkov 1a981d8e83 fix(telegram): bots_require_mention gates bot quote-replies behind an explicit @mention (closes #106430)
(cherry picked from commit a67fa8c4b21e31a44019d850aedc5be9015a546d)
2026-09-09 10:37:37 -07:00
teknium1 8d93081971 fix(desktop): stop flagging local/LAN auxiliary pins as stale
An aux task pinned to a private endpoint via `base_url` (a home Ollama
box at `byron.local`, a LAN IP, localhost) is the intended per-task
endpoint feature and can never bill a provider. The Settings → Model
banner still counted it as "still run on openai" forever and offered
"Reset all to main", which would wipe the working local setup; the
post-switch `stale_aux` report had the same blind spot; and the aux row
never showed the `base_url` the backend already sends, so the pin was
indistinguishable from a paid-provider pin.

- `GET /api/model/auxiliary` now stamps each task with `local_endpoint`,
  the verdict of the one canonical classifier
  (`agent/model_metadata.py::is_local_endpoint`) — no TS mirror of the
  private-range rules, so frontend and runtime cannot drift.
- Desktop: the persistent banner filter is the pure
  `staleAuxAssignments()` and skips `local_endpoint` pins; the pinned row
  appends ` · <base_url>` when one is set.
- `_stale_aux_pins` (post-switch report) skips local pins the same way.
- `is_local_endpoint`: `*.local` (RFC 6762 mDNS) now counts as local, and
  IPv6 literals no longer ride the "no dots ⇒ unqualified host" rule, so
  a global-scope address (`2607:f8b0::1`) is not local while `::1`,
  ULA and link-local still are via the `ipaddress` scope checks.

Slim redo of #106236 (@webtecnica) and #106234 (@huklaa), which fixed the
same symptom with a client-side classifier copy; the bug class, row
display and mDNS/IPv6 classifier corrections are theirs.

Refs #106228

Co-authored-by: Hukla <129692708+huklaa@users.noreply.github.com>
Co-authored-by: webtecnica <webtecnica@gmail.com>
2026-09-09 10:33:00 -07:00
teknium1 113304199e refactor(desktop): gate the WSLg D3D12 selection inside the helper and test the real launch env
Move the WSL / /dev/dxg / d3d12_dri.so probes into _prefer_wsl_d3d12 with
the probed paths as module constants, so the launcher call site is a single
line and a test can lay out a fake WSLg host without touching real
/dev or /usr/lib. The two tests now run the real _desktop_launch_env end to
end (selected under WSL+dxg+driver; untouched with an explicit Mesa
override, off WSL, without /dev/dxg, or without the driver file) instead of
unit-testing the helper with a precomputed boolean.

Docs: one paragraph in the Desktop guide on the automatic selection and
the env vars that keep an explicit choice authoritative.

Follow-up to Xipong's fix for #106117 (salvaged from #106118).
2026-09-09 10:28:52 -07:00
Xipong 51fa04d49d fix(desktop): select installed WSL D3D12 driver before Electron exec 2026-09-09 10:28:52 -07:00
teknium1 a785db3672 fix(cli): inline the $HERMES_HOME/npmrc lookup, trim tests to two, document it
Fold the helper into _npm_lifecycle_env itself: the whole fix is one
is_file() check plus a setdefault, so a separate function, the
try/except around get_hermes_home() (it never raises) and the
dict-returning indirection were shape-gate violations. Build the path
with os.fspath so it is correct on Windows too.

Tests: keep the two invariants (file present -> NPM_CONFIG_USERCONFIG
points at it; explicit process/caller value wins and a missing file
sets nothing), fold the other two into the negative test.

Docs: one paragraph in the desktop troubleshooting page next to
ELECTRON_MIRROR describing $HERMES_HOME/npmrc.

Refs #106373
2026-09-09 10:26:06 -07:00
Konstantin Khlopkov ce4a33a9f7 fix(cli): keep $HERMES_HOME/npmrc npm config across updates (#106373)
(cherry picked from commit 339368f2215ffcfd04acf295c81806bf1e850770)
2026-09-09 10:26:06 -07:00
teknium1 d3dcc064df fix(cli): detect ssl.SSLError by type in the Codex login hint; trim tests; add the openssl.cnf snippet to docs
- _ssl_interop_hint: also match ssl.SSLError instances (and one level of
  __cause__/__context__) plus the bare UNEXPECTED_EOF marker, so an
  SSLEOFError whose text httpx did not repeat still gets the hint. The
  hint now names the TLS 1.2 diagnostic and links the providers docs
  note instead of an issue number.
- tests: 3 -> 2 invariants (parametrized login_post/poll SSL case keeps
  the raw text + hint + cause; a plain httpx timeout gets no hint).
- docs: providers.md Codex note carries the reporter's exact openssl.cnf
  classic-groups snippet (EN + existing zh-Hans copy).

Refs #106384. The TLS max-version cap itself stays PR #44392's scope.
2026-09-09 10:14:58 -07:00
liuhao1024 d8eb177c93 fix(cli): keep SSL detail and add middlebox hint on Codex device-login transport errors
Device-login requests on networks whose middlebox rejects the larger
TLS 1.3 ClientHello sent by OpenSSL 3.5+ (post-quantum hybrid groups)
fail with SSLEOFError / handshake timeouts while curl still works, so
they masquerade as a Codex outage (#106384). The polling loop let the
raw httpx error escape unshaped, and _codex_login_post dropped the
exception chain and gave no actionable hint.

- add _ssl_interop_hint() applied to both device-login transport paths
- re-raise _codex_login_post failures with 'from exc' to preserve cause
- wrap the poll POST so transport failures become a shaped AuthError
  (device_code_poll_error) carrying the SSL detail and OPENSSL_CONF
  workaround hint; KeyboardInterrupt handling is unchanged

(cherry picked from commit 8cd94c36ce8437db5b00290b9edbedcd2116c02c)
2026-09-09 10:14:58 -07:00
Teknium 42d28d64f0 test(hermes_state): trim compacted-paging tests to the invariants that fail on base
Six new tests collapsed into three that each go red without the indexed
projection: bounded VM steps for a page read and for an append (the
symptom), composite user-handoff identity + first-row position + internal
columns never leaking + signed-zero timestamp identity (the parity
contract), and a legacy store read-only then lazily migrated (the
persistence contract). The parametrized symmetry/visibility-toggle test
exercised the same key through raw SQL edits no production path performs
and passed on base, so it was a change-detector for the trigger shape.
2026-09-09 10:05:59 -07:00
Xipong 1c6683e8e0 fix: index compacted display identity writes 2026-09-09 10:05:59 -07:00
Xipong 49e6d661a0 fix: bound compacted display history paging 2026-09-09 10:05:59 -07:00
Eva 2536772301 fix: preserve summary boundaries when restoring model replay 2026-09-09 09:59:13 -07:00
teknium1 5de30f36f1 refactor(gateway): reuse recorded_gateway_home_conflicts for the scoped PID home check
The salvaged fix added `_pid_record_matches_home`, a near-copy of
`recorded_gateway_home_conflicts(record, expected_home=...)` (already the
scoped-home predicate used by the #89315 stop guard). Reuse it instead of
carrying a second helper with the same semantics (legacy records without
`hermes_home` are accepted by both).

Also trims the salvaged tests to the two invariants that prove the symptom
(scoped probe reports a live foreign profile's PID and leaves its
identity files intact; a dead-PID scoped record is still cleaned). The
third-home-claim variant exercised the same `saw_live_pid` branch.
2026-09-09 09:55:52 -07:00
liuhao1024 a23319d0f7 fix(gateway): scoped PID queries validate against the probed home (#106406)
get_running_pid(pid_path) validated records against the serve process's
HERMES_HOME, so a dashboard scoped status poll (?profile=) rejected a live
foreign profile's record, force-unlinked its gateway.pid/gateway.lock, and
reported running=false. Validate scoped queries against the probed home
(pid_path.parent, like the expected_home sibling) and never cleanup-unlink
a live record's identity files; dead-PID records still clean up.

(cherry picked from commit 472ca1b8d87df5246d83864e9b1492d06e99e8e5)
2026-09-09 09:55:52 -07:00
Teknium b24a781b6f test(agent): trim the restart-bound tests to two invariants
Collapse the four class-based tests into two parametrized invariants over both
refunding restart flags and move them to tests/agent/ (the phase modules live in
agent/): a single restart still refunds-and-continues; a re-armed restart breaks
after max_retries refunds. The stub grows the redirect seam the follow-up commit
uses so the queued-correction contract is covered by the same test.
2026-09-09 09:51:31 -07:00
yoyodine-industries e9312da68b fix(agent): bound redirect/rebuilt restart refunds so a runaway turn can't hold the session lease
The redirect and rebuilt-for-fallback restart paths in apply_retry_restarts
refund the iteration budget and re-issue the iteration with no per-turn
bound. A redirect/interrupt that keeps re-arming the flag refunds forever,
so the turn loop never exits and the durable session turn lease is held
indefinitely (concurrent processes block up to LEASE_WAIT_SECONDS).

Add a per-turn restart_count accumulator (threaded through _run_phase like
the other loop locals) and break out once it exceeds max_retries, matching
the bound the compression path already has.
2026-09-09 09:51:31 -07:00
Halldrix 78de23053f fix(gateway): report media-only turns as SUCCESS when attachments deliver
Thread record_delivery through _deliver_attachments, _deliver_media_attachments
and _send_image_batch so attachment sends feed the turn outcome tracker.
send_multiple_images (base default and Signal override) now returns SendResult
(success when at least one image/batch was accepted); _send_attachment_batch
returns bool. Legacy native-batch overrides that still return None record
nothing, keeping their previous behavior until migrated.

Fixes #106153
2026-09-09 09:45:54 -07:00
Teknium 00bcef9b5f test(kanban): install the reviewer profile the review-surface fixture hands off to
kanban_request_review now rejects reviewers that are not installed profiles
(#106163); the cross-surface lifecycle test used a bare "reviewer" name with no
profile behind it, which is exactly the phantom the guard exists to catch.
2026-09-09 09:45:13 -07:00
teknium1 e2763baf1c refactor(kanban): route the reviewer guard through _check and tighten its tests
Use the module's `_check`/`_Reject` idiom instead of an inline
`return tool_error(...)` so every kanban_request_review validation
failure renders through the same path, and drop the unreachable
`or "none"` (list_profile_names() always contains "default").

Tests: compare the task's (status, assignee, run) tuple and the event
log before/after instead of the unordered 6-assert block, use the
context-managed kanban_db_connect.connect (the kb.connect alias is a
plugin-compat pointer — scripts/check_compat_pointers.py flagged it),
and reference #106163 in the invariant's docstring.

Salvage note vs #106214 (@gaoanze888): that PR guards the same condition
inside hermes_cli/kanban_db.py::request_review, but the DB primitive is
also the chokepoint for `hermes kanban request-review` and the
dashboard's drag-to-review, both operator surfaces where a non-profile
assignee (external/human review lane) is a documented board shape
(website/docs/user-guide/features/kanban-worker-lanes.md) — and it forced
five unrelated test fixtures to monkeypatch profile_exists to True. The
model-facing tool wrapper is the layer where a typo'd string is a bug,
so the guard lives there.
2026-09-09 09:45:13 -07:00
auroracapital 1d89286b36 fix(kanban): reject phantom worker reviewers
kanban_request_review(reviewer=<name>) reassigned the task to whatever
string the model supplied. A non-profile value (e.g. the literal
"reviewer") parked the card in `review` on an assignee the dispatcher
can never spawn, with no error to the worker — the chain stalled
silently (#106163). Validate the explicit reviewer against installed
profiles before touching the board and return a tool error listing the
installed profiles so the model can self-correct.

Salvage of #97429: the kanban_diagnostics `review_reopened` hunk and its
tests were dropped (main already replaced that loop with
`_latest_event_ts`; the tests targeted the PR's pre-refactor base).
Re-authored from the placeholder identity `regen <regen@local>` to the
PR author's GitHub noreply address (misconfigured local git, not malice).
2026-09-09 09:45:13 -07:00
Teknium e74c4a00ca Merge pull request #69446 from NousResearch/feat/plugin-catalog
feat: plugin catalog — curated SHA-pinned plugin index (CLI, admission CI, docs, dashboard)
2026-09-09 09:22:21 -07:00
Teknium 3026f4a993 test(compression): trim batch clarify coverage to two invariants
Drop the sentinel-only batch test: a batch sentinel is already rejected by the
shared _is_clarify_non_response_sentinel list check that the existing sentinel
tests pin, so the case adds no new contract. Also add the contributor email
mapping for the cherry-picked commit so release CI can attribute it.
2026-09-09 09:21:55 -07:00
gaoanze888 8af248042c fix(compression): preserve batch clarify answers in summarize pass
_sum_clarify only extracted the top-level ``user_response`` key, so batch clarify
results (questions=[...] -> responses[].user_response) fell through to the generic
placeholder and the summarizer never saw the user's answer/permission decision.

Closes #106077.
2026-09-09 09:21:55 -07:00
Teknium bca7cd0eb0 fix(state): projected compression tip inherits the root's title when the tip is untitled
`hermes peer dm` resolves the target's canonical Bot Chat with
GET /api/sessions?title=Bot%20Chat&include_hidden=1. list_sessions_rich
admits the hidden root via the chain search, then _project_compression_tips
overwrites every surfaced field — title included — with the live tip's. The
title is carried root->tip by the agent AFTER publish_compression_child's
transaction; a rotation cut off in between (crash, closed app, the tip's
title write failing) leaves "Bot Chat" on the ended root and NULL on the tip,
so the projected row carries title=None, the handler's exact-title filter
drops it, the peer POSTs a duplicate and the UNIQUE(title) guard answers
400 "Title already in use" (#106165).

Fix at the projection: fall back to the root's title only when the tip has
none (a titled tip keeps winning). Same COALESCE in the bounded recent-
sessions lister, the other place that projects a lineage onto its tip. This
replaces the handler-level fallback in PR #106365 (a second lookup path
bolted onto _handle_list_sessions with try/except: pass) with a 5-line fix
at the one place the title is lost, so every list consumer sees the name.

Salvage of #106365 by @finn763.
2026-09-09 09:21:46 -07:00
finn763 0c604d7e80 test(gateway): peer dm e2e against a hidden Bot Chat that rotated through compression (#106165)
Regression test from PR #106365 (one of its two tests kept: the full peer-dm
e2e; the listing-shape test asserted the same row and was dropped). The
handler-level fallback that shipped with the test is replaced by a SessionDB
fix in the follow-up commit, so this commit carries only the test.
2026-09-09 09:21:46 -07:00
1052326311 17fe7bc75f test(compression): cover cooldown rollback on a concurrently deleted session (#106271)
Regression tests carried from #106277 (its fix hunk is redundant with #106276's, picked before this).

Salvaged from #106277.
2026-09-09 09:21:39 -07:00
teknium1 02005cfe20 fix(kanban): promote refuses undone parents instead of a false --force success
`hermes kanban promote --force <id>` printed `Promoted <id> -> ready` and
then the very next claim (a human `claim`, or the dispatcher tick seconds
later) demoted the task back to `todo` with `claim_rejected
{parents_not_done}` and returned None (#106195). The non-force refusal
even pointed operators at `--force` as the escape hatch.

The claim gate is deliberate: `claim_task` is the single enforcement point
("never ready -> running with an undone parent, whichever writer set
'ready'", cda20eec0c), and `complete_task`/`request_review` re-check the
same predicate, so a child let through by a forced claim could still never
finish. A promotion override therefore has no honest outcome; the
dependency edge is the real knob.

- drop `--force` from `promote` (parser, CLI handler, `promote_task`
  kwarg, the `forced` event field nothing read)
- the refusal message now states why the gate cannot be bypassed and names
  the working remedies: complete the parents or `hermes kanban unlink`
- two invariant tests: refusal on an undone parent leaves `todo` with no
  fake `ready`; the flag no longer parses

Salvage direction from #75354 by @vyacheslavk (diagnosis of the promote ->
claim gap); the consume-at-claim authorization there is not taken because
the same parent gate also blocks completion of the forced child.
2026-09-09 09:21:29 -07:00
Teknium ae65399d8f test(cron): trim kind-flip repeat tests to the two invariants
Keep the two tests that fail without the fix (one-shot -> recurring drops the
implicit times=1, recurring -> one-shot gains it) and fold the explicit-repeat
case into the first; drop the same-kind and explicit-finite cases, which only
pin behaviour the fix never touches.
2026-09-09 09:20:20 -07:00
Konstantin Khlopkov 111aea1a01 fix(cron): re-derive repeat defaults when a schedule update flips the kind 2026-09-09 09:20:20 -07:00