Commit Graph

20646 Commits

Author SHA1 Message Date
kshitij e9a8b70fc4 chore: map jun@junho.co to junhohong 2026-08-04 14:43:10 +05:30
kshitijk4poor 4075c8fd5a fix(credential-pool): lock the quarantine read-modify-write of _entries
#71775 moved deferred single-use-token refreshes outside the pool lock
(correct — they hold a cross-process flock plus network I/O). But
_refresh_entry_impl's three terminal-auth-failure quarantine paths do a
bare read-modify-write of self._entries. Those used to run with the
caller holding self._lock; on the deferred path they run unlocked, so a
concurrent mutation between the read and the write is silently lost.

Wrap all three in 'with self._lock' (an RLock, so locked callers
re-enter safely) and correct the _refresh_pending_entries docstring,
which claimed the mutations were already self-locking.

Post-merge gate-sweep finding on the #71775 salvage (#77714).
Sibling to the acquire_lease re-select fix.
2026-08-04 13:20:15 +05:30
kshitijk4poor db0bd42119 fix(credential-pool): re-select in acquire_lease after a deferred refresh
select() re-selects once deferred single-use-token refreshes complete;
acquire_lease() performed the refresh but returned its pre-refresh
answer. Since _acquire_lease_under_lock returns early exactly when a
refresh is pending (if not available: return None, pending_refresh),
a pool whose entries all needed a refresh always returned None — the
caller failed an answerable request right after the refresh succeeded.

Retry once, only when the first pass was empty and a refresh ran.

Post-merge gate-sweep finding on the #71775 salvage (#77714).
2026-08-04 13:12:24 +05:30
kshitijk4poor fb4e17b1ea fix(test): feed the SSE writers an asyncio queue, not queue.Queue
CI caught a missed caller-shape update. Both PRODUCTION callers of
_write_sse_chat_completion / _write_sse_responses were converted to
ThreadSafeAsyncQueue, but two pre-existing tests in
tests/gateway/test_api_server.py construct the writer's queue
themselves and still passed a stdlib queue.Queue.

The consumer now does 'await asyncio.wait_for(stream_q.get(), ...)',
which on a queue.Queue blocks the thread forever:
test_stream_cancelled_persists_incomplete_snapshot hung until
pytest-timeout killed it (CI reported the whole file as 'no tests
ran (timeout before collection)'). The sibling disconnect test only
survived because it pre-fills before the first await.

tests/gateway/test_api_server.py: 99 passed (was 1 failed + a 60s
hang); with the SSE/api_server suites: 147 passed.
2026-08-04 13:07:44 +05:30
kshitijk4poor 7e344dc0dc test: exercise the production _loop_ref path in put_threadsafe tests
Gate finding (/simplify-code pass): both cross-thread tests passed
loop=loop explicitly, but no production caller does — all six
(_on_delta, _on_tool_*) rely on the queue resolving its own
_loop_ref in __init__. The kwarg made the tests vacuous: a broken
_loop_ref still passed them.

Dropping the kwarg exercises the real path. Verified by mutation:
with self._loop_ref = asyncio.new_event_loop() (wrong loop), both
tests now FAIL; they passed before this change.
2026-08-04 13:07:44 +05:30
zabih-sudo 64882bc684 perf(tui): bound reasoning-clean input to the displayed tail
CI caught a split defect in this salvage: the PR's long-reasoning tail
test was kept but its production hunk was dropped as 'cosmetics'. It
isn't — cleanThinkingText runs several full-string regex passes and
reasoning grows on every streamed token, so re-cleaning the whole
accumulated string per chunk is O(n) per token / O(n^2) per stream.
Only the tail is displayed (boundedLiveRenderText caps it downstream),
so bound the input to 1.5x LIVE_RENDER_MAX_CHARS first.

Restores the one text.ts hunk from cd99e65fc (author preserved); the
italic-thinking display change and profile script from that commit
remain out of scope.
2026-08-04 13:07:44 +05:30
kshitijk4poor 98165daacb fix: reconstruct fused test after conflict resolution
The conflict-marker strip fused test_agent_task_raises with the body of
test_failed_result_dict — restore both as separate tests (content from
the PR head, verified verbatim).
2026-08-04 13:07:44 +05:30
zabih-sudo fc8e3936a6 test: add cross-thread put_threadsafe + long-reasoning tail tests
Addresses teknium1 sweeper review (2026-07-30) requiring coverage of:

1. ThreadSafeAsyncQueue.put_threadsafe() off-loop boundary: a real
   daemon thread pushes into the queue from outside the owning event loop
   while the consumer awaits get(), mirroring the run_conversation
   worker-thread producer path. Includes a 20-concurrent-thread
   no-drop regression.

2. Long-reasoning bound stability for thinkingPreview: 100k-char input
   plus empty/collapsed cases must not crash and must retain the visible
   tail marker inside the bounded 24k clean window.
2026-08-04 13:07:44 +05:30
zabih-sudo 221afc0cb0 refactor(gateway): route session event stream through _sse_frame (ensure_ascii=False)
The session event stream (api_server.py:~2236) was the one genuinely
unicode-distinct SSE writer — json.dumps(payload, ensure_ascii=False) +
.encode('utf-8'). Every other writer uses plain json.dumps. Route it
through _sse_frame(..., ensure_ascii=False) so _sse_frame is now the single
source of truth for ALL SSE frame serialization in the module (chat-
completion, responses._write_event, /v1/runs, and the session stream).

Byte-identical for non-ASCII payloads: verified against the historical
inline encoder (raw bytes preserved). The ensure_ascii=False path is now
exercised by test_sse_frame_ensure_ascii_false_reproduces_session_event_stream.
2026-08-04 13:07:44 +05:30
zabih-sudo 1a09b07253 refactor(gateway): route all three SSE writers through _sse_frame()
_extend _sse_frame with an explicit ensure_ascii param (default True,
byte-identical to a bare json.dumps) and route the two sibling writers
through it: _write_sse_responses._write_event and the /v1/runs event
stream. This completes the dedup PR #65009 — previously only the five
_write_sse_chat_completion sites used the helper, leaving the other two
writers on inline json.dumps with no shared shape.

No behavior change: every writer's emitted bytes are unchanged (verified
byte-for-byte, including non-ASCII payloads where the default
ensure_ascii=True matches the original inline encoders). The ensure_ascii
option is exposed so a future writer can opt into raw non-ASCII bytes
without fractalizing the format again.

Adds tests/gateway/test_sse_frame.py asserting the byte-contract
invariant between _sse_frame and the historical inline encoders.
2026-08-04 13:07:44 +05:30
zabih-sudo 7a1f2e3a66 refactor(gateway): extract _sse_frame() helper, dedup 5 inline SSE encode call sites
_write_sse_chat_completion had five near-identical
f"data: {json.dumps(...)}\n\n".encode() (and one event-tagged variant)
scattered across its role/content/finish/error chunk writes. Pure
extract-method, no behavior change: encoding is byte-identical for every
call site touched.

Left the pre-serialized-string writers elsewhere (_write_event's
json.dumps(..., ensure_ascii=False) path, the /v1/runs SSE writer) alone
— routing them through this helper's plain json.dumps(data) would
silently change their unicode-escaping behavior, which is out of scope
for a pure dedup.
2026-08-04 13:07:44 +05:30
zabih-sudo 7098862dea perf(gateway): replace SSE poll loop with call_soon_threadsafe-fed asyncio.Queue
_write_sse_chat_completion and _write_sse_responses bridged their
stream_delta_callback queue into the event loop via
`await loop.run_in_executor(None, lambda: stream_q.get(timeout=0.5))`
in a while-True poll — a thread-pool round trip on every 0.5s tick even
when idle, plus up to 500ms of tail latency between a delta landing in
the queue and it reaching the SSE response.

Add ThreadSafeAsyncQueue (asyncio.Queue + a put_threadsafe() that wraps
call_soon_threadsafe), used by both streaming producer closures
(_on_delta, tool start/complete callbacks — all invoked from the worker
thread running run_conversation via loop.run_in_executor). Consumers
now do a plain `await asyncio.wait_for(stream_q.get(), timeout=0.5)` —
woken immediately when a delta arrives, no executor hop, no poll
interval.

Updated tests/gateway/test_sse_agent_cancel.py's 7 call sites to
construct ThreadSafeAsyncQueue inside the running loop (required, since
it captures asyncio.get_running_loop() at construction) instead of a
bare queue.Queue() at test-method scope.
2026-08-04 13:07:44 +05:30
hermes-seaeye[bot] 9076adaca5 fmt(js): npm run fix on merge (#78271)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2026-08-04 07:10:23 +00:00
kshitij be54f28b16 test(desktop): cover minimized/hidden window-state + visibilitychange pause for GlyphSpinner
Regression coverage requested in review of #74357: mock
window.hermesDesktop.onWindowStateChanged (pattern from
persistent.test.tsx) and assert minimized/hidden clears the spinner
interval while restore resumes it; also cover document.visibilityState
hidden/visible via visibilitychange.
2026-08-04 12:30:44 +05:30
Mykola Bashmakov 9a20d7f680 perf(desktop): keep spinner frames out of React commits
Advance the existing animated status glyph through its DOM text node instead of React state, and pause its timer for hidden panes or inactive windows. Cover frame advancement, zero update-phase commits, and timer suspension with behavior tests.
2026-08-04 12:30:44 +05:30
kshitij 8f52040dd0 test(cli): regression tests pinning auth-first ordering skips registry sweep
Teknium's review on #63457: existing tests pin the final boolean but not
that the slow PROVIDER_REGISTRY sweep is skipped. Add three tests that
booby-trap hermes_cli.auth.get_auth_status and verify
_has_any_provider_configured() short-circuits on:
- config.yaml model.provider
- config.yaml base_url/api_key (custom endpoint shape)
- auth.json active_provider (sweep-only call-pattern guard)

Mutation-checked: reverting the reorder makes all three fail.
2026-08-04 12:28:39 +05:30
frohsinnllc dbafb59227 perf(cli): check local auth.json/config before slow provider registry sweep
_has_any_provider_configured() probed every api_key provider (gh subprocess
for copilot alone takes 5s; full sweep ~18s) before consulting auth.json and
config.yaml, which are instant local reads. Desktop setup.status calls
blocked past the UI's timeout, causing the connect/disconnect boot loop.
Reorder so cheap local checks run first. Same semantics, ~35x faster here.
2026-08-04 12:28:39 +05:30
kshitij 5c078b987e test(tui): pin picker-cache prewarm wiring in entry.main()
teknium's review gap on #72021: the helper's worker/once-guard was
covered, but nothing asserted the stdio TUI entry point actually
invokes prewarm_picker_cache_async() — or that it does so in the right
place. Add a focused entrypoint test that runs the real entry.main()
with stubbed collaborators (same monkeypatch-module-attrs harness as
test_tui_entry_mcp_owner.py), spies on the helper in
hermes_cli.model_switch (the lazy-import source), and asserts:

- prewarm fires exactly once, strictly AFTER the gateway.ready write
- startup stays non-blocking: main() reaches the stdin loop and
  returns on EOF
- a prewarm failure is swallowed (fire-and-forget) without breaking
  startup

Mutation-checked: deleting the prewarm hunk from entry.py fails both
tests.
2026-08-04 12:28:05 +05:30
ZachariahChu bdc82e39e9 perf(gateway): prewarm /model picker cache on TUI startup
The classic CLI run() loop calls prewarm_picker_cache_async() during the
idle window after the banner is shown, so the first /model open hits a warm
provider-models disk cache and renders in ~100ms. The stdio TUI entry point
never did this, so the first /model open in a TUI session blocked on serial
/v1/models fetches for every authenticated provider.

Mirror the CLI behaviour: kick off the same off-thread prewarm right after
gateway.ready is emitted (banner shown, user about to type). Fire-and-forget,
guarded once-per-process, fully exception-isolated so a slow or offline
provider can never affect TUI startup.
2026-08-04 12:28:05 +05:30
kshitij 743dc94ab9 chore: AUTHOR_MAP — add BobClawblaw for PR #77870 salvage
Bare noreply email (no NNN+ prefix) needs explicit mapping.
2026-08-04 11:26:39 +05:30
kshitij 9fc8926975 perf: reuse request_input_estimate instead of recomputing estimate_request_tokens_rough
The output-cap error handler already computes request_input_estimate at
line 4722 via estimate_request_tokens_rough(api_messages, tools=...).
The new compression block ~50 lines below was calling the same function
with the same inputs again. Reuse the existing local.
2026-08-04 11:26:39 +05:30
kshitij 78c8bcd122 chore: drop CHANGELOG.md and docs/reports/ — not shipped with salvage PRs 2026-08-04 11:26:39 +05:30
BobClawblaw 04098e2b5f fix(conversation_loop): prune dead vision-strip fallback; harden output-cap retry tests 2026-08-04 11:26:39 +05:30
Hermes Agent 9938d20503 fix(conversation_loop): compress messages on output-cap retry path (#55546)
The output-cap retry loop reduced max_tokens by 64 tokens per attempt but
never called _compress_context(), so the compressor never fired. Input
growth (~65 tokens/attempt) canceled the savings, leaving the session
stuck at 200,001 tokens — 1 over the 200,000 ceiling.

The fix adds compression to the output-cap retry path. The compressor
drops the middle window, freeing ~50% of tokens. If compression makes
>=5% savings, the session continues; otherwise vision payloads are
stripped or the session ends with compression_exhausted=True.

Also adds CHANGELOG.md entry and bug fix report.
2026-08-04 11:26:39 +05:30
kshitij 15d51bb88a refactor: dedup stale-marker regex — use compiled _STALE_MARKER_RE in conversation_loop
The bracketed-marker regex was inlined in conversation_loop.py as
re.fullmatch(r"\[...", ...) while hermes_state.py defines the same
pattern as _STALE_TOOL_CALL_MARKER_RE. Both must agree on what counts
as a stale marker — a drift here means the runtime guard silently
disagrees with the load-on-read repair and CLI purge in hermes_state.

Consolidate onto a single compiled constant (_STALE_MARKER_RE) at
module level in conversation_loop.py, with a comment noting it must
mirror _STALE_TOOL_CALL_MARKER_RE in hermes_state.py. A direct import
from hermes_state was tried first but caused a regression: hermes_state
initializes DEFAULT_DB_PATH = get_hermes_home() / 'state.db' at module
import time, which breaks tests that monkeypatch get_hermes_home() to
return a str (test_slash_worker_accepts_profile_home).

Follow-up to PR #78175 (@JoaoMarcos44).
2026-08-04 11:26:15 +05:30
joaomarcos e18c040c3d fix(cli): back up state.db before clean-markers writes by default
purge_stale_tool_call_markers ran a permanent, irreversible UPDATE with
no backup — inconsistent with repair_state_db_schema's backup-by-default
convention for destructive state.db operations elsewhere in this file.

Take a full snapshot via VACUUM INTO (safe against a live connection,
unlike the raw-copy _backup_db_file used for malformed-schema repair)
before the write, timestamped beside state.db. Skipped when dry_run or
when there's nothing to change. Add --no-backup to `hermes sessions
clean-markers`, mirroring `sessions repair`.

Verified end-to-end: the CLI run against a real temp state.db produces
the backup file before printing the cleared-row count.
2026-08-04 11:26:15 +05:30
joaomarcos e1a2739692 feat(cli): add sessions clean-markers to permanently purge stale tool-call markers (#78148)
The load-on-read repair (_strip_stale_tool_call_markers) fixes affected
sessions in memory on every resume, but never touches the DB — long-lived
sessions re-scan and re-repair the same rows on every load, and the
contaminated bytes stay in state.db (and any backup/cache snapshot of it)
indefinitely.

Add SessionDB.purge_stale_tool_call_markers(dry_run=False): a one-time,
idempotent UPDATE that permanently blanks the content column on affected
rows. Only content is touched — tool_calls and every other column are
left untouched, so provider tool_call/tool_result pairing survives.
dry_run reads through the no-lock read path and never writes.

Wire it up as `hermes sessions clean-markers [--dry-run]`, mirroring the
existing optimize/repair subcommands. Verified end-to-end against a real
temp state.db: dry-run reports the row without writing, the real run
clears it and preserves tool_calls, and a second run is a no-op.
2026-08-04 11:26:15 +05:30
joaomarcos 70d7e4cbdf fix(agent): repair sessions already contaminated with stale tool-call markers (#78148)
The conversation_loop fix (previous commit) stops new "[memory]"-style
bare tool-call markers from being cached/persisted, but sessions written
before that fix can still carry rows where a bare marker was saved as
the assistant's "final response".

Add a load-on-read repair pass in hermes_state.py, mirroring the existing
_strip_background_review_harness defense-in-depth: on session restore,
any assistant row whose content is only a bracketed marker (e.g.
"[memory]", "[skill_manage]") AND that carries tool_calls has its content
blanked before the history re-enters the model's context. The tool call
and its result are left untouched so provider tool_call/tool_result
pairing stays intact. Sessions with no affected rows pass through the
normal path unchanged.
2026-08-04 11:26:15 +05:30
joaomarcos ba9068c8b6 fix(agent): discard bare tool-call marker before fallback/persistence (#78148)
Local tool-call templates can emit a bare bracketed token (e.g. "[memory]")
as assistant content alongside a function call. The loop treated that
protocol scaffolding as visible content: it got cached as the post-tool
fallback, and when the next turn came back empty, the marker was replayed
as the final response and written into the persisted transcript. Later
context compaction preserved that history, letting the model repeat the
marker in subsequent turns.

Detect content that is only a bracketed marker (`[name]`) when the
response also carries tool_calls, and drop it before it can be cached
or persisted. Scoped narrowly: only fires alongside tool_calls, so a
genuine final response of "[memory]" without a tool call is unaffected.
2026-08-04 11:26:15 +05:30
JR Razmus e623432b89 fix: close the Codex app-server session on agent teardown
Salvage of #65260's b7d7cfd0e (ported — the PR's close() predates ~4K
commits of teardown-step churn, so the hunk is re-anchored after step
6b rather than cherry-picked).

agent/codex_runtime.py already drops _codex_session on turn crash and
on retirement, but AIAgent.close() — the hard teardown for /new,
/reset, and session expiry — had no owner for it, so the app-server
child process survived until interpreter exit. Long-lived gateways
accumulate one leaked subprocess per ended Codex session.

The attribute is cleared BEFORE close() so a concurrent reader can't
observe a half-closed session and a raising close() can't strand a
stale reference (tested).

Tests extend the author's original lifecycle test with the
raising-close and no-codex-session cases.
2026-08-04 11:25:18 +05:30
kshitij 9c88625e25 fix(gateway): bound go_dormant ws.close with teardown timeout
Sibling site to the disconnect() fix: go_dormant() still did an
unbounded await self._ws.close(), the exact same pattern bounded in
disconnect(). go_dormant runs on the scale-to-zero suspend path (Fly
autostop), which also has timeout constraints. Apply the same 1s
wait_for treatment using _TEARDOWN_AWAIT_TIMEOUT_S.

Found during review of PR #78027.
2026-08-04 11:17:11 +05:30
Dannyzen 3b0bb3b8bb fix(gateway): keep event loop alive during /compress and Relay drain
Offload manual /compress temporary-agent cleanup through the existing
bounded off-loop helper so a slow agent.close() cannot freeze the
gateway event loop, heartbeat, or platform polling.

Guarantee Relay transport teardown even when the runner cancels
adapter.disconnect() during go_idle: shielded finally, 2s drain-path
idle ACK budget under the 5s outer disconnect budget, and bounded
supervisor/reader/ws.close awaits.

Original commits:
- fix(gateway): offload manual /compress cleanup from the event loop
- fix(gateway): tear down Relay transport even if go_idle is cancelled
- fix(gateway): keep Relay disconnect budgets inside the runner window

By @Dannyzen (PR #78027), salvaged onto current main.
2026-08-04 11:17:11 +05:30
kshitij e4888a9f21 Merge pull request #78226 from kshitijk4poor/chore-razmus-email
chore: add contributor email mapping for johnrazmus
2026-08-04 11:15:55 +05:30
kshitijk4poor f66d625825 chore: add contributor email mapping for johnrazmus 2026-08-04 11:15:36 +05:30
Jordan 60c721ada6 fix(model_metadata): read llama.cpp context from meta.n_ctx + accept sole model 2026-08-04 11:08:32 +05:30
xxxigm 942ff91f21 test(gateway): cover named-custom context pin on session-info banner 2026-08-04 11:00:04 +05:30
xxxigm 3a0a295109 fix(agent): keep context_length pin for named custom providers
Empty model.base_url plus a runtime custom-provider URL was treated as a
route mismatch, so gateway session-reset banners dropped model.context_length
and fell back to the Qwen family default (131K) while /status still showed
the configured 262K pin.
2026-08-04 11:00:04 +05:30
kshitij d218496113 Merge pull request #77924 from kshitijk4poor/chore/author-map-elsnacko
chore: add contributor email mapping for ElSnacko
2026-08-04 10:56:47 +05:30
Jeffrey Quesnelle 70db671fac Merge pull request #76643 from NousResearch/fix/termux-nemo-relay
exempt android installs from nemo-relay
2026-08-04 00:06:56 -04:00
Teknium 91937a6dc3 test: swap context-switch-guard fixture off qwen3.8-max-preview
test_custom_provider_context_avoids_false_shrink_warning used
qwen3.8-max-preview as a slug that deliberately falls through to the
generic 'qwen' 131K catalog match. The new qwen3.8-max
DEFAULT_CONTEXT_LENGTHS entry (1M) now substring-matches the preview
slug too, so the no-custom-providers branch stopped warning. Swap the
fixture to qwen3.9-max-preview, which still hits the generic fallback
— the test's intent (custom_providers threading) is unchanged.
2026-08-03 17:19:49 -07:00
Teknium 3c3ae7428d feat(models): add qwen3.8-max to Nous portal + OpenRouter catalogs, replacing qwen3.7-max
Qwen3.8 Max is live on both OpenRouter and the Nous portal
(qwen/qwen3.8-max, 1M context, 131K max output). Per the
newest-max-replaces-last-max convention, it takes qwen3.7-max's slot
in both curated lists.

- hermes_cli/models.py: OPENROUTER_MODELS + _PROVIDER_MODELS[nous]
  swap qwen/qwen3.7-max -> qwen/qwen3.8-max
- agent/model_metadata.py: DEFAULT_CONTEXT_LENGTHS entry for
  qwen3.8-max at 1,000,000 (verified against OpenRouter live
  metadata and Nous /v1/models 2026-08-03)
- tests/test_empty_model_fallback.py: swap incidental catalog fixture
  to the surviving slug
- website/static/api/model-catalog.json: regenerated

Pricing snapshot skipped: both routes bill via official_models_api
(live pricing), verified with resolve_billing_route. Reasoning
timeout floor already covered by the qwen3 prefix (180s).
2026-08-03 17:19:49 -07:00
Jeffrey Quesnelle dac4bbea09 fix comment about relay workaround 2026-08-03 19:13:22 -04:00
Teknium a991dfc25d docs: document /personality none|default|neutral reset across personality docs
The reset keywords have existed in both CLI and gateway handlers since
June but were undocumented — users couldn't find how to cancel a
personality overlay. Adds a 'Resetting to the default' section to the
personality feature page and mentions the reset in the CLI guide,
slash-command reference (both tables), and messaging command table.
2026-08-03 12:29:49 -07:00
kshitij 0845232d76 fix: prefer explicit anthropic api key
Cherry-picked from PR #58560 by @itsflownium, adapted to current main
(_getenv instead of os.getenv). Moves ANTHROPIC_API_KEY check ahead of
Claude Code credential file and credential_pool auto-discovery so an
explicitly configured key is never shadowed by auto-discovered OAuth.

Fixes #58546
2026-08-04 00:12:45 +05:30
kshitij 827bb0dd16 chore: add contributor email mapping for ElSnacko 2026-08-04 00:10:03 +05:30
Hao Wang aad8f7412c fix(backup): serialize and atomically publish snapshots 2026-08-03 23:48:55 +05:30
kshitij 53cc628045 Merge pull request #77912 from kshitijk4poor/chore-haowang-email
chore: add contributor email mapping for HAOWANG116
2026-08-03 23:42:45 +05:30
kshitijk4poor f40d63d5db chore: add contributor email mapping for HAOWANG116 2026-08-03 23:42:33 +05:30
kshitij d92a28dd34 Merge pull request #77902 from kshitijk4poor/chore-zabih-email
chore: add contributor email mapping for zabih-sudo
2026-08-03 23:32:26 +05:30
kshitijk4poor 164c3d60b2 chore: add contributor email mapping for zabih-sudo 2026-08-03 23:32:12 +05:30