Adapted from PR #26014's test file to the canonical seam
(tests/run_agent/test_anthropic_prompt_cache_policy.py _make_agent
helper) instead of a new top-level file with sys.path manipulation.
Covers: kimi-k2.6 + moonshot-v1 on OpenRouter (envelope layout),
kimi via Nous Portal, and the non-OpenRouter negative case.
Kimi/Moonshot models on OpenRouter honour the same envelope-layout
cache_control markers as Claude on OpenRouter, but the policy fell
through to (False, False) — serving ~1% cache hits on 64K-token prompts
and re-billing the full prompt every turn. Observed within-turn
progression with cache enabled: 1% -> 67% -> 84% -> 97%.
(cherry picked from commit 3b857a35e, agent/agent_runtime_helpers.py hunk only;
the original PR #26014 branch also carried unrelated .dev-workflow artifacts
which are intentionally not included)
Structured review (2a/2b/2c) findings, all fixed:
- MAJOR: detect_local_server_type memo was process-lifetime with no
invalidation, permanently pinning a URL's server type. Now a bounded
1h TTL ((type, monotonic) tuples) so a backend swap on the same port
is re-detected. Test covers ollama->lm-studio swap after expiry.
- MAJOR: legacy disk-row compat was one-way. get_cached_context_length
and _invalidate_cached_context_length now consult the same key-shape
set {canonical, literal, canonical+slash} in both directions, so an
old slashed row is found (and cleared) when the runtime passes the
normalized URL. Tests pin both migration directions.
- MINOR: _localhost_to_ipv4 did whole-string replacement, which could
corrupt a proxy URL embedding http://localhost in its query. Now a
scheme-anchored host-only regex; localhost.example.com and embedded
substrings pass through. Tests added.
- MINOR: _invalidate_cached_context_length now also drops the
in-memory TTL probe rows for the pair, so a resolution inside the
TTL window can't re-persist the value just declared stale.
- Test gaps closed: detect-type cache hit + TTL-expiry re-detection,
ollama-show TTL expiry re-probe, reverse legacy-row lookups.
- Attribution gate: added zhchl@hermes-agent.local -> 8294 (PR #50572
author) to AUTHOR_MAP; the strict CI grep needs bare non-plus emails
literal in release.py.
Gates: ruff clean; targeted suites 202 passed / 0 failed; full
tests/agent 5426 passed with 17 failures identical on clean
upstream/main (pre-existing env-dependent anthropic/bedrock/credpool
tests); mypy delta vs base: 0 new errors; live smoke 6/6 PASS.
#37595 fixed the Windows dual-stack IPv6 timeout only inside
detect_local_server_type. The same 2s-per-probe penalty existed at every
other helper that builds a probe URL from base_url. Extract the rewrite
into _localhost_to_ipv4() and apply it at:
- query_ollama_num_ctx
- query_ollama_supports_vision
- _query_ollama_api_show (server_url derivation)
- _query_local_context_length (server root + LM Studio native URL)
Tests cover the helper's URL forms, non-localhost passthrough, and that
the ollama probes actually POST to 127.0.0.1.
Follow-up hunks completing the probe-cache cluster:
1. _query_ollama_api_show now goes through the existing
_LOCAL_CTX_PROBE_CACHE (30s TTL, positive-only, namespaced key) —
it was the one remaining per-resolution POST not covered by the
#56431-era wrapper. Failures are never memoized so a server that
comes up mid-startup is re-probed. Idea credit: #42081 (@Morad37),
reworked to comply with the positive-only rule.
2. Persistent context-cache keys are normalized through
_context_cache_key (trailing-slash strip) so http://host/v1 and
http://host/v1/ share one entry; reads and invalidation honor
legacy un-normalized rows. Idea credit: #37905 (@stevenau21).
Tests: TTL hit collapses to one POST, failure-not-memoized
(mutation-verified: unconditional caching makes it fail), namespace
no-collision vs the sibling probe, slash-variant dedup, legacy-row
read, dual-shape invalidation.
_cli's show_banner() calls _resolve_active_context_length() at every
startup. For non-OpenRouter providers (e.g. minimax-cn, kimi-coding,
custom endpoints) the resolver falls through to step 6 (OpenRouter
live /models fetch), which blocks ~2-3s per CLI launch and adds up
to 7+ minutes when openrouter.ai is unreachable through a proxy that
403s CONNECT (#46620).
Two complementary changes:
1. model_tools.py: read model.context_length from config.yaml and pass
it as config_context_length to get_model_context_length. The
step-0 config override short-circuits the entire resolution chain
including the OpenRouter fetch. No network call is made when the
user has set the value explicitly.
2. agent/model_metadata.py: replace flat timeout=10 with (5, 10)
tuple at all five sites (fetch_model_metadata + four endpoint
probes). urllib3 can otherwise block for 10s per retry stage
through proxies that 403 CONNECT. The tuple bounds connect at 5s
while still allowing slow reads.
Complements the in-flight PR #46685 (which adds HERMES_DISABLE_MODEL_METADATA
env var + same timeout tuple change for fetch_model_metadata). This PR
extends the timeout fix to the other four endpoint probes and adds the
config-override path that addresses the slow-but-reachable scenario
where env-var disable is too heavy-handed.
Refs #46620, PR #46685.
(cherry picked from commit e7faa34199)
Remaining hunk of the PR-branch fixup commit: the LM Studio first-probe
assertion now expects the IPv4-resolved URL (the code half — applying
the rewrite to `normalized` before deriving lmstudio_url — was folded
into the previous cherry-pick's conflict resolution).
(cherry picked from commit 7d324b0e47)
On Windows, `localhost` resolves to both ::1 (IPv6) and 127.0.0.1 (IPv4).
httpx tries IPv6 first, hanging 2 sec per probe when the server binds IPv4
only. detect_local_server_type() is called 3+ times during init, each with
a new httpx.Client, compounding to ~14s of dead time.
Replace localhost with 127.0.0.1 inside the function before connecting.
The function is only called for local endpoints (callers guard with
is_local_endpoint()), so IPv6 loopback adds no diagnostic value.
Measured: 19.9s → 4.0s on Windows with a local proxy on 127.0.0.1:8317.
(cherry picked from commit a075d3194b)
Every 5 minutes fetch_endpoint_model_metadata() re-runs the full server-type
waterfall (LM Studio -> Ollama -> llama.cpp -> vLLM), spraying 404s at
endpoints the server never exposes (e.g. /api/v1/models and /api/tags on a
vllm backend).
Add _endpoint_probe_path_cache (base_url -> server type) so the first
successful probe's result is reused for the lifetime of the process.
Subsequent refreshes skip straight to the known-good path.
Fixes#29971.
(cherry picked from commit f3d7a8960a)
Follow-up hardening on the salvaged NS-591 mobile-chat reconnect fix, from
review findings:
- Guard the page-resume reconnect against the async socket-open window:
a connectInFlightRef is set synchronously before the ticket-URL await so
a visibilitychange/focus fired during that gap (wsRef still null) can't
spawn a redundant second socket. Threaded through
shouldReconnectPtyOnPageResume as connectInFlight.
- Recover a socket wedged in WS_CONNECTING (half-open mobile socket after a
radio handoff — the NS-591 scenario) via a PTY_CONNECTING_TIMEOUT_MS
force-close so onclose routes into scheduleReconnect. Cleared on
open/close/effect-cleanup.
- Avoid collapsing legitimate single-letter reduplication ("a a") in the
mobile duplicate-final-word heuristic (>=2-char guard).
- Extract the 350ms replacement window and 1000ms resume throttle to named
exported consts; drop the dead WS_CONNECTING term from the resume
predicate's final expression.
Adds tests for the in-flight guard and the single-letter reduplication case.
Two review fixes on the mobile input normalization path:
- updatePtyInputLine appended the printable payload of escape sequences
(the '[D' of a left-arrow) to the tracked line, and after any cursor
movement the flat tracker no longer matched the visual line — the
DELETE-repeat replacement could then be computed against a stale
snapshot. Any chunk containing ESC now resets the tracker, disarming
replacement normalization until a cleanly-tracked line starts.
- Move the SGR mouse-report filter ahead of the blocked-input check so
scrolling a disconnected terminal doesn't print the reconnect notice.
Follow-up to HexLab98's fix. The sync-before-regenerate invariant was
enforced by convention across 6 callsites (~3 idempotent unit-file reads
per command). Consolidate it into the one function every compare/regenerate
path funnels through — systemd_unit_is_current — and drop the now-redundant
callsite pre-syncs in refresh_systemd_unit_if_needed / systemd_start /
systemd_restart / systemd_status.
Kept the systemd_install pre-sync: the --force path bypasses the
is_current gate and calls generate_systemd_unit() directly, so it needs
its own sync to avoid baking /root/.hermes under sudo.
Reworked the two callsite-ordering tests into a chokepoint-invariant guard
(test_is_current_syncs_before_reading_unit) + a delegation test proving
start/restart no longer pre-sync. Both fail if the chokepoint sync is
removed; the pre-existing behavior test still passes.
Under sudo, start/restart refreshed the unit from /root/.hermes before
adopting the unit's pinned home, so TimeoutStopSec and env drifted and
status stayed stuck on "service definition is outdated".
Follow-up to the salvaged str(tools) fix. The id()-keyed
_TOOLS_TOKENS_CACHE had no eviction, so a long-lived gateway/desktop
backend could accumulate an unbounded number of stale entries as it
builds transient tool lists. Cap it at 256 with oldest-first eviction
(insertion-ordered dict) and add a regression test asserting the cache
never exceeds the cap.
Estimate tool-schema size without repeatedly stringifying full tool lists, and cache the result per tool snapshot to reduce GIL-heavy work during preflight and compaction.
PR #61281 removed the client-side X-Hermes-Session-Token requirement from the
dashboard OAuth mutation calls so cookie-authenticated hosted/mobile sessions
can start provider logins. That change is safe only because the server still
gates those endpoints (gated_auth_middleware cookie check + _require_token).
The PR's api.test.ts suite mocks fetch and only asserts client behavior, so a
re-break of the gated-mode cookie gate would pass CI unnoticed.
Add gated-mode TestClient tests asserting POST /api/env/reveal and the OAuth
mutation endpoints (disconnect/start/submit/cancel) return 401 with no session
cookie. Mutation-verified: neutering both the middleware gate and _require_token
flips all five to 200.
The new oauth.copyCode/copyFailed keys existed only in en.ts, with
optional types and English literal fallbacks in OAuthLoginModal — so
non-English users got English strings on the device-code copy button.
Backfill translations in all 16 non-English locales, refresh the
updated oauth.description/notConnected copy (dashboard Login flow
mention) to match en.ts, make the two keys required in the
Translations interface, and drop the English fallbacks from the modal.
Verified with web tsc --noEmit (required keys enforce locale
completeness), vitest, and a web build.
Electron 40 ships Node 24.15, where tsx's ESM load hook returns null and
crashes with ERR_INVALID_RETURN_PROPERTY_VALUE. Bundle main+preload via
esbuild for `npm run dev` and always load the JS preload from dist/.
grok-4.5 is GA and is now the single curated Grok entry on the
aggregator lists. grok-4.3 is NOT retired upstream — it remains fully
usable by typing the model name (validated against the live catalogs);
this only removes it from the short curated picker snapshots. The
xAI-direct list is models.dev-cache-driven and unaffected.
The model often emits a follow-up batch of tool calls as its own
assistant message with no prose or reasoning. On screen those rows look
like one continuous run, but assistant-ui only groups tool calls within a
single message, so the auto-scrolling tool window never triggered on them
(e.g. two batches of two searches read as 2 + 2, never reaching the
threshold).
Coalesce each settled tool-only assistant message into the preceding
assistant message in the render pipeline so its calls join that message's
tool group. Render-only (never touches the $messages store) and
settle-only (pending messages are skipped) so a live turn is never
merged/un-merged mid-stream; merged results are cached by source identity
so a stable turn yields stable objects with no re-render churn.
- Return the boundary snapshot from
_launch_session_boundary_memory_flush as a local value instead of
staging it on self._session_boundary_snapshot. The instance-attr
handoff could leak (no memory manager configured) or mis-fire a
stale snapshot on a later /new if an exception hit between staging
and consumption. A local variable eliminates the class; the helper
also returns None when no memory manager is configured so
new_session takes the inline-switch path.
- Drop the now-dead session_id kwarg from commit_memory_session:
after the redesign no production caller passes it (gateway, TUI,
compression all use the default), and speculative params are
rejected per AGENTS.md. The explicit-old-session need is served by
cli.py's direct engine call + commit_session_boundary_async.
- Drop the dead providers snapshot in commit_session_boundary_async
(only the emptiness check used it).
- Tests updated accordingly (dead-kwarg test removed, snapshot
assertion now covered by return-value contract).
Phase-2 gates: 2a tests/cli 1048 passed + 6 memory files 137 passed;
2b programmatic live smoke 0.38ms non-blocking caller, end→switch→sync
ordering verified; 2c structured 4-angle review — no Criticals, these
warnings fixed.
Deep review of the cherry-picked #16454 found the ad-hoc flush thread
raced new_session()'s inline on_session_switch(reset=True): memory
providers key off internal _session_id state (MemoryManager.on_session_end
takes no session id), so a late off-thread extraction ran against
post-rotation bindings — misattributing the old transcript to the new
session id, double-ingesting the old turn buffer (supermemory), or
double-committing (openviking already async-finalizes in
on_session_switch).
Redesign: new MemoryManager.commit_session_boundary_async queues
on_session_end + on_session_switch as ONE task on the manager's existing
single-worker background executor (the same worker sync_all already
uses). This preserves the strict end→switch ordering providers depend on,
serializes against per-turn syncs FIFO, keeps /new non-blocking, and
degrades to inline (pre-#16454 behavior) when the executor is
unavailable. No ad-hoc threads; no per-provider changes needed.
The context-engine on_session_end half stays synchronous in
_launch_session_boundary_memory_flush (cheap, must land before
reset_session_state rebinds the engine).
Exit durability: _run_cleanup calls the manager's existing
flush_pending(timeout=10) barrier before shutdown, so '/new then quit'
doesn't drop the queued extraction (shutdown_all's own drain is ~5s and
cancels queued tasks). Bounded well inside the 30s exit watchdog.
Tests: ordering invariant with slow (LLM-like) extraction, FIFO
serialization vs sync_all, switch-fires-even-if-end-raises, no-provider
no-op, CLI snapshot handoff + inline-switch fallback, sync engine
boundary, cleanup flush_pending.
Fixes#3356
Build the skills snapshot manifest in one directory walk, avoid importing gateway session context during CLI prompt startup, and reuse direct platform-list matching for snapshot entries.
(cherry picked from commit 1a64c2ed04)
Follow-ups on the #60987 salvage (review pass):
- _refresh_fallback_model: keep last known-good chain on transient
config.yaml read/parse failure (user mid-edit, torn write) — only a
successful read that lacks the key clears the chain. Previously a
refresh error wiped a cached agent's working fallback for the turn.
- Move the cached-agent refresh+apply OUTSIDE the agent-cache lock:
config.yaml read is disk I/O and the idle-sweep watcher contends on
that lock (same reasoning as #52197). Per-session turn serialization
keeps the post-lock apply safe.
- _apply_fallback_chain_to_agent: clear _unavailable_fallback_keys when
chain content actually changes, so an entry re-configured mid-uptime
(e.g. credentials added) is retried instead of staying suppressed for
the cached agent's lifetime; no-op refreshes keep the memo.
- Tests: cwd-independent source pin (Path(__file__) anchor), pin the
reuse-path apply call, + regression tests for last-known-good, memo
clear-on-change, memo keep-on-unchanged (mutation-verified).
Pin reload + cached-agent apply helpers for #60955 so a mid-uptime
fallback chain change reaches messaging sessions without a restart.
(cherry picked from commit fafb341035)
Gateway froze the fallback chain at process start while cron reloads it
per job, so a chain configured after hermes gateway was running never
reached messaging sessions. Refresh from disk on agent create and when
reusing a cached agent.
Fixes#60955.
(cherry picked from commit b64e7155b2)
When an API error carries an httpx.Response whose body was consumed via
iter_bytes() during streaming error handling (e.g. GeminiAPIError from
agent/gemini_native_adapter.py), accessing .text raises
httpx.ResponseNotRead. The secondary exception replaced the real,
already-computed provider error (429 free-tier quota guidance) with the
generic 'Attempted to access streaming response content' message on
every turn.
Guard the .text access so it degrades to an empty snippet and falls
through to the str(error) fallback, which carries the full original
message. Mirrors the existing guards in
agent/error_classifier.py::_extract_error_body() and
agent/gemini_native_adapter.py::gemini_http_error().
Fixes#59769
Salvaged from PR #59868 (guard + regression test); the unrelated
desktop Ctrl-C fix bundled in that PR was intentionally dropped and is
triaged separately.
Rebase reconciliation with #60884: _count_status_active_sessions (from
#58238) now passes compact_rows=True (this branch's #47437 projection),
so the fake asserts both.
tui_gateway session.list/most_recent now pass compact_rows=True
(#47437 salvage); the keyword-only fake signatures in
test_tui_gateway_server.py rejected the new kwarg and CI slice 6/8
failed with TypeError. Other list_sessions_rich fakes use **kwargs and
are unaffected.
Review finding: get_messages(offset=N) with no limit dropped the OFFSET
entirely. SQLite requires a LIMIT clause for OFFSET, so emit LIMIT -1
(unbounded) when only offset is given. Regression test added.
- derive the compact_rows projection from SCHEMA_SQL (parse once, cache)
instead of a hardcoded column list: the original #47437 list was cut
against a June schema and silently dropped session_key/chat_id/chat_type/
thread_id/display_name/origin_json/expiry_finalized/git_branch/
git_repo_root/compression_failure_* — including desktop sidebar fields.
Schema-derived means declaratively reconciled new columns are included
automatically; only system_prompt is excluded.
- guard test pinning the schema<->projection contract (mutation-verified:
dropping a column from the projection fails it)
- wire compact_rows=(not full) into /api/sessions and /api/profiles/sessions
so the SQL projection pairs with the API-level field strip (?full=1 still
returns complete rows end-to-end)
- pass compact_rows at the remaining hot list callers: /api/status active
count, _session_latest_descendant fallback, /api/sessions/stats by-source
- thread compact_rows through the compression-tip projection
(_get_session_rich_row) so projected tips can't reintroduce the blob
- add pagination tests for get_messages (#60347 shipped none): paging order,
offset-past-end, active-flag interaction; add tip-projection compact test
- AUTHOR_MAP entries for mahdiwafy + CodeForgeNet (plain emails)
list_sessions_rich and _get_session_rich_row previously used SELECT s.*,
pulling the system_prompt TEXT blob on every row even for dashboard and
picker callers that never display it. On large databases this blob routinely
runs to tens of kilobytes per session, causing unnecessary B-tree I/O.
Add compact_rows=False param to both functions. When True, an explicit
column list omitting system_prompt is substituted for s.* in both the
simple and the recursive-CTE (order_by_last_active) query paths.
Default is False so all existing callers are unaffected.
Update dashboard and session-picker callers in web_server.py and
tui_gateway/server.py to pass compact_rows=True.
Add seven regression tests covering: omission of system_prompt, presence
of all metadata fields, both query paths, _get_session_rich_row, and
backward-compat default.
(cherry picked from commit c470cbd304)
The session messages endpoint returned ALL messages in a single
response with no limit/offset. Sessions with 500+ messages produced
1.2-1.6 MB JSON payloads, causing GIL starvation and WebSocket
timeouts on the Desktop client (#60155).
Add optional limit/offset query params to both the API endpoint and
SessionDB.get_messages(). Limit clamped to 500 max per page. Response
now includes a pagination object with limit/offset/returned count.
Backward compatible: callers that omit limit get the old behavior
(all messages).
Closes#60155
(cherry picked from commit d58396b154)
get_status now probes via get_running_pid_cached() (#53511 salvage);
these tests were added on main after that PR was cut and still patched
web_server.get_running_pid, so their fakes were bypassed and CI slice
5/8 failed. Patch the name the handler actually calls.
