Opus pass-2 review of v0.50.251 caught a critical regression in PR
#1375:
The cancel-partial message stored captured tool calls under the
'tool_calls' key. That key is whitelisted by _API_SAFE_MSG_KEYS so
_sanitize_messages_for_api forwarded the entries to the next-turn
LLM call. But the captured entries use the WebUI internal shape
({name, args, done, duration, is_error}) — they don't have the
OpenAI/Anthropic id + function: {name, arguments} envelope. Strict
providers (OpenAI, Anthropic, Z.AI/GLM) would 400 on the malformed
entries. Net effect: the very cancel-then-continue scenario PR
#1375 aimed to improve becomes a hard fail.
Fix:
- Rename the persisted key to '_partial_tool_calls' (underscore-
prefixed private key NOT in _API_SAFE_MSG_KEYS, so sanitize
correctly strips it).
- Update static/messages.js hasMessageToolMetadata check to also
recognize _partial_tool_calls for UI rendering.
- Update test_issue1361_cancel_data_loss.py assertion to check
_partial_tool_calls (and tool_calls as legacy fallback).
Plus 2 NIT fixes from the same Opus review:
NIT 1 (api/profiles.py:153): re.match → re.fullmatch for consistency
with other _PROFILE_ID_RE callers in the codebase. The trailing-
newline footgun ($ matches before final \n in re.match) is now
closed. Without #1373's is_dir() guard, a name like 'valid\n' would
have created a directory named 'valid\n' on Linux. Doesn't escape
<HERMES_HOME>/profiles/ via Path joining, but unintended.
NIT 2 (test_issue798.py): R19j coverage gaps — added trailing-
newline tests, length-boundary tests (64-char valid, 65-char
rejected), single-char minimum, and non-ASCII / Unicode-trick tests.
New regression test (tests/test_pr1375_partial_tool_calls_sanitize.py):
- test_partial_tool_calls_field_not_forwarded_to_llm: pins that
sanitize-for-API strips _partial_tool_calls + reasoning + does
NOT have tool_calls on a partial message
- test_legitimate_tool_calls_are_preserved_for_completed_turns:
pins that real OpenAI-shape tool_calls on completed turns survive
sanitize unchanged
Tests: 3486 passing (3484 → 3486, +2 sanitize tests).
Adds two more contributor PRs to the v0.50.251 batch per user
directive (per-PR review + Opus review for #1373; #1375 was clean
ship-on-sight).
#1375 (@bergeouss, +382 LOC, all CI green) — fixes#1361 paid-token
data loss on Stop/Cancel. Mirrors the existing STREAM_PARTIAL_TEXT
pattern from #893: adds STREAM_REASONING_TEXT and STREAM_LIVE_TOOL_CALLS
shared dicts populated during streaming and read by cancel_stream().
Also fixes the §C reasoning-only-creates-no-message gap where the
strip-thinking-blocks regex returned empty string and the if-guard
skipped the partial append. 8 regression tests covering all 3
sections plus tools+text combinations.
#1373 (@bergeouss, +105 LOC, had CI failures pre-fix) — fixes#1195
new-profile-routes-to-default. The is_dir() guard in
get_hermes_home_for_profile() caused new profiles (no session yet)
to silently route every session back to the default profile until
the directory existed on disk. Removed the guard; profile path is
now returned unconditionally.
Pre-release fix for #1373's CI failures: the change flipped two
behaviors pinned by tests in #798:
- R19c (test_get_hermes_home_for_profile_falls_back_for_missing_profile)
asserted nonexistent → base. Renamed and updated to assert the
new always-return-profile-path behavior.
- R19j (test_get_hermes_home_for_profile_rejects_path_traversal)
asserted that valid-but-nonexistent profile names → base. Updated
to assert profile-scoped path. Also updated docstring: the
_PROFILE_ID_RE regex is now the SOLE defense against path
traversal (previously is_dir() was a defense-in-depth layer);
verified each known-bad shape still returns base.
Tests: 3484 passing (3471 → 3484, +13).
When a user switched profiles and created a new session, the session
was saved to the default profile directory instead of the active
profile directory — because get_hermes_home_for_profile() silently
fell back to _DEFAULT_HERMES_HOME when the profile directory didn't
exist yet on disk.
Root cause: api/profiles.py:156 had `if profile_dir.is_dir(): return
profile_dir; return _DEFAULT_HERMES_HOME`. New profiles (no session
yet, so no dir) routed every session back to default.
Fix: remove the is_dir() guard, return the profile path
unconditionally. The profile directory is created on first use by
the agent/session layer.
5 regression tests in tests/test_issue1195_session_profile_routing.py:
existing-profile, non-existent-profile (the core fix), None, empty-
string, 'default' all return the expected path.
Co-authored-by: bergeouss <bergeouss@users.noreply.github.com>
Three distinct data-loss paths fixed:
§A — Reasoning text was accumulated in a thread-local _reasoning_text
inside _run_agent_streaming. cancel_stream() never saw it because it
went out of scope when the thread was interrupted. Now mirrored to a
new shared dict STREAM_REASONING_TEXT keyed by stream_id, populated
in on_reasoning() and the reasoning branch of on_tool(), read in
cancel_stream().
§B — Live tool calls in thread-local _live_tool_calls were similarly
invisible to cancel_stream(). Now mirrored to STREAM_LIVE_TOOL_CALLS
on tool.started + tool.completed.
§C — Reasoning-only streams produced no partial message because the
thinking-block regex strip returned empty string and the `if _stripped:`
guard skipped the append. Now appends the partial message when EITHER
content text, reasoning trace, OR tool calls exist.
Mirrors the existing STREAM_PARTIAL_TEXT pattern from #893 exactly:
same dict creation in _run_agent_streaming, same _live_config fallback
in cancel_stream, same cleanup in _periodic_checkpoint.
8 regression tests in tests/test_issue1361_cancel_data_loss.py
covering all three sections plus tools+text combinations.
Co-authored-by: bergeouss <bergeouss@users.noreply.github.com>
Opus pre-release findings on #1370 applied:
SHOULD-FIX 1: Tightened parent_session_id exposure to only emit when
the parent's end_reason is in {compression, cli_close}. Without this,
two distinct WebUI sessions sharing a non-continuation parent (e.g.
'user_stop') would get clustered by frontend's _sessionLineageKey
(which falls through to parent_session_id when _lineage_root_id is
missing) and incorrectly collapsed into a single sidebar row.
Updated assertions in:
- tests/test_session_lineage_metadata_api.py::
test_non_compression_state_db_parent_does_not_create_sidebar_lineage
- tests/test_pr1370_lineage_metadata_perf_and_orphan.py::
test_non_compression_parent_does_not_extend_lineage
SHOULD-FIX 2: Chunked the IN-clause to 500 vars to stay under
SQLITE_MAX_VARIABLE_NUMBER. Python 3.9 ships sqlite 3.31 with the
default limit of 999. A power user with 2000+ sessions in the
sidebar would hit OperationalError, the silent except-wrapper would
swallow it, and lineage collapse would never work. Added
test_in_clause_chunked_for_large_session_set with SQL interception
to lock the invariant in source.
PR addition (per user directive — Opus + my review, no second
independent review round needed for combined batch):
#1372 from @NocGeek — fix: persist manual cron run results.
Self-contained 89 LOC fix split out from the held #1352. Mirrors the
scheduled-cron path (cron/scheduler.py:1334-1364) exactly: saves
output, marks job complete, treats empty response as soft failure
with matching error string. 2 behavioral tests using sys.modules
monkeypatch to mock cron.scheduler.run_job. CI not yet attached
because branch is brand-new; ran the new tests + adjacent suites
locally — all pass.
Final test count: 3471 passing, 0 failed.
Also adds 2 more regression tests for the perf-fix invariants:
- test_in_clause_chunked_for_large_session_set
- test_two_children_sharing_non_continuation_parent_not_collapsed
Manual WebUI cron runs previously called cron.scheduler.run_job(job)
and then only cleared the in-memory running flag. That meant output
could be dropped and job metadata like last_run_at / last_status was
not updated after a manual run.
This PR matches the scheduled cron path (cron/scheduler.py:1334-1364)
exactly:
- Save manual-run output via save_job_output
- Mark manual runs complete via mark_job_run
- Treat empty final_response as a soft failure with the same error
string as the scheduled path
- Record manual-run failures in job metadata via mark_job_run(False)
- Keep _run_cron_tracked self-contained for worker-thread execution
Includes 2 behavioral regression tests using monkeypatch.setitem on
sys.modules to mock cron.scheduler.run_job + cron.jobs helpers — the
right test pattern (exercises the real _run_cron_tracked code path).
Split out from #1352 (the larger profile-aware-cron-panel PR that's
on hold) per pre-release-review feedback. Self-contained, doesn't
touch the held PR's profile-filtering scope.
Co-authored-by: NocGeek <NocGeek@users.noreply.github.com>
Bundles:
- #1370 fix: expose session lineage metadata in API (@dso2ng)
Pre-release fixes applied:
1) Perf: replaced full table scan with parameterized WHERE id IN (...)
query. Original code did SELECT id, parent_session_id, end_reason
FROM sessions on every sidebar refresh. Measured 9ms cached scan at
1000 rows in production (up to ~450ms cold-cache); scales linearly.
New approach hits PRIMARY KEY + idx_sessions_parent — 50x faster
at 1000 rows, ~0.2ms regardless of total row count. Depth-bounded
to 20 hops to cap query count under pathological data.
2) Orphan-parent guard: suppress parent_session_id in API output when
the referenced parent row doesn't exist in state.db. The frontend's
#1358 _sessionLineageKey falls through to parent_session_id when
_lineage_root_id is missing — orphan references would create
never-collapsing single-row groups in the sidebar.
3) Regression suite (5 tests in
test_pr1370_lineage_metadata_perf_and_orphan.py):
- Pins the no-full-scan invariant by intercepting all SQL queries
and asserting no SELECT FROM sessions without a WHERE clause
- Pins orphan-parent suppression
- Pins cycle termination via threading.Event watchdog (2s timeout)
- End-to-end test for 4-segment compression chain root resolution
- Pins non-compression end_reason boundary stops walk
PR #1358 added the client-side lineage collapse helper, but
/api/sessions often did not include _lineage_root_id for the WebUI
JSON sessions visible in the sidebar. In that case the helper has no
grouping key and multiple same-title continuation rows remain visible.
This PR:
- Reads parent_session_id and end_reason from state.db.sessions for
the WebUI sidebar's session ids
- Walks the parent chain when end_reason is 'compression' or
'cli_close', producing _lineage_root_id and _compression_segment_count
- Cycle-detects via a 'seen' set
- Preserves projected lineage metadata on imported/gateway session rows
- Allows sidebar collapse to group cross-surface continuation chains
(CLI-close → WebUI continuation) while keeping non-continuation
parent rows flat
Co-authored-by: Dennis Soong <dso2ng@gmail.com>
Pre-release Opus review of v0.50.250 caught a UX regression in PR
#1369: _autosavePreferencesSettings unconditionally cleared
_settingsDirty=false and hid the unsaved-changes bar on every
successful autosave. But password and model are still committed via
the explicit 'Save Settings' button (password for security; model
goes through /api/default-model). Race scenario:
1. User opens System pane, types a new password (sets
_settingsDirty=true; bar appears on close)
2. User switches to Preferences, toggles any checkbox -> autosave
fires -> _settingsDirty=false, bar permanently suppressed
3. User closes panel -> _closeSettingsPanel short-circuits because
!_settingsDirty -> typed password silently discarded
(loadSettingsPanel blanks pwField.value='' on next open)
Same shape with model selector: pick a new default model, then
toggle any preference -> autosave fires -> no warning on close ->
model never persists.
Fix: only clear _settingsDirty and hide settingsUnsavedBar when both
the password field is empty AND the model selector matches its
on-open snapshot.
Pinned by an updated regression test asserting the conditional guard
exists.
9 source-level invariants covering #1369:
- All 13 preference fields appear in _preferencesPayloadFromUi
- Listeners use _schedulePreferencesAutosave, not _markSettingsDirty
- Password field STILL uses _markSettingsDirty (security invariant)
- _autosavePreferencesSettings clears _settingsDirty + hides unsaved bar on success
- Status div present in static/index.html
- Status function uses shared i18n keys from Phase 1
- Retry function falls back gracefully when no stored payload
- Debounce clears prior timer (350ms, matching Phase 1)
- Phase 1 (Appearance) autosave still intact
Phase 2 of #1003: extend the autosave pattern from the Appearance
panel to the Preferences panel so all preference changes are saved
automatically without requiring a manual 'Save Settings' click.
Mirrors the Phase 1 (Appearance) pattern exactly:
- 350ms debounce on field changes (500ms additional debounce on
the bot_name text input — effective ~850ms latency for typing)
- Inline status feedback (saving / saved / failed + retry button)
- Clears dirty flag and hides unsaved-changes bar after successful save
- Password field excluded — still requires explicit save (security)
- Model selector excluded — still requires explicit save
13 fields now autosaving: send_key, language, show_token_usage,
simplified_tool_calling, show_cli_sessions, sync_to_insights,
check_for_updates, sound_enabled, notifications_enabled,
sidebar_density, auto_title_refresh_every, busy_input_mode, bot_name.
i18n keys (settings_autosave_saving/saved/failed/retry) already exist
in all 8 locales from Phase 1.
Co-authored-by: Feco Linhares <feco.linhares@gmail.com>
The timer fires every 60s either way; what changed is whether it
triggers a reconnect. Under steady clarify traffic the reconnect
never happens; on long-idle sessions it still reconnects every
60-120s (the residual idle churn is now a tracked follow-up rather
than the original v0.50.249 unconditional per-minute reconnect).
Tightens the CHANGELOG language to match observed behavior.
Bundles 2 PRs:
- #1366 fix: guard finalizeThinkingCard with session ID check (with pre-release fix)
- #1367 fix(clarify-sse): stale-detector health timer (Opus SHOULD-FIX from v0.50.249)
Pre-release fix on #1366: the contributor's guard depends on
liveAssistantTurn.dataset.sessionId, but no code in the repo sets
that attribute. Without the fix, the guard would always early-return
(undefined !== sid is always true), breaking the streaming UI
completely — every assistant turn's thinking card would stay open
forever. Added per-site stamps at all 3 places that create
liveAssistantTurn in static/ui.js, plus a regression test that fails
any future creation site that forgets the stamp.
Without this check, switching browser tabs while a stream is running
causes finalizeThinkingCard() to operate on the wrong session's
thinking card DOM — the card belongs to the stream that started it,
not the session currently displayed in the tab. The guard ensures
finalize only runs when the live assistant turn's session matches
the current session.
Co-authored-by: Josh <josh@fyul.link>
Follow-up to v0.50.249 / PR #1365 absorbing Opus SHOULD-FIX #2.
Originally reset out of #1365 because the reviewer flagged it as
out-of-scope; brought back per follow-up guidance that
correctness-improving changes should ship even when out of scope.
The clarify SSE health timer at static/messages.js:1715 was an
unconditional 60s force-reconnect, not the 'no event in 60s' detector
its comment claimed. Now actually a stale-detector that tracks
lastEventAt on initial+clarify event arrivals; only reconnects when
the gap exceeds 60s. Under healthy conditions the timer never fires.
Co-authored-by: nesquena-hermes <nesquena-hermes@users.noreply.github.com>
The new _handle_clarify_sse_stream handler in #1355 holds clarify._lock and
then calls clarify.get_pending(sid) under the lock. get_pending also acquires
_lock internally — and clarify._lock is a non-reentrant threading.Lock(),
so the second acquisition deadlocks the SSE handler thread the moment any
client connects to /api/clarify/stream.
Existing tests pass because they only exercise sse_subscribe, sse_unsubscribe,
_clarify_sse_notify, and submit_pending directly — none of them invoke the
route handler. The deadlock would only manifest when a real EventSource opens
the connection.
Reproduced with a tiny harness that holds _lock and calls get_pending: the
worker thread is still blocked after a 2s timeout. With the fix, both empty
and populated queue cases complete in <1ms.
Fix: read clarify._gateway_queues / clarify._pending inline under the same
_lock acquisition, mirroring the approval SSE handler's pattern at
api/routes.py:2785-2793. No recursive lock; head-of-queue snapshot is
identical to what get_pending would have returned.
Added tests/test_pr1355_sse_handler_no_deadlock.py with three tests:
- behavioural: empty queue snapshot completes within 2s
- behavioural: populated queue snapshot returns the head entry
- source-level invariant: routes.py must not call get_clarify_pending()
inside `with _clarify_lock:` block (locks the regression in)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replaces the 1.5s HTTP polling loop for clarify with a Server-Sent Events endpoint at /api/clarify/stream that pushes clarify events to the browser instantly. Mirrors the approval SSE pattern from v0.50.248 (#1350) including all the correctness lessons:
- Atomic subscribe + initial snapshot under clarify._lock
- _clarify_sse_notify called inside _lock for ordering guarantees (no notify-out-of-order race)
- Notify passes head=q[0].data (head-fidelity, not the just-appended entry)
- resolve_clarify also calls notify after pop so trailing clarifies surface immediately (no stuck-clarify bug)
- Empty-state notify with None,0 after pop-empty so frontend hides the card
- 30s keepalive comments, _CLIENT_DISCONNECT_ERRORS handling
- Bounded queue (maxsize=16) with silent drop on full
- Frontend: EventSource with automatic 3s HTTP polling fallback on onerror
Co-authored-by: fxd-jason <wujiachen7@gmail.com>
Adds a 'storage' event listener for the hermes-webui-session localStorage key. Idle tabs auto-load the new active session and re-render the sidebar; busy tabs show a toast and do not interrupt the active turn.
Co-authored-by: Dennis Soong <dso2ng@gmail.com>
When a session's compression lineage spans multiple segments (linked via _lineage_root_id from api/agent_sessions.py), the sidebar previously rendered each segment as a separate top-level row. Adds _collapseSessionLineageForSidebar() that groups by lineage root and keeps only the most recently active tip per group, with a _lineage_collapsed_count marker for future UI affordances.
Co-authored-by: Dennis Soong <dso2ng@gmail.com>
Session.load_metadata_only().compact() was dropping is_cli_session, source_tag, session_source, and source_label, so imported CLI/gateway sessions lost their provenance in sidebar/API payloads. Adds these to METADATA_FIELDS and Session.compact().
Co-authored-by: Dennis Soong <dso2ng@gmail.com>
- api/streaming.py SSE payload now falls back to agent.model_metadata.get_model_context_length when compressor doesn't supply context_length (mirrors the session-save fallback shipped in v0.50.247).
- api/streaming.py also falls back to s.last_prompt_tokens to avoid using the cumulative input_tokens counter.
- static/ui.js tracks rawPct separately from pct and shows '(context exceeded)' tooltip when rawPct > 100 instead of misleading '100% used (0% left)'.
- static/messages.js clears 'Uploading...' composer status after upload completes.
Co-authored-by: nesquena-hermes <nesquena-hermes@users.noreply.github.com>
Pre-release Opus review caught three correctness bugs in the original
PR #1350 SSE wiring beyond the snapshot/subscribe race:
A) **Notify-ordering race (MUST-FIX A):** _approval_sse_notify took _lock
only for the subscriber-list snapshot, then released it before
put_nowait. With two parallel submit_pending calls, T2's notify
could fire before T1's, leaving the UI showing pending_count=1 while
the server actually had 2 queued.
C) **Trailing approval lost (MUST-FIX C):** _handle_approval_respond
never called _approval_sse_notify after popping. With parallel
tool-call approvals (#527), a second approval queued behind the one
being responded to was invisible until the next event ever fired —
in practice, the agent thread parked on it would appear hung.
D) **Payload showed tail not head (MUST-FIX D):** payload built from
the just-appended entry instead of queue[0]. /api/approval/pending
returns the head; SSE returned the tail. Diverging contracts.
Fix:
- Split into _approval_sse_notify_locked (caller holds _lock, no
internal locking) and _approval_sse_notify (convenience wrapper).
- submit_pending: call _locked variant inside the queue-mutation lock,
passing queue_list[0] as head.
- _handle_approval_respond: call _locked variant inside the pop lock,
passing the new head (or None/0 if queue is empty).
- Restore fallback poll to 1500ms (was bumped to 3000ms; degraded-mode
parity with v0.50.247 is more important than save 1.5s of polling).
New regression tests in tests/test_pr1350_sse_notify_correctness.py:
- test_second_submit_pending_sends_head_not_tail (D)
- test_respond_to_first_pushes_second_as_new_head (C)
- test_respond_to_only_pending_pushes_empty_state (C edge)
- test_pending_count_is_monotonic_under_contention (A)
Updated test_approval_sse.py to pin the new contract:
- _approval_sse_notify_locked(session_key, head, total)
- 1500ms fallback interval
Total: 3411 tests passing.
Co-authored-by: jasonjcwu <jasonjcwu@users.noreply.github.com>
Bundles:
- #1349 fix(ui): show context indicator percentage without explicit context_length
- #1350 feat(approval): SSE long-connection for real-time approval notifications
Pre-release fixes applied:
- Inline subscribe + snapshot under a single _lock acquisition in
_handle_approval_sse_stream() to close the snapshot/subscribe race
flagged in pre-release review. A submit_pending() arriving between
the snapshot read and subscribe call would have been lost (appended
to _pending after our snapshot AND notified to subscribers before we
joined). Now atomic.
- Added tests/test_pr1350_sse_atomic_subscribe.py (4 source-level
invariants covering the atomic-lock-block guarantee).
Co-authored-by: jasonjcwu <jasonjcwu@users.noreply.github.com>
Replaces the 1.5s HTTP polling loop with a Server-Sent Events endpoint
at /api/approval/stream that pushes approval events to the browser
instantly. The backend uses a thread-safe subscriber registry
(_approval_sse_subscribers) with bounded queues to prevent memory
leaks from slow clients. Frontend uses EventSource with automatic
fallback to 3s HTTP polling on SSE error.
- Backend: subscribe/unsubscribe/notify lifecycle in api/routes.py
- New route: GET /api/approval/stream?session_id=
- submit_pending() now calls _approval_sse_notify() after queue append
- Frontend: EventSource with onerror -> _startApprovalFallbackPoll()
- 30s keepalive comments, _CLIENT_DISCONNECT_ERRORS handling
- 42 new tests (static analysis + unit + concurrency)
Co-authored-by: jasonjcwu <jasonjcwu@users.noreply.github.com>
Frontend companion to backend fix in v0.50.246 (#1341 + a5c10d5).
Default context window to 128K when usage.context_length is falsy.
Show '(est. 128K)' label when using the default.
Use input_tokens as fallback for last_prompt_tokens.
Co-authored-by: jasonjcwu <jasonjcwu@users.noreply.github.com>
* fix(streaming): fallback to model_metadata for context_length when compressor missing (#1318 follow-up)
PR #1318 (shipped in v0.50.246 via PR #1341 + commit a5c10d5) persisted
context_length on the session so the context-ring indicator survives
page reloads. But the writer only fired when agent.context_compressor
was present and reported a non-zero value. Fresh agents, interrupted
streams, or compressors without the attribute would still leave
s.context_length=0 — and the indicator would still show 0% on reload.
This follow-up adds a fallback that calls
agent.model_metadata.get_model_context_length(model, base_url) when the
compressor didn't populate the value. The function returns a sensible
static context window for any known model (with a 256K default for
unknown models). Wrapped in a broad try/except because older
hermes-agent builds may not expose the helper.
Sourced from PR #1344 (@jasonjcwu) — extracted into this focused
follow-up after #1344 was closed as superseded by #1341.
Adds 6 structural tests covering: import + call presence, falsy-gate,
agent.model/base_url passing, exception swallowing, save() ordering,
result assignment.
Closes the data-flow gap in #1318 for the compressor-missing case.
* test: relax pr1341 block-size assertion to accommodate the new fallback
---------
Co-authored-by: nesquena-hermes <nesquena-hermes@users.noreply.github.com>
Pre-release Opus review on PR #1345 (Finding #3) flagged that
get_cli_sessions() was calling ensure_cron_project() once per cron
session in the loop — N lock acquires + N disk reads of projects.json
for N cron sessions per sidebar refresh.
Hoist a per-scan lazy memoizer (_cron_pid()) so we pay the resolution
cost at most once per get_cli_sessions() call. The memoizer is local
to the function (closure) so it's naturally scoped to a single scan
and doesn't leak across calls.
Could also have made ensure_cron_project() module-memoized, but that
would need invalidation on project deletion — the per-scan cache is
simpler and correct without coordination.
Single PR — #1345 (@bergeouss): auto-assign cron job sessions to a
dedicated 'Cron Jobs' project (closes#1079).
143 LOC, 5 new tests, locale parity across 8 languages, CI green
on all Python versions before merge.
Pre-release Opus + nesquena review on v0.50.246 caught that PR #1341
added the data-structure scaffolding (Session.__init__ accepts the 3
fields, save() persists them, compact() exposes them, GET /api/session
returns them) but did NOT add the writer that actually populates them.
Without a writer, the user-visible bug (context-ring shows 0% after
page reload) was NOT fixed by #1341 alone — the fields stayed None
forever because nothing wrote to s.context_length anywhere.
Adds the writer at api/streaming.py:2188 (post-merge per-turn save block,
before s.save()) so the values from agent.context_compressor land on
disk and survive page reloads.
Also moves the SSE usage payload comment to clarify that the live SSE
payload and the session-level persistence are now distinct paths
(payload below, persistence above).
Adds tests/test_pr1341_context_window_persistence.py — 6 structural +
round-trip tests covering Session __init__/save/compact, the routes
response, and the streaming.py writer placement.
Closes#1318 (the actual user-visible bug, not just the scaffolding).
Pre-release Opus review on v0.50.246 caught a SHOULD-FIX in PR #1338's
cancel_stream synthesis: the symmetric substring guard
(_pending_user in _last_content OR _last_content in _pending_user) was too
loose. Common confirmation replies ("ok", "yes", "go") in the prior turn
would match longer follow-up prompts ("ok please continue"), the synthesis
would be skipped, and the user's typed text would be lost — exactly the
data-loss bug #1298 was supposed to fix.
The fix: gate the substring check on a timestamp comparison. Only treat
the latest user turn as 'already merged by the streaming thread' if its
timestamp is at or after pending_started_at. Earlier turns whose content
happens to be a substring of the pending must not short-circuit synthesis.
Also drops the symmetric (_last_content in _pending_user) branch — that
direction was the false-positive vector. Keeps the equality and prefix
match (workspace-prefix tolerance from the streaming thread).
Adds tests/test_issue1298_cancel_and_activity.py::
test_cancel_synthesizes_when_prior_turn_content_is_substring_of_pending —
regression for the exact 'ok' → 'ok please continue' scenario.
Combines:
- 4 contributor PRs (#1335 user fenced code, #1337 mermaid+cache-bust,
#1339 fallback_providers list, #1341 context_length persistence)
- Self-built #1338 (cancel data-loss + activity panel) — already
independently APPROVED by nesquena before absorption
- CONTRIBUTORS.md and markdown refresh from #1340
See CHANGELOG.md for the full list with author credit.
- tests/test_issue765_streaming_persistence.py — replace timing-based polling
in test_checkpoint_fires_on_activity_counter_increment with deterministic
threading.Event-driven sync. The old version used time.sleep(0.15)+(0.25)+(0.25)
with a 0.1s polling thread, which under CI scheduling jitter could miss the
second increment and complete with only 1 save instead of 2. Now waits up
to 3.0s for save_count to advance to the target after each increment.
Locally observed flake on Python 3.11 in CI run 25175204451.
- tests/test_pr1339_fallback_providers_list.py — new structural test that
asserts streaming.py handles both legacy fallback_model (single dict) and
new fallback_providers (list form) without calling .get() on a list. Three
assertions: both keys consulted, list-form has explicit isinstance check,
_fallback_resolved defaults to None.
From PR #1338. Already independently APPROVED by nesquena before being absorbed into v0.50.246.
CHANGELOG entries from this PR were dropped during squash (the v0.50.245 section is already
shipped); they will be re-added under [v0.50.246] in the release commit.
Co-authored-by: nesquena-hermes <nesquena-hermes@users.noreply.github.com>
