Installing a heavy dependency like vllm crashes in a "stale — restarting" loop:
it restarts mid-install, reuses the cached wheels, then stalls again.
The download/install watchdog (cookbookRunning.js) keyed its stall signal purely
off the downloaded-byte counter ("1.81G/2.49G"). A dependency install spends long
stretches with NO byte counter — pip dependency resolution and the native CUDA
build/compile — so the signal froze and after STALE_PROGRESS_MS the watchdog
declared it stale and auto-restarted it mid-build, looping forever.
Extract the signal into a pure computeProgressSignal (cookbookProgressSignal.js):
keep the byte counter for the download phase (so a genuinely stuck download is
still caught, and an animating-but-frozen ETA frame is NOT mistaken for progress),
and when there's no byte counter fall back to a fingerprint of the output tail so
resolver/compile lines count as progress. Only a truly frozen tail now reads as
stalled.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Two problems made deep research report "No information could be gathered" even
after it had extracted findings, on slow local models (reporter served a 20B
via LM Studio):
- _synthesize hard-capped its LLM call at timeout=60, while extraction uses the
user's extraction_timeout (300s here) and the final report uses 180s. The slow
model needed >60s to synthesize the round's findings, so synthesis timed out
after 3 attempts. Raised it to 180s to match the final-report call.
- When synthesis produced no report (it returns the unchanged, still-empty
report on failure during round 1), the run hit
`if not report: return "No information could be gathered…"` and discarded the
findings it had already gathered. Now it falls back to a compiled report built
from those findings (_fallback_report) so the user keeps the gathered material.
Tests stub the LLM (no live model/DB), pin the synthesis timeout >= 180, that the
fallback surfaces the findings rather than the give-up message, and that a failed
synthesis preserves the previous report.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A CPU-only llama.cpp serve config still emitted --flash-attn on and exported
GGML_CUDA_ENABLE_UNIFIED_MEMORY=1 (independent toggles, often left on by an Auto
profile), so the command mixed "zero GPU layers" with CUDA/flash-attn and failed
to start (issue #1291). Gate both on a _cpuOnly check (ngl == 0). GPU serving is
unchanged — the gate only affects the ngl=0 path.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
deleteMessage() bailed at `if (!sessionId) return;`, so the "x" on an output
shown before a model/API was selected did nothing — there's no session yet
(issue #1428). The session id is only needed for the server-side delete; without
one (or with no persisted message ids) we now fall through to removing the DOM,
so the "x" always at least dismisses the bubble.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
is_vision_model() classified several genuinely multimodal families as text-only
because their names contain neither "vision" nor "vl": Gemma 3 (4b+), Llama 4,
Mistral Small 3.1/3.2, and *-multimodal models (e.g. phi-4-multimodal). For those
the attached image was stripped before the request, so the model never saw it —
a "can't read the image" report (issue #1274), common with Ollama tags like
gemma3:4b.
Add those keywords (plus a generic "multimodal"). Per the file's err-toward-True
policy (#124), a rare text-only tag treated as vision is the safer failure than
dropping a real image. Guard tests confirm the text-only siblings (gemma2, plain
gemma, mistral-small, phi-3) are not over-matched.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
uploadPending() read `data.files` from /api/upload without checking `res.ok`, so
a non-OK response (429 rate limit, 413 too large, …) was swallowed: the pending
files vanished and the chat sent with no attachments and no feedback — part of
why the model "didn't even see them" in #1346.
Check res.ok; on failure show the server's reason via a toast and keep the
pending files so the attach strip re-renders for a retry (matching the existing
"restored on error" comment that the code never actually honored).
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Clicking "New chat" (the brand/welcome navigation path) left the previous
session's unsent draft in the composer (issue #1343). The direct model-picker
path (createDirectChat) already cleared it, but the welcome path did not.
Clear `#message` in chatRenderer.showWelcomeScreen() — the shared entry point
for that state — resetting its autosized height and dispatching an `input` event
so the send button / autosize listeners update. Switching between existing
sessions loads them directly and does not call showWelcomeScreen, so genuine
drafts are not erased.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Stop multi-file uploads from tripping the per-IP concurrency guard
The /api/upload concurrency check summed its condition over `files`, but the
condition didn't reference the loop variable — so it collapsed to len(files)
whenever the IP had any recent upload. A single multi-file batch sent right
after another upload therefore counted itself as N concurrent uploads and hit
max_concurrent_uploads (3), returning 429. The browser swallows the 429 (no
`files` in the body) and sends the chat with no attachments, so the model
"doesn't even see" them (issue #1346).
Count genuine recent upload events instead, via a pure count_recent_uploads()
helper, independent of the current batch's file count. save_upload still
enforces the per-minute sliding-window rate limit per file, so throttling is
preserved.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Also reconcile the per-minute upload rate limit with the batch cap
Follow-up within #1346: even after the concurrency-guard fix, a 6+ file batch
still failed because save_upload() counts each file against upload_rate_limit
(was 5/min) while the composer allows MAX_FILES=10 per batch — the reporter saw
"5 attachments work, 6 fail". Raise the per-minute file cap to 60 so a single
full batch (and a few of them) isn't self-rejected; burst abuse stays bounded by
max_concurrent_uploads. Add a real 6-file regression + a config guard that the
cap exceeds the frontend MAX_FILES.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
odysseus waits on searxng's healthcheck (depends_on: condition: service_healthy),
so when the upstream `searxng:latest` tag is broken the whole app never starts.
The 2026.6.2 image crashes on boot with `KeyError: 'default_doi_resolver'`,
failing the healthcheck and blocking fresh Docker installs (issue #1414).
Pin to the last known-good tag (2026.5.31-7159b8aed) instead of :latest, with a
comment to bump it deliberately after verifying a newer tag boots clean.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The Cookbook download path showed its error toasts with the default ~1.2s
duration, so an actionable message like "tmux is required for Cookbook
background downloads/serves … install it with your OS package manager" vanished
before it could be read (issue #1355). The serve path already uses multi-second
durations.
Give the three "Download failed" toasts a 9s duration to match.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The decorative banner under the title wasn't in a fenced code block, so GitHub's
markdown collapsed its leading whitespace and joined the box-drawing rules,
rendering the ASCII art misaligned instead of monospace-as-typed (issue #1390).
Fence it; the H1 title stays a real heading.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
PRs #738 and #644 committed their before/after review screenshots into the
repo (docs/a11y/focus-*.png, docs/a11y/login-*.png, docs/gallery-314-*.png).
Nothing references these files, so they only showed up as "random images" in
the doc folder (issue #1335). The README hero image and the feature preview
clips are referenced and are left untouched.
Add tests/test_docs_no_orphan_images.py to guard against recurrence: it fails
if any image under docs/ is referenced by no tracked text file.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
After a deep-research job completes, a follow-up like "check it out" / "read
that report" had the agent web_fetch the /api/research/report/{id} HTML render
(and then drift into unrelated searches) instead of reading the saved report
(issue #1363). The report text is already available via the manage_research
tool (action read), and action list returns ids most-recent-first, so the
agent can resolve "the recent report" itself.
Strengthen the manage_research instructions: read a finished report via
action list -> action read; do NOT web_fetch/app_api the report URL (it renders
HTML, not clean text) and do NOT start a fresh web_search just to read an
existing report. Annotate the app_api endpoint list to say the same.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Deep research generated search queries from the LLM's training-cutoff
knowledge, so it emitted stale-year queries like "best Python tutorials
2025" when the actual year is later (issue #1341). The chat/agent path
already grounds the model with "Today is ..." (src/agent_loop.py); the
deep research planning and query-generation prompts had no equivalent.
Add a small current_date_context() helper and prepend it at the plan and
query-generation prompt sites (and the research_handler plan preview path
that reuses RESEARCH_PLAN_PROMPT). System-TZ local, portable strftime.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat: document rrule in the manage_calendar tool schema (#1320)
The create_event handler already persists `rrule` (a single event carrying an
iCalendar RRULE), but the manage_calendar tool schema didn't list it, so the
agent had no documented way to make a recurring event and took a roundabout
path. Add `rrule?` to the create_event field list with examples
(FREQ=WEEKLY;BYDAY=MO etc.) and an explicit note to create ONE event with the
rule rather than looping.
Covered by tests/test_calendar_rrule.py: do_manage_calendar create_event with an
rrule stores one event with that recurrence; without it, the event is single.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: restore SessionLocal via monkeypatch in #1320 rrule test (review)
Per review: the test patched core.database.SessionLocal at module import and
never restored it, which could leak the temp DB into later tests in the same
process. Move the patch into an autouse monkeypatch fixture so it is restored
after each test.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: closed document no longer stays active and leaks into new chats (#1160)
Closing a document tab calls _detachDocFromSession: a doc with content is
PATCHed to session_id="" (unlinked, session_id -> NULL, is_active stays True),
an empty one is DELETEd. But the in-memory active-document pointer
(tool_implementations._active_document_id) was never cleared on either path.
The chat doc-injection last-resort looks up that pointer by id and injects it
when `not cand.session_id or cand.session_id == session`. An unlinked doc has
session_id NULL, so the stale pointer re-surfaced a closed document in later,
unrelated chats — the agent kept reading/suggesting edits to a doc the user
had closed.
Fix: add clear_active_document(doc_id) and call it when a document is unlinked
(PATCH session_id="") or deleted, so the pointer no longer resurrects a closed
document. clear_active_document only clears when the id matches (or no id), so a
different active doc is left untouched.
Covered by tests/test_active_document_clear.py (4 cases).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: add route-level regression for #1160 (detach/delete clears active doc)
Per review: prove the actual API path, not just the helper. Drives
PATCH /api/document/{id} (session_id="") and DELETE /api/document/{id}
through TestClient against a temp SQLite DB under real owner routing, and
asserts get_active_document() is cleared (and untouched when a different
document is closed).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: make #1160 route regression hang-proof and dev-DB-independent
The route test could hang in other environments: it set DATABASE_URL at import
time, which is ignored if core.database was already imported, so it fell back to
the real dev DB and could contend for its locks (maintainer saw it hang, exit
124).
Rebind to a DEDICATED temporary SQLite engine (NullPool) and patch the document
route module's SessionLocal to it via an autouse fixture — so the test never
touches the dev DB and is independent of import order. Runs in ~0.3s.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: drive #1160 route regression without TestClient (fixes local hang)
The route test used Starlette TestClient (middleware app + threadpool), which
hung in the maintainer's environment. Rework it to call the async route handlers
directly — extracted from the router — with a minimal fake request against a
temp-SQLite-patched SessionLocal. Same real coverage (handler + DB + owner
routing), but it completes reliably (~0.3s) with no TestClient/threadpool.
Verified the maintainer's exact batch now passes:
pytest tests/test_document_close_clears_active_route.py \
tests/test_active_document_clear.py \
tests/test_document_tool_owner_scope.py -> 14 passed
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat: CalDAV write-back — push local event create/update/delete to the remote (#800)
CalDAV sync was pull-only (src/caldav_sync.py), so events created, edited, or
deleted in Odysseus on a CalDAV-backed calendar only changed local SQLite and
never reached the server — they silently vanished on the next pull and never
appeared on the user's phone (iCloud, etc.).
This adds the missing write half:
- src/caldav_writeback.py builds the VEVENT, re-discovers the remote calendar by
the same URL-hash the local id was derived from (the remote URL isn't stored),
and PUTs/DELETEs the event by UID via the caldav lib. The pure pieces
(build_event_ical, find_remote_calendar, push_event) take inputs by argument so
they unit-test against a fake client with no network.
- create/update/delete event handlers (routes/calendar_routes.py) call it
best-effort for caldav-sourced calendars only: the local DB stays the source of
truth, a remote failure is logged, never fatal, and local calendars are untouched.
Tests: tests/test_caldav_writeback.py (9, pure logic incl. iCal serialization,
hash discovery, create/update/delete orchestration) and
tests/test_caldav_writeback_route.py (3, route-level: a caldav calendar pushes,
a local one does not, delete pushes a delete). 12 passed.
Note: write-back re-discovers the remote calendar per write (the URL isn't
persisted locally); a follow-up could cache it. Live-iCloud verification needs a
real account — flagging for a maintainer pass.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: drive #800 route regression without TestClient (fixes local hang)
Same fix as the document route test: the CalDAV write-back route regression used
Starlette TestClient (middleware app + threadpool) which hung in the maintainer's
environment. Rework it to call the async create/delete calendar handlers directly
— extracted from the router — with a minimal fake request, temp-SQLite-patched
SessionLocal, and writeback_event stubbed to record calls. Same coverage (a
caldav calendar pushes, a local one does not, delete pushes a delete), completes
in ~0.3s with no TestClient.
Verified the maintainer's exact batch:
pytest tests/test_caldav_writeback.py tests/test_caldav_writeback_route.py -> 12 passed
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
src/search/ranking.py computed result age as `(datetime.now() - dt).days`, where
`dt` is parsed from a UTC-style published date with no timezone. Using local
`datetime.now()` skewed the age by the host's UTC offset (off-by-up-to-a-day near
boundaries), and was a latent crash: once neighbouring code becomes timezone-aware
the naive/aware subtraction raises TypeError (the landmine called out in #1116).
Recency is now measured against naive UTC. The scoring is also lifted out of the
rank_search_results closure into a module-level, time-injectable `recency_score`
so it's unit-testable, and `_utcnow_naive()` avoids `datetime.utcnow()` (removed in
Python 3.14).
Covered by tests/test_search_ranking_recency.py (5 cases); the existing
tests/test_search_ranking.py still passes.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The agent soft-trims input context to `agent_input_token_budget` (default 6000).
The old computation `min(context_length or budget, budget)` made the 6000 default
a hard ceiling for every model, so 128K/1M context models were silently capped at
6000 input tokens — now that num_ctx is sent correctly (#1056), this was the last
barrier to actually using a long context window.
This derives the default budget from the model's discovered context window
(~85%, capped at a generous hard max) while honouring an explicit user setting
exactly (clamped to the window). When the window is unknown it falls back to the
previous value, so behaviour is unchanged for that case.
- src/context_budget.py: pure `compute_input_token_budget()` (unit-testable)
- src/settings.py: `is_setting_overridden()` to tell an explicit user value from
the merged default (load_settings merges DEFAULT_SETTINGS, so equality alone
can't distinguish them)
- src/agent_loop.py: use the helper in the soft-trim path
Covered by tests/test_context_budget.py (6 cases).
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
POST /api/embeddings/endpoint takes a user-supplied URL and immediately
makes an outbound httpx request to it with no validation. The admin gate
added earlier (PR #80) closed the unauthenticated-access part of #132; this
addresses the remaining request: validate the URL before fetching it.
Odysseus is local-first, so pointing the embedding endpoint at a loopback or
LAN server (local vLLM / llama.cpp / Ollama) is a normal setup — a blanket
private-IP block would break the primary use case. So the guard:
- always rejects non-HTTP(S) schemes (file://, gopher://, ftp:// …),
- always rejects the link-local range (169.254.0.0/16, incl. the cloud
instance-metadata 169.254.169.254 exfil vector) plus multicast /
reserved / unspecified, and IPv4-mapped-IPv6 forms of the above,
- keeps loopback/LAN allowed by default, and
- adds EMBEDDING_BLOCK_PRIVATE_IPS=true for full SSRF lockdown on exposed
multi-tenant deployments.
Logic lives in src/url_safety.py (stdlib only, resolver injectable) so it is
unit-testable without real DNS; the route calls it before the health-check
request. Covered by tests/test_url_safety.py (8 cases).
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
/api/health is a liveness ping. This adds /api/ready as a readiness /
integrity self-check that returns 503 unless every critical subsystem is
whole, so an orchestrator (Docker/Compose/k8s) can gate traffic on real
readiness rather than mere process liveness:
- database: opens a connection and runs SELECT 1
- data_dir: confirms the data directory exists and is writable
- local_first: reports whether storage stays on the host (informational;
a remote database is a valid deployment, so it never fails readiness)
The check logic lives in src/readiness.py so it is unit-testable in
isolation; the route is a thin wrapper. Covered by tests/test_readiness.py.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
