Gallery search built a single `%{search}%` LIKE, so multi-word queries only matched the exact adjacent phrase ("red car" missed "a car that is red") and literal % / _ acted as SQL wildcards. Split on whitespace and require each token to match (prompt OR tags OR ai_tags), escaping LIKE wildcards per token; same escaping for the tag filter. Promote _escape_like to public escape_like_pattern() shared helper.
Part of #2123.
Tests: tests/test_gallery_search_multiword.py (5 tests); 4 fail pre-fix, 5 pass post-fix. Neighbors (session_search, gallery null-user, shims): 25 passed.
update_skill only checked whether the target directory existed. A skill
with that name in another category lives elsewhere on disk, so the
rename went through and left two skills with one name. Update and
delete look skills up by name, so the next delete removed whichever
file os.walk reached first.
Check the owner's skills in every category before renaming, and answer
409 from PUT /api/skills/{id} instead of the misleading 404.
Replace urllib-based PyPI metadata retrieval with curl --retry 8 to
handle transient TLS/SSL EOF errors that abort the Docker image build.
The sdist download also gets retry logic. No functional change to the
patching or wheel-building steps.
Co-authored-by: isharak7m <192635824+isharak7m@users.noreply.github.com>
budget_context_for_model() returns 0 when the endpoint does not prove its
context window, and compute_input_token_budget() answers 0 with the
conservative default budget (6000). The agent loop's small-local-server
clamp (`candidate_context <= 8192`) also matched 0 and cut the request to
max(1200, 0) tokens, so on any endpoint with an unreported window an open
document or a few thousand tokens of earlier context were trimmed away
before the model saw them ("5519 tokens > 1200 budget (ctx=1800)").
Apply the clamp only to a known window.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
When the chat model cannot see images, the separate vision call's description
is appended to the user's message. Nothing marked it as machine-derived, so the
chat model read it as the user's own prose and answered the description instead
of the question.
The label goes below the `[Image: <name>]` marker line because the client
strips the block by matching that exact prefix; renaming the marker would leave
the raw description rendered in the user's bubble.
Fixes#5573
Co-authored-by: Claude <noreply@anthropic.com>
`_gather_inputs()` fails soft: a source that raises leaves its inventory as
`[]`. Every probe reads an empty inventory as "not configured" and answers
`disabled`, so a broken integrations file, email store, or endpoint database is
indistinguishable from a subsystem the operator deliberately turned off. With
the remaining subsystems disabled, `GET /api/diagnostics/services` then reports
`overall: "ok"` while three of its inputs failed to load — the exceptions appear
only in DEBUG logs.
Record each failure alongside the empty value (`failed`: source -> controlled
category) and report the affected subsystem through `_source_unavailable()`
rather than probing it with an inventory that is empty for the wrong reason.
- `degraded`, not `disabled`: the configured state is unknown, not known-off.
Not `down` either — nothing reached the subsystem and failed; the inventory
could not be read. Severity is non-zero either way, so a report containing a
failed source can no longer roll up to `ok`.
- A source that loads and is genuinely empty still reports `disabled`.
- One broken source degrades one entry; the others are still probed.
- `meta` carries the source name and the controlled `_classify_error()`
category only, never exception text, credentials, or database detail.
- `inputs.get("failed")` so an inputs payload without the key still probes
normally.
Verified with the reporter's harness: settings loading with
`search_provider: "disabled"` while the other three sources raise now yields
`overall: "degraded"` with `searxng` still `disabled`; before, all five read
`disabled` and `overall` was `ok`.
In routes/cookbook_routes.py, the exception handler for GET /api/cookbook/hf-gguf-files referenced repo instead of the parameter repo_id, causing an unhandled NameError and 500 status when upstream requests to Hugging Face failed.
Fixes#6341.
Six regexes over tool output backtracked polynomially on long whitespace
runs or repeated openers: the browser snapshot generic-line filter and
post-interaction split, the task-row and skill-bullet parsers, the email
"no results" check, and the Google /sorry/ interstitial check.
Rewrite each without overlapping quantifiers, keeping the same matches for
the text these tools emit. Move the /sorry/ check into
is_google_sorry_url() so it can be tested.
Preserve complete scientific notation and signed floating-point literals across
arbitrary streaming chunk boundaries in _DegenerateStreamGuard. Buffer pending
tokens until delimiter characters arrive to avoid splitting numbers into
incomplete or arbitrary alphanumeric tokens, while maintaining the 2048-number
runaway backstop and detection of repeated phrases and word loops.
Grzegorz