Commit Graph
6 Commits
Author SHA1 Message Date
michaelxerandmichaelxer 387e2de092 fix: hide shell access and plan mode buttons in chat mode (#3417)
When in chat mode, the shell access and plan mode buttons should not be
visible. These buttons are only relevant in agent mode where the AI can
use shell commands and planning features.

Changes:
- Modified applyModeToToggles() to hide bash-toggle-btn and plan-toggle-btn
  when mode is 'chat'
- Added immediate hiding on page load to prevent flash of buttons
- Buttons are shown again when switching to agent mode

Fixes #3411

Co-authored-by: michaelxer <michaelxer@users.noreply.github.com>
2026-06-08 11:32:37 +02:00
michaelxerandmichaelxer 09f5ee10f2 fix: expose supports_tools toggle for local endpoints in UI (#3195)
* fix: expose supports_tools toggle for local endpoints in UI

Local endpoints (Ollama, vLLM, etc.) default to fenced tool blocks
when supports_tools is not set, which breaks tool calling for models
that support native function calling. The backend already supports
per-endpoint supports_tools overrides via the PATCH API, but there
was no UI to set it.

Add a 'Tools: Auto/On/Off' toggle button for local endpoints that
cycles through the three states:
- Auto (null): use the existing heuristic
- On (true): always use native function calling
- Off (false): always use fenced tool blocks

Fixes #3141

* docs: add screenshot of supports_tools toggle showing Auto/On/Off states

* Add Tools toggle screenshot for PR #3195

* refactor: convert Tools toggle to select dropdown per review feedback

Replace cycle-through button with a <select> dropdown for the
supports_tools tri-state setting. Options: Auto / On / Off with
explicit labels. Uses existing admin select styling. Fires PATCH
on change event. Same API contract (Auto=null, On=true, Off=false).

* Update Tools toggle screenshot (now dropdown select)

* fix: remove orphan screenshot and move Tools dropdown below button row

- Remove docs/screenshots/tools-toggle-three-states.png (unreferenced image causing test_no_orphan_images_in_docs to fail)
- Move Tools dropdown to its own line below Disable/Delete buttons, aligned right
- Keep Disable and Delete buttons grouped together per maintainer feedback

* fix: move Tools select onto same row left of Disable/Delete, use CSS class

Per vdmkenny feedback: move the Tools dropdown select from its own row below
the button group onto the same row, to the left of the Disable and Delete
buttons (which stay adjacent on the right). Replace inline style on the
button row with the existing .admin-ep-actions CSS class, adding
align-items:center for proper vertical alignment.

* chore: remove committed screenshots from tree

Screenshots should be in PR description/comments, not in repo history.

---------

Co-authored-by: michaelxer <michaelxer@users.noreply.github.com>
2026-06-08 00:29:06 +02:00
michaelxerandmichaelxer 14e5b5f655 fix: show backend error detail in context-popup compact button (#2721)
When the context-popup compact button receives a non-OK response (e.g.
409 for active-run), the error detail from the backend was being
discarded in favor of a generic 'Compaction failed' message.

Now parses the JSON response body for non-OK responses and prefers the
detail field when present, matching the behavior of the /compact slash
command. Uses textContent for safe rendering.

Co-authored-by: michaelxer <michaelxer@users.noreply.github.com>
2026-06-07 18:16:58 +02:00
michaelxerandmichaelxer 1fc7a5d35f fix: fall back to /models probe when base URL returns 404 (#3205)
_ping_endpoint() probes the bare base URL for non-Ollama endpoints.
OpenAI-compatible servers like llama-swap return 404 on the /v1 prefix
but 200 on /v1/models, causing endpoints to appear offline despite being
fully functional.

Add a /models fallback when the base URL returns a non-auth 4xx.
Auth failures (401/403) are treated as definitive — probing /models
would just repeat the same rejection.

Fixes #3181

Co-authored-by: michaelxer <michaelxer@users.noreply.github.com>
2026-06-07 16:09:33 +02:00
michaelxerandmichaelxer 43c31ae008 fix: raise imaplib line limit for large mailboxes (#2895)
Python's imaplib._MAXLINE defaults to 1 MB. Mailboxes with tens of
thousands of messages exceed this on UID SEARCH ALL, crashing with
'got more than 1000000 bytes'.

Set _MAXLINE to 50 MB after opening the connection so large mailboxes
work without error.

Fixes #2883

Co-authored-by: michaelxer <michaelxer@users.noreply.github.com>
2026-06-05 22:59:35 +02:00
michaelxerandmichaelxer f07bf99236 fix: respect user round count in deep research (#2896)
The STOP_PROMPT did not include the target round count, so the LLM
could decide to stop after 2-3 rounds even when the user requested 8.
Additionally, min_rounds was capped at 3 regardless of max_rounds.

- Add max_rounds to STOP_PROMPT so the LLM knows the target
- Change min_rounds from min(3, max_rounds) to max(2, max_rounds - 2)

Fixes #2863

Co-authored-by: michaelxer <michaelxer@users.noreply.github.com>
2026-06-05 20:49:42 +02:00