Commit graph

6 commits

Author SHA1 Message Date
Christian Bromann
abf354bb05
feat(open-swe): stream agent chat via @langchain/react v2 protocol (#1475)
* feat(dashboard): stream agent chat via @langchain/react v2 protocol

Replace the bespoke SSE + React Query polling path with LangGraph’s
v2 event stream through credentialed dashboard proxies. Run starts go
through stream commands; mid-run follow-ups still queue via /messages.

* fix import path

* fix tests after rebase

* format

* PR feedback

* improved model fallback

* fix image handling

* embrace sdk

* cleanup

* cr

* more cleanup

* fix cors

* harden security

---------

Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-11 09:54:35 -07:00
Johannes du Plessis
8c7b789122
feat: add right-click open trace context menu for threads (#1490)
* feat: add right-click open trace context menu for threads

Add a context menu to sidebar thread rows exposing an Open trace action
that links to the LangSmith thread trace, surfaced via a new traceUrl
field on the thread summary.

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>

* chore: drop stray yarn artifacts from PR

Remove accidentally committed ui/.yarnrc.yml and ui/.yarn/install-state.gz
that broke immutable installs against the v1 lockfile, and gitignore yarn
artifacts to prevent recurrence.

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>

* chore: reuse thread_id var, drop redundant danger-color fallback

---------

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-10 15:40:43 -07:00
Johannes du Plessis
5430672edb
fix: revert dashboard stop run controls (#1461)
Revert the dashboard stop-button behavior from #1433 because it allows duplicate submissions while optimistic prompts are still pending.
2026-06-08 21:47:53 -07:00
Johannes du Plessis
1f619eae0f
feat: add stop button to cancel running agent from web UI (#1433)
* feat: add stop button to cancel running agent from web UI

* fix: handle stopped agent runs

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>

---------

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-06 08:12:30 -07:00
Johannes du Plessis
449cb5d1a8
fix: make default repository configurable (#1429)
* fix: make default repository configurable

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>

* fix: preserve dashboard repo-less runs

* fix: distinguish explicit repo-less dashboard runs

---------

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-05 13:48:47 -07:00
Johannes du Plessis
dee78e7e84
fix: make repository optional when starting a dashboard run (#1397)
* fix: make repository optional when starting a dashboard run

The agent infers and clones the target repo from the task itself, so a
default repo is never actually required to run — but the dashboard 400'd
("no default repository configured") when a user had none set.

Treat repo as optional: _resolve_repo_config returns {} instead of
raising, repo metadata/config are only written when a repo is present,
and the "missing repository metadata" gate on follow-up messages is
dropped. UI hides the repo chip when absent.

* feat: add repo picker to the run prompt bar

Adds an optional, searchable repository selector next to the model picker
on the Agents home prompt bar (Cursor-style). It pre-fills the user's saved
default repo and can be cleared to "No repository" for a repo-less run.

Because the picker now resolves the default on the client, the create
endpoint honors the request value verbatim: _resolve_repo_config just parses
what's sent ({} when empty) instead of falling back to the saved default,
so an explicit "No repository" is respected.

* refactor: match Cursor layout for repo placement

Move the repo selector out of the prompt-box footer to a pill row above
the input (folder + caret, dropdown opens downward); the model picker
stays inside the box. In the thread view, show the thread title and repo
in a header at the top of the chat, with the follow-up input pinned to
the bottom as before.
2026-06-03 14:24:08 -07:00