feat: bridge daemon POST /run for agentic code tasks (0194) - #159
Merged
Conversation
Completes the bridge daemon's surface (health + chat + run). Wires devkit's
existing-but-unserved handleBridgeRun into the daemon as POST /run: isolate in a
worktree → coding agent edits → validation gate → checkpoint/rollback. Opt-in
and safe-by-default (it runs a coding agent + the gate = arbitrary code exec):
when no run handler is configured, /run answers 501.
@xnetjs/devkit:
- createBridgeServer gains an optional `run` handler; POST /run validates
{taskId, prompt, worktreeName?} and delegates to it (400 on missing fields,
502 on throw). Decoupled from handleBridgeRun via the handler type so it's
tested with an injected fake (no git needed).
@xnetjs/cli:
- `xnet bridge serve --code` builds the run handler from handleBridgeRun over the
repo at --cwd (Git + cliAgentRunner + defaultXnetGate + worktreeRoot).
This is the HTTP seam the in-app UI will call to trigger a gated code task.
Tests: devkit 54 (bridge-server 11: /run 501-disabled, delegate, 400, 502).
typecheck, eslint --max-warnings 0, prettier clean. Electron /run deferred
(repo ambiguity); in-app UI button deferred.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Contributor
|
Preview removed for PR #159. |
crs48
added a commit
that referenced
this pull request
Jun 18, 2026
…193/0194) (#201) The `changelog-section` required check was only added in #164, so the 0192/0193/0194 feature batch merged before it never got changelog entries. This backfills the 12 user-facing features that were missing, each dated to its merge day with its PR number and contributors: | PR | Entry | |----|-------| | #138 | A safer foundation for plugins | | #145 | One trust model across plugins and Labs | | #146 | Reliability you can see for managed hubs | | #148 | Drive your own coding agent from xNet | | #149 | AI that can act on your workspace | | #150 | Your Labs become AI tools | | #152 | Your agent can use your workspace | | #154 | AI edits, right inside the editor | | #155 | An agentic dev loop in your terminal | | #158 | Review AI edits before they apply | | #159 | Kick off agentic code tasks from xNet | | #162 | Plugins run on the Labs runtime | Skipped: PRs already covered by umbrella entries (#142 plugin ecosystem, #144 extensibility fabric, #147 automated changelog, #163 agent panel, #180 changelog gallery), internal-only changes (#139 schema authz — zero user-facing effect), and meta/test/docs PRs. 🤖 Generated with [Claude Code](https://claude.com/claude-code)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What & why
Exploration 0194. Completes the bridge daemon's surface — health + chat + run — by wiring devkit's existing-but-unserved
handleBridgeRuninto the daemon asPOST /run. This is the HTTP seam the in-app UI will call to trigger a gated agentic code task (the counterpart toxnet code, over the bridge).Changes
@xnetjs/devkit—createBridgeServergains an optionalrunhandler;POST /runvalidates{taskId, prompt, worktreeName?}and delegates (400 on missing fields, 501 when not enabled, 502 on throw). Decoupled fromhandleBridgeRunvia the handler type, so it's tested with an injected fake — no git needed.@xnetjs/cli—xnet bridge serve --codebuilds the run handler fromhandleBridgeRunover the repo at--cwd(Git+cliAgentRunner+defaultXnetGate+ worktreeRoot).Safe by default:
/runruns a coding agent + the validation gate (arbitrary code execution), so it's opt-in — without--codethe endpoint answers 501.Tests / validation
/run501-disabled, delegate-to-handler, 400-missing-fields, 502-on-throw) + CLI 43, green.typecheck(devkit + cli),eslint --max-warnings 0,prettier --checkclean. No new deps.Deferred
Electron
/run(repo ambiguity in a packaged app); the in-app "create/edit plugin" button that callsPOST /run; plus the earlier ACP transport / in-panel approval items.🤖 Generated with Claude Code