Commit Graph
9 Commits
Author SHA1 Message Date
can1357 ce1ec2103f Merge PR #7006: fix(tools): stop browser automation from stealing focus in an attached browser (@terrxo)
# Conflicts:
#	packages/coding-agent/src/tools/browser/tab-supervisor.ts
2026-07-31 19:42:12 +02:00
Nik Divjak b8b0d342da fix(tools): stop browser automation from stealing focus in an attached browser
Attaching over app.cdp_url points automation at a browser the user is driving,
so two behaviors that are correct for a browser we own are wrong there.

pickElectronTarget enumerated CDP targets and took the first usable one, which
is not necessarily the tab in front of the user, and #captureScreenshot always
called page.bringToFront(), which switches the user's visible tab and pulls
window focus on every screenshot.

Connected browsers now prefer a tab that reports document.visibilityState
"visible" and skip the pre-capture activation, accepting the compositor stall
risk that activation avoids. Headless and spawned browsers are unchanged.
2026-07-29 11:26:13 +02:00
Nik Divjak da1d393c39 fix(tools): navigate to the requested url when opening an attached browser tab
buildInitPayload dropped opts.url, opts.waitUntil and opts.timeoutMs on the
attach branch, so `browser open` with a url against app.cdp_url or app.path
adopted the existing target without navigating and reported its current url as
the result. Reusing the same tab name afterwards did navigate, because the reuse
path issues tab.goto, so the same call behaved differently on first open.

Thread the navigation fields through the attach arm of WorkerInitPayload and
goto after the page is adopted and the dialog policy is installed, mirroring the
headless arm.
2026-07-29 11:20:52 +02:00
roboomp fe2fdf6564 fix(browser): isolated request interception per run
- Removed run-scoped Puppeteer request handlers and disabled interception on every browser.run exit path.
- Recycled workers when bounded interception cleanup cannot restore the tab, with raw CDP recovery for held requests.
- Added live Chromium coverage for held requests, normal traffic restoration, and thrown setup calls.

Fixes #6004
2026-07-18 16:22:40 +00:00
can1357 0d07da529a feat(coding-agent-tools): implemented browser execution safety controls
- Implemented cell budget clamping for timeouts to prevent stalled browser operations from exceeding execution limits.
- Added `recover` capabilities for tab workers to clear blocking dialogs and safely terminate hung navigations.
- Introduced `//!world=main` support for `tab.evaluate` via Puppeteer patch to allow execution in main execution contexts.
- Improved failure attribution for tab terminations by tracking dialogs, stalled operations, and specific termination reasons.
2026-07-13 00:05:43 +02:00
can1357 dd5c329bc3 fix(coding-agent): resolved browser teardown crashes by tracking expected abort errors
- Added `markHandled` helper to prevent unhandled promise rejections in fire-and-forget browser tasks.
- Integrated `postmortem.markExpectedCleanupError` to distinguish between expected teardown aborts and actual runtime failures.
- Updated `runCmuxCode` and `WorkerCore` to propagate abort reasons via `ToolAbortError` cause chains.
- Modified `tab-protocol` and supervisor logic to signal expected cleanup states during tab release.
- Added test coverage for `ToolAbortError` wrapping and cause preservation.
2026-07-06 08:07:24 +02:00
can1357 92fba8d486 fix: addressed model-aware image handling for tool image WebP filtering
- Added model-aware session image normalization by passing active model.
- Propagated model-derived WebP exclusion into browser snapshot capture and resizing.
- Applied model-derived WebP exclusion to eval, fetch, read, and inspect image paths.
2026-06-13 16:17:56 +02:00
can1357 2d4d70e47e feat(coding-agent): added shared JS runtime for worker execution
- Added shared JS runtime infrastructure with RuntimeHooks, RuntimeOptions, JsRuntime, and indirectEval-based execution.
- Reworked worker execution to use runtime.run, track active runs, and clean pending tool calls on close.
- Added tool-call and tool-reply message variants and wired supervisor/worker to route run-scoped calls.
- Added shared helper globals (read, writeFile, diff, tree, env) for browser-tab JS execution.
2026-05-12 08:42:30 +02:00
can1357 cf60e6df51 feat(coding-agent): implemented eval framework and replaced python tool
- Added a unified eval framework with parser grammar, backend interfaces, and JS/Python execution result types.
- Added eval tool docs and updated prompts for fenced cells, `eval.py`/`eval.js`, and fallback behavior.
- Replaced the built-in `python` tool with `eval` across registry, rendering, interactive modes, and tool settings.
- Migrated Python execution runtime from `src/ipy` to `src/eval/py`, renamed state fields, and removed legacy introspection.
- Refactored browser tooling from in-process VM helpers to worker-managed tab supervisors and protocol transport.
- Added eval parser fallback and JS tool-bridge tests, updated imports, and removed obsolete python-mode suites.
2026-04-30 18:08:37 +02:00