Commit Graph

54 Commits

Author SHA1 Message Date
can1357 d562f28c1b Merge remote-tracking branch 'origin/farm/795471ef/cancel-timed-out-browser-run' 2026-07-01 04:46:41 +02:00
roboomp f7398a1aa8 fix(browser): bound cmux facades to runs
Wrapped cmux page, browser, and tab globals with per-run abort checks so stale continuations cannot reuse the long-lived CmuxTab after timeout.

Fixes #3964
2026-07-01 02:30:07 +00:00
roboomp 09625b1ca8 style: bun run fix 2026-07-01 02:21:41 +00:00
roboomp db8560f934 fix(browser): stopped stale timed-out runs
Aborted browser run helpers and recycled timed-out workers so losing JavaScript continuations cannot mutate a live tab after timeout.

Fixes #3964
2026-07-01 02:21:19 +00:00
roboomp 19b85bca70 fix(browser): reap Chromium/Puppeteer on aborted open and session dispose
Two termination boundaries in the browser tool leaked browser-owned OS resources into the long-lived coding-agent process.

1. Aborted 'open' published an orphan. #open wrapped acquisition in untilAborted, which rejects its outer wrapper on abort but lets the inner launch resolve in the background; acquireBrowser then unconditionally stored the resolved handle in the module-global browsers map. releaseAllTabs walks tabs, not browsers, so the refCount:0 handle stayed alive to process exit.

2. Session dispose had no browser teardown. Browser/tab state lives in module-global maps, and AgentSession.dispose() had no hook to walk them, so headless/spawned Chromium the session opened survived it.

acquireBrowser now short-circuits before launch on a pre-aborted signal and disposes the handle when the launch completes after abort. TabSession records the creating session's id (opts.ownerSessionId, threaded through BrowserTool.#open), preserved across reuse so a subagent re-driving an existing tab does not yank teardown responsibility. AgentSession.dispose() invokes releaseTabsForOwner bounded by withTimeout(3s), mirroring the async-job/MCP disposal pattern.

Regression tests exercise both boundaries via spied CmuxSocketClient (no real puppeteer/socket) and cover: pre-aborted open short-circuit, aborted-mid-launch cleanup, releaseTabsForOwner reaping only owned tabs, and reuse preserving original ownership.

Fixes #3963
2026-07-01 02:09:04 +00:00
can1357 1dd78b207e feat(coding-agent): removed unused eval helper functions
- Removed deprecated eval prelude helpers `append`, `tree`, `diff`, `sort`, `uniq`, and `counter` from all supported runtimes.
- Cleaned up runtime implementations, protocol definitions, and UI rendering logic associated with the removed helpers.
- Updated project documentation, prompts, and test suites to reflect the reduced helper API surface.
- Recorded functional changes in the package changelog.
2026-06-23 01:39:24 +02:00
can1357 1cb433cbde feat(coding-agent): added browser navigation helpers and improved timeout management
- Implemented `waitForSelector` and `waitForNavigation` methods in the browser tool API.
- Introduced per-operation fail-fast budget management with dynamic timeout clamping.
- Added validation for selector engines to reject unsupported Playwright-only platform features.
- Standardized error handling to provide descriptive, named timeouts for stalled browser operations.
2026-06-21 18:10:10 +02:00
can1357 e649017322 feat(coding-agent): added ARIA snapshot support for browser tools
- Implemented `tab.ariaSnapshot()` to capture and represent page structures as ARIA-tree YAML.
- Introduced `tab.ref()` and ref-based selector parsing to enable precise element interaction via unique ARIA identifiers.
- Integrated automated script bundling for cross-environment evaluation of ARIA snapshot logic.
- Updated browser action methods to resolve and target elements using ARIA-ref handles.
2026-06-21 06:39:14 +02:00
can1357 57cb7447e0 feat(coding-agent): enhanced browser stealth and automation capabilities
- Overhauled stealth spoofing mechanisms for WebGL, screen dimensions, Web workers, and iframe contexts using prototype-aware injection.
- Centralized function string representation patching to improve mimicry of native browser behavior across global objects.
- Patched puppeteer-core to remove detectable evaluation markers and implement lazy, pull-style execution context management.
- Enabled support for capturing LLM request JSON dumps and adjusted launcher flags to improve organic request patterns.
2026-06-21 04:14:26 +02:00
can1357 8427e69e1e fix(coding-agent): prevented puppeteer startup crashes
- Avoided value-imports of `puppeteer-core` in main startup files to prevent eager loading of the browser-data dependency graph.
- Used `import type` and literal string checks to defer `puppeteer-core` initialization until browser tools are actually invoked.
- Added a test to verify that `puppeteer-core` and `@puppeteer/browsers` remain off the eager startup import graph.
- Externalized additional heavy dependencies to reduce bundle size and improved minification settings in the build script.
2026-06-18 17:22:37 +02:00
can1357 eb67863e75 feat(coding-agent/tools): secured browser stealth scripts against detection
- Bound native Reflect methods to local variables in the browser launch script to prevent detection.
- Updated stealth injection scripts to use the bound Reflect methods instead of global Reflect calls.
- Fixed a type assertion issue in the AgentSession tool proxy.
2026-06-17 20:59:20 +02:00
can1357 3ab675a83b fix: added buffered worker inboxing and standardized worker selectors
- Added `WorkerInbox` and `installWorkerInbox(port)` to queue worker messages before bind.
- Added `consumeWorkerInbox()` to replay buffered messages and clear one active inbox.
- Added buffered inbox consumption in JS and tab worker transports before direct message handlers.
- Normalized worker selector arguments to the `__omp_worker_*` naming across workers and tests.
2026-06-15 11:59:44 +02:00
can1357 60a46f37db fix(ai): fixed SSE cancellation to stop upstream requests on client stream cancel
- Extended gateway stream control to pass abort signals and onCancel into encodeStream.
- Added optional cancellation control parameters to provider encodeStream handlers.
- Stopped provider stream loops on cancellation and suppressed SSE completion/error output after abort.
- Added a regression test verifying reader.cancel triggers onCancel and aborts upstream request.
2026-06-13 17:53:53 +02:00
can1357 746f521868 feat(coding-agent-browser-cmux-tooling): added cmux browser mode support
- Added cmux browser mode options and resolved mode selection from env and app flags.
- Added cmux tab operations for navigation, JS execution, observations, and screenshots.
- Added CMUX socket client messaging with auth, timeouts, and ordered request dispatch.
- Updated browser docs and examples to describe cmux behavior, selectors, and API limits.
2026-06-13 17:35:56 +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
Can Bölük 608cd4103b Merge branch 'main' into fix/browser-cdp-discovered-pages 2026-06-11 17:51:41 +02:00
can1357 dcda0e49b8 fix(coding-agent/tools): honored screenshot path extensions in image capture
- Added imageFormatForPath to map explicit save extensions to Puppeteer image formats.
- Derived screenshot capture type from explicit save paths and used it for both element and page screenshots.
- Updated MIME and extension handling so saved full-resolution image bytes and names match the chosen format.
2026-06-10 23:12:20 +02:00
danzaio e6b0e76341 fix(browser): cover cdp attach fallbacks 2026-06-10 14:37:58 -03:00
danzaio b73c9bce94 fix(browser): attach to discovered CDP pages 2026-06-10 14:22:55 -03:00
can1357 61a57c1d21 fix(coding-agent): stabilized streaming TUI rendering with readonly rows and memoized reuse
- Changed render methods to return component-owned `readonly string[]` rows.
- Added `RenderStablePrefix` row reuse to avoid repainting unchanged streaming content.
- Stabilized streaming gutters and spinner placement to reduce preview jitter and flicker.
- Finalized commit-safe transcript behavior for tool-call previews and added streaming edge-case tests.
2026-06-10 07:26:02 +02:00
can1357 8583421362 perf(coding-agent): deferred heavy imports until first feature use
- Added lazy async module loaders for @babel/parser, linkedom, puppeteer/browsers, @mozilla/readability, @xterm/headless, and mnemopi to avoid loading them during cold startup.
- Added an interactive startup splash before session construction and skipped it for resume/fork/continue, quiet mode, timing mode, or non-TTY runs.
- Updated JS import-rewrite and memory tests to match async parser loading and preloaded mnemopi modules for sync state helpers.
2026-06-10 03:57:32 +02:00
can1357 dc5c93462f feat: rerouted worker subprocesses through the bundled CLI host entrypoint
- Rerouted sync, tab, js-eval, and tiny workers to re-enter CLI modes via `__omp_*` selectors.
- Adjusted `cli.ts` startup to dispatch worker entrypoints before parsing and exit 1 on uncaught errors.
- Bundled CLI as `dist/cli.js` in prepack, switching `omp` binary and published files.
- Removed explicit Bun `--compile` worker entrypoints from build/release scripts in favor of host-entry dispatch.
- Added `declareWorkerHostEntry()` and `workerHostEntry()` environment helpers and `PI_COMPILED` binary detection.
2026-06-10 03:57:31 +02:00
can1357 f638a5b3e0 refactor(coding-agent): added lazy loading for heavy dependencies
- Introduced memoized dynamic import loaders for Babel parser, mnemopi modules, puppeteer, and HTML-related packages.
- Refactored eval import-rewrite helpers and runtime call sites to use asynchronous wrapping and parsing flows.
- Shifted fetch and web-scraper linkedom usage to on-demand imports so heavy modules load only when needed.
2026-06-10 03:09:09 +02:00
can1357 39c08f5434 fix(coding-agent): stopped web-search query mangling and API-key log leakage
removed the rewrite replacing every 202x with the current year (corrupted CVE ids); MCP request logs redact key/token/secret/auth query params; fetch honors declared charsets, surfaces transport causes, retries 429 once abort-aware, flags mid-stream truncation, stops double-downloading binaries; browser tab reopen/registry/single-flight races fixed, queued opens honor abort, init failures release the temp hold; MCP calls get a default timeout and per-line SSE parse guards.
2026-06-10 01:28:04 +02:00
can1357 bda3102451 ux(coding-agent): updated status glyphs and fixed extension model discovery refresh
- Added status.done and tool.* symbols to theme mappings and presets.
- Replaced generic success glyphs with contextual +/-, tool icons, and warnings.
- Mapped tool/task/job completions to status.done or status.enabled with icon overrides.
- Triggered runtime provider refresh after extension registration and warned on failure.
2026-06-08 18:28:15 +02:00
can1357 1f00057584 fix(tools): fixed browser helper timeout handling and stalled-op diagnostics
- Tracked in-flight browser helpers with names and durations for timeout reporting.
- Wrapped observe, screenshot, and extract in per-op deadlines capped at 20_000ms.
- Updated timeout cancellation errors to list stalled helper names and elapsed time.
2026-06-08 13:37:50 +02:00
can1357 8173b7ea8c feat(tools/browser): enabled shared browser tab reuse and extract safety
- Applied `opts.viewport` on reusable tabs in `tab-supervisor.acquireTab` before conditional `tab.goto`.
- Skipped `runInTabWithSnapshot` on tab reuse when no viewport or URL change was requested.
- Changed `tab.extract` to return `Promise<string>` and throw on missing or empty Readability content.
- Redacted `user:pass@` from tab URLs returned in observations to avoid leaking credentials.
- Documented `tab.extract(format)` to return markdown/text and throw when no readable content exists.
2026-06-08 02:04:59 +02:00
can1357 ecd80120a3 feat(coding-agent): added framed tool rendering with capped streaming previews
- Wrapped tool call/result renderers with framed block markers for full-width display.
- Added preview-line caps via capPreviewLines to bound multiline outputs with truncation hints.
- Added code-cell tail rendering so streaming output shows capped tail slices with markers.
- Added setPaddingX in Box and applied framed-inline padding adjustments for tight layouts.
2026-06-06 15:19:06 +02:00
can1357 8cd8fd9b70 fix(coding-agent/tools): aligned screenshot file extensions with saved buffer format
- Computed screenshot destination extensions from the MIME type of bytes being written.
- Updated auto-generated paths in screenshot and temp directories to use the matching extension.
2026-06-02 04:36:21 +02:00
can1357 e831c2c758 chore: reformat 2026-05-30 18:08:51 +02:00
Can Bölük 70480e9875 Merge branch 'main' into fix/coding-agent-misc 2026-05-26 21:27:39 +03:00
can1357 a450bbf9a6 fix: corrected runtime execution context variable from session.cwd to msg.session.cwd
- Corrected runtime execution context variable from session.cwd to msg.session.cwd to use correct execution context.
2026-05-26 15:27:16 +02:00
can1357 8a5b3e9552 feat(eval): added shared executor inheritance for subagents with concurrent async cells
- Removed per-session run queues from JS and Python backends, allowing async cells on the same session id to interleave.
- Introduced `getEvalSessionId` on ToolSession so subagents spawned via `task` inherit the parent's executor id and share JS VM and Python kernel state.
- Switched JS runtime state from module-level fields to AsyncLocalStorage so concurrent runs route output and tool calls to their own context.
- Changed Python runner to an asyncio event loop with per-request tasks and ContextVar-based run id tracking for concurrent execution.
- Added mtime-based module cache eviction to preserve singleton state across re-imports of unchanged local files.
2026-05-26 14:37:56 +02:00
oldschoola 2171ae4dd1 fix(coding-agent): browser default, patch error path, mcp:// selectors, find timeout/sort, DAP launch races, debugpy diagnostics
- browser tool's existing-tab re-nav defaults to waitUntil: 'load' (matching
  new-tab path); identical acquireTab() calls no longer hang on dev servers
- patch tool error path uses caller-supplied relative path; absolute
  resolvedPath stays in structured context only ($HOME no longer leaks to TUI)
- splitInternalUrlSel keeps mcp:// resource URIs opaque even when they end in
  ':raw' or '/:1-50' (McpProtocolHandler matches by verbatim URI)
- find tool: timeout signal honored by onMatch; partial results sorted by
  mtime desc; backslash-escaped commas skipped in path-list validation
- DAP throwPreferredDapStartError waits up to 50ms for the underlying
  launch/attach error instead of one microtask
- debug tool surfaces 'python missing' and 'pip install debugpy' diagnostics
  separately when adapter: 'debugpy' is requested
2026-05-26 01:54:09 -07:00
roboomp 1a279bba88 fix(browser): handled null head in stealth bootstrap
Appended the stealth iframe to documentElement when document.head is not available during new-document evaluation.

Added regression coverage for the null-head bootstrap path.

Fixes #1267
2026-05-21 15:43:02 +00:00
can1357 ef505142bf fix(coding-agent): fall back to inline worker when tab worker startup errors
Worker emits BuildMessage errors via the async error event, after the
surrounding try/catch in spawnTabWorker has already resolved, so the
documented spawnInlineWorker fallback was unreachable for the very case
it was added to cover. initializeTabWorker now terminates the broken
worker and retries once via spawnInlineWorker, with the original error
attached as cause if the inline fallback also fails.
2026-05-19 19:24:16 +09:00
can1357 d700004489 fix(coding-agent): default browser waitUntil to "load"
networkidle2 requires <=2 in-flight requests for 500ms which never
resolves on dev servers (HMR, websockets, telemetry beacons), so
browser.open and tab.goto timed out before user code ran. "load" matches
Puppeteer's documented default and works on real-world pages.
2026-05-19 19:24:16 +09:00
can1357 f0ff398607 fix(coding-agent/tools): stripped duplicate output notices from TUI tool renderers
- Added stripOutputNotice to output-meta to remove appended truncation notices when output metadata is available.
- Updated bash, eval, browser, read, and ssh renderers to strip the notice before display so the styled warning line is not duplicated.
- Left fallback behavior unchanged so outputs without a notice continue through unchanged.
2026-05-15 03:16:16 +02:00
Can Bölük 26931fe8ce Merge pull request #1055 from jiwangyihao/fix/browser-worker-startup-errors
fix(browser): surface tab worker startup errors
2026-05-14 04:47:31 +02:00
Can Bölük 3d2bbe5e8f Merge branch 'main' into fix/browser-stealth-target-setup 2026-05-14 04:46:30 +02:00
can1357 f1f6516056 refactor: reorganized exports and removed obsolete helper branches
- Removed export leakage by demoting many helper and const symbols to module-local scope.
- Renamed underscore-prefixed internals and cache fields, then updated related references and `satisfies never` checks.
- Deleted obsolete logic branches and helpers, including harmony-stream interruption flow and unused benchmark runtime helpers.
- Updated Biome config and manifests by broadening lint coverage and removing an unused `@napi-rs/cli` dev dependency.
- Adjusted tests and utilities to use renamed test helpers and remove redundant private test-only helpers/locals.
2026-05-14 04:36:19 +02:00
jiwangyihao 11a19eb8d4 fix(browser): bound stealth target setup during tab open
Keep the active page stealth setup synchronous, but make the broader CDP target UA override sweep selective and best-effort. Non-page or ephemeral Chrome targets can otherwise block worker initialization long enough for browser.open to hit the tool timeout before the tab worker sends ready.

Fixes #1053
2026-05-14 01:19:01 +08:00
jiwangyihao 8830b2e367 fix(browser): surface tab worker startup errors
Forward worker error and messageerror events while acquireTab waits for the initial ready/init-failed response. This prevents async worker module-load or early startup failures from being reported only as a generic tab worker init timeout.
2026-05-14 00:34:55 +08:00
can1357 1cb451a071 fix(workers): replaced file-URL import pattern with compiled-binary-aware spawn
- Replaced `with { type: "file" }` worker imports with `isCompiledBinary()` hybrid: literal string for `--compile` static analysis, `new URL(import.meta.url)` for dev portability.
- Added worker entrypoints as explicit `--compile` args in `build-binary.ts` so Bun emits them into bunfs.
- Added `smokeTestSyncWorker` and `omp --smoke-test` to catch silent worker-load failures in compiled binaries (fixes #1011, #1027).
- Added `isCompiledBinary()` utility to `@oh-my-pi/pi-utils` detecting bunfs path markers.
2026-05-12 16:40:15 +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 92ec8607ff fix(coding-agent/tools): added ts-expect-error for Bun file URL worker import
- Documented why the tab worker entry must be imported with Bun's file attribute despite tsgo limitations.
- Added a @ts-expect-error on the tabWorkerEntryUrl import to suppress tsgo TS1192/TS5097 errors.
2026-05-12 06:32:12 +02:00
can1357 ebbe66a3d6 fix(coding-agent/browser): bundle tab-worker-entry for prebuilt binaries (#1011)
The Worker spawn in spawnTabWorker used `new Worker(new URL(...).href, ...)`
through a local variable, which Bun's --compile static analysis does not
recognize. As a result, tab-worker-entry.ts was never embedded in single-file
binaries (v14.5.13+), and the worker thread failed to load its entry at
/$bunfs/root/tab-worker-entry.ts, surfacing as the user-visible
"Timed out initializing browser tab worker".

Switch to a `with { type: "file" }` import of the entry module so the
bundler discovers and embeds it in both dev and compiled targets.

Regression test asserts `Bun.build` emits tab-worker-entry as an asset
alongside the tab-supervisor entry point — the same static-analysis pass
that powers `bun build --compile`.
2026-05-12 06:16:05 +02:00
can1357 ca84ee760d perf: optimized ai providers with lazy-loading imports and cached init
- Consolidated AI provider imports through register-builtins and moved Gemini/Antigravity header helpers to a shared module.
- Added lazy loading for heavy providers and SDK-backed modules with cached initialization to trim startup cost.
- Converted markdown conversion helpers to async and awaited htmlToBasicMarkdown in affected scraper and kernel output paths.
- Parsed bundled agent definitions on-demand and moved BrowserTool prompt rendering behind a memoized getter.
- Added cached validation/error handling paths by replacing AJV runtime checks with Value.Check and trimming validation error output.
2026-05-01 18:54:21 +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
can1357 4737cf62fb fix(coding-agent/tools): added stricter browser timeout and execution cancellation handling
- Set a shared 60s Puppeteer protocol timeout and applied it to browser launch/connect.
- Added a combined cancel-or-timeout signal in `runInTab` and raced user code against it for prompt cancellation behavior.
- Reduced the browser tool max timeout to 30s to keep execution limits aligned with tool-level deadlines.
2026-04-30 16:13:28 +02:00