On macOS the shared headless browser daemon launched from the system Google Chrome app bundle, running as a com.google.Chrome instance. macOS LaunchServices could then deliver the user's open-URL Apple Events to the daemon instead of their own Chrome, silently swallowing link clicks.
ensureChromiumExecutable now prefers the isolated Chrome for Testing binary (com.google.chrome.for.testing) on macOS, falling back to system Chrome only when Chrome for Testing cannot be obtained. Other platforms keep the download-avoiding system Chrome preference.
Fixes#8673
Mirrored registry status from pre-wire session run-state transitions and required live session corroboration before a peer can sustain bare hub waits.
Fixes#8634
Added Chromium no-startup-window to the broker-owned browser launch so no unowned foreground page survives session tab cleanup.
Covered the resolved Chromium argv and documented the Windows regression.
Fixes#8615
The shared-browser CDP liveness probes (probeEndpoint, waitForCdp, probeCdpAt) used a bare fetch() against the loopback DevTools endpoint. Bun's fetch honors HTTP_PROXY/HTTPS_PROXY and forwards even 127.0.0.1 requests to the proxy unless NO_PROXY covers them, so a local proxy (e.g. Clash) that 502s internal addresses made a healthy daemon look dead and ensureSharedBrowser tore it down.
Replace the three probes with probeCdpStatus(), a raw-TCP HTTP/1.1 GET that never routes through a proxy and resolves to the response status (or null on unreachable/aborted/timeout).
Fixes#8567
- Add `renderPdfPageScreenshot` to render PDF pages via headless Chromium.
- Update `ReadTool` to intercept legacy PDF image paths and return page screenshots.
- Ensure daemon clients are closed on read command exit.
- Replaced the custom MuPDF-WASM PDF extraction and rendering pipeline with the new `pdfToMarkdown` native function from `@oh-my-pi/pi-natives`.
- Removed legacy MuPDF extraction modules, WASM embedding scripts, and PDF image extraction tools.
- Added OCR warnings and browser/text redirection for unsupported PDF image reads.
- Updated native package definitions, documentation, and test suites for the new PDF inspection capability.
Move the rewind instruction out of the permanent checkpoint tool result into a transient post-checkpoint notice that is branch-cut away on rewind; rewrite the rewind-report prompt forward-looking (no negation); collapse the rewind tool description to one line. Closes#8499.
formatReadHashlineHeader collapsed every relative in-workspace path to its
basename, so reading a nested file (e.g. src/settings.json) emitted
[settings.json#tag]. When a same-basename file existed at the session cwd,
a verbatim follow-up edit resolved against the cwd file; Patcher.prepare only
runs snapshot-tag path recovery when the authored path is missing, so the
valid edit was deterministically rejected with "hash is not from this
session". Keep the workspace-relative path, which names the file uniquely and
stays directly resolvable against cwd. Out-of-workspace absolute paths remain
shortened; root-level files are unchanged.
Fixes#8482
The executable version probe added in ecb22957 ("validate Linux browser
executables") replaced the file-only check in resolveSystemChromium with
isChromiumExecutable, which spawns the candidate `--version` for every
platform. On Windows chrome.exe is a GUI-subsystem binary: `--version`
does not print to a detached stdout and can hand off to a running
instance, opening/activating the user's normal browser window, after
which the probe rejects the candidate and falls back to cached Chrome
for Testing.
Gate the spawn probe on process.platform === "linux" (its intended
platform, where non-Chromium PATH wrappers are the real risk) and trust
the executable-file check on Windows and macOS.
Fixes#8445
- Multi-question dialogs now advance on Enter in multi-select mode
instead of submitting every question at once (roboomp blocking)
- Ask tool accepts an empty multi-select submission as a "select none"
answer instead of aborting as a cancellation (codex P2)
- Footer hint reflects advance vs submit for multi-question dialogs
- Move the #8252 changelog entry to Unreleased (codex P2)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Added shared auth storage and model registry for concurrent and eager compaction tests.
- Replaced per-test auth storage creation and cleanup routines with shared lifecycle management.
- Removed local auth storage variables and individual cleanup hooks from test harness instances.
- Added `splitAddressableFileLines` to strip terminal newlines from line addressability without removing genuine blank lines.
- Updated coding-agent read tool context parsing to use addressable file lines.
- Added archive and member size assertion limits along with path byte-length checks for PAX and GNU metadata targets.
- Added support for global PAX attributes, old-GNU name records, and signed GNU base-256 numeric header fields.
- Updated archive reading in WriteTool to accept a filesystem path instead of buffered bytes.
- Added test coverage for signed GNU base-256 values, PAX extensions, overlong path rejections, and oversized archives.
- Bound PAX sparse record memory overhead by caching sparse markers and specific keys.
- Update system prompt phrasing and tests for tool inventory and date displays.
- Added Google provider thinking configuration parameters and force-reasoning-off controls.
- Implemented MCP SSE stream resumption using Last-Event-ID and `SSEResumeError`.
- Added support for TAR old-GNU sparse extension blocks, path length checks, and archive entry overrides.
- Restricted external thinking support to specific models and added semver fallback parsing.
- Added the `--external-thinking` CLI flag alongside model capability checks to gate external thinking tool availability.
- Updated Anthropic and Google transports to honor `forceReasoningOff` for native thinking-off controls.
- Renamed the `thoughts` property and parameter to `notes` across think fixtures, tools, and tests.
- Updated system prompt instructions and test suites to verify transport-specific thinking and tool activation.
- Added support for external thinking and forced reasoning disablement across AI provider options and request transformers.
- Implemented the private scratchpad think tool along with its renderer, system prompt rules, and schema configuration.
- Updated agent session management and SDK tools to support dynamic runtime activation of the think tool via the externalThinking setting.
- Added comprehensive unit tests covering reasoning fallbacks, tool activation, and rendering behavior.
- Define a centralized `USER_AGENT` constant in `@oh-my-pi/pi-utils` formatted as `omp/<version>`.
- Replace hardcoded and platform-specific user agent strings across AI providers, catalog scrapers, tools, and search providers with the unified `USER_AGENT`.
- Add unit tests for update-cli binary release distribution gating.
- Updated user agent and openrouter titles in packages/ai from Oh-My-Pi to omp.
- Integrated getOpenRouterHeaders into image generation tool requests in packages/coding-agent.
- Updated provider documentation and test assertions to reflect the rebrand.
- Expanded web search and fetching providers with robust parsing, authentication storage integration, and response validation.
- Added support for new configurations including SearXNG safesearch, Cloudflare AI Gateway endpoints, and dynamic Firecrawl base URLs.
- Implemented comprehensive test suites covering error handling, content filtering, and provider-specific response behaviors.
Long write/edit streams made the TUI stutter or freeze for seconds at a
time (ui.loop-blocked warnings, keystrokes starving while the single JS
thread rebuilt previews). Two compounding quadratic paths:
1. parseStreamingJsonThrottled re-parsed the entire accumulated args
buffer on a FIXED 256-byte cadence. The comment claimed this bounded
mid-stream work to O(N), but a constant growth gate still parses an
N-byte buffer N/256 times at O(N) each: O(N^2) with a smaller
constant. The gate now scales geometrically (max(256, len/32)), so
parse points form a geometric progression: O(log N) parses, O(N log N)
total, with mid-stream snapshots staying within ~3% of the stream.
Small buffers keep the exact fixed cadence as before.
2. write.ts formatStreamingContent normalized + split('\n') the WHOLE
accumulated content on every 30Hz reveal tick (renderCall also ran a
full-payload normalize first): O(N) per tick, O(N^2) per stream, per
concurrent writer. The collapsed tail-window path now tracks the
newline count incrementally (append-only resume keyed on the
component's persistent render-state object via WeakMap) and extracts
only the tail window with a backward scan: O(delta + preview lines)
per tick, byte-identical output to the split-based reference. The
expanded (Ctrl+O) path is unchanged in output and skips its
split+join round-trip.
Tests: geometric-gate bounds + freshness + small-buffer cadence in
parse-streaming-json-throttled.test.ts; append-growth/reference-
window/CRLF/trailing-newline/restart battery in
write-streaming-incremental.test.ts. Full write/tool-render battery
(56 tests) and ai streaming-args tests (117 tests) pass.
- 28 symbols across discovery, mcp header policy, agent-hub projection and
rendering, the agent registry, shell tokenizing and changelog comparison
were exported but referenced only inside their own module; they are now
module-private, shrinking the deep-import surface.
- Kept AGENT_PLUGIN_MANIFEST_SCHEMA, AGENT_PLUGIN_MCP_SCHEMA,
parseAgentPluginManifest, clearAgentPluginRootCache and mergeMCPHeaders
exported: each is a seam for tests that defend real parsing or header
precedence behavior.
- Nothing reachable from an explicit exports entry or public barrel changed.
- gh.ts held wire types, search, Actions run-watch, PR checkout/push/create,
PR diff parsing and view fetch/format in 3958 lines.
- Split into gh-types, gh-search, gh-run-watch, gh-pr-checkout, gh-pr-diff,
gh-view and a gh-common module holding the shared primitives and the single
process-lifetime default-repo memo pair; gh.ts is now 246 lines.
- All 22 exports stay on gh.ts because tools/index.ts star-exports ./gh, so
the issue:// and pr:// protocol handlers needed no edits.
- ReadTool mixed plain-file reading with archive, sqlite, pdf-image, summary,
selector, formatting and renderer concerns in one 3763-line module.
- Each now owns a sibling module; read.ts drops to 2020 lines and keeps its
public exports, including the readToolRenderer re-export required because
tools/index.ts star-exports ./read through the explicit ./tools entry.
- The pdfImageExtractions map and summaryParseCaches WeakMap stay single
instances; execute() was deliberately left intact.
While the agent worked through a plan, every sub-todo rendered unchecked
no matter how far along the run was: the phase header highlighted, the
task rows below it looked untouched. Three separate causes, all on the
collapsed path that is the default view.
`selectCollapsedTodos` dropped every closed row while a phase held open
work, so finishing a task only ever *removed* a line — the panel never
rendered a checked box until the whole phase settled. That also made the
card's completion animation dead code: `details.completedTasks` drives a
14-frame strike reveal at 65ms with a component render per tick, against
a row the viewport had already discarded. The existing animation test
missed it by asserting on `expanded: true`.
The viewport now keeps the newest closed task as a checked lead row,
additive to the open-task cap so it never evicts open work, and the
strike sweep lands where users actually see it.
Second, the card gave a `done/total` count to every collapsed untouched
phase but not to the active one, so the phase being worked in was the
single phase reporting no progress. Extracted `formatPhaseProgress` and
put it on every phase header.
Third, the todo auto-clear (`tasks.todoClearDelay`, default 60s) armed
on any list holding a closed task and physically deleted those tasks
from the HUD's copy. An in-flight phase at `3/4` silently became `0/1`
sixty seconds later, fully-closed phases vanished, and stage roman
numerals renumbered off the filtered index — until the next `todo` call
restored the real snapshot. It now fires only once the whole list is
settled, which is the case the setting exists for; the walking viewport
already hides closed rows while work remains.
Progress counters also count closed tasks rather than only completed
ones. The viewport hides abandoned tasks too, so counting only
completions left a phase reading permanently stuck.
When an xd:// device is dispatched through the write tool, the outer
approval gate now consults tools.approval.<deviceName> before falling
back to tools.approval.write. This lets users scope allow/deny/prompt
to a single device mount without changing the blanket write tool policy.
The write tool's approval function returns { tier, policyKey: deviceName }
for xd:// device dispatches. resolveApproval uses the policyKey to look
up the user override on the device name, falling back to the invoking
tool's own policy when the device has none configured.
Adds:
- ToolApprovalDecision.policyKey field (optional, additive)
- policyKey-aware lookup in resolveApproval and requiresApproval
- Updated error messages naming the correct config key
- Unit tests for policyKey resolution and WriteTool integration
Fixescan1357/oh-my-pi#7923
- Runtime error now just says to download vscode-js-debug from its GitHub repo;
tarball recipe, extract path, env var, and Mason detail stay in docs/tools/debug.md.
can1357