- Updated the nightly rust toolchain channel in rust-toolchain.toml to nightly-2026-07-28.
- Adopted slice chunking and multiple-of helper methods across native and vendor crates.
- Replaced option map adapters and conditional patterns with idiomatic combinators.
- Reworked the `/guided-goal` command to send a hidden interview brief instead of a modal popup flow.
- Removed the deprecated `guided-setup.ts` module and system prompt template.
- Updated goal tool availability and activation logic to support goal creation during the interview.
- Replaced existing tests and added new verification for the updated guided-goal workflow.
- Remove the per-call `save` option from `tab.screenshot()` to simplify usage.
- Update `tab.screenshot()` to return the saved file path as a promise string.
- Configure screenshot persistence to use daemon path or custom `browser.screenshotDir`.
- Add comprehensive tests verifying temp path return and custom directory saving.
- Remove `annotateForStaleness` and `hasFreshBacklog` from the advisor runtime.
- Stop appending staleness warnings to delivered advisor notes when newer primary turns queue.
- Add the `ts-no-local-is-record` built-in rule to detect local `isRecord` definitions and direct agents to shared guards.
- Add unit tests validating detection of local function and lambda definitions for the new rule.
- Replaced getTool with getExecutableTool in CursorExecBridgeOptions to prioritize mounted-device permission wrappers over canonical tools.
- Updated createAgentSession to check isAutoQaEnabled against restricted tool filtering when configuring system prompts.
- Added test coverage verifying execution overrides preserve approval gates and restricted sessions omit auto-qa guidance.
- Treat `403 Forbidden` errors as retryable credential-rotation triggers similar to usage limits.
- Skip refresh-same detours for 403 responses and cycle directly through the sibling credential pool.
- Replaced the `XdevRegistry` class with the `XdevState` interface and pure helper functions across core and session tools.
- Updated session configurations, tool execution, and renderers to utilize canonical tool map initialization and sharing.
- Adapted unit tests and mocks to use `XdevState` and associated helper functions for permission and dispatch verification.
- Raised fs.nr_open from 1,048,576 to 8,388,608 through the Kata guest kernel command line.
- Added a smoke check for guest, soft, and hard open-file limits.
- Documented the cold Bazel sandbox failure mode and lazy descriptor allocation.
- Enhance CI workflows to build and reuse native addon artifacts instead of recompiling.
- Update bazel cache actions with selective backend detection and separate remote and disk modes.
- Add `--source` CLI option to install prebuilt native targets without requiring Bazel.
- Increase Kata runner memory configuration from 12Gi to 24Gi.
- branch() and navigateTree() now return the selected user message's image
parts (selectedImages/editorImages) alongside the text, extracted in marker
order by #extractUserMessageImages.
- CustomEditor.setDraft() replaces the composer draft with text plus its
pending images, so restored [Image #N] markers resolve on resubmit instead
of degrading to literal text.
- Wired all six restore call sites (selector-controller, extension-ui-controller)
through setDraft; updated rpc-subagents mocks for the new branch shape.
- Added offline regression tests for branch/navigateTree image restitution,
multi-image marker order, and text-only prompts.
- The inspect_image availability contract treats a session with neither
isToolActive nor xdevRegistry as mode-resolved (auto + unknown model =>
metadata-only reads); the local:// image stub must report the tool
inactive so the read keeps inlining image blocks.
- The 2s deadline returned the -999 kill sentinel when a cold bun spawn
transpiling the pi-utils module graph exceeded it on loaded parallel CI
runners; green runs still resolve on child exit, so the bound only
guards genuine hangs.
- read now treats an xd://-mounted inspect_image as available (top-level
predicate OR mounted device gated by the effective mode), so default
xdev sessions with a text-only model keep metadata-guidance reads
instead of inlining images the provider boundary would scrub
- advisor tool session stops inheriting the primary's isToolActive and
xdevRegistry: advisors cannot execute xd:// devices, so their reads
inline images again
- setModelWithProviderSessionReset is now async and awaited at every
callsite, so retry-fallback model switches cannot race the
inspect_image tool-slate reconcile
- regression tests for both xd:// availability directions
- Added `prepareToolCallDispatch` and `PreparedToolCall` to handle argument validation and `beforeToolCall` before message snapshotting.
- Implemented `preparedDispatchByMessage` WeakMap to store pre-dispatch results for streamed messages.
- Updated `executeToolCalls` to consume pre-computed dispatch preparation results.
- Updated documentation and changelog to specify `beforeToolCall` timing on the streamed path.
- Added a prepareToolCall phase to the agent loop running before tool scheduling for validation and hooks.
- Updated BeforeToolCallContext and result types to support argument replacement instead of in-place mutation.
- Updated coding-agent extension handling and runner to track emitted tool calls and re-evaluate approvals on input revisions.
- Added comprehensive test coverage for argument replacement, concurrency resolution, and schema validation.
- read now derives its image behavior from actual tool availability
(session.isToolActive) with the mode computation as fallback, so
restricted sessions whose explicit slate omits inspect_image (e.g.
subagents) never get metadata-only reads pointing at an absent tool
- reconcile passes the post-change availability into the read
description sync, keeping the advertised prompt correct across flips
in both directions and when tool construction fails
- flat quoted-dotted inspect_image.mode is normalized into the nested
target during migration instead of being silently dropped when a
legacy flat enabled key is present
- regression tests for all three: availability-driven read behavior,
flat+flat migration, description advertising
- Reconcile inspect_image centrally from setModelWithProviderSessionReset
so retry-fallback model changes (turn-recovery.ts) that bypass
syncAfterModelChange cannot leave a stale tool set
- Apply persisted inspect_image.mode changes immediately from the
settings selector via a new handleSettingChange branch
- Refresh the read tool's advertised description during reconciliation,
before applyActiveToolsByName rebuilds the prompt, instead of only
lazily on the next image read
- Fix the flat (quoted-dotted) enabled->mode migration to write the
nested target form the resolver actually reads
- Add committed regression tests: tri-state x capability matrix,
override precedence, and enabled->mode migration (nested, flat, and
explicit-mode-wins)
Replace the inspect_image.enabled boolean with inspect_image.mode
(auto|on|off, default auto). In auto the tool is registered only when
the active model lacks native image input, so vision-capable models
(e.g. kimi-code/k3) read images inline with their own capabilities
instead of delegating to a separate vision model. on/off force
registration regardless of model capability.
- New utils/inspect-image-mode.ts resolves the effective state from the
/vision session override, the persisted setting, and model capability
- read tool re-evaluates the effective state per image read and
re-renders its description, so it returns decoded image blocks again
whenever inspect_image is hidden
- /vision [on|off|auto|status] slash command (modeled on /computer)
overrides the mode for the current session only
- Tool set is reconciled on model switch with a status notice when
inspect_image appears/disappears
- Legacy inspect_image.enabled true/false migrates to mode on/off
- Render device doc parameter schemas as TypeScript types instead of raw JSON schema dumps.
- Optimize marked streaming block rules and add pre-gates to reduce CPU overhead.
- Increase the markdown render cache entry budget from 32 KiB to 256 KiB.
- Added V8 `.cpuprofile` parser and bottleneck summary generation utilities.
- Integrated profile summary rendering into the read tool execution.
- Refactored profile rendering machinery into shared tree utilities.
- Added comprehensive unit and integration tests for cpuprofile parsing and read tool dispatch.
- Add an LRU cache to `scanSessionFile` in `session-listing.ts` keyed by file path, stat identity, and scan mode.
- Add a match key union probe in `CustomEditor` in `custom-editor.ts` to bypass per-action lookups on plain text input.
- Add tests covering cache hits, size and mtime invalidations, and negative result caching.
- Added a new parser and bottleneck summary renderer for macOS `/usr/bin/sample` reports with symbol demangling.
- Integrated automated summary parsing for sample reports into the ReadTool.
- Updated model configurations and pricing parameters across multiple providers.
- Added comprehensive unit and integration tests for sample profile parsing and ReadTool integration.
- 3d9f28dd46 changed pi-walker Cargo.toml dependency features without
CARGO_BAZEL_REPIN, so crate_universe failed the digest check and CI
could not start the rust workspace validation.
- Restructured the user interjection prompt to use a system-notice envelope instead of nested message tags.
- Updated associated tests to verify the new system-notice formatting for steering messages.
- Add conditional attributes to silence dead-code warnings on platform-specific code and fields.
- Update target dependencies in pi-walker/Cargo.toml with explicit windows-sys feature sets.
- Simplify time cast expressions in linux_reflink and rcopy modules.
- Native (non-mcp://) resource URIs now pass through byte-for-byte via
rawHref; slash elision applies only to the legacy mcp:// wrapper, so
catalog://root/ style URIs match exact-equality server lookups.
- resources/templates/list failure no longer discards a successful
resources/list (Promise.allSettled; templates retried later).
- Opaque RFC 3986 URIs (urn:doc, custom:item) are recognized by both
the router and read-cli discovery gates, with drive-path and
read-selector false positives guarded.
- Review follow-up for PR #6790.
- task.maxEffort only clamped the initial thinking level; a retry
fallback candidate could clamp back up to its model floor and run a
low-capped spawn at high.
- The ceiling now rides the session as thinkingLevelCeiling: clamped in
ModelControls (constructor, setThinkingLevel, auto classifier,
restore) and in applyRetryFallbackCandidate; fallback candidates whose
floor exceeds the ceiling are skipped.
- Effort value import moved to @oh-my-pi/pi-catalog/effort; changelog
attribution added.
- Review follow-up for PR #6794.
- Added a suppress load option so disabled servers still claim their
capability key: a project foo with enabled:false shadows a same-named
enabled user foo again, while scope-removed entries drop fully.
- Tool-name collisions now resolve by stable server+tool origin key
instead of manager array order, so reconnect re-appends cannot flip
the routed implementation.
- Review follow-up for PR #6787.
- kill -l -- 9 printed the whole signal table because the -l branch read
only pre-marker args; listed_signals() now chains both collections
without allocation and print_signals takes an IntoIterator.
- Review follow-up for PR #6780.
- Dropped the terminal split artifact so repeated saves no longer grow a
blank line per write.
- Replaced the partition-and-concat merge with an ordered line list:
headings, prose, and footers keep their positions; new lessons insert
at the head of the first bullet run and the cap trims oldest bullets.
- Strengthened tests to byte-exact idempotence and mixed-Markdown order.
- Review follow-up for PR #6774.
- WT_SESSION leaks into tmux/screen/Zellij panes, so the automatic raw
0x08 -> ctrl+backspace override deleted a word on plain Backspace.
- The heuristic now requires isWindowsTerminalSession() and not
isInsideTerminalMultiplexer(); PI_TUI_RAW_BACKSPACE_IS_CTRL=1 stays an
unconditional opt-in.
- Review follow-up for PR #6784.
- Retargeted the dynamic-only regression test at source-owned
CATALOG_PROVIDERS instead of the generated models.json type.
- Reused withCatalogDiscoveryTimeout for the models.dev lookup so the
timer clears on success.
- Deferred bundled-model reference index construction into the dynamic
fetch, keeping the ModelManager cache fast path free of a 12K-model
walk.
- Review follow-up for PR #6765.
can1357