F6: defer the JSON -> YAML migration out of ConfigFile's constructor and
add an async path so the boot sequence stops blocking the event loop on
sync I/O. New ConfigFile.tryLoadAsync/loadAsync/loadOrDefaultAsync/
getMtimeMsAsync and static ConfigFile.warmup. The migration is now
idempotent (per-process cache) so relocate() does not re-run it.
ModelRegistry.create(authStorage, modelsPath?) is a new async factory
that runs the warmup before the sync constructor's bundled-model load.
Production call sites (main.ts, sdk.ts, task/executor.ts, commit
pipelines, SDK example) all switched. Sync new ModelRegistry(...)
constructor is still supported for tests.
F2: rewrite MemorySessionStorage's mirror as { chunks: string[]; byteLen;
mtimeMs } so writeLineSync appends a single chunk in O(1) instead of
read-modify-writing the entire file (which was O(N) per append, O(N^2)
per session). statSync now reports true UTF-8 byte length instead of
character count. readTextPrefix walks chunks until the byte budget is
exhausted instead of materialising the full mirror.
Also rolls in per-package CHANGELOG entries for F1-F8.
F3 (agent): mutate state.messages and state.pendingToolCalls in place on
appendMessage/popMessage/clearMessages/reset/tool_execution_start/_end
instead of allocating a fresh array/Set on every transition. Subscribers
that capture state.messages by reference now observe updates directly.
Public type signature unchanged.
F5 (ai): add parseStreamingJsonThrottled to utils/json-parse — a per-delta
wrapper around parseStreamingJson that skips the re-parse until the
buffer has grown by minGrowthBytes (default 256). Wired into every
provider's tool-call argument accumulator (anthropic, amazon-bedrock,
openai-completions, openai-codex-responses, openai-responses-shared) so
per-delta cost becomes O(N) in total buffer length instead of O(N²).
Every provider's toolcall_end still runs a final unthrottled parse, so
the published block.arguments is unchanged.
F8 (coding-agent): drop the per-delta structuredClone of streaming tool
arguments in ToolExecutionComponent.updateArgs. event-controller.ts and
ui-helpers.ts already spread their input into a fresh object on each
delta, so cloning here was dead work on the rendering hot path. Added a
reference-equality short-circuit so repeat calls with the same args
object skip the preview-diff and display refresh.
F1 (coding-agent): close the withFileLock mkdir-vs-writeLockInfo race that
let a losing contender wipe the winner's freshly-created lock directory.
Every lock now carries a per-process UUID token; releaseLock verifies the
token before fs.rm, and isLockStale no longer treats an info-less but
fresh dir (or a dir that vanished mid-check) as stale.
F4 (coding-agent): sanitize tabs and truncate oversized error strings in
formatErrorMessage so error renderings that embed file content
(apply_patch, hashline, etc.) cannot break terminal alignment or
overflow the line width.
F7 (ai): support named-tool routing on Google providers. Widens
GoogleSharedStreamOptions.toolChoice and GoogleGeminiCliOptions.toolChoice
to accept { mode: 'ANY'; allowedFunctionNames }. mapGoogleToolChoice
now converts ToolChoice { type: 'tool'|'function', name } to the wire
shape (mirroring mapAnthropicToolChoice). buildGoogleGenerateContentParams
and the gemini-cli request serializer honor the allow-list.
- Updated the internal URL resolution test input pattern to use a new search phrase.
- Updated the expected assertion string to match the revised phrase in command output.
- Changed canonical config path from `keybindings.json` to `keybindings.yml`.
- Added automatic migration of legacy JSON to YAML on first load.
- Retained read support for `keybindings.yaml` without promoting it to canonical.
- Added tests for yml, yaml, and JSON migration scenarios.
- Expanded search scope handling for virtual multi-file targets and executed grep only when searchable paths existed.
- Merged `searchVirtualResources` results into main output and rendered internal URL matches as accent lines.
- Updated grouped-file output to detect URL-like paths and keep full URL headers for root grouping.
- Documented URL path/range behavior and added tests for doc routing, missing-content errors, and `omp://` expansion.
- Added virtual internal URL path resolution in `SearchTool` via `InternalUrlRouter` for in-memory search.
- Added `omp://` root expansion so `search` resolves and scans each completion target.
- Fixed `SearchTool` handling of internal URLs without `sourcePath` by returning virtual matches instead of `Path not found`.
- Extended `edit-renderer.test.ts` coverage for normalizing raw streamed text in custom text renderers.
- Renamed the partial-json helper and removed edit-mode checks so raw streamed text in `__partialJson` is converted to `input` whenever `input` is absent.
- Updated preview, render, and fallback argument preparation to use the shared helper for consistent `input` fallback handling.
- Updated interactive-mode plan review tests to capture shared fixtures, clear references, and run cleanup with explicit garbage collection before disposal.
- Increased the MCP HTTP transport test connection timeout from 200ms to 1,000ms.
- Adjusted the tool streaming command delay and tightened a start-pending-submission spy type in tests for better stability and type accuracy.
- Added helper logic to treat raw non-JSON `__partialJson` values as edit `input` for hashline and apply_patch args.
- Updated edit argument preparation, preview generation, and streaming fallback rendering to use that derived input.
- Added renderer tests verifying raw hashline and apply_patch partial streams render target paths and patch content.
- Added an amend option to the save selector that prompts for feedback and returns amend, rejected, or aborted outcomes.
- When the user chooses amend, the controller regenerated the candidate using prior rule content plus feedback before attempting to save.
- Updated prompt text and interaction tests to pass amendment context into candidate generation and validate the new save/amend flow.
- Added `/omfg <complaint>` command integration from slash registry to mode context and input handling.
- Added OMFG panel and controller for live draft streaming, up to three retries, and confirmed save flow.
- Added strict OMFG rule extraction and validation with JSON parsing, alias checks, and history-based repair.
- Fixed auto-thinking restore to preserve resolved effort instead of reverting to pending auto sessions.
- Auto classification now writes the concrete effort to the session log after the first real user turn.
- Resumed sessions restore the last resolved effort instead of reverting to pending auto.
- Added `dedupeReply` opt-out flag for ephemeral turn reply deduplication.
- Updated hashline preview diffing to route section edits through shared apply/resolve logic and partial streaming parsing.
- Allowed previews to accept live content-hash matches immediately when snapshot records are missing.
- Enabled stale-tag recovery from the snapshot store for anchor-scoped edits and added coverage for snapshot-capture behavior and session-mismatch failures.
- Added a `skipHashValidation` flag to hashline diff options and skipped section hash checks when it is set.
- Updated streaming edit preview generation to set `skipHashValidation` while streaming is active.
- Added streaming preview tests asserting stale hash errors are suppressed during streaming and surfaced after completion.
- Updated footer and status-line rendering so resolved auto-thinking status displays just the thinking level.
- Kept unresolved auto-thinking status unchanged by retaining the existing pending `auto` marker text.
- Changed tiny-device preference resolution to always default to CPU instead of platform-specific DirectML/CUDA heuristics.
- Updated settings schema, documentation, and changelog text to describe the CPU default while keeping accelerated providers behind explicit `providers.tinyModelDevice`/`PI_TINY_DEVICE` choices.
- Updated ACP thought-level resolution to use a helper that prefers session.configuredThinkingLevel and falls back to session.thinkingLevel when unavailable.
- Added a private AcpAgent method to safely compute configured thinking level without assuming a method exists on every session.
- Extended the ACP event-mapper replay test session with configuredThinkingLevel so it follows the new lookup path.
- Added AUTO_THINKING as a configured thinking level in settings, schema, SDK, and session plumbing.
- Implemented per-turn auto reasoning classification with online/local prompts, effort clamping, and skip guards.
- Updated model selectors, ACP options, footer/status UI, and events to render auto and auto->resolved states.
- Added AUTO_THINKING parse/clamp tests and fixed local-module cycle and hashline preview regressions.
The JS eval kernel's LocalModuleLoader linked and evaluated every local
module individually inside the recursive vm.SourceTextModule linker
callback. On any import cycle that re-enters Bun's node:vm linker
mid-instantiation and segfaults JSC (getImportedModule on a null record,
SIGTRAP at 0xFFFFFFFFFFFFFFF8) — e.g. `await import(".../edit/streaming.ts")`,
whose relative-import subtree is cyclic.
Construct the entire local module graph first, then drive a single
link() + evaluate() from the graph root so cyclic graphs instantiate in
one pass. The shared static linker only constructs dependencies;
external (node_modules) modules stay eagerly loaded since they carry no
imports and cannot form a cycle. Failed loads invalidate any
not-fully-evaluated modules so a retry reconstructs them.
Upstream Bun bug: https://github.com/oven-sh/bun/issues/31623
- Removed `trimTrailingPartialLine` from hashline preview path, as the streaming-tolerant parser already handles partial ops correctly; trimming stripped the sole payload of single-op patches, collapsing the preview to "No changes."
- Broadened trailing-section error suppression to apply during streaming regardless of section count, preventing transient mid-typed ops from wiping stable prior frames.
- Replaced fixed calendar timestamps with `minutesAgo()` so beam-store items stay within the 24h working-memory TTL.
- Broadened background-color assertion to match both truecolor (`48;2;`) and 256-palette (`48;5;`) terminals.
- Added persistent settings in the Providers tab for ONNX execution provider and quantization/precision, replacing env-var-only configuration.
- PI_TINY_DEVICE and PI_TINY_DTYPE env vars still override the matching setting at spawn time.
- Added tinyWorkerEnvOverlay to map settings onto worker env without clobbering explicit env vars.
- Updated docs and tests to reflect the new setting-first resolution order.
- Added 14 bundled TTSR rules (TypeScript and Rust conventions) embedded into the binary via the lowest-priority `builtin-defaults` provider.
- Extracted rule bucketing into `bucketRules` with support for `disabledRules` and `builtinRules` settings.
- Added `ttsr.builtinRules` and `ttsr.disabledRules` settings to control which rules are active per session.
- Replaced single-candidate resolution with `enumeratePythonRuntimes`, returning venv, managed env, and system interpreter in priority order.
- Availability check now probes each candidate and falls through to the first that executes, so a stale `uv`-managed Python no longer fails the whole session.
- Kernel spawn reuses the probed runtime from the availability result instead of re-resolving independently.
- Expanded test coverage for enumeration, fallback, and env isolation between candidates.
- Added `PI_TINY_DEVICE` env var to control ONNX execution provider (`gpu` default, `cpu`, `metal`, `cuda`, `dml`, `coreml`).
- Local tiny-model inference now tries accelerated GPU provider first and retries on CPU if initialization fails.
- Added `device.ts` module with normalization, preference resolution, and load-order helpers.
- Updated docs and model descriptions to drop CPU-specific language.
- Added clockwise sweeping dark segment animation to output block borders while bash/eval tool calls are pending/running.
- Changed bash renderCall to immediately render a full bordered block instead of a one-liner status preview, so silent commands show the framed block for their entire runtime.
- Added shimmerEnabled() helper and wired animate flag through OutputBlockOptions, CodeCellOptions, and shell/eval renderers.
- Added unit tests for renderSegmentTrack verifying per-segment coloring, active chip fill formatting, and active-index movement.
- Added tests for theme.getContrastFgAnsi to ensure selected foreground contrast remains clearly readable against RGB fills.
- Removed the OAuth selector keybinding test and its local auth-storage scaffolding, and documented the new model-tier/role-cycle chip-track behavior in the changelog.
- Added a shared `renderSegmentTrack` helper to render colored segment tracks with a filled active chip style.
- Updated hook selector and role-cycle status-line rendering to use the shared track renderer and aligned role-cycle output.
- Added contrast text-color logic to `Theme` so active chip labels stay legible across fill colors.
- Added `replace block N:` syntax in grammar/parser/tokenizer/types, emitting `kind: "block"` edits with empty-body checks.
- Added block-resolution in hashline apply/recovery, wiring `BlockResolver` to resolve edits with throw/drop unresolved behavior.
- Added native `blockRangeAt` support and exported block range/options types through pi-ast, pi-natives, and JS bindings.
- Added coding-agent resolver wiring plus internal visibility/exports updates and new parser, patcher, and setup-wizard tests.
- Added `SetupTab` abstractions and wired Sign-In/Web-Search tabs under the new providers onboarding scene.
- Added `providersSetupScene` and swapped `providerSetupScene` for `providers` in setup-wizard scene registration.
- Added `WebSearchTab` option loading, provider availability checks, and persisted selected search-provider preference.
- Changed sign-in flow handling to keep the scene active across providers and support cancellation during authentication.
- Changed glyph-mode picker initialization and rendering to preselect current preset and show live symbol previews.
- Updated setup wizard tests to use the `providers` scene id and cover the new web search tab path.
- Added setup wizard with provider login, glyph mode, and theme scenes shown once per setup version.
- Wired `omp setup` (no args) to trigger the wizard in a TTY; `--check`/`--json` still show help.
- Extracted `gradientEscape` and exported `PI_LOGO`/`ShineConfig` from welcome for shared use in splash/outro.
- Fixed race condition in `setSymbolPreset`/`setColorBlindMode` by tracking load request IDs.
- Mirrors the alt+p keybinding for switching provider mid-session.
- Added test verifying showModelSelector is called with temporaryOnly: true.
- Updated tips.txt to document the /switch shortcut alongside alt+p.
- Added `stripCodeBlocks` to remove fenced code blocks before titling, preventing literal noise (e.g. version strings in UI mockups) from becoming the session title.
- Added `prepareTitleInput` composing strip and truncate steps, updated `formatTitleUserMessage` to use it.
- Added unit tests for stripping logic and an integration test verifying the model never receives code block contents.
- Removed `scrubProcessEnv` from procmgr and its explicit call in cli.ts.
- Scrubbing now happens automatically when `dirs.ts` is imported, eliminating the need for a manual call at startup.
- Added `omp completions ` command generating scripts from live command/flag metadata.
- Added hidden `omp __complete` helper for dynamic model and session candidates.
- Completions never drift from the CLI: flags, enums, and subcommands are derived from static descriptors.
- Updated read tool prompt to show alternate image description when inspect_image is disabled.
- Passed INSPECT_IMAGE_ENABLED flag into prompt rendering context.
- Added test verifying description omits inspect_image references when disabled.
Allowed live input renders to bypass unknown Windows viewport deferral while preserving the default scrollback protection for background mutations.
Fixes#1550
- Added pending extraction tracking to BeamMemory and a flush loop that waits for queued extraction promises.
- Added Mnemosyne.flushExtractions export and awaited it after forced session retention in coding-agent backend.
- Implemented remember/rememberBatch extraction scheduling with runFactExtraction, skipping empty content and swallowing extraction errors.
- Replaced extractAndStoreFacts insertion logic with storeFactStrings and updated entity counts from its return value.
- Added extraction wiring tests and changelog notes for extraction shutdown and todo animation visibility behavior.
- Added todo_write strike-frame animation timing and updated execution flow after completion finalizes.
- Added strike animation cancellation in cleanup to clear todo timer and reset frames when spinner is idle.
- Removed todo-closing state and timeout handling from interactive mode and simplified empty todo-list rendering.
- Reworked todo-write to compute completion transitions, track completedTasks, and render strike-through frames.
- Added test coverage for completedTasks, theme setup, and strike-through progression at hold-frame thresholds.
- Added a new `providers.memoryModel` setting with tiny memory model options and `ONLINE_MEMORY_MODEL_KEY` default in settings.
- Updated Mnemosyne provider resolution so a configured local tiny model overrode remote completion and used new memory extraction and consolidation prompts.
- Expanded the tiny-model CLI registry to download and report all local tiny models (title plus memory) through a unified list.
oldschoola