Loaded Kokoro's side-installed transformers runtime by absolute path before requiring kokoro-js, avoiding host/workspace onnxruntime libraries in the worker process.
Kept runtime-cache bare module requests inside the registered runtime cache when the parent module is already inside that cache, and covered the resolver boundary with a regression test.
Fixes#2591
Adds regression coverage the PR's stated 'bounded retries' contract
needs but lacked: gives up after the 4-retry bound and rethrows the
original EBUSY (no infinite loop, no masking), skips non-transient
codes, and never retries off Windows. Also adds the missing final
newline biome required on the new test file.
Addresses review feedback on #2382.
- Added unified `omp setup speech` flow with JSON/check modes and model picker.
- Added local STT pipeline with sherpa workers, recorder/download flow, and streaming inference.
- Added local TTS pipeline with `omp say`, backend selection, and streaming vocalization.
- Replaced legacy speech settings with unified `speech`/`speechgen` configuration keys.
Always-on LoopWatchdog (armed in TUI.start/stop) logs ui.loop-blocked with blockedMs and the current loop phase on the rising edge of a late probe tick. New pushLoopPhase/popLoopPhase/currentLoopPhase stack in pi-utils feeds it; breadcrumbs at in-process subagent dispatch (subagent:<id>) and the SelectList fuzzy filter (ui.select-filter) attribute residual main-thread stalls.
- Reworked createAbortableStream to forward abort signals to the source stream reader.
- Added cleanup logic so abort/cancel/error paths release locks and emit AbortError consistently.
- Updated related tests to verify source-stream cancellation and handoff escape-handler behavior.
- Added isMacosMallocStackLoggingEnvName() function to identify MallocStackLogging and MallocStackLoggingNoCompact variables. Updated filterProcessEnv() and Bun.env initialization to skip these variables during environment filtering. Added test case to verify malloc stack logging toggles are dropped instead of forwarded.
- Moved `fastembed` and `onnxruntime-node` to optional peerDependencies.
- Fixed bundled installs that could not resolve `onnxruntime_binding.node`.
- Added shared `runtime-install` utilities for on-demand module resolution.
- Added tests for runtime-resolution parsing and exact peer-version checks.
The format-on-write path sent a hardcoded {tabSize:3, insertSpaces:true}
on every textDocument/formatting request from two duplicated DEFAULT_FORMAT_OPTIONS
constants. Servers that honour tabSize for re-indent (yaml-language-server, the
common YAML/Kustomize/Flux case) reserialized 2-space files at a 3-space stride
on every write — exactly the corruption reported on Kubernetes/Flux YAML repos.
Replace both constants with a single resolveFormatOptions(filePath, content)
helper that layers, in order:
- .editorconfig (indent_style, indent_size, tab_width) via the new
getEditorConfigFormatting() helper in pi-utils — strict, no fallback.
- Indent sniffed from the in-memory content the agent is about to write
(first indented line decides spaces vs tabs; GCD of space-indent widths
fixes the unit).
- Hardcoded 2-space fallback. The previous 3-space stride was an unusual
default that actively damaged every file with a 2/4-space convention.
Tests cover the editorconfig and content-sniffing paths plus a direct
regression check that 2-space YAML stays 2-space (the issue's repro).
Fixes#2329
- Added a new @oh-my-pi/snapcompact package and redirected compaction call sites to it.
- Added provider-aware snapcompact shape resolution for model-specific mixed-frame behavior.
- Added optional image detail support by extending ImageContent and passing hints through OpenAI providers.
- Added native snapcompact render options, including 5x8/8x8 font loading and palette/geometry controls.
- Fixed help rendering so `--help` no longer triggers unrelated command loaders.
- Fixed startup span logging to emit markers only with PI_DEBUG_STARTUP set.
- Fixed logger startup trace behavior for `:start`, `:done`, and `:fail` phases.
- Fixed prompt template processing with cached raw-template compilation and safer formatting.
- Optimized symbol and tag parsing in prompt templates via manual parsers.
- Packed id via one BigInt hex format instead of four 16-bit segments (~1.7x faster).
- Extracted timestamp via exact double arithmetic, dropping BigInt round-trip.
- Lazily initialized the default source.
- Added round-trip and ordering tests across packing boundaries.
- Moved the overlong-component guard to run after resolveFilePath so syntactically noisy but valid paths like long/../src/file.ts still honor editorconfig rules.
- Added a regression test that proves normalized paths with an eliminated overlong component resolve the configured tab width.
Fixes#1872
- Tightened parseCachedEditorConfig to absorb any FsError, not just
ENOENT. Editorconfig lookup is best-effort indentation hinting; an
unreadable .editorconfig (ENAMETOOLONG, ENOTDIR, EACCES, ELOOP,
EINVAL, …) means "no usable config here", not a fatal condition for
callers like the edit renderer.
- Added a path-component length gate (NAME_MAX = 255 bytes) in
getIndentation that short-circuits to the default tab width before
any syscall. Renderers can hand arbitrary strings into replaceTabs
(e.g. a malformed edit tool call whose file_path is gibberish);
attempting to open <dir>/.editorconfig for a 500-byte component
would otherwise crash the TUI with an uncaught ENAMETOOLONG.
- Added regression tests covering both safety nets.
Fixes#1872
parseCachedEditorConfig caught only ENOENT, so an oversized path segment
(e.g. a 2KiB garbage string emitted by a hallucinating model) blew up
the renderer with an uncaught ENAMETOOLONG from fs.readFileSync. The
editorconfig probe is best-effort — there is no useful difference
between 'file missing' and 'open() refused for any other reason' from
the renderer's perspective. Catch every error, cache the miss so we do
not re-probe the same bogus path on every redraw, and add a regression
test that exercises the 2KiB-segment path through getIndentation.
Fixes#1871
Move the color math added for the session-accent fix into the shared
@oh-my-pi/pi-utils color module instead of a coding-agent-local file:
- colorLuma, relativeLuminance, and hslToHex now live in
packages/utils/src/color.ts (hslToHex lifted out of session-color.ts).
- Drop the duplicate hex parser: toRgb reuses the existing hexToRgb and
paletteToRgb returns the shared RGB type, so hex parsing lives once.
- Delete packages/coding-agent/src/utils/color.ts; theme.ts and
session-color.ts import from @oh-my-pi/pi-utils.
- Move the color unit test into the utils package; repoint session-color
test imports.
No behavior change to accent luminance capping.
- Classified each session's final message as done, interrupted, aborted, error, or pending from a 32 KiB tail read.
- Rendered the status as a colored segment on the session metadata line.
- Added `peekFileTail` and `readTextSuffix` across storage backends to read file tails in one pass.
- Simplified `MemorySessionStorage` to a string array mirror with a sidecar mtime map.
- Clamped `formatDuration` to return `0ms` for non-positive, NaN, or infinite inputs.
- Updated usage report rendering to suppress reset countdowns when `resetsAt` is absent or no longer in the future.
- Added unit tests for `formatDuration` covering clamped values and standard duration formatting.
- Added a custom JSON replacer that unwraps `Error` instances in logger output, preserving name, message, stack, cause, and enumerable fields.
- Updated uncaught-exception and unhandled-rejection logging paths to pass only `{ err }`, relying on the logger serializer for full error details.
- Extended transient socket-close matching to detect HTTP2 stream reset/refused/calm errors and added regression tests for logger error serialization behavior.
- Restructured the auth-broker `openSnapshotStream` tests to be top-level cases under the describe suite.
- Added a stream parser test asserting pure ": keepalive" lines are not included in subsequent SSE event raw output.
The Bun.env scrub and filterProcessEnv used isValidEnvName (strict shell
identifier shape), which deleted standard Windows variables like
ProgramFiles(x86) and CommonProgramFiles(x86). procmgr.ts imports this
module before resolving the shell and reads Bun.env['ProgramFiles(x86)']
to find Git Bash under 32-bit Program Files, so installations that only
had Git there were no longer discovered and failed with 'No bash shell
found'.
The unsafe cases for native execve are '=' or NUL in names and NUL in
values, not parentheses. Introduce isSafeEnvName covering exactly those
cases and use it for the in-place Bun.env scrub and the spawn-env
filter. Keep isValidEnvName (strict) for dotenv parsing, where strict
shell-identifier shape is the right contract.
- Introduced `FetchImpl` type with optional `preconnect` to accept non-Bun fetch implementations without type errors.
- Applied the new type across all providers and `StreamOptions.fetch`.
- Added tests verifying fetch override routing for openai-completions, openai-responses, and fetchWithRetry.
Adds an opt-in onSseEvent callback across HTTP-streaming providers (Anthropic, OpenAI Responses/Completions, Azure OpenAI Responses, OpenAI Codex SSE, Google Gemini CLI, GitLab Duo, Kimi, Synthetic) so callers can inspect raw SSE frames without altering parsed output. Provider fetch wrapping only tees response bodies when an observer is wired; standalone packages/ai consumers without onSseEvent are not penalized.
Adds streamIdleTimeoutMs (env: PI_STREAM_IDLE_TIMEOUT_MS, with PI_OPENAI_STREAM_IDLE_TIMEOUT_MS as a backward-compatible alias). Anthropic now enforces a steady-state idle watchdog (default 120s) in addition to the first-event watchdog. OpenAI Responses, Azure Responses, and Codex (SSE + WebSocket) gain a semantic-progress predicate so response.in_progress-style keepalives no longer keep stalled tool calls alive forever.
Adds a coding-agent debug-panel raw SSE viewer backed by a per-session bounded buffer (1000 records / 512KB) that AgentSession populates unconditionally so users can post-hoc inspect a stuck stream from the TUI.
- Added `readSseEvents` and `ServerSentEvent` exports in utils for reusable SSE stream parsing.
- Replaced Anthropic's local SSE parser with shared `readSseEvents(response.body, signal)` decoding.
- Updated abort handling in agent stream loop to race an `ABORTED` sentinel with `responseIterator.next()`.
- Expanded stream tests for `readSseEvents` parsing of CRLF, comments, split UTF-8 chunks, and trailing events.
- Extracted tab width resolution from pi-natives to pi-utils with EditorConfig caching support.
- Made tabWidth parameter required in native text functions (visibleWidth, truncateToWidth, wrapTextWithAnsi, sliceWithWidth, extractSegments).
- Removed process-wide tab width state management from pi-natives text module.
- Consolidated wrapper node promotion logic in chunk classification with abbreviated string representations.
- Removed path-clean and pathdiff dependencies from pi-natives.
- Updated all consuming packages to import tab width functions from pi-utils and pass explicit tabWidth parameters.
- Fixed file not found error handling in auto-generated marker detection to gracefully return undefined instead of propagating errors.
- Made assertEditableFileContent function synchronous to simplify API and improve error handling consistency.
- Updated test assertions to match synchronous function behavior using toThrow instead of rejects patterns.
- Removed obsolete test case for doc comment preservation during replace operations.
- Extracted image metadata detection and MIME type utilities to @oh-my-pi/pi-utils package for shared use across projects.
- Consolidated image-input.ts and mime.ts modules into image-loading.ts with simplified API removing redundant metadata parameters.
- Updated all import paths across coding-agent to use readImageMetadata from @oh-my-pi/pi-utils instead of local utilities.
- Added peek-file utility module to @oh-my-pi/pi-utils with buffer pooling for efficient file header reading.
- Migrated native bindings from TypeScript wrappers to NAPI-RS generated modules with auto-generated type definitions and runtime enums.
- Replaced chunk tree API with stateful ChunkState class supporting render, edit, and resolve operations with improved error handling.
- Converted callback signatures to error-first pattern (error, result) for shell, PTY, glob, and grep operations.
- Introduced type-safe enums for MacOSAppearance, GrepOutputMode, KeyEventType, ImageFormat, and AstMatchStrictness replacing string literals.
- Refactored chunk tree implementation with dedicated modules for edit, indent, resolve, and state management with comprehensive validation.
- Moved clipboard utilities from native bindings to coding-agent package with improved OSC 52 and Termux compatibility.
- Added a `display.tabWidth` setting to control default tab rendering.
- Integrated `.editorconfig` resolution for c ontext-aware tab indentation.
- Updated native text processing to use the resolved tab width for calculations.
- Improved tab visualization in diffs and other UI elements for consistency.
- Migrated timing instrumentation from custom utils/timings module to centralized logger.time() and logger.timeAsync() methods across coding-agent and natives packages.
- Removed PI_DEBUG_STARTUP environment variable and debugStartup() function, consolidating debug output to logger.debug() for conditional logging.
- Replaced custom TextDecoder buffer decoding with native toString('utf-8') method in natives package for simplified string conversion.
- Added RingBuffer<T> circular buffer implementation to pi-utils with comprehensive test coverage for efficient queue operations.
- Enhanced logger interface with time() and timeAsync() methods providing unified operation timing and performance tracking across packages.
- Added `sanitizeText` function to pi-natives that strips ANSI escape sequences, removes control characters and lone surrogates, and normalizes line endings.
- Moved `sanitizeText` function from `@oh-my-pi/pi-utils` to `@oh-my-pi/pi-natives` for better code organization and native performance.
- Added line length clamping (4000 characters) to bash and Python execution output to prevent excessively long lines.
- Replaced internal `#normalizeOutput` methods with `sanitizeText` utility function in bash and Python execution components.
- Fixed bash interactive tool to gracefully handle malformed output chunks by normalizing them with `sanitizeText`.
- Simplified documentation by removing WASM terminology from package descriptions and comments.
- Removed createAbortablePromise function and inlined Promise.withResolvers usage in untilAborted for simpler abort handling.
- Replaced Bitmap class with simpler Uint8Array lookup table for whitespace detection in SSE parsing.
- Fixed subarray calculation in ConcatSink.pullJSONL to use correct read offset instead of computed remainder.
- Simplified copyWithin call in ConcatSink.pullJSONL to use read offset directly.
- Changed String.replace with regex to replaceAll for carriage return removal in sanitizeText.
- Removed unused test utilities and test cases for TextDecoderStream.
- Extracted stream abort handling into dedicated `createAbortableStream` utility function for reuse across stream operations.
- Refactored `sanitizeBinaryOutput` to handle surrogate pairs correctly and filter additional control characters (DEL and C1 control block) with lazy array allocation.
- Simplified JSONL parsing by replacing manual buffer management with new `pullJSONL` generator method in ConcatSink class.
- Removed unused `createSanitizerStream` and `createTextDecoderStream` helper functions that are no longer needed.
- Refactored `readSseJson` to use generator-based line processing with fast-path optimization for OpenAI-style done markers.
- Updated stdio transport to use new `readJsonl` utility instead of manual JSON parsing with TextDecoder.
roboomp