- Mark demoted thinking blocks with a symbol to decouple paragraph separators from the raw text content.
- Update `openai-completions` to conditionally insert a newline only when a demoted thinking block is followed by other content.
- Ensure terminal demoted thinking blocks are trimmed to prevent trailing whitespace that causes rejection by the Anthropic API.
- Implemented classifyJsonPrefix to categorize buffers as complete, valid prefix, or invalid based on RFC 8259 strictness.
- Added utility to support disambiguation of identifierless streaming tool-call deltas during model response processing.
- Validated classifier logic with comprehensive suite covering nested structures, escape sequences, and strict formatting rules.
- Added support for parsing unquoted bareword strings in object and array value positions.
- Implemented safety checks to prevent bareword recovery from masking structure, consuming non-finite atoms, or swallowing valid JSON delimiters.
- Included logic to preserve URL-style and Windows-style paths containing colons while rejecting invalid or ambiguous syntax.
- Extracted the `tls-fetch` implementation and tests from `@oh-my-pi/pi-ai` to `@oh-my-pi/pi-utils`.
- Exported the `wrapFetchForExtraCa` and `withExtraCaFetch` utilities publicly from `@oh-my-pi/pi-utils`.
- Introduced `ExtraCaError` to replace the AI-specific `ValidationError` for missing `NODE_EXTRA_CA_CERTS` paths.
- Updated imports in `packages/ai/src/stream.ts` to consume the relocated utility.
- Added preprocessing to quote ambiguous plain scalars containing a colon-space sequence when standard YAML parsing fails.
- Preserves the parsed types of unaffected fields and prevents fallback warnings for common unquoted description strings.
- Added tests to verify successful recovery of unquoted values and continued fallback warning coverage for unrecoverable syntax.
- Restored the fetchWithRetry early return for Retry-After and quota hints larger than maxDelayMs.
- Added coverage so oversized provider retry hints do not sleep and retry internally.
- Introduced `isProbablyBinary` utility to sniff file headers for NUL bytes or invalid UTF-8 sequences.
- Updated `ReadTool` to use the binary sniffer, preventing mojibake corruption in output when reading non-text files.
- Refined `file-mentions` auto-reads to skip binary files and mark them as `binary` in the message transcript.
- Added comprehensive unit tests for binary detection logic, covering NUL bytes, truncated multibyte characters, and path-based file sniffing.
Rejoined split Windows extension module paths before launch parsing finishes and stripped extended-length Win32 prefixes before Bun import and worker spawn APIs see them.
Fixes#3804
Bun's `Response(stream).bytes()` returns the raw `ArrayBuffer` once the
body arrives in more than one chunk, which happens for subprocess stdout
past ~128 KB. The public contract of `ptree.ChildProcess.bytes()` is
`Promise<Uint8Array>`, and callers — most visibly the `ssh://` read
path's `decodeUtf8Text` — rely on `Uint8Array` methods such as `.indexOf`
and `.subarray`. On larger remote text files this surfaced as:
TypeError: bytes.indexOf is not a function
Normalize the result at the boundary: when `Response.bytes()` hands back
an `ArrayBuffer`, wrap it in a zero-copy `Uint8Array` view before
returning. Adds a regression test that drives a 256 KB stdout payload
through `ptree.spawn(...).bytes()` and asserts the contract.
Fixes#3712
The #3348 change is a single retry-window constant (25->50ms); the test asserted
it via mock.module("node:fs") + process.platform/Bun.sleepSync mutation, which
AGENTS.md bans (leaks across the full suite). The retry-on-EBUSY loop already has
coverage; a config constant does not warrant a global-mutating test.
- Centralized JSON parsing and stream processing logic by moving utilities from `packages/ai` to the shared `@oh-my-pi/pi-utils` package.
- Standardized import paths for JSON parsing and streaming across the agent, ai, and coding-agent packages.
- Refactored SSE stream handling to use consolidated `parseStreamingJson` logic and introduced robust error recovery for malformed container-shaped tail events.
- Cleaned up legacy bundled registry references and updated related module exports and tests to reflect the new utility structure.
- Set logger to silent mode when no transports are active to avoid "no transports" errors during log emission.
- Added a regression test to verify that disabling all transports suppresses warnings and that log output resumes after re-enabling transports.
- Corrected TTY property restoration to properly delete injected properties instead of redefining them as truthy values.
- Updated environment restoration to modify process.env keys individually to prevent breaking environment object reference bindings.
- Prevented pollution of TTY-gated code and environment variable state across test suites.
- Pin colorMode to none in golden test suites to prevent nondeterministic ANSI escape sequences.
- Normalize render calls across test files to ensure stable output comparison.
- Prevent test flakes caused by environment-specific TTY auto-detection in the renderer.
Snapshot and restore PI_CODING_AGENT_DIR, OMP_PROFILE, PI_PROFILE, and
XDG_CACHE_HOME instead of relying on setAgentDir(originalAgentDir), which
cannot restore previously-unset or profile-derived env state. Reset the
profile snapshot and rebuild dirs from env in cleanup to prevent
suite-order pollution.
Also reject empty cached content in parseCacheEntry() to harden the
cache contract against corrupted/empty entries.
Repeated reads of unchanged PDFs, Office documents, and EPUBs re-ran the
full markit conversion every time. Add a transparent, content-addressed
cache for successful conversions keyed by SHA-256(content) + normalized
extension, so repeat reads reuse converted markdown instead of
reconverting.
- packages/utils: XDG-aware getDocumentConversionCacheDir() helper
- coding-agent: markit-cache module (bounded 256 MiB, oldest-first prune,
best-effort writes that never fail conversion) layered over the central
convertFileWithMarkit/convertBufferWithMarkit wrappers
- imageDir conversions stay uncached (cache:"skipped") to preserve PDF
image extraction side effects; failed/empty/aborted conversions are
never cached
- abort-safe: file byte reads run under untilAborted; cache I/O rechecks
the signal
- Introduced `abortableSource` as a lighter, direct-reader async generator.
- Removed the `createAbortableStream` public API to eliminate unnecessary stream wrapper layers.
- Updated internal stream processing to use `abortableSource` for improved memory and performance.
- Added `safeSend` helper wrapping `Subprocess.send()` so sync throws and async EPIPE rejections cannot escape.
- Replaced inline try/catch send wrappers in STT, TTS, and tiny-title clients with shared `safeSend`.
- Added `isIpcSendEpipe` predicate and made matching rejections non-fatal in the `unhandledRejection` handler.
- Added contract tests for `safeSend` and `isIpcSendEpipe` covering sync throws, async rejections, and edge cases.
- Removed configurable tab width support and the `display.tabWidth` setting across all packages.
- Deleted obsolete utility functions `getIndentation`, `getIndentationNoescape`, and `setDefaultTabWidth`.
- Standardized tab expansion logic to use a fixed `DEFAULT_TAB_WIDTH` globally.
- Cleaned up related configuration schemas, test suites, and internal API signatures to remove path-dependency.
- 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.
- Fixed OAuth credentials to keep unknown fields in schema while preserving existing shape checks.
- Fixed MCP OAuth IDs to be profile-scoped and avoid deleting credentials from non-active profiles.
- Fixed string-flag parsing so PROFILE_BOOTSTRAP_BOUNDARY tokens are not consumed as values.
- Fixed active-profile directory resolution to refresh after env updates so profile .env overrides apply.
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.
can1357