- Replaced Bun.sleep with scheduler.wait for Node-compatible cancellable sleeps.
- Added module-level timestamp gate to skip yields within 50ms of the last one.
- Threaded AbortSignal through ExponentialYield.sleep to cancel losing timers in race.
- Added tests covering gate behaviour and stray-timer cancellation.
Fire Pass support:
- New provider with login command 'omp /login firepass'
- Hand-seeded kimi-k2.6-turbo model with Fire Pass router wire id
- pi-ai CLI --help lists firepass
AI provider fixes surfaced during the Fire Pass review:
- service_tier whitelist restored for openai/openai-codex only (was leaking to
Fireworks, Firepass, OpenRouter, Azure OpenAI Responses)
- Anthropic tool schema normalizer collapses {} -> true for additionalProperties
- anthropic.prepareParams fires onPayload after drop helpers so callers see the
real wire body
- isServiceTier type guard narrowed to ResolvedServiceTier
- transformMessages stops dropping orphan tool_result when all pending tool
calls have already resolved
- zodToWireSchema preserves null for non-scalar nullable() inner schemas
- isEmptyObject / isJsonObjectEmpty use Object.keys().length === 0 instead of
prototype-walking for...in
- Telemetry records resolved service_tier (priority) instead of scoped
placeholder (openai-only/claude-only)
- Robomp dirty-state reminder no longer asserts a formatter-failure premise
- Replaced `#pendingDa1Sentinels` integer with `#da1SentinelOwners` FIFO array tracking `"keyboard" | "osc11"` ownership.
- Keyboard and OSC 11 probes now own separate sentinel slots, preventing cross-contamination of DA1 replies.
- Simplified kitty detection to use `\x1b[?u` query-only (dropped `\x1b[>31u` push) so shutdown's single `\x1b[
- Restricted Hangul Compatibility Jamo 1-cell override to macOS in both TS and Rust paths.
- Linux terminals (WezTerm, etc.) honor UAX#11 and render jamo as 2 cells, causing layout corruption with the unconditional correction.
- Updated tests to skip darwin-only jamo assertions off-darwin and parameterize expected widths via JAMO_CELLS.
- Rejected negative values in addition to non-numeric ones, falling back to per-server config or default 30s.
- Emitted a logger warning when an invalid env value is ignored.
- Added tests covering negative and non-numeric rejection cases.
- Extended `buildWellKnownUrls` and `#resolveRegistrationEndpoint` to try `/.well-known//` as a third candidate after origin-root and path-prefixed forms.
- Fixed single-segment path handling so `/my-service` is treated as the gateway prefix rather than dropped.
- Fixed missing `await` on `#tryWellKnownForRegistration` that caused path-prefixed fallback to return an unresolved Promise.
- Added tests for single-segment prefix discovery and RFC 8414 path-ful issuer fallback.
- Adjusted hashline natural-order preview handling so op-insert and op-replace tokens now emit inline body content as payload when available.
- Added an inline-body presence check so those op tokens are skipped only if path or payload is missing for that line.
- Dropped the `fileType: natives.FileType.File` restriction so glob searches can return directories as well as files.
- Updated the find tool prompt to document directory results and trailing-slash output.
- Added tests verifying directory matches are included and emitted with a trailing `/`.
- 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.
- Replaced inline definitive-failure checks with shared isDefinitiveOAuthFailure in auth-storage and refresher.
- Disabled credentials during definitive OAuth refresh failures and captured the disabling cause on the credential row.
- Wrote null usage-cache entries with expiresAt set to 0 when credentials were disabled to prevent stale reports.
- Added tests for invalid_grant and transient OAuth refresh outcomes, including cache and credential-state assertions.
- Updated Unreleased changelog notes to document OAuth refresh fixes and stale usage-cache clearing behavior.
brush_core::interp::setup_open_file_with_contents wrote the entire heredoc/here-string body into an anonymous pipe synchronously before handing the reader to the downstream command. Bodies that exceed the OS pipe buffer (~4 KiB on Windows, 16-64 KiB on macOS) deadlocked the writer forever, and the bash tool tripped its 305 s hard timeout without ever launching the consumer. The Linux fast path still uses F_SETPIPE_SZ to grow the pipe inline; every other platform (and Linux bodies that overflow pipe-max-size) now decouples the write onto a fire-and-forget thread that terminates on drain or BrokenPipe.
Adds a 256 KiB regression test that exercises the worst-case shape (: builtin, which never drains stdin), guarded by tokio::time::timeout(10s) so a regression fails CI fast instead of hanging.
Recursive fuzzyFind walks rooted at `@../`, `@~/`, or `@/abs` can
visit thousands of files in unrelated sibling projects and stall the
editor for seconds before the popup appears. CombinedAutocompleteProvider
now lexically classifies the @ prefix and, when it resolves outside the
project root, short-circuits to plain prefix listing of the immediate
directory — matching Claude Code's behavior. Inside-cwd queries keep
the existing fuzzy-then-prefix flow.
Fixes#1395
- Migrated OAuth provider authentication from standalone `pi-ai` CLI to in-process `AuthStorage.login()` flow in coding-agent.
- Made provider argument optional for `login` and `logout` commands with interactive provider picker when omitted.
- Added `list` command to enumerate registered OAuth providers with optional `--json` output format.
- Removed `pi-ai` CLI binary and `bin` entry from @oh-my-pi/ai package; library API remains unchanged.
- Updated documentation and examples to reflect new `omp auth-broker` command interface and in-process OAuth flow.
Threaded cache freshness/authoritativeness through #loadCachedStandardProviderModels so dropProviderModels only fires when the cached Vertex project-catalog row is both fresh and authoritative. A stale or non-authoritative snapshot (e.g. after ADC discovery failure rewrote the row with authoritative=0) now keeps the bundled Gemini fallback in place, which would otherwise be the last working catalog in API-key-only environments.
Refs #1412
- Updated `TempDirGuard` creation in grep tests to include PID and an atomic sequence, preventing temp path collisions.
- Removed the `branch` filter from GitHub action run queries so results are matched by `head_sha` only.
- Adjusted run-watch calls to the simplified `fetchRunsForCommit` interface without the branch argument.
Preferred the Google Vertex API-key static catalog whenever an API key is configured, even if project and location are also present, so failed or unavailable ADC discovery cannot hide usable Vertex Gemini entries.
Refs #1412
Returned an empty static catalog from the Google Vertex model manager when no ADC project, location, or API key is detected so the bundled Gemini fallback cannot mix into /models alongside an authoritative cached Vertex project catalog on later refreshes.
Refs #1412
Added Google Vertex OpenAI-compatible model discovery with ADC auth and treated authoritative Vertex project catalogs as replacements for bundled Gemini fallbacks in the model registry.
Fixes#1412
- Added detection for OpenCode Zen's big-pickle alias to DeepSeek family checks in OpenAI completions compatibility.
- Mapped big-pickle tool-call handling to require exact reasoning_content replay instead of synthetic content.
- Added a regression test asserting assistant tool-call messages carry empty `reasoning_content` and empty `content` output.
The Hangul Compatibility Jamo width correction (U+3131..=U+318E → 1 cell)
was applied unconditionally, but macOS terminals (Ghostty, Terminal.app,
iTerm2) are the only ones that render jamo as 1 cell. WezTerm and most
Linux terminals follow UAX#11 and render them as 2 cells.
The unconditional correction caused a width mismatch between the TUI's
calculated column positions and the terminal's actual rendering, resulting
in corrupted layout and broken Korean input on non-macOS platforms.
- Rust: gate the correction with cfg!(target_os = "macos")
- TS: gate the correction with process.platform === "darwin"
- On non-macOS, use UnicodeWidthStr for multi-char graphemes (perf)
Constraint: macOS terminals render jamo as 1 cell despite UAX#11.
Rejected: removing the correction entirely — would break macOS.
Tested: native build succeeds, typecheck passes.
Not-tested: visual verification on macOS terminals.
Scope-risk: narrow
Plan-mode subagents (and any subagent with an explicit `agent.tools` array)
were given the `yield` tool in the registry but not in
`agent.state.tools`. The session prompts and idle reminders still
demanded a `yield` call to terminate, so the model would reason
"there doesn't seem to be a yield tool available" and the turn went
nowhere.
`createTools` correctly appends `yield` to the registry when
`requireYieldTool: true`, but `createAgentSession` then derived the
active tool list from `options.toolNames` directly, dropping `yield`
again. Mirror the invariant already enforced in
`parseAgentFields` (discovery/helpers.ts): when `requireYieldTool` is
set and the caller passes an explicit list, append `yield` to it
before normalization.
Fixes#1408
- Extract resource_metadata URL from WWW-Authenticate and follow RFC 9728 chain
- Add buildWellKnownUrls with path-prefixed well-known fallback for gateways
- Fix resolveRegistrationEndpoint to try path-prefixed well-known (was missing await)
- Support relative Mcp-Auth-Server URL resolution against server URL
- Pass resourceMetadataUrl through all discoverOAuthEndpoints call sites
- Add comprehensive tests for path-prefixed, resource_metadata, and relative URL flows
- Replaced external watchdog timers with per-request SDK timeouts for first-event budget across OpenAI, Anthropic, and Azure providers.
- Keyed Python shared kernels by (sessionId, cwd) to prevent cross-directory state bleed.
- Deduplicated concurrent cold-start session acquisition for JS and Python executors.
- Moved `isOpenAIResponsesProgressEvent` to shared module and scoped display output routing per run for interleaved async cells.
