Extension commands (e.g. /sonnet) and TypeScript custom commands that
consume the input without calling the LLM return early from
session.prompt() with no agent turn. In ACP mode this left the pending
prompt promise unresolved, hanging the client forever.
Change session.prompt() to return Promise<boolean>: true when the LLM
was invoked, false when the command was fully handled locally.
#runPromptOrCommand calls #finishPrompt immediately on a false return so
the ACP turn completes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
ACP_BUILTIN_SLASH_COMMANDS only carries primary names; the reserved set
passed to getRegisteredCommands was therefore missing aliases like
"models" (/model) and "force:" (/force). An extension registering one
of these aliases would appear in the palette but the builtin would win
at dispatch time (lookupBuiltinSlashCommand searches aliases too).
Export ACP_BUILTIN_RESERVED_NAMES from acp-builtins — the union of all
primary names and aliases for ACP-surfaced builtins — and use it as the
reserved set. Widen getRegisteredCommands parameter to ReadonlySet since
it only calls .has().
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Dispatch in AgentSession runs #tryExecuteExtensionCommand before
#tryExecuteCustomCommand, so the palette must reflect the same order.
Moving the extension-runner block before session.customCommands ensures
that on a name collision the advertised command matches what will
actually execute.
Update the test to assert the extension description wins over the
colliding custom TS description.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Update ordering comment in #buildAvailableCommands to document the
extension tier and explain why skills/custom TS commands intentionally
shadow extension commands (unlike interactive mode)
- Add CHANGELOG entry under [Unreleased]
- Add regression test: verifies extension commands surface in
available_commands_update and that a builtin-colliding extension
command is excluded via the reserved-set, with no duplicates
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
`#buildAvailableCommands` was omitting commands registered by extensions
via `extensionRunner.getRegisteredCommands()`. ACP clients (e.g. Zed)
never saw these in the `available_commands_update` notification, so they
couldn't forward the corresponding slash commands to the agent.
Mirrors the interactive-mode pattern: pass ACP builtin names as the
reserved set so extensions cannot shadow core commands.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The pi-coding-agent prepack (bundle-dist.ts) imports the pi-utils barrel,
which eagerly loads the pi-natives addon; release_npm never downloaded the
linux x64 .node artifacts, so the publish died in prepack. Mirror the
test job's download-artifact step (release runs always rebuild natives in
the same run, so the default run-id resolves).
The streaming-spinner relocation in 61a57c1d2 re-added the trailing
"(preview)" label to expanded approval previews whenever a spinner frame
was active, breaking the #1992 contract. Expanded previews now drop the
label but keep the animated glyph so the volatile tail stays live.
- Applied CREATE_NO_WINDOW and CREATE_NEW_PROCESS_GROUP when spawning Windows child processes to isolate console use.
- Removed per-command Windows flag mutations so process-group/console flags are now applied uniformly in the central spawn path.
- Added a win32-safe terminal write guard that restored UTF-8 input/output codepages before each write when drift was detected.
- Raised Anthropic provider retries to 10 attempts and used a shared jittered exponential backoff for each retry.
- Updated coding-agent retry defaults and session delay calculation to a 500ms base with an 8,000ms jittered cap.
- Added tests that verify capped ten-step backoff sequences and recovery after repeated 502 errors.
- Separated non-contiguous diff regions with a single blank gap row, normalized after block-context insertion.
- Rendered gap rows as one dim ellipsis in the TUI and HTML export.
- Applied the same blank-separator dedupe and edge-trimming to hashline's compact diff preview.
- Added "available" status so recognized servers show under lazy mode without warmup.
- Rendered full welcome box as pre-TUI splash with fixed slot heights to avoid layout shift.
- Reported lazy servers as available in /status instead of omitting the section.
- Replaced minLevel/maxLevel range with explicit efforts array plus baked effortMap/supportsDisplay wire facts.
- Removed runtime enrichment layer and modelOmitsReasoningEffort; providers now read baked fields.
- Fixed dotted Opus 4.7/4.8 ids missing adaptive display via classifier-based predicates (#1373).
- Bumped model cache schema to v4 to invalidate pre-efforts rows.
- Added an `lsp.lazy` boolean setting with default `true` so LSP servers start on first use.
- Updated session startup logic to run LSP warmup only when `enableLsp`, UI is enabled, and lazy startup is disabled.
- Documented the new lazy LSP initialization behavior and defaults in SDK and LSP tool docs.
Route direct model role resolution through the configured pattern normalizer so comma-separated fallbacks are parsed before thinking selectors. Add resolver coverage for preserving :off and trying later entries.\n\nFixes #2228
- Normalized untrusted `questions` arguments by parsing double-encoded JSON strings and skipping invalid question entries before rendering.
- Added option normalization that dropped malformed option items while preserving valid entries in multi-choice rendering.
- Expanded ask tool renderer tests to verify malformed or unparsable questions no longer crash and now fall back safely.
- Renamed `packages/coding-agent/scripts/dev-launch` to `packages/coding-agent/scripts/omp` and updated the preload script reference in that launcher.
- Renamed `packages/coding-agent/scripts/dev-launch-preload.ts` to `packages/coding-agent/scripts/omp.ts` and adjusted its header comment.
- Updated the `install:dev` script in `package.json` to symlink the global `omp` command from the renamed launcher path.
- Centralized catalog and registry handling on `ModelSpec` and `buildModel`, resolving compatibility at model build time.
- Removed runtime compatibility detectors and switched provider request flows to direct `model.compat` reads.
- Added compat fields (`supportsReasoningParams`, `alwaysSendMaxTokens`, `strictResponsesPairing`, `whenThinking`).
- Persisted explicit compatibility overrides through `compatConfig` in discovery and cache merge paths.
Stopped Ollama Cloud dynamic discovery from importing cross-provider context and max-output-token limits while keeping provider-specific bundled metadata.
Honored omitMaxOutputTokens on ollama-chat, sent think:false when reasoning is explicitly disabled, and surfaced HTTP 400 response bodies.
Fixes#2224
- Switched `bin.omp` to `src/cli.ts` so `bun link`/`install.sh --source` work without a build.
- Added `publishBin` override so release rewrites `bin` to the prepack bundle `dist/cli.js`.
- Exported `applyPublishBin` and packed the agent with its published bin in the install smoke.
- Added Windows batch-command detection and COMSPEC-based cmd.exe resolution for MCP stdio spawns.
- Escaped and quoted batch command arguments, then routed .cmd and .bat commands through cmd /d /s /c.
- Updated the stdio transport tests to assert wrapped cmd.exe command arrays and escaping behavior.
- Updated usage-window reporting to track remaining account quota instead of required-account counts.
- Replaced the computed "needed" metric with a non-negative remaining-quota value derived from each window's total minus used fraction.
- Changed usage output lines from "need" to "capacity" and now show used/total accounts with remaining quota multiplier.
- Added catalog-level host/model predicates and compat resolvers.
- Extended compatibility types and model schema with timeout and replay flags.
- Replaced provider-specific heuristics with shared resolver-based checks.
- Updated host/identity and resolver tests to validate the new behavior.
- Added a `pasteText` handler to `HookEditorComponent` to forward non-bracketed OSC 5522 paste text into its inner editor.
- Added a `pasteText` handler to `HookInputComponent` that forwards text to the input and resets the interaction timeout.
- Extended hook editor and timeout tests to cover enhanced-paste payload absorption and behavior retention.
- Added type-to-search filtering across setting labels, IDs, values, and descriptions.
- Preserved selected item focus by ID when replacing settings during an active filter.
- Displayed search status, empty-filter hints, and no-match messaging while searching.
- Updated Escape handling to clear an active query before cancelling the list.
- Applied selection and navigation to filtered items to keep behavior consistent under search.
Resolved the Windows stdio MCP regression by keeping resolved .cmd shims on the direct argv spawn path instead of rewriting them through cmd.exe /c. Added regression coverage for explicit and PATHEXT-resolved codegraph.cmd commands.\n\nFixes #2220
Move bundled models, model cache/manager, thinking metadata, effort helpers,
provider descriptors/discovery, wire constants, and model identity utilities
into the new @oh-my-pi/pi-catalog package.
Update pi-ai to keep provider runtime/auth concerns, move catalog provider
metadata into CATALOG_PROVIDERS, and migrate coding-agent, agent, stats, docs,
and tests to import catalog values from pi-catalog.
Split coding-agent model registry helpers into discovery, roles, and models
config modules while preserving registry orchestration.
BREAKING CHANGE: @oh-my-pi/pi-ai no longer exports catalog subpaths such as
/models, /model-cache, /model-manager, /model-thinking, /effort,
/provider-models*, discovery helpers, and provider wire constants; use the
matching @oh-my-pi/pi-catalog subpaths instead.
- Added a `/stats` builtin slash command that parses `--port` arguments and reports usage errors.
- Added a stats dashboard helper that syncs sessions, reuses a running server, and opens the local dashboard URL.
- Updated the changelog to document the new `/stats` command behavior for active sessions.
- Added auth-storage regression coverage in `packages/ai` for `markUsageLimitReached` returning the earliest sibling unblock time when all credentials are momentarily blocked.
- Added an agent-session retry-cap test ensuring usage-limit 429 retries wait for sibling unblock and succeed within `retry.maxDelayMs` instead of giving up.
- Updated retry-policy docs and both package changelogs to document the sibling-unblock fallback behavior.
- Added lazy async module loaders for @babel/parser, linkedom, puppeteer/browsers, @mozilla/readability, @xterm/headless, and mnemopi to avoid loading them during cold startup.
- Added an interactive startup splash before session construction and skipped it for resume/fork/continue, quiet mode, timing mode, or non-TTY runs.
- Updated JS import-rewrite and memory tests to match async parser loading and preloaded mnemopi modules for sync state helpers.
- Rerouted sync, tab, js-eval, and tiny workers to re-enter CLI modes via `__omp_*` selectors.
- Adjusted `cli.ts` startup to dispatch worker entrypoints before parsing and exit 1 on uncaught errors.
- Bundled CLI as `dist/cli.js` in prepack, switching `omp` binary and published files.
- Removed explicit Bun `--compile` worker entrypoints from build/release scripts in favor of host-entry dispatch.
- Added `declareWorkerHostEntry()` and `workerHostEntry()` environment helpers and `PI_COMPILED` binary detection.
Project-tagged Hindsight mental-model seeds now use project-qualified ids and legacy bare ids only satisfy the matching project tag. The injected mental-model block also filters tagged models to the active project while retaining untagged models.\n\nFixes #2218
- Introduced memoized dynamic import loaders for Babel parser, mnemopi modules, puppeteer, and HTML-related packages.
- Refactored eval import-rewrite helpers and runtime call sites to use asynchronous wrapping and parsing flows.
- Shifted fetch and web-scraper linkedom usage to on-demand imports so heavy modules load only when needed.
- Returned earliest sibling block expiry from markUsageLimitReached.
- Capped usage-limit retry to whichever frees up first, avoiding multi-hour waits.
- Added 1s buffer so retry lands after the block actually lapses.
- Stored last-seen version in ~/.omp/agent/last-changelog-version so version bumps no longer dirty user configs.
- Migrated the legacy config.yml key into the marker, never clobbering a newer existing marker.
- Added read/write helpers and migration tests.
Updated the read tool's provider-visible path schema, prompt docs, CLI help, and internal URL docs so URL and internal URI targets are advertised consistently. Added schema coverage for the read path description.\n\nFixes #2215
- 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.
- AuthStorage now writes the schema version row only when the recorded version differs from the current version.
- Backfill no longer performs UPDATEs for rows with null-derived identity keys, skipping startup no-op writes.
- The bundled model registry now initializes lazily via getModelRegistry(), and a new test verified reopening a current-schema DB does not advance data_version.
- 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.
- Rewrote prescriptive prose to MUST/NEVER/SHOULD/MAY phrasing.
- Pruned internal mechanism the agent can't act on from tool prompts.
- Fixed garbled grammar and a stale plan-title placeholder.
- Made ssh tool description synchronous via cached host info.
- Removed restated warnings, dead `rsed` references, and an internal file pointer.
- Dropped blocked `sed -i`/heredoc commands from the replace bash-alternatives table.
- Factored the shared repo-default clause across `gh` search ops.
- Switched gh job-success icon to the status.success symbol.
