Resolve the explicit interpreter from the session's Settings instance
(ToolSession.settings / AgentSession.settings) instead of re-reading the
process-global Settings.init() singleton, so project-scoped and cloned
session settings take effect. The availability cache is now keyed by
cwd + interpreter, and PythonKernel.start/executePython accept the
resolved interpreter as an option. Also expand home-relative paths
(~/...) before resolving against cwd, and document the contract of
resolveExplicitPythonRuntime.
Addresses review feedback on #2204.
main's CachedOutputBlock.render now returns readonly string[]; the
cache slot added by this PR was still mutable, failing check:types.
Addresses review feedback on #2083.
- Added CredentialRankingStrategy scope hooks so providers can rank and block only the limits relevant to the requested model.
- Scoped Antigravity usage reports by model family: Gemini/Gemma use Google counters, Claude uses Anthropic counters, and GPT/OpenAI models use OpenAI counters.
- Added scoped backoff keys so a Gemini quota block no longer suppresses healthy Claude/OpenAI Antigravity sessions on the same OAuth credential.
- Threaded modelId through coding-agent API-key resolvers and usage-limit rotation paths.
- Added regression coverage proving a Google/Gemini exhaustion block still allows Claude selection on the same credential.
Fixes#2198
Follow-up to the loop guard + artifact cap that addressed the root cause
of issue #2081's runaway captures. The reporter then noted Ctrl+X/Ctrl+C
remaining unresponsive — confirming the secondary symptom: per-keystroke
TUI repaints walked every visible bash row and re-ran `split` /
`replaceTabs` / `truncateToVisualLines` over the stored output. With a
1,000+ message transcript and a 50KB-tail per row, that string work was
what pinned the main thread, not the loop itself.
The eval renderer already caches its computed lines keyed by `(width,
previewLines)` — see `eval-render.ts:709-752`. Mirrored that pattern in
the bash result renderer with a slightly wider key (`width`,
`previewLines`, `expanded`, `rawOutput`, `isPartial`) so the cache is
busted whenever any input that affects the produced lines actually
changes. `invalidate()` continues to clear `CachedOutputBlock` and now
also clears the lines cache, so callers that already drive invalidation
keep working unchanged.
A render() with cache-equivalent inputs is now an array-reference
return; the `CachedOutputBlock` round trip is skipped entirely. New
test in `test/tools/bash-sixel-render.test.ts` pins the contract:
identical inputs → same array reference; width change → cache miss;
invalidate() → fresh array.
Refs #2081
Two pathologies surfaced in the same captured failure (#2081): a subagent
spent 16 minutes hammering 205 `edit` calls (182 byte-identical no-ops)
against a file that already matched its payload, while a sibling bash
invocation persisted 7.6MB of PowerShell rich-object metadata to
`~/.omp/agent/artifacts/<id>.bash.log` from what was intended as a small
tail. Both are addressed independently here:
- Hashline executor now consults a per-ToolSession `noopLoopGuard` that
hashes the raw patch input and tracks consecutive no-ops per canonical
path. After NOOP_HARD_LIMIT (3) repeats of the same payload the soft
"byte-identical" hint escalates to a thrown ToolError, which the agent
loop surfaces as a tool failure rather than success-with-text — far
more effective at breaking the loop than the soft hint alone. A
non-noop commit (or any variant payload) resets the counter; state is
isolated per ToolSession so subagents cannot inherit each other's
history.
- OutputSink artifact-on-disk writes are now bounded by
`artifactMaxBytes` (default 4 MiB = 3 MiB head + 1 MiB rolling tail).
Once the head budget is exhausted, subsequent chunks divert into a
fixed-size tail ring; `dump()` replays the ring behind a single
`[ARTIFACT TRUNCATED: kept first … + last … of …; … elided from the
middle]` notice before closing the sink. Setting `artifactMaxBytes: 0`
restores the historical unbounded behavior. Sized comfortably above
anything a model would reasonably scroll through via the artifact URL
scheme while preventing the captured 7.6MB spray from sitting on disk.
The terminal-typing lag the reporter observed has multiple compounding
causes (transcript-render freezing is disabled on win32; the bash result
renderer lacks the per-render cache that the eval renderer already has).
Those land in a follow-up — the loop guard + artifact cap address the
root pathologies that turned the session into a multi-MB transcript in
the first place.
Fixes#2081
- 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.
- 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.
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 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.
- 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.
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
- 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.
pr_push invalidates PR+diff rows; current-branch merge/close invalidates without a positional; run_watch polls adaptively, survives rate limits, gives up on zero runs, and evicts completed-run job caches when a rerun is observed; multi-PR checkout uses allSettled; pagination compares raw page length; date qualifiers drop ms precision; leading-dash identifiers cannot become flags; auth key memoized against hosts.yml mtime; diff stored once per row.
single OutputSink owner per cell artifact; JS parallel() honors its documented barrier (allSettled) instead of orphaning in-flight thunks; Python subprocesses no longer inherit the NDJSON frame pipe (stdout captured and forwarded); JS timeouts annotate the VM reset; console bridge implements dir/time/group/assert/trace; python availability probe cached; runner frames coalesce per write.
non-exact patch matches warn and prefix/substring matches must preserve the discarded suffix; multi-entry edits stop at first failure and report applied vs not; ast-edit and file-mention snapshots use canonical realpath keys and re-record post-apply; notebook marker-shaped lines escaped on render; fuzzy matcher pre-normalizes once per seek; streaming preview caches text+tree per tick.
vault writes now rated write-tier and plan-mode enforced; .tar.gz rewrites keep gzip, are atomic, and write through symlinks; CRLF conflict detection works; conflict twins only invalidated when truly stale; ask discloses timeout auto-selection in result and transcript; todo rejects duplicate ids and stops persisting half-applied batches; auto-generated guard validates against mtime+size; ACP writes run post-write bookkeeping; irc errors set isError.
artifact spill now includes the head-retained bytes (full capture was missing first ~20KB); chunk throttle coalesces instead of dropping; cd-prefix extraction defers shell-expanded paths; interceptor rule is quote-aware and catches clobber and variable targets; completed async jobs release their Shell; at job cap commands degrade to foreground; PTY mode drops the non-interactive env and notes silent downgrades; timeout/abort annotations always appended; removed dead idle-timeout-watchdog.
tar/tgz stat-gated at 256MB, zip entries reject oversized declared sizes; raw ?q= sqlite capped at 1000 rows; giant-file reads stop scanning to EOF; multi-range reads slice one pass; malformed URL selectors error instead of dumping; archive-root selectors, member tag immutability, case-insensitive selector tokens, session-pinned artifact lookups, shared+escaped suffix globs; archive dir listings honor offsets; binary files get a NUL-sniff notice.
abort signal + 30s timeout threaded into native grep; per-file cap stops one hot file starving the result set; footer hedges totals when capped; skip-past-end says no-more-results instead of no-matches; oversized-file skips surfaced; virtual-resource context lines deduped; patterns no longer trimmed.
- Added a new `view` todo operation in the tool schema and dispatch path, returning the current list without mutating it.
- Implemented a read-only execution path in the todo tool so all-`view` calls skipped state updates, completion transitions, and normalization.
- Updated tool prompts to document `view` usage and clarified when bash commands are acceptable for fact-computing pipelines.
Same shape of bug the reviewer flagged for custom tools: forwarding
`LoadExtensionsResult` from parent to subagent reused Extension instances
whose factories closed over the parent's `ExtensionAPI` — cwd, eventBus,
and runtime all pointed at the parent. Any tool/handler/command that
referenced `api.exec()`, `api.events`, or `api.runtime` still acted on the
parent session/worktree from inside an isolated subagent.
Forward only the path list; each session rebuilds extensions through
`loadExtensions` so factories see the right `ExtensionAPI`.
- `extensibility/extensions/loader.ts`: extract `discoverExtensionPaths`
(FS scan only) from `discoverAndLoadExtensions`. The combined helper now
composes the two. New export added to the package barrel.
- `sdk.ts`:
- Add `discoverSessionExtensionPaths()` (the `disableExtensionDiscovery`-aware
path-only counterpart of `loadSessionExtensions`).
- Add `preloadedExtensionPaths?: string[]` to `CreateAgentSessionOptions`.
Three loader branches: `preloadedExtensions` (CLI same-process reuse,
still shallow-cloned), `preloadedExtensionPaths` (subagent: skip scan,
reload locally), or full discovery.
- Document `preloadedExtensions` as same-process-only; subagent
forwarding MUST use `preloadedExtensionPaths`.
- `tools/index.ts`: `ToolSession.extensionsResult` → `extensionPaths:
string[]` for the same reason.
- `task/executor.ts` and `task/index.ts`: forward `extensionPaths`. Drop
the forward for the isolated `runSubprocess` branch — worktree cwd ≠
parent cwd, so the subagent re-discovers extensions against its own
tree.
- New `test/sdk-extensions-per-session-binding.test.ts` pins the contract:
two `loadExtensions` calls on the same path with different `cwd` and
different `EventBus` instances yield distinct Extension + runtime
objects whose factories close over the per-call bindings.
- Updated `executor-pass-through` and `sdk-preloaded-extensions-isolation`
tests for the new option name and comment context.
Refs PR review on #2193
Reviewer flagged that forwarding `LoadedCustomTool[]` from a parent session
to a subagent reused tool instances whose factories had closed over the
parent's `CustomToolAPI` — `cwd`, `exec`, `pushPendingAction`, and `ui` all
pointed at the parent. In isolated tasks the tool would `exec` against the
parent worktree and queue pending actions on the parent session.
Forward only the path list; let each session rebuild tools through
`loadCustomTools` so factories see the right `CustomToolAPI`.
- `extensibility/custom-tools/loader.ts`: extract `discoverCustomToolPaths`
(FS scan only) from `discoverAndLoadCustomTools`; export
`ToolPathWithSource`. The combined helper is now `discoverCustomToolPaths`
+ `loadCustomTools`.
- `sdk.ts`: replace `preloadedCustomTools` (`LoadedCustomTool[]`) with
`preloadedCustomToolPaths` (`ToolPathWithSource[]`). The custom-tools
block runs `loadCustomTools` unconditionally; only the path scan is
skipped when the caller pre-discovered it.
- `tools/index.ts`: `ToolSession.loadedCustomTools` →
`ToolSession.customToolPaths` for the same reason.
- `task/executor.ts` and `task/index.ts`: forward `customToolPaths`.
Drop the forward for isolated subagents — the worktree shifts `cwd`, so
the subagent re-discovers tools against its own working tree.
- New `test/sdk-custom-tools-per-session-binding.test.ts` pins the contract:
two `loadCustomTools` calls on the same path with different `cwd` and
different `pushPendingAction` callbacks yield distinct tool instances
whose factories see the per-call bindings.
- Updated `executor-pass-through` and `sdk-preloaded-extensions-isolation`
tests for the new option name and added a `ToolPathWithSource` fixture.
Refs PR review on #2193
Each `runSubprocess` call re-ran `loadCapability<Rule>()`,
`loadSessionExtensions()`, and `discoverAndLoadCustomTools()` because
`ExecutorOptions` and the `createAgentSession()` call inside the executor
omitted three pass-through fields the parent had already paid for. The
already-correct paths (skills, context files, workspace tree, MCP manager)
showed the intended pattern.
- Cache `rules`, `extensionsResult`, and `loadedCustomTools` on the
parent's `ToolSession`.
- Add `rules` / `preloadedExtensions` / `preloadedCustomTools` to
`ExecutorOptions`; forward them from both `runSubprocess` call sites
in `task/index.ts` and into the executor's `createAgentSession()`.
- Add `preloadedCustomTools` to `CreateAgentSessionOptions` and skip
`discoverAndLoadCustomTools()` when it is supplied.
- Shallow-clone `extensionsResult.extensions` when reusing
`preloadedExtensions`, so the per-session autoresearch + custom-tools
inline wrappers never leak back into the caller's array.
Fixes#2190
Completes the injectable-fetch transport wiring (15.10.8) that the feature
left half-done, fixing the deterministic CI test failures:
- compaction.compact() rebuilt summaryOptions field-by-field but dropped
`fetch`, so the injected transport never reached
requestOpenAiRemoteCompaction / generateSummary's remote path. Thread it.
- Read-tool URL pipeline had no fetch seam: renderHtmlToText gained a
fetchOverride param but renderUrl/ToolSession never carried one, so the
jina/parallel reader backends always used global fetch. Add
ToolSession.fetch -> renderUrl -> renderHtmlToText (defaults to global).
- searchWithParallel mirrored extractWithParallel but missed the fetch
option; add it.
- Repair tests whose deleted hookFetch interceptors were never replaced
with a FetchImpl seam (fetch-kagi-toggle, web-search-parallel,
issue-970 discovery).
- Update issue-1746 POSIX case to the #2154 preserved-scrollback contract:
unknown-viewport streaming deferral is now platform-independent.
- Added optional FetchImpl fields to compaction, proxy, AI, coding-agent, and mnemopi options.
- Threaded injected fetch implementations through OAuth, discovery, and search/LLM request flows.
- Removed exported hookFetch utility and its package entrypoint from utils.
- Replaced global-fetch test monkeypatching with per-test FetchImpl mocks across test suites.
- Added a `bash.enabled` boolean setting with a default of `true` in the settings schema.
- Updated tool generation to include the `bash` model tool only when `bash.enabled` is enabled.
- Extended createTools tests to assert `bash` is omitted when disabled and omitted from requested disabled tool lists.
- Introduced filterInitialToolsForDiscoveryAll() to centralize tool filtering when discovery mode is "all", replacing inline logic in createAgentSession.
- Added forceActive parameter to ensure tools required by forced tool_choice features (e.g., eager todo) remain active in the request, preventing provider 400 errors.
- Updated eager todo enforcement to check active tool set instead of registry, ensuring it respects tool discovery hiding.
- Added status.done and tool.* symbols to theme mappings and presets.
- Replaced generic success glyphs with contextual +/-, tool icons, and warnings.
- Mapped tool/task/job completions to status.done or status.enabled with icon overrides.
- Triggered runtime provider refresh after extension registration and warned on failure.
- Ran the operand as an ordinary descendant so it is reaped with the host instead of leaking as an orphan.
- Propagated the command's exit status; reported missing operand and exit 125 with no operand.
- Updated the bash tool prompt's daemon guidance away from nohup/setsid/disown detachment.
- Switched shell renderer success icon/state to "done".
- Matched the `bash` tool's max in the Zod schema and runtime clamp.
- Allowed heavy local-compute cells to request budgets above 10 minutes.
- Updated docs and prompt to reflect the new 1-3600s range.
- Set AskTool concurrency to exclusive so the tool runner executes ask calls serially.
- Updated the changelog to document the hanging ask failure when multiple asks were triggered concurrently in one batch.
- Added tree-sitter `enclosing_block_boundaries` API with line range models.
- Added N-API `enclosingBlockBoundaries` bridge and exported JS declarations.
- Replaced matching-bracket context resolution with source-aware block context in read and diff flows.
- Passed source path through diff/read generators to surface native block boundary previews.
- Added matching-bracket utilities to locate partner lines for visible spans.
- Added read tool output to use displayContent text and startLine for bracket-aware previews.
- Added matching-bracket context rows to generateDiffString and generateUnifiedDiffString.
- Adjusted diff row insertion to deduplicate and keep contiguous changed groups together.
- Tracked in-flight browser helpers with names and durations for timeout reporting.
- Wrapped observe, screenshot, and extract in per-op deadlines capped at 20_000ms.
- Updated timeout cancellation errors to list stalled helper names and elapsed time.
- Renamed eval oneshot helper from llm() to completion() across JS/Python APIs.
- Remapped eval bridge internals to completion semantics (__completion__, runEvalCompletion, completion status op).
- Updated docs, prompts, and timeout guidance to describe completion() usage and behavior.
- Adjusted completion defaults for active-session model preference, fallback parsing, and slow-tier effort handling.
- Introduced `AsideMessage` as a message-or-thunk union so aside providers can defer injection decisions.
- Updated agent loop handling to resolve aside thunks at injection time and skip entries that returned `null`, then switched the session yield queue to `drainLazy` for deferred message building.
- Added tests validating lazy aside evaluation and staleness-aware dropping when everything becomes stale after dequeueing.
- Added a session-global file mutation counter and accessor methods to tool sessions.
- Updated the write tool to bump a file's mutation version after each write.
- Updated the edit tool to use session-wide mutation versions when checking stale deferred diagnostics.
- Processed explicit multi-path `find` targets independently and merged scoped results.
- Ignored missing or invalid extra targets in multi-path `find` queries instead of failing the whole run.
- Deduplicated overlapping matches when combining per-target `find` results.
- Tracked streamed match paths to prevent repeated update rows during long-running scans.
- Added a LateDiagnosticsMessageComponent to render delayed LSP diagnostics as grouped tree nodes in transcript messages.
- Updated message handling to use that component and honor tool-output expansion while reusing shared diagnostics formatting.
- Added tests for shared rendering output, collapsed/expanded limits, and empty diagnostics behavior.
can1357