- Added a shared session command helper that aggregates extension, prompt, and skill slash commands.
- Updated ACP, extension UI, runtime-init, and task executor extension contexts to return session command data instead of empty arrays.
- Updated root marker detection to read the directory once and match glob markers against top-level entries, preventing recursive scans when checking project roots.
- Adjusted root-marker glob error handling to warn on directory listing failures and treat the marker set as absent when unreadable.
- Reduced marksman's configured warmup timeout from 15,000 ms to 2,000 ms in LSP defaults.
Some HTTPS endpoints (e.g. corporate API gateways behind reverse proxies) advertise h2 via ALPN but then refuse or reset the connection at the HTTP/2 framing layer. Bun surfaces these failures as ConnectionRefused, ConnectionReset, or ConnectionClosed rather than HTTP2Unsupported.
Previously only HTTP2Unsupported triggered the transparent h1 retry, so any custom provider pointing at such a gateway would fail with a cryptic "Connection error." that was impossible to diagnose from user-land.
This commit widens the fallback set to include ConnectionRefused, ConnectionReset, and ConnectionClosed — all of which are transport-layer indicators that the h2 attempt itself failed, not the underlying application request.
- Updated collectPayload to accept intervening blank lines as empty payload when requirePayload is true and no payload has been collected yet.
- Added a fallback path alongside the HL_EDIT_SEP check so blank insertions without a separator are tolerated as required-payload op payload lines.
- Removed mimalloc from workspace and crate Cargo.toml dependency lists.
- Eliminated the global `MiMalloc` allocator registration from `pi-natives`.
- Updated Cargo.lock by deleting stale `mimalloc` and `libmimalloc-sys` package entries.
- Strengthened `defaultConvertToLlm` filtering with a `Message` type predicate.
- Added an `Array.isArray` guard before checking `partial.content` length for assistant partial messages.
Commit d43655541 made splitHashlineInputs silently drop sections whose
body has no operations, so '@<path>\n' alone now yields zero sections
and trips the 'exactly one hashline section' guard before reaching the
no-op or local-URL checks the tests intended to exercise.
- 'returns no-op error for unchanged content' now uses '= 1<hash>..1<hash>'
with the existing line as payload (true no-op via formatLineHash).
- 'returns a handled error when the source path is a local URL' appends
'+ EOF\n' so the section is emitted and resolveToCwd surfaces the
internal-scheme rejection.
Mirrors the pi-mono API surface so apps can preflight tool execution
(block or mutate validated args) and post-process tool results
(override content/details/isError) without wrapping tools.
- `AgentLoopConfig.beforeToolCall` runs after argument validation. Return
`{ block: true, reason }` to short-circuit with a tool-error result.
Mutations to `context.args` are forwarded to `tool.execute` without
revalidation, matching pi-mono semantics.
- `AgentLoopConfig.afterToolCall` runs after execution and before
`tool_execution_end` / tool-result message emission. Returned fields
override the executed result; omitted fields fall through. Hook
exceptions surface as tool errors and do not abort the batch.
- `Agent` exposes both hooks as public, reassignable fields so extension
reloads can swap implementations mid-session.
Compatibility: fully additive. Both hooks default to undefined and the
loop behaves identically when neither is set. The internal
`executeToolCalls` signature was collapsed to `(context, message,
signal, stream, config)` -- it is not exported, so this is not a public
API change. Pi-mono's `terminate` field on `AfterToolCallResult` is
omitted because our `AgentToolResult` has no batch-level early-stop
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.
- Introduced a `fetch` option on `StreamOptions` and threaded it through providers to let callers supply a custom request transport.
- Updated provider clients and direct HTTP calls across Anthropic, OpenAI, Azure, Google, GitLab Duo, Gemini CLI, Ollama, and Codex flows to use the injected fetch implementation.
- Extended retry helper options to accept a fetch override and preserved preconnect support from the selected fetch function.
- Updated hashline splitting to skip emitting a section when a path header has no following operations.
- Added a trimmed non-empty check so only sections with diff content are returned.
- Added tests for duplicate and trailing headers to ensure empty header-only chunks are silently dropped.
- Exempted the `fmt:rs` task from the early-exit skip logic so formatting always runs.
- Reformatted `apply_command_env` signature in shell.rs to satisfy the formatter.
Brush-core applied POSIX parameter expansion to $env before dispatching a command, mangling PowerShell references like Write-Host $env:SystemRoot to :SystemRoot. Move the fix down to env-var application: every brush session now defines env=$env as an internal (non-exported) shell variable, so the bash expansion of $env yields the literal $env and PowerShell tokens reach the child intact. User assignments (env=prod; echo "$env:8080") still shadow the fallback in their command scope, so the POSIX bash contract is preserved.
Fixes#1079
- Stop now marks the client as closed via `_mark_closed` with `RpcProcessExitError`, so `_wait_for_agent_end` wakes immediately instead of waiting for a timeout.
- Added a regression test using a hanging server subprocess to verify `stop()` unblocks `prompt_and_wait` promptly and raises `RpcProcessExitError`.
- Updated Kimi compatibility tests to distinguish Moonshot-hosted models from OpenCode-hosted ones for `reasoning_content` and assistant-content tool-call behavior.
- Added a `resolveSearchRepoScope` helper that uses an explicit `repo` when provided, skips defaulting when a query already contains a repo/org/user/owner scope qualifier, and otherwise resolves the current checkout via `resolveDefaultRepoMemoized`.
- Updated `search_issues`, `search_prs`, `search_code`, and `search_commits` to use the resolver before composing API queries, defaulting `repo` when omitted but silently falling back to an unscoped search on resolution failure.
- Documented the new search-repo defaulting rules in tool prompts, user docs, and the package changelog.
- Added a new `.dockerignore` to keep build context clean by excluding targets, node_modules, logs, IDE files, OS junk, generated outputs, and secrets.
- Created a multi-stage Dockerfile that builds Linux `pi_natives.linux-*.node` and `omp-rpc` wheel artifacts in dedicated builder stages.
- Published a minimal scratch artifacts stage that only exports the compiled native addon and wheel into `/out/` for downstream image consumption.
The agentic commit pipeline (`omp commit`) wrote its commit and then sat
spinning on Ctrl+C because nothing in `Commit.run()` drained the lingering
event-loop handles: `installH2Fetch()` keeps idle HTTP/2 sockets warm to
the provider, the Settings autosave timer can still be armed, and the
AgentSession's extension/runner machinery holds onto async-job and OAuth
refresh state even after `session.dispose()` releases what it knows how
to. Mirror the `runPrintMode` exit path from `main.ts` by calling
`postmortem.quit(0)` once `runCommitCommand` resolves so the CLI returns
to the shell, runs registered cleanup callbacks, then exits — same model
the non-interactive launch flow already uses.
Also widens the private bash-tool helpers' `notices` parameter to
`readonly string[]` so `bun check:types` keeps passing — the public outer
arm already accepted `readonly string[]` and an upstream commit had only
partially propagated the change.
Fixes#1041
The previous examples used " • " in the source file and inserted "·"
as the new content. Some agents were copying the middle-dot literally
into real edits as if it were format scaffolding, since the demo
inserts were near-twins of the existing string.
The new example uses TITLE = "Mr" → "Mrs" with "Dr" inserts:
ASCII-only, clearly distinct from any payload separator, and obviously
domain content rather than punctuation the model could confuse for
syntax. Every original op shape is preserved (single-line replace,
multiline replace, insert AFTER/BEFORE, append, delete, blank, both
anti-patterns). Pure prompt change; parser/schema/runtime untouched.
- Added an explicit notice in the eval tool docs cautioning against using one-off `-c`/`-e` shell executions.
- Documented that the eval tool should be used instead for persistent runtimes, structured outputs, and cancellation or timeout support.
The ClaudePluginManifest interface was missing the `commands` field
(the standard Claude plugin format), and resolvePluginDir only checked
the legacy `slash-commands` key. Plugins declaring their command path
via `"commands": "..."` silently fell back to the hardcoded
`<plugin-root>/commands/` directory, which doesn't exist for
Claude-format plugins, so no slash commands were ever loaded.
Changes:
- Added `commands?: string` to ClaudePluginManifest.
- Changed resolvePluginDir to accept ReadonlyArray<keyof
ClaudePluginManifest> and iterate in priority order; the first
non-empty match wins.
- loadSlashCommands now passes ["commands", "slash-commands"] so
the canonical Claude plugin key takes precedence over the legacy one.
- Added two regression tests: one covering the `commands` key in
isolation, one verifying its precedence over `slash-commands` when
both fields are present.
Fixes#1076
- Updated `collectPayload` to treat blank lines inside a payload run as empty entries when subsequent payload text is present.
- Added lookahead-based end-of-run detection so blank lines before a non-payload operation remain section separators.
- Added tests verifying blank-line recovery inside payloads and non-consumption of trailing blanks between hashline sections.
- Converted several single-line guard-style `if let`/`let Some` exits in `fixup.rs` into multiline blocks for consistent style.
- Reformatted the safe-argument regex definition and normalized test case formatting in `fixup.rs` without altering assertions.
- Reordered `lib.rs` module exports by moving `fixup` ahead of `minimizer`.
Loaded cached standard provider discovery models into ModelRegistry at startup so retry fallback validation can resolve Ollama Cloud models that are already visible through --list-models.
Added regression coverage for cached ollama-cloud fallback selectors and fixed a readonly notices type error exposed by the focused type check.
Fixes#1052
- anthropic: add signal to AnthropicSearchParams, callSearch(), and
AnthropicProvider.search()
- exa: add signal to ExaSearchParams, callExaSearch(), and ExaProvider.search()
- jina: add signal to JinaSearchParams, callJinaSearch(), and JinaProvider.search()
- zai: add signal to ZaiSearchParams, callZaiTool(), and ZaiProvider.search()
- gemini: add signal to GeminiSearchParams, callGeminiSearch() and
buildInit() so both fetchWithRetry calls (initial + auth-refresh retry)
carry the signal
The five providers listed above never forwarded SearchParams.signal to the
underlying HTTP layer, so pressing Esc during a web_search call had no effect
and the session froze until the request resolved or Ctrl+C was pressed.
brave, kimi, perplexity, searxng, tavily, synthetic, codex, kagi, and parallel
already thread the signal correctly and are unchanged.
Fixes#1044
- Added stripOutputNotice to output-meta to remove appended truncation notices when output metadata is available.
- Updated bash, eval, browser, read, and ssh renderers to strip the notice before display so the styled warning line is not duplicated.
- Left fallback behavior unchanged so outputs without a notice continue through unchanged.
TypeScript 6 tightens mutability checks; the notices parameter was typed
as string[] but the caller held a readonly string[] (from the options
object). Widening both private method overloads to readonly string[]
satisfies the type checker without any runtime change — filter(Boolean)
works on readonly arrays.
discoverAgents() called listClaudePluginRoots() unconditionally, so agents
from Claude Code marketplace plugins appeared in /agents and the Agent
Control Center even when claude-plugins was listed in disabledProviders.
Guard the listClaudePluginRoots() call with isProviderEnabled("claude-plugins"),
returning an empty roots array when the provider is disabled — matching how
filterProviders() handles every other capability's provider set.
Added regression test that verifies both the enabled path (agents visible)
and the disabled path (agents absent) using a real temp-directory plugin
registry fixture.
Fixes#1075
- Added user, group, and extra_groups parameters to RpcClient initialization.
- Propagated those parameters through to subprocess startup calls.
- Added tests to verify the new kwargs are passed correctly, including None defaults and empty extra groups.
can1357