- Added `fanOutFileItems` plumbing through `resolveSearchPathItems`/`resolveExplicitSearchPaths` and `ToolScopeOptions` so plain-file entries can be scanned as explicit targets instead of being folded into an unrequested ancestor walk.
- Search tool now enabled `fanOutFileTargets` and deduplicated overlapping results by tracking a `path\0line` key before merging matches.
- Expanded multi-path tests for shared non-root ancestors, explicit `.git/config` targets, and overlap deduplication behavior.
Programmatic `git push` operations should not follow annotated tags configured by a user's `push.followTags = true`. This setting can lead to push failures if the remote rejects tag creation (e.g., in PR-head forks), even if the branch update itself is valid.
Adding `--no-follow-tags` explicitly overrides this user setting, ensuring only the specified refspec is pushed and preventing rejections.
The format-on-write path sent a hardcoded {tabSize:3, insertSpaces:true}
on every textDocument/formatting request from two duplicated DEFAULT_FORMAT_OPTIONS
constants. Servers that honour tabSize for re-indent (yaml-language-server, the
common YAML/Kustomize/Flux case) reserialized 2-space files at a 3-space stride
on every write — exactly the corruption reported on Kubernetes/Flux YAML repos.
Replace both constants with a single resolveFormatOptions(filePath, content)
helper that layers, in order:
- .editorconfig (indent_style, indent_size, tab_width) via the new
getEditorConfigFormatting() helper in pi-utils — strict, no fallback.
- Indent sniffed from the in-memory content the agent is about to write
(first indented line decides spaces vs tabs; GCD of space-indent widths
fixes the unit).
- Hardcoded 2-space fallback. The previous 3-space stride was an unusual
default that actively damaged every file with a 2/4-space convention.
Tests cover the editorconfig and content-sniffing paths plus a direct
regression check that 2-space YAML stays 2-space (the issue's repro).
Fixes#2329
The root compose recorded seams last-writer-wins, so the status
container's new seam (mounted loader) overwrote the transcript's seam
whenever both reported in the same frame. With a volatile live block
(no commit-safe end) the boundary then moved below the transcript's
still-mutable rows and committed them as stale history — the same
duplication class this PR fixes for the loader, relocated upward.
Commits are prefix-only: the first child reporting a live region (plus
its own commit-safe extension) already bounds everything below it, so
the topmost seam now wins. Adds a two-reporter regression test and
documents the multi-reporter contract on NativeScrollbackLiveRegion.
The previous refactor dropped `if (this.aliasOf) return` into
consolidate(), which made `/memory enqueue` invoked from inside a
subagent a no-op. The old enqueue() body short-circuited only
forceRetainCurrentSession (via its own guard) but still flushed
extractions and slept on state.memory, which for aliased states points
at the parent's shared retain bank.
Moved the alias guard back out of consolidate(): forceRetainCurrentSession
keeps its own early-return (the subagent's transcript is the parent's
concern), so consolidate() runs the SQL-level flush+sleep on every
owned bank for both primary and aliased states. The lifecycle guard
stays in dispose() so disposing a subagent still does not flush, sleep,
or close the parent's memory.
Added a regression test: a /memory enqueue routed through the aliased
child state calls flushExtractions + sleepAllSessions(false) on the
parent's owned memory exactly once, and forceRetainCurrentSession runs
on the child (where its own guard returns early) but not on the parent.
Addresses #2327 review.
`/memory clear` (mnemopiBackend.clear) calls dispose() right before
removing the SQLite files. Running the consolidation pass first would
make a destructive clear spend tokens/time creating memories that get
deleted on the very next line, and a slow extraction could block the
clear path under llmMode: remote.
Added a `{ consolidate?: boolean }` option to
MnemopiSessionState.dispose; defaults to true so normal shutdown still
runs the SHMR/beam pipeline. mnemopiBackend.clear passes
`{ consolidate: false }` so the close path stays unsubscribe + close
only. Added a regression test that spies on forceRetainCurrentSession,
consolidate, flushExtractions, and sleepAllSessions to pin the new
behavior, while close still runs once per owned bank.
Addresses #2327 review.
MnemopiSessionState.dispose() now drains pending fact extractions and
runs sleepAllSessions on every owned bank before closing handles, and
AgentSession.dispose() awaits the result. This matches the manual
`/memory enqueue` slash command which was the only caller of the
consolidation pipeline.
Without the shutdown hook, episodic_memory, gists, consolidation_log,
graph_edges, and triples stayed empty for every deployment that never
typed `/memory enqueue|rebuild` — working memory accumulated forever
and long-term recall never formed.
Factored the consolidate step out of `mnemopiBackend.enqueue` into a
shared MnemopiSessionState#consolidate so the slash command and the
shutdown path share one implementation. Added two regression tests
verifying owned-bank consolidation order (flush -> sleep -> close, per
bank) and that aliased subagent dispose stays a no-op against the
parent.
Fixes#2320
- Extended `AgentTool.concurrency` to accept per-call resolver functions and resolved concurrency mode from each tool call, falling back to exclusive on resolver errors.
- Updated BashTool to schedule non-PTY calls as shared and PTY calls as exclusive so non-interactive bash calls can run in parallel within one message.
- Tracked in-use persistent shell sessions in the bash executor and routed overlapping calls on the same session key to isolated one-shot shells while preserving owner session availability.
A subagent's send await:true to Main during a blocking task spawn was a structural deadlock: deliverIrcMessage queues mid-turn messages as step-boundary asides, but Main's next boundary requires the sender's own batch to finish, so the sender always burned the full irc.timeoutMs. Awaited sends now pass expectsReply through IrcBus.send; a mid-turn recipient with async.enabled off generates an ephemeral no-tools reply via runEphemeralTurn, records an irc:autoreply aside in its own history, and delivers it back over the bus with replyTo threading so the sender's waiter resolves.
PR #2297's new test interleaved fixture writes with loader calls in one temp
dir; Bun's resolver caches directory entries process-wide, so tool.ts written
after loadExtensions() resolved extension.ts was invisible to the subsequent
dynamic import on macOS. Write all fixtures up front.
Reorders sections in the streaming call preview to match `renderResult` and the
schema's field order. This prevents visual jumps when the preview transitions
to a result and ensures append-only growth of streamed content.
Additionally, omits the agent-list divider when no agent rows are present.
- Added smooth streaming reveal of streamed tool-call args and `{ input }` partial previews.
- Integrated ToolArgsRevealController in EventController to route partial and final args.
- Implemented UTF-16-safe slicing to prevent surrogate-pair splits during reveal boundaries.
- Implemented reveal lifecycle controls to flush or stop streamed arg frames at message boundaries.
- Added tests for monotonic reveal progression, non-smooth immediate output, and flush/stop behavior.
- Replaced the ACP agent test's fixed bootstrap wait with a deterministic `/reload-plugins` flow and asserted against the latest available-commands advertisement.
- Added a TUI probe test that verifies native committed scrollback rows are passed to children before render.
- Added transcript and assistant block version tracking for finalized segments.
- Changed committed block reuse logic to require prior finalization and same version.
- Fixed rerendering of committed finalized blocks when version values changed.
- Updated the catalog changelog by removing a duplicate `Fixed` heading and leaving the NVIDIA Qwen fix in the current release notes.
- Restructured the coding-agent changelog by moving unresolved fixes into Unreleased and removing duplicated historical entries.
- Added `requestComponentRender` to mocked `ui` objects in coding-agent controller tests to match the updated interface.
- Updated TaskTool to skip `session.asyncJobManager` and run `task` spawns inline whenever `async.enabled` is false.
- Set `async.enabled` default to `true` and updated task prompts/settings text to reflect async-versus-sync behavior.
- Adjusted task batching tests to cover both async background execution and synchronous batched execution when async is disabled.
Status line painted theme.statusLineBg across the bar, which renders as
visible dark/black blocks on terminals (Ghostty, transparent themes,
custom palettes) whose background does not match the theme's hardcoded
status-line color. Powerline end caps inherited the same fill so they
also stood out against the surrounding terminal.
The new statusLine.transparent appearance setting (default off) routes
the bar to the terminal's default background via the existing empty-bg
sentinel (\x1b[49m) and drops the powerline end caps, which need a
contrasting fill to bridge into the terminal.
Theme authors can opt in per-theme by setting statusLineBg to '' — the
existing empty-string sentinel already resolves to the same ANSI escape
the new toggle uses.
Fixes#2306
Only chain rows should force their nearest connector gutter back to vertical.
Inherited gutters from older last-sibling ancestors must stay suppressed so
linear continuations under nested branched grandchildren do not draw floating
vertical lines below unrelated branch connectors.
Updated the TUI renderer, mirrored the HTML export renderer, regenerated the
HTML template, and extended the #2298 regression to cover nested branched
grandchildren with linear continuations.
Fixes#2298
The /tree selector and HTML session export rendered chain rows (flattened
user/assistant turns) with bare spaces when their nearest branched ancestor
was the last sibling, breaking the visual connection back to the branch
parent.
Cause: tree-selector.ts and export/html/template.js propagated
`show: !isLast` to descendant gutters, so any chain row under a `└─`
ancestor rendered the gutter as space instead of `│`. Branched
grandchildren correctly need that space to keep standard tree drawing, but
chain-flattened conversation rows lost their anchor.
Fix: at render time, when the row has no connector of its own (chain row),
force the gutter to `│` regardless of the ancestor's `show` flag. Rows
with their own connector still respect the `show` flag so a `│` never
floats below an unrelated `└─` for branched descendants.
Applied identically in tree-selector.ts (TUI) and export/html/template.js
(HTML export, regenerated into template.generated.ts).
Fixes#2298
Anthropic OAuth web search now uses resolveAnthropicMetadataUserId so metadata.user_id matches the main streaming path's {session_id, account_uuid?, device_id} JSON envelope. API-key paths keep forwarding the raw session id.
Exported resolveAnthropicMetadataUserId from pi-ai. Extended the regression test to cover the OAuth shape.
Refs #2295
Forwarded the active web search session id as Anthropic Messages metadata.user_id so enterprise gateways can attribute and rate-limit search calls consistently with the main streaming path.
Added a focused Anthropic web search request-shape regression test.
Fixes#2295
Kept classifier refusals eligible for model fallback, but restored the retry.maxRetries guard so fallback chains cannot consume extra provider calls after the turn budget is exhausted.
Fixes#2290
Preserved Anthropic stop_details on assistant messages so the agent can distinguish classifier refusals from transport failures.
Taught AgentSession to use configured retry fallback chains for refusal and sensitive stops without same-model retries, then pin the fallback for the conversation.
Fixes#2290
Wrap Windows MCP .cmd/.bat stdio launches through a hidden cmd.exe invocation so PATH shims such as npx keep stdio attached without flashing a console.
Fixes#2287
can1357