Delete unused system-prompt.ts, agent-prompt.md, and the entire
terminal-mcp/ directory (tmux-based MCP server) — nothing imports
any of these. The codebase uses src/terminal/ (node-pty) instead.
When interrupting a Claude agent mid-tool-call and sending a replacement
message, the SDK's abort error result was being attributed to the new
foreground turn, causing [System Error] banners and displaced replies.
Root cause: pendingInterruptAbort was cleared by visible activity from
the new turn before the stale result arrived (timing race), and the
stale result then poisoned the replacement turn.
Fix:
- Suppress stale non-success results at the top of routeSdkMessageFromPump
before any turn attribution, using both flag-based (pendingInterruptAbort)
and content-based (isAbortError) detection
- Stop clearing pendingInterruptAbort on visible activity — only consume
it when a result message arrives
- Prevent idle flash during replacement by checking pendingReplacement
in agent-manager turn_completed/turn_canceled handlers
- Fix vitest env loading to use import.meta.url instead of process.cwd()
- Load .env.test eagerly in agent-configs.ts for collection-time availability
Includes regression tests covering the exact f160a2a3 daemon log ordering.
When a foreground message interrupts an autonomous turn, the notification
content has already been dispatched to subscribers. Canceling says "this
turn didn't happen" — but it did. Complete it instead, preserving the
lifecycle semantics and preventing notification loss.
- Change interrupt() to call completeAutonomousTurn instead of
cancelAutonomousTurn, with flushPendingToolCalls before completion
- Remove dead cancelAutonomousTurn method (no remaining callers)
- Fix autonomous wake tests B and C to handle notification/foreground
timing race: when task_notification arrives during a foreground turn,
there is no separate autonomous running edge afterwards
Remove `pendingInterruptAbort = false` from startTurn() and
`queryRestartNeeded = true` from requestCancel(). Both violated the
existing coordination contracts:
- pendingInterruptAbort must only be cleared by the stream pump at its
safe consumption points, not eagerly by the turn lifecycle
- queryRestartNeeded is for transport-level restarts (config changes,
rewind), not for normal interrupt/cancel flows — setting it on every
cancel killed the Claude process and destroyed background tasks
The actual fix for the send-during-tool-call bug was the manager-side
pendingForegroundRun settlement wait added in the previous commit.
- Fix race in agent-manager where pendingRun wasn't fully cleaned up
before the next streamAgent call, causing "already has an active run"
- Fix Claude agent query restart: null out query/input before awaiting
old iterator return so the old pump skips failActiveTurns
- Reset pendingInterruptAbort on new foreground turn
- Add system error assertion to send-during-tool-call e2e test
- Rename mode color tiers: drop "default", rename "readonly" to
"planning", update color assignments across providers and UI
Strip parent Claude Code session env vars (CLAUDECODE, CLAUDE_CODE_ENTRYPOINT, etc.)
from child agent environments so spawned agents don't fail with "cannot be launched
inside another Claude Code session". Centralize isProviderAvailable to check both
binary and credential availability. Add red e2e test for send-during-tool-call bug
and force-cancel stale foreground turns in cancelAgentRun.
Replace three competing event paths (foreground stream, live event pump,
JSONL history poller) with a single push-based subscribe() + startTurn()
contract. This fixes duplicate user messages and stuck running state caused
by timing-based routing between concurrent event sources.
Key changes:
- AgentSession interface: remove stream(), add subscribe() and startTurn()
- All providers (Claude, Codex, OpenCode): single subscribers Set with
notifySubscribers() for push-based event delivery and turnId stamping
- Agent manager: identity-based turn ownership via activeForegroundTurnId
replacing pendingRun async generator
- Delete: dual queues, routeSdkMessageFromPump, startLiveHistoryPolling,
snapHistoryOffsetToEnd, liveEventBacklog, Pushable
- Fix Codex provider not clearing activeForegroundTurnId on turn completion
- Add real-provider integration tests for event stream invariants
* Expose PASEO_AGENT_ID to managed agents
* refactor(server): make managed agent launch context explicit
* refactor(server): pass launch env through agent providers
* fix: use workspace-agnostic root tsconfig
* fix(server): align CI tests with current agent behavior
* fix(server): restore Claude history and sidechain CI coverage
Client-side xterm.js was generating Device Attributes responses via
onData, which fed back to the PTY as visible text. Register CSI handlers
to consume query responses on the client and respond to DA1 on the server.
TimelineAssembler.messages map retained full assistantText and
reasoningText for every message for the lifetime of the session.
Replace with a lightweight finalizedMessageIds set that prevents
duplicate emission during history replay without holding the text.
Several emitState() calls were missing a preceding touchUpdatedAt(),
causing agent state updates to be silently dropped by the bootstrap
dedup logic in session.ts (which drops updates where
updateUpdatedAt <= snapshotUpdatedAt).
This caused two user-visible bugs:
- Permission mode switches not reflected in UI until next message
- Agent stuck showing "running" when it had transitioned to idle
Added touchUpdatedAt() to: setAgentMode, setAgentModel,
setAgentThinkingOption, setLabels, streamAgent.finalize,
replacement error fallback, and cancelAgentRun permission clear.
- Replace REST API PR lookup with `gh pr view` which handles fork PRs
- Fix state comparison to use lowercase (matching server output)
- Remove pill/badge styling, show plain icon + #number
- Add brighter hover colors and underline for clickability hint
- Create packages/highlight with shared Lezer-based syntax highlighting (types, parsers, highlighter, color maps)
- Add syntax highlighting and line numbers to file-pane.tsx with memoized CodeLine component
- Import shared highlight colors in git-diff-pane.tsx instead of local definitions
- Delete duplicated syntax-highlighter.ts from both app and server
- Fix TSX dialect to "ts jsx" (correct per Lezer docs)
User messages with array content were routed through mapBlocksToTimeline
which hardcoded all text blocks as assistant_message. This caused user
interrupt text to appear as assistant output in paseo logs and the app UI.
Add textMessageType option so callers declare the role explicitly.
When set to "user_message", text blocks coalesce into a single item
matching extractUserMessageText semantics.
Workspaces whose directories were deleted (e.g. cleaned-up worktrees) and
workspaces where every agent has been archived now get auto-archived during
reconciliation, cascading to project archival when no active siblings remain.
Extracts detectStaleWorkspaces() as a pure function in workspace-registry-model.ts
with standalone unit tests.
