- Ensures in-memory overlay edits are durably written to the plan file before proceeding with approval.
- Avoids asynchronous write races by awaiting the final plan file serialization.
- Aligns synthetic approved-plan prompts with reference-only expectations.
- Thread the postmortem reason through the session teardown pipeline to the session dispose process.
- Prevent generic "dispose" logs from overwriting real triggers like SIGTERM, SIGHUP, or uncaught exceptions.
- Ensure the first teardown trigger's reason is preserved when concurrent disposal calls occur.
- Add comprehensive test coverage verifying signal-specific reason mapping inside exit diagnostics.
- Fix a minor unhandled-exception test utility expectation in input controller tests.
/quit and /exit hung for many seconds because AgentSession.dispose()
awaited MnemopiSessionState.dispose() unconditionally, and that path
runs consolidate() (state.ts:421) which fires a fresh LLM fact
extraction for the just-retained transcript and then awaits
flushExtractions() per owned bank. One LLM round-trip per shutdown,
no upper bound, no visible status.
- Add a timeoutMs option to MnemopiSessionState.dispose. When the cap
fires the in-flight consolidate is detached to the background and the
SQLite handles close once it settles, so writes never race a closed
handle.
- AgentSession.dispose passes SHUTDOWN_CONSOLIDATE_BUDGET_MS = 1_500 on
the user-visible shutdown path. Per-turn maybeRetainOnAgentEnd has
already retained earlier turns, so the worst case is losing episodic
promotion for the last few turns. State-replacement disposes
(mnemopiBackend.start) stay unbounded.
- InteractiveMode.shutdown surfaces a 'Closing session…' status before
dispose runs so the brief pause is explained rather than mysterious.
Two regression tests in memory-tools.test.ts cover (1) dispose returns
within the budget when flushExtractions stalls and the deferred close
still runs once consolidate settles, and (2) unbounded dispose still
runs the full #2320 consolidate-then-close pipeline.
Fixes#3641
EventController.handleEvent rebuilt the editor's status-line top border
synchronously on every session event via updateEditorTopBorder(). During
a long-running eval that fires 5-10 events/s, each rebuild ran
StatusLine.getTopBorder → #buildSegmentContext → getCachedContextBreakdown
→ session.getContextUsage → estimateTokens (with JSON.stringify per
toolCall block) — the render pipeline is throttled to ~30 fps, so most
rebuilds were dropped before painting. Combined with a scheduler that
collapsed cadenceDelay to zero whenever a frame overran the 33ms budget,
the TUI busy-looped at ~40-50% CPU.
Fix:
- Editor gains setTopBorderProvider(): a lazy builder invoked once per
editor render. InteractiveMode installs it in the constructor and on
setEditorComponent, so the rebuild coalesces to the render tempo
regardless of event rate.
- Delete updateEditorTopBorder wrapper (now equivalent to
ui.requestRender) and inline every call site.
- Add adaptive render backpressure: a frame that exceeds
MIN_RENDER_INTERVAL_MS inflates the next scheduling delay to
2 * last_frame_cost, capped at 200 ms, targeting a 50% render duty
cycle instead of pinning the CPU at t=0.
New regression tests:
- editor-top-border-provider.test.ts: provider fires exactly once per
render, wins over eager setTopBorder, falls back when cleared, gets
the correct availableWidth.
- adaptive-render-backpressure.test.ts: cheap frames keep the 33 ms
cadence, a slow frame idles proportionally, pathological frames are
capped at 200 ms.
Verified with bun test packages/tui/test (all 246 relevant tests pass)
and bun test packages/coding-agent/test/modes (455 tests pass). Three
pre-existing agent-session-handoff snapcompact failures on main are
unrelated (snapcompactSupportedChars binding).
Fixes#4145
The postmortem SIGTERM/SIGHUP/uncaughtException handlers only ran the registered
cleanup callback list before process.exit, and the only session-related callback
was session-manager-flush. So a real kernel signal (terminal close, process
manager killing omp, IDE stop) skipped saveDraft, session.dispose (session_shutdown
emit, owned async job disposal, kernel disposal, MCP disconnect, browser tab
release), and violated the SessionShutdownEvent docstring contract that promises
delivery on SIGINT/SIGTERM. The LSP client also owned its own SIGINT/SIGTERM
handlers that called shutdownAll then process.exit(0), which could race postmortem's
async runCleanup and short-circuit the session teardown.
- Extracted a promise-memoized createSessionTeardown helper (modes/session-teardown.ts)
that snapshots the editor draft, persists it via sessionManager.saveDraft, then
invokes session.dispose. A saveDraft failure is logged but never aborts disposal.
- Memoized AgentSession.dispose so the keypress path and the signal path share one
settled promise and cannot double-emit session_shutdown or double-drain the owned
AsyncJobManager.
- Registered the teardown on postmortem as "session-teardown" in InteractiveMode.init,
replacing the narrower session-manager-flush callback. InteractiveMode.shutdown
now delegates the draft+dispose steps to the same helper.
- Replaced the LSP client's SIGINT/SIGTERM handlers with a "lsp-shutdown" postmortem
callback so LSP cleanup runs alongside every other session teardown instead of
racing them via process.exit(0). beforeExit is unchanged.
- Added session-teardown.test.ts covering: draft-then-dispose ordering, disposal
after saveDraft rejects, empty-string clears stale sidecar, promise memoization
under concurrent invocation, and snapshot-at-first-call semantics.
Fixes#4080
- Anchors the incomplete-todo reminder block inside the scrollback transcript instead of a floating live container.
- Eliminates duplicate reminder copies piling up in terminal scrollback during terminal reflows.
- Removes the dedicated `todoReminderContainer` and simplifies state synchronization on todo reload.
- Updates tests to verify sequential reminders commit as separate blocks and are left intact when tools succeed.
Captured the configured thinking selector when entering plan mode so approving a plan restores auto instead of the provisional concrete effort. Reloaded DEFAULT(auto) badges from defaultThinkingLevel and covered the plan-approval handoff plus /model display.
Fixes#3901
User-invoked skills (typed /skill:, steered, follow-up, interrupted/
resumed via compaction, ACP, RPC) only appended a bare "Skill: <path>"
line, so the model neither learned the user had invoked that specific
skill nor where the skill directory was. Relative paths in skill bodies
(scripts/, templates/) could not be resolved.
Route all user-invoked paths through a self-identifying, baseDir-aware
prompt template; keep hidden autoload skills on the minimal non-user
format. Interactive skillCommands now carries the loaded Skill object
instead of a bare path so baseDir flows through without reconstruction.
The invocation kind defaults to "user" to keep buildSkillPromptMessage
source-compatible.
Op: correct
Restores: spec:user-invoked-skill-prompt-self-identifies-and-exposes-skill-directory
The replan-driven title refresh (title.refreshOnReplan, fired after a
`todo init`) called `generateSessionTitle()` without the user's
`TITLE_SYSTEM.md` override, silently falling back to the bundled
`prompts/system/title-system.md` and overwriting auto titles with the
default policy. The override was only ever discovered by main.ts and
passed into the first-input title path on InteractiveMode, never into
`AgentSession.#refreshTitleAfterReplan`. Most visible in Plan Mode,
which initializes todos early.
`AgentSession` now owns the resolved title prompt:
- New `CreateAgentSessionOptions.titleSystemPrompt` threaded by
`createAgentSession()` into the constructor.
- New `AgentSessionConfig.titleSystemPrompt` stored on
`#titleSystemPrompt` with a `get titleSystemPrompt` /
`setTitleSystemPrompt(...)` pair.
- `#refreshTitleAfterReplan` passes `#titleSystemPrompt` as
`customSystemPrompt` to `generateSessionTitle()`.
- `input-controller.ts` reads from `session.titleSystemPrompt`, and
the duplicate `InteractiveMode.titleSystemPrompt` field /
constructor arg / `InteractiveModeContext` field / `runInteractiveMode`
parameter are removed. `InteractiveMode.refreshTitleSystemPrompt`
now calls `session.setTitleSystemPrompt(...)` so a `/move`-style cwd
change keeps the override in sync.
Regression test asserts the prompt handed to `completeSimple()` from
`#refreshTitleAfterReplan` is the configured override, not the bundled
`title-system.md`.
Fixes#3734
- Introduced comprehensive support for multiple concurrent, independently-configured advisors via `WATCHDOG.yml` files.
- Implemented a full-screen TUI overlay for managing advisor rosters, models, tools, and instructions.
- Added session-wide advisor initialization, telemetry aggregation, and named transcript isolation.
- Enhanced advisor security and observability with secret redaction in tool results and secure XML attribute encoding.
- Added `statusLine.compactThinkingLevel` setting to render the thinking level as a leading icon.
- Replaced the verbose ` · <level>` suffix with a single glyph when compact mode is enabled.
- Updated the status line controller and component to resolve and propagate the new configuration.
Propagated the first observed reasoning-content unlock to the active streaming assistant component before the reveal controller re-renders it. Added a regression that starts a hidden thinking-off stream and verifies the first reasoning delta becomes visible.
Tracked received thinking content per interactive session so OpenAI-compatible providers that omit reasoning metadata can still reveal streamed reasoning blocks. Added a Ctrl+T regression covering the unlocked visibility path.
Fixes#3669
`handleShakeCommand` calls `rebuildChatFromMessages()`, which clears
`chatContainer` and replays only committed `state.messages`. The agent's
in-flight `streamMessage` and its still-pending tool calls live OUTSIDE
`state.messages` until `message_end`, so the live `streamingComponent`
and `pendingTools` entries were detached while their references stayed
live — every subsequent `message_update`/`message_end` event then
updated orphaned components that never re-rendered, and the in-flight
LLM output disappeared from the chat. Other mid-stream rebuild paths
(setting toggles such as `display.cacheMissMarker` and
`tui.renderMermaid`) had the same flaw.
Snapshot the live `streamingComponent` and `pendingTools` (in their
original chat-container order) before clear, re-append after the
historical replay, and restore the `pendingTools` map so the next
streamed tool-call delta routes back into the preserved component
instead of stacking a duplicate ToolExecutionComponent below it. Idle
rebuilds are unchanged.
Fixes#3656
- Redesigned the Todo HUD as a connector tree with fixed-budget stage previews.
- Anchored status and HUD containers to prevent redundant UI elements in terminal scrollback.
- Implemented tree-based rendering for project phases and tasks while removing dynamic border rules.
- Upgraded `sherpa-onnx` and related packages to support current infrastructure.
- Added a check to restore the live "Working..." loader when streaming events occur after a transient status overlay clears the UI.
- Updated `ensureLoadingAnimation` to re-attach the animation to the status container if it is missing.
Hidden slider means the operator made no choice; a singleton cycle built around the active plan model must not be pinned as executionModel, otherwise approval re-applies the plan model after #exitPlanMode restored the pre-plan one.
Added regression coverage for the plan-only role configuration.
Refs #3554
Same-model role with an explicit thinking suffix that differs from the pre-plan thinking now passes through applyRoleModel instead of being treated as an implicit match.
Added regression coverage for the sonnet:off vs pre-plan thinking-high case.
Refs #3554
Compared the selected approval tier against the model restored after plan mode instead of the active plan-mode tier.
Added regression coverage for keeping the active planning model selected on approval.
Fixes#3554
Replaces the old /move (which relocated the current session file) with a
new flow that starts a fresh empty session in the target directory, leaving
the previous session resumable via /resume. With no argument, /move opens
a path autocomplete overlay (type to filter, Tab to accept, Enter to
confirm). If the target directory does not exist, a confirmation prompt
offers to create it. Empty move sessions are cleaned up on shutdown.
Generated with [Devin](https://devin.ai)
Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Address 4 P2 review comments on PR #3314:
1. effectiveHideThinkingBlock now uses viewSession.thinkingLevel
instead of session.thinkingLevel — in focused-agent mode, the
viewed transcript may have a different thinking level than the
main session.
2. thinking_level_changed handler now iterates existing
AssistantMessageComponent children and calls setHideThinkingBlock
with the new effective value, then resetDisplay() to repaint.
Previously only new/streaming messages got the updated visibility.
3. Changed AssistantMessageComponent import from type-only to value
import for instanceof check.
4. Agent Hub callback already uses effectiveHideThinkingBlock which
now reflects viewSession — no separate fix needed.
can1357