The continue() mock used mockResolvedValue(), which never consumed the
queued follow-up. After threshold compaction, #endInFlight ->
#drainStrandedQueuedMessages -> #scheduleQueuedMessageDrain reschedules a
zero-delay continue whenever messages remain queued, so the no-op mock spun
the drain into an unbounded microtask loop that allocated until the test
worker OOM'd (~101GB) and segfaulted, taking sibling tests down with it.
Mirror real continue() semantics (it polls and consumes the queue) by
clearing the queues in the mock, matching the sibling steer-idle-drain
tests. The drain now settles after one resume.
- Added session-domain modules and exports for session-entries, context, listing, loader, and migrations.
- Changed persistence to async append writes plus writeTextAtomic, removing sync line APIs.
- Added compaction-aware session context rebuild with dangling tool-call cleanup.
- Added resumable session resolution with status inference, id/stem/suffix matching, and backup recovery.
Add a display-only `activity` field to AgentRef plus `setActivity`, fed
from the subagent progress chokepoint with a short gist of the agent's
latest intent (or current tool). Render it in the `irc list` output, the
subagent peer roster, and the TUI peer card, beside the role-derived
display name. setActivity emits no event — the roster reads on demand —
so the per-tool-call rate stays off the registry listener path. Peers
with no activity render without a dangling clause.
Refs #2470
Op: extend
When a spawner with remaining depth capacity spawns generic role-less
workers (a task/quick_task spawn without a `role`, or the same agent
cloned >=2x all without roles), TaskTool.execute appends a non-blocking
advisory steering it toward tailored specialists. Gated on DepthCapacity
so a leaf at max recursion is never nudged; the task-tool depth gate is
extracted into a shared `canSpawnAtDepth` helper reused by both the tool
gate and the advisory.
Refs #2469
Op: extend
Document the `role` parameter in the task-tool description (both the
batch and single-spawn shapes) and make tailored specialists the default
rule, not the exception. Direct a recursing worker to pass a `role` for
each sub-specialist. Activates the role field from #2467 for the model.
Refs #2468
Op: extend
Add an optional `role` field to the task spawn contract, threaded end to
end through resolveSpawnItems/spawnParamsFor into the executor. A role
injects a specialization preamble into the subagent system prompt and
becomes the subagent's display name and telemetry identity (label
normalized, length capped), so delegated trees stop being clones of one
generic worker. Empty/absent roles fall back to the agent type name.
Refs #2467
Op: extend
- Added new system prompts that ask models to emit titles inside `<title>` markers when forced tool calls are unavailable.
- Updated `generateTitleOnline` to use marker-based prompting and disable required `set_title` tool calls for models that do not support forced tool choice.
- Adjusted title parsing to extract the `<title>...</title>` value and fall back to stripped marker text when wrapping tags are incomplete.
- Validated queued toolChoice against active tools in agent and coding-agent sessions.
- Rejected queued forced choices with reason "unavailable" when selected tools were inactive.
- Dropped provider toolChoice payloads when requested function tools were not offered.
- Probed Tokio worker-thread support and fell back to current-thread runtime creation.
- Added a changelog entry describing that submitted user messages no longer pair OSC 133 command-start markers with missing end markers.
- Annotated the user-message component with guidance to avoid emitting OSC 133 command-start markers for submitted prompts.
ToolExecutionComponent.#updateDisplay() re-ran renderResult (O(result-size)) on every invalidate - spinner ticks, stream chunks, resizes, keystrokes - so large results blocked the loop for seconds and typing lagged. It now early-returns on an unchanged dirty key (result version, expanded, partial, spinner frame, image visibility, theme epoch), and theme.ts exposes getThemeEpoch() bumped on every theme swap so cached blocks re-render on theme change.
With display.showTokenUsage on, the usage row was rendered inside the
assistant block above the turn's tool blocks. Finalizing the assistant
block was therefore deferred, and the late append recommitted the
already-committed tool rows, duplicating them in scrollback (worst with
parallel tool calls).
The assistant block now always finalizes as soon as a tool-call appears,
and the usage row is emitted as a standalone finalized block below the
turn's tool blocks across all three render paths (live event-controller,
transcript rebuild, agent-hub). The now-dead setUsageInfo/#usageInfo path
on AssistantMessageComponent is removed.
Each live ToolExecutionComponent advanced its spinner glyph from its own
per-instance start time, so concurrent tool spinners showed different
frames and read as janky. Derive the glyph from a single shared monotonic
clock (sharedSpinnerFrame) so every live block animates in lockstep; the
per-instance interval still drives requestRender. The unused
#lastSpinnerAdvanceAt anchor is removed; the todo-strike counter is
untouched.
- Fixed initial assistant persistence by synchronously materializing in-memory entries and keeping a writer open.
- Fixed mid-close append handling to write entries through a one-shot sync writer instead of queuing a rewrite.
- Fixed persist-task gating by tracking pending writes before starting immediate persistence.
- Added tail-only transcript rendering via `renderViewportTail`, stopping at `maxRows` and returning `EMPTY_TAIL`.
- Added `ViewportTailProvider`/`asViewportTailProvider` API and resize getters for viewport state.
- Implemented viewport-only painting during non-mux resize with deferred full repaint after settle.
- Added settle-resize helpers and coverage for deferred repaint timing and cancel paths.
- Queued steering now drains after session settlement, so aborted auto-continued turns no longer leave queued messages stranded.
- Resumable-state detection now treats tool-result messages as resumable so continue can process queued steering after an interrupted tool execution.
- Regression tests were added for queued steer draining after abort and after an interrupted tool result.
InteractiveMode.refreshSlashCommandState() built the autocomplete
provider from builtins, hook/custom/skill commands, and file-based
slash commands but never read session.promptTemplates, so templates
loaded from cwd/.omp/prompts/ and the agent prompts directory expanded
when typed manually yet never appeared in the / picker. Pass them
through alongside file commands; filter out templates whose names
collide with an existing command so the picker mirrors the runtime
expansion order (expandSlashCommand precedes expandPromptTemplate in
AgentSession.prompt).
Added a regression test that constructs InteractiveMode with a session
that carries a prompt template, spies on editor.setAutocompleteProvider,
and asserts the captured provider returns the template for both the
empty / menu and a fuzzy /rev prefix, plus the collision-dedup contract
against the builtin /exit.
Fixes#2462
Bare `omp --list-models` (or any other stale/typoed --flag) was silently
consumed by `parseArgs` and the agent went on to start a real session,
connect to the configured MCP servers, and hang waiting on the model.
Any positional after the unknown flag was reinterpreted as the initial
prompt, so a documentation drift turned into an unintended LLM invocation.
`parseArgs` now tracks flag-shaped tokens that did not match any built-in
or extension-registered flag in a new `unrecognizedFlags: string[]` field,
and `reportUnrecognizedFlags` prints a clean `Error: unknown flag(s): …`
line plus the `--help` hint. `runRootCommand` invokes the helper right
after the post-extension reparse and `process.exit(2)`s before any
session, MCP, or initial-message work runs.
The validation is gated on the extension-aware reparse, so extension
flags (`--spawn-peer`, `--headless`, `--plan`, …) still pass through
the same way `applyExtensionFlags` already handles them. `-` (stdin
marker) and `--` (POSIX separator) are deliberately allowed through.
Fixes#2459
- Refactored status-line context caching to be keyed by message, tail, and window.
- Updated context usage flow to pass breakdown tokens and expose null usage when unknown.
- Adjusted context percentage handling so zero or unknown windows yield nullable values.
- Expanded status-line cache tests for usage provenance, memoization, and invalidation.
- Reworked createAbortableStream to forward abort signals to the source stream reader.
- Added cleanup logic so abort/cancel/error paths release locks and emit AbortError consistently.
- Updated related tests to verify source-stream cancellation and handoff escape-handler behavior.
- Added cmux browser mode options and resolved mode selection from env and app flags.
- Added cmux tab operations for navigation, JS execution, observations, and screenshots.
- Added CMUX socket client messaging with auth, timeouts, and ordered request dispatch.
- Updated browser docs and examples to describe cmux behavior, selectors, and API limits.
- Replaced queued-message interrupt flow with session abort calls on empty submit and escape.
- Removed interrupting state and notifyInterrupting teardown paths from abort handling.
- Updated AgentSession queue operations to use shared steering and follow-up queue views.
- Propagated isAborting through session state and collab payloads to suppress late updates.
- Added a credential-picker `/logout` flow for selecting one OAuth account.
- Added optional `/logout` provider argument and unknown-provider error handling.
- Changed logout handling to delete only the chosen credential and keep others.
- Added AuthStorage APIs to list and remove credentials by id, with remote deletion hook.
Stopped goal objective commands from resolving the interactive input waiter while the agent is already streaming. The goal context still uses steer immediately, and the next idle goal continuation submits the objective work without AgentBusyError spam.
Added goal-mode integration coverage for both initial and replacement objective commands during streaming.
Fixes#2454
- Replaced async getApiKey probing with modelRegistry.hasConfiguredAuth during session model restore and fallback selection.
- Removed the per-provider key cache and avoided startup getApiKey/network work by checking configured auth synchronously.
- Deferred real key retrieval to the request-time resolver while preserving existing model selection flow.
- Filtered dot-only or blank thinking blocks so they no longer render as assistant thought.
- Adjusted assistant-message and streaming-reveal logic to use visible-thinking helpers for consistency.
- Coalesced concurrent interruptAndFlushQueuedMessages() calls through one in-flight promise.
- Replaced continue()-retry logic with agent.prompt() to flush queued messages from empty contexts.
- Skipped queued-message flush replay while compacting or streaming to avoid turn overlap.
- Updated flush path to consume queued steering first, then follow-ups, via dequeuing helper.
- Added a regression test for empty-state interrupt-and-flush delivering queued steers safely.
- Coalesced repeated interrupt-and-flush calls into one queued-steer resume flow.
- Retried queued continues on AgentBusyError after waitForIdle up to a 30s timeout.
- Handled queue-flush failures in input controllers with warning logs and TUI error display.
- Applied a finite 64,000-token fallback for OpenAI completion requests when model maxTokens is unavailable.
- Refactored stream max-token computation to use a shared helper and preserve a finite cap when caller and model limits are null.
- Added regression coverage for null maxTokens flows and bumped the model-cache schema to invalidate entries using retired unknown-limit sentinels.
- Updated AgentSession.setModel and setModelTemporary to validate credentials with hasConfiguredAuth instead of eagerly resolving API keys.
- Changed ModelRegistry.hasConfiguredAuth to probe configured credentials without executing command-backed key programs or refreshing OAuth tokens.
- Added model switch auth tests that verify resolver calls were removed and unconfigured models are rejected synchronously.
- Replaced unknown model contextWindow/maxTokens sentinels with nullable values across types and catalog data.
- Mapped request token calculations to treat null maxTokens as unlimited output caps.
- Updated remote compaction and context checks to ignore unknown limits by using Infinity/0 fallbacks.
- Adjusted CLI/model registry flows to skip cap enforcement for null limits and render unknown values as '-'.
- Added `omp models` command with `ls`, `find`, `canonical`, and `refresh` actions.
- Removed top-level `--list-models` parsing from CLI args, launch, and main command flow.
- Implemented action-driven model listing with provider filtering, extension loading, and `--json` output.
- Updated unknown provider/model errors and tests to direct users to `omp models` guidance.
- InputController now acknowledged empty-submit interrupts before flushing queued steering or queued-abort paths to preserve interrupting feedback.
- EventController now recreated the loading animation on interrupt acknowledgement and deferred end-of-turn teardown while queued resume recovery was still arming.
- AgentSession exposed an isResumingQueuedMessages phase around interruptAndFlushQueuedMessages so stale agent_end events no longer tear down the loader prematurely.
beautiful-mermaid@1.1.3 measures label width in UTF-16 code units, but
terminals render East Asian characters (Hangul/CJK/kana) and emoji 2
columns wide, so fenced mermaid blocks in assistant messages and
render_mermaid tool output had misaligned box borders for non-Latin
labels (upstream: lukilabs/beautiful-mermaid#119, #122).
Adds a patchedDependencies entry rebuilding the ASCII renderer to
measure terminal display columns: grapheme-cluster segmentation
(Intl.Segmenter), wcwidth-style policy (East Asian Wide + emoji
presentation + ZWJ/VS16/flag sequences = 2 columns; text-presentation
symbols like the renderer's own arrowheads stay narrow), and atomic
wide-glyph cell pairs so label collisions cannot shift row widths.
The patch modifies only existing files (bun cannot patch in new files,
and the exports "bun" condition loads src/ directly, so both src and
dist are patched). It mirrors the upstream PR and should be dropped
once the fix ships in a beautiful-mermaid release; a new CJK alignment
regression test keeps that transition honest.
Verified: bun test packages/coding-agent/test/modes/components/
assistant-message-mermaid.test.ts (8 pass, incl. new display-column
alignment regression test); bun test packages/utils (154 pass); Korean
flowchart renders with uniform display-column row widths through the
patched package.
- Replaced Azure and OpenAI provider calls with `postOpenAIStream` flow.
- Fixed stream error handling by retaining status, headers, and body on failures.
- Fixed stream parsing by handling raw JSON SSE frames and `[DONE]` events.
- Added `OpenAIHttpError` with parsed messages and timeout-aware retry behavior.
- Added remote-compaction tests for timeout, abort, and 500-fallback behavior.
- Removed `userMessageId` from `AcpAgent` prompt state and response payloads.
- Removed `models` from new/load/resume/fork session responses and deleted model-state building.
- Removed `unstable_setSessionModel` and routed model changes through `setSessionConfigOption`.
Fell back to the PowerShell clipboard bridge when the native Windows clipboard reader reports no image, preserving Ctrl+V image paste in PowerShell terminals.\n\nFixes #2429
can1357