/usage, /session, /advisor status, /jobs, /changelog, /context, and
/memory view mounted their finalized panel immediately via ctx.present()
instead of ctx.presentCommandOutput(), the streaming-deferral path added in
#5427 for /tools and /mcp. When invoked mid-turn, the panel landed above a
still-growing live block and the append-only scrollback contract recommitted
it lower down, so it appeared twice in native scrollback.
Route all six large command panels through presentCommandOutput() so they
defer until agent_end, matching /tools and /mcp.
Fixes#6767
/usage and omp usage now report Synthetic (synthetic.new) quota state
via GET /v2/quotas (free, does not consume quota): the rolling 5-hour
request limit with per-tick regeneration rate, and the weekly credit
quota in USD. Applies to API-key credentials for the synthetic
provider; every payload section is parsed defensively since only
subscription is documented.
The TUI /usage matrix sorted each quota window's account columns
independently by used fraction, so the positional `account N` labels
denoted different credentials on each row. An account exhausted on one
window but light on another (e.g. a Kimi Code account's 5h limit)
rendered its exhausted bar under a sibling that still had quota, making
the section `% free` and capacity numbers look wrong.
Order account columns once per provider (worst-first) and hold that
order stable across every window row.
Fixes#6067
Preserved settled user and assistant component instances during compaction-only transcript rebuilds so warmed Markdown and layout caches remain valid.
Covered both manual and automatic compaction paths with focused regression tests.
Fixes#6033
Brings the per-advisor toggle, status-line glyphs, quota display, and the
failing-advisor stall/abort fix (f4c8143) onto main's rewritten advisor
runtime. Conflict reconciliation kept main's architecture (fingerprint
prefix reconciliation, host-level onTurnError recovery + fallback chains,
terminal-failure classification) and ported the branch semantics onto it:
- #failing latch: waitForCatchup resolves immediately while an advisor is
mid-failure; parked waiters wake the moment a turn fails, before any
async hook or retry sleep.
- Turn-end render containment: a formatter bug restores the cursor/prefix/
dedup snapshot and never propagates into the primary's turn-end callback
(per-advisor try/catch boundary in AgentSession).
- Quota pause: when host recovery declines a usage-limit failure, the
runtime latches quotaExhausted, requeues the batch, and notifies —
cleared only by an explicit reset.
- Hard halt after a permanent rejection or three backlog-drop cycles.
- #recoverAdvisorTurn also marks usage limits for structural errors thrown
before any assistant turn is recorded.
Removed the 24-column cap from account cells so wide terminals can show full disambiguating labels.
Kept usage bars independently capped and added regression coverage for same-email organization accounts.
Fixes#5701
The /usage show "in use by this session:" marker took only the bare
email from OAuthAccountIdentity, so two same-email Anthropic credentials
in different orgs were indistinguishable. Route the label through a
shared formatActiveAccountLabel that suffixes the active org, matching
the account list and login-success surfaces.
Fixes#5691
- Added the `xd://` virtual device protocol (`internal-urls/xd-protocol.ts`, `tools/xdev.ts`): tools declaring `loadMode: "discoverable"` are unmounted from the request tools array and driven via `read xd://` (list/docs+schema) and `write xd://<tool>` (execute), gated by the `tools.xdev` setting (default on) and inlined into the system prompt.
- Merged the `irc`, `job`, and `launch` tools into a single `hub` tool (`tools/hub/`, `async/job-manager.ts`): messaging keeps `send`/`inbox`/`list`, job control maps to `wait`/`cancel`/`jobs`, process supervision keeps `start`/`logs`/`stop`/`restart`/`describe` with `ps`, and the unified `wait` races background jobs against peer messages; SDK `IrcTool`/`JobTool`/`LaunchTool` are replaced by `HubTool`.
- Removed the hidden `resolve` tool in favor of the `xd://resolve`/`xd://reject`/`xd://propose` resolution devices, auto-including `write` whenever a deferrable tool or plan mode is present.
- Removed the BM25 tool-discovery system: the `search_tool_bm25` tool, the `tool-discovery` module, the `tools.discoveryMode`/`mcp.discoveryMode`/`mcp.discoveryDefaultServers`/`tools.essentialOverride` settings, per-tool MCP selection, and the `mcp_tool_selection` message type.
- Unified tool presentation on `ToolLoadMode` (`essential`|`discoverable`), replacing the custom-tool `xdev?: boolean` opt-out; custom, extension, MCP, RPC host, image-generation, and TTS tools now default to `discoverable`, and added a `satisfies` predicate to `SoftToolRequirement`.
- Removed the standalone `ssh` command tool and `ssh/ssh-executor` (the `ssh://` read/write/search protocol stays), and made `--tools` address hidden built-ins.
- Updated collab-web to render `xd://` dispatches and `hub` op families, dropped the `search_tool_bm25`/`ssh`/`report-finding` renderers, refreshed tool docs and prompts, and migrated the affected tests and changelogs.
Vibe worker roster lived only in a process-local Map, so a resumed parent
session started with an empty registry and vibe_send failed with
"Unknown vibe session". Persist a versioned, parent-scoped lifecycle
journal (spawn/turn/tombstone events), rehydrate validated idle workers
through the persisted-subagent reviver on resume, and gate the flow with
generation/CAS protection so stale finalizers cannot clobber a
replacement worker. Killed transcripts stay readable but non-revivable;
mode-exit commits tombstones atomically with the mode change and rolls
back cleanly on storage failure.
Ported from @mastertyko's fork branch fix/vibe-session-persistence.
Fixes#5303
- Introduced conditional scrollback clearing during UI renders when transcript compaction is enabled.
- Updated `CommandController` and `EventController` to respect the `display.collapseCompacted` setting.
- Configured `SelectorController` to trigger a chat rebuild and UI reset when the compaction setting changes.
- Updated `InteractiveMode` to dynamically toggle between collapsed and full inline history based on user settings.
One Anthropic account email can hold multiple organizations (a Team seat
plus a personal Max plan), each with its own org-scoped OAuth token and
independent 5h/7d limit pools. Credentials were deduped by bare email, so
logging in with the second subscription silently replaced the first, and
usage reports from the two pools merged into one row with mixed numbers.
- capture organization uuid/name at login (token exchange response, with
a claude_cli/bootstrap fallback); token refreshes never rewrite it
- key anthropic credential identity as email + org; a legacy email-keyed
row is claimed in place by the first org-scoped login with the same
email, and org-less credentials never clobber org-scoped rows
- partition usage-report dedupe and the per-credential usage cache by
org so the two subscriptions' limit pools stay distinct for rotation
- show the organization in omp usage (redaction-safe) and name the
stored account/org in the login success message
- Treated missing or invalid changelog markers as first install and persisted the current version without replaying historical notes.
- Shared bounded changelog rendering between startup and recent changelog views, with a 64 KiB startup cap and full-history hint on truncation.
- Added marker, truncation, recent/full rendering, and PTY startup regression coverage.
Fixes#5135
- Add 'enabled' field to AdvisorConfig (default true, persisted in WATCHDOG.yml)
- Filter disabled advisors in #resolveAdvisorRuntimeDescriptors, keep in status map
- Classify quota/rate-limit errors separately from transient server errors
- Auto-pause advisor on quota exhaustion, auto-resume after 5min cooldown
- Add AdvisorRuntimeStatus enum (running/paused/no_model/quota_exhausted/error)
- Render per-advisor status dots in status line: ●○✕ with truncation to 4+ '+'
- Include disabled/no-model advisors in PerAdvisorStat with status field
- Add notifyQuotaExhausted host callback distinct from notifyFailure
- Tests: config round-trip for enabled field, quota classification, overloaded path
Stopped new-session and session-switch UI paths from detaching active loader/render components without running their disposal hooks.
Added container and loader coverage for disposing children before destructive transcript/status replacement.
Fixes#4686
- Enforced strict history protection by gating ephemeral block removal on uncommitted state across controllers and UI components.
- Optimized settled-row calculations using explicit mermaid fence detection and improved scrollback integrity.
- Refactored transience management to target only actively streaming blocks, preventing redundant label rendering.
- Implemented persistent compaction for auto-retry errors and enabled consistent terminal title updates during session renaming.
Plan-approval's 'Approve and compact context' used to pass the rendered
plan-mode-compact-instructions prompt as the first positional argument
to handleCompactCommand -> session.compact(), which landed on the
session_before_compact extension hook as customInstructions. Extensions
treating that field as user focus (e.g. to bias a query-focused summary)
would then see plan-mode boilerplate instead of operator intent and
produce query-biased compactions.
Add CompactOptions.internalGuidance: a private summarizer-only channel.
session.compact() reads it into the fallback-model summarizer while the
session_before_compact hook payload still only carries the public
customInstructions arg (undefined for the plan-compact path). The
snapcompact-disable predicate and the /compact rejectsFocus guard cover
both fields so a directed summary is never silently downgraded.
Extend the interactive-mode handleCompactCommand facade + command
controller with a fourth internalGuidance parameter, and switch the
plan-approval callsite in interactive-mode.ts to route the plan prompt
through it.
Fixes#4359
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
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
- 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.
roboomp