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.
- 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.
The time_spent segment rendered Date.now() - sessionStartTime, so an
idle session displayed hours of "time spent" while the agent did
nothing — the only inputs were wall-clock and the unmoving session
start.
Replace sessionStartTime with activeMs in SegmentContext and accumulate
inside StatusLineComponent across agent_start -> agent_end windows.
markActivityStart/markActivityEnd are idempotent (reentrant agent_start
events and superseded agent_end events never double-count); the segment
ticks live during an open window and freezes when the agent yields.
The session-boundary hook drops the now-meaningless wall-clock argument
and is renamed setSessionStartTime -> resetActiveTime; it zeroes the
accumulator and drops any in-flight window so /clear / fresh-session /
joined-collab paths start the meter at zero.
Fixes#3681
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>
renderUsageReports (command-controller) carried the #3268 dedup contract
with no regression test; the PR's added CLI test asserts the opposite
(per-limit CLI rendering shows the note twice). Export renderUsageReports
and add a real regression through it: two accounts sharing one window group
render a provider-wide UsageReport.note once and an identical per-limit note
once. Verified failing on the pre-fix flatMap form (0 and 2 occurrences) and
passing on head (1 and 1).
Address review feedback: provider notes could contain tabs, embedded
newlines, or control characters that break TUI rendering. Both note
rendering sites (provider-wide and per-group) now wrap the joined text
through sanitizeText → truncateToWidth → replaceTabs per AGENTS.md
TUI Sanitization rules.
Provider-wide disclaimers (e.g. OpenCode Go's "OMP-observed spend
only") were duplicated onto every UsageLimit, then repeated N times
in the TUI aggregate renderer (once per account × window). With
2 accounts × 3 windows, the same disclaimer appeared 6 times
bullet-joined.
Structural fix:
- Add notes?: string[] to UsageReport (interface + both schema
copies: usage.ts and auth-broker/wire-schemas.ts) so the field
survives the broker client's "+": "reject" deserialization gate.
- Move opencode-go's disclaimer from per-limit notes to
provider-level notes.
Defensive fix:
- Dedup identical per-limit notes in the TUI aggregate renderer
(command-controller.ts) via [...new Set(...)].
- Render provider-level notes once above per-account sections in
all three rendering paths: TUI (command-controller), CLI
(usage-cli), and ACP (usage-report helper).
Regression tests:
- usage-cli.test.ts: provider-level notes render once, not
duplicated per account or limit; positioned above per-account rows.
- usage-report-notes-schema.test.ts: wire-schema round-trip proving
notes survives usageResponseSchema validation.
Fixes#3268
Jeff Scott Ward