- 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
The bank id used to be hashed from
`git.repo.resolveSync(cwd)?.repoRoot ?? path.resolve(cwd)`, so adding or
removing a `.git` anywhere above the working directory silently
repointed the same conversation to a new bank and stranded its
memories. Same cwd `/home/x/projects/repo` flipped between
`projects-<hash>` and `repo-<hash>` depending on whether the parent
directory still looked like a repo.
`packages/coding-agent/src/mnemopi/config.ts` now hashes
`path.resolve(cwd)` directly. Session startup also widens the recall
set with any sibling bank under `<dbDir>/banks/` whose
`working_memory` rows already carry the active cwd in
`metadata_json.$.cwd`, so memories stranded by the old, less-stable
derivation become visible again on the next session without manual
migration.
Fixes#2412
Pre-fix `loadSkills` in `extensibility/skills.ts` gated the OMP-native
`agents` provider (the canonical `~/.agent[s]/skills` and project-walkup
`.agent[s]/skills`) on the `anyBuiltInSkillSourceEnabled` fall-through —
the OR of `enableCodexUser`/`enableClaudeUser`/`enableClaudeProject`/
`enablePiUser`/`enablePiProject`. A user who turned off the named
third-party toggles to clean noise from other CLIs silently lost their
own canonical OMP-native skills, so typing `/` showed no `/skill:<name>`
entries for `~/.agents/skills/*/SKILL.md`.
- Added `skills.enableAgentsUser` and `skills.enableAgentsProject` to
the settings schema (default true) and to the `SkillsSettings` shape.
- Routed `isSourceEnabled` to the new toggles for `provider === "agents"`
(per level). The fall-through still covers providers without a
dedicated toggle (`claude-plugins`, `opencode`, `gemini`, `github`, …);
agents joins claude/codex/native at the named-source layer where it
always belonged.
- Updated `docs/skills.md` to document the new toggles and the corrected
enablement rule.
- Refactored `test/skills.test.ts` to share a `DISABLE_ALL_BUILTIN_SKILLS`
helper (so the isolation tests stay correct when new toggles are
added) and added two regression tests: one asserting that the
pre-fix scenario (named third-party toggles off, agents defaulted) now
loads `~/.agents/skills/<name>/SKILL.md`, and one pinning the explicit
`enableAgentsUser: false` opt-out.
Fixes#2401
- InputController now clears typed editor text and triggers a render when Esc is pressed with content, then resets the double-Esc timer.
- The double-Esc selector path was updated to reset the terminal display before opening tree or branch message selectors.
- Escape handling tests were expanded with settings setup/teardown to verify default, branch, and draft-clearing Esc scenarios.
The host schedules a debounced state broadcast right after hello; on slow
runners it lands between a guest's mutating frame and the directed error
reply, so nextFrame() saw "state" instead of "error". Guests now drop
broadcast-only frames (state/agents/entry/event/bus) and wait solely on
directed welcome/error replies.
- Re-polled steering at the loop yield boundary and included it in the pre-stop pending batch so late messages are processed immediately.
- Added session-side draining for stranded queued messages, scheduling an auto-continue when a prompt settles and follow-ups or steers remain.
- Added a regression test for late steering injection at yield and updated mid-turn collab prompt handling to keep steering messages in the pending display queue until consumed.
- Changed the link grammar from `<roomId>#<key>` / `host[:port]/r/<roomId>#<key>` to dot-joined `<roomId>.<key>` in `formatCollabLink`/`parseCollabLink` (`packages/coding-agent/src/collab/protocol.ts`) and the collab-web mirror (`packages/collab-web/src/lib/link.ts`): RFC 3986 forbids a raw `#` inside a fragment, so strict URL stacks (macOS Foundation behind terminal click-to-open) percent-encoded the second `#`.
- Kept legacy `#`-joined links parseable via `BARE_LINK_RE` and added lenient `%23` → `#` decoding for mangled deep links.
- Updated the `ConnectScreen` placeholder, `app.tsx` deep-link comment, `DEFAULT_RELAY_URL` doc in `packages/wire`, `docs/collab.md` examples, and both package CHANGELOGs.
- Extended `crypto.test.ts` and `link.test.ts` with dot-joined, legacy-hash, and `%23`-mangled link coverage.
- Added optional `useless` flags to tool result types and payload builders.
- Added `pruneUseless` and `dropUeless` options to control uneventful result pruning.
- Changed compaction and shake passes to prune or ignore non-error useless tool results.
- Changed conversation serialization to omit useless toolCall/toolResult pairs from output.
- Added coverage for useless tagging, pruning, and serialization behavior.
Restored the default double-Esc action to the editable message-history selector and covered the default controller route with a regression test.
Fixes#2396
- Added a focused-agent left-key input listener that consumes double left taps when the input is empty.
- Routed focused session left-tap behavior through #handleFocusedLeftTap so it matches the Esc-style unfocus timing.
- Updated tests/fixtures for the new listener flow and refreshed a hashline block-edit error assertion.
- Added a SessionFocusController to switch transcript and input context between main and subagent sessions.
- Added agent-hub Enter activation and double-left return behavior for focused local agents.
- Added view-session-based event and render logic to avoid stale focus-session state.
- Added status-line focused agent display with ghost icon and focused-mode border dimming.
- Updated `codexResets.autoRedeem` from a boolean to `unset`/`yes`/`no` in schema and settings types, with updated description text.
- Adjusted Codex auto-reset evaluation to skip checks in `no` mode and to prompt once in `unset` mode before spending, while preserving immediate spend for `yes`.
- Migrated legacy boolean config values to tri-state during settings load and added tests for mode defaults, helper behavior, and migration results.
- Added `src/export/share.ts`: `/share` now snapshots the session JSON, gzips and seals it with a fresh AES-256-GCM key, and pushes the blob to a secret gist or the share server (1 MB cap with image/string/entry truncation via `sealToFit`); links are `<serverUrl>/<id>#<key>` with the key only in the fragment.
- Added `share-loader.js` and `scripts/generate-share-viewer.ts` building the static viewer the relay serves at `GET /s/<id>`: it fetches the sealed blob, decrypts in-browser, and hands the JSON to the export template via `window.__OMP_SESSION_DATA__`.
- Reworked the `/share` command in `command-controller.ts`/`builtin-registry.ts` off the plaintext-gist HTML upload, exported `LoadedCustomShare`, and exposed the session `SecretObfuscator` getter on `AgentSession` for redaction.
- Added `share.serverUrl` and `share.redactSecrets` settings backed by `DEFAULT_SHARE_URL` from pi-wire.
- HTML exports now embed subagent transcripts: `collectSubSessions` walks `<session>/<AgentId>.jsonl` recursively into `SessionData.subSessions`, with `includeSubSessions` opt-out and the exported `buildSessionData` reused by share snapshots.
- Added `share.test.ts` (snapshot/seal/server-url contracts) and `export-subsessions.test.ts`.
- Changed `DEFAULT_RELAY_URL` in `@oh-my-pi/pi-wire` from `wss://relay.omp.sh` to `wss://my.omp.sh` and updated the constants, collab-link, and join-command tests asserting the old origin.
- Added `DEFAULT_SHARE_URL` (`https://my.omp.sh/s`) to pi-wire with its changelog entry; it shares a changed run with the relay constant and is consumed by the upcoming /share work.
- Updated collab-web canonical/OG/twitter URLs in `index.html`, `robots.txt`, `sitemap.xml`, README, and the `local-relay.ts` doc comment to the new domain.
- Refreshed the `/collab` entry in the coding-agent changelog to reference the new relay origin.
- Added detached spawn metadata to lifecycle, progress, and executor session payloads so task and evaluator runs can mark background jobs.
- Updated subagent session tracking and HUD rendering to only show active detached spawns.
- Extended HUD tests to verify non-detached sync and eval spawns are excluded while detached flags propagate through events.
- Changed collapsed progress rendering to keep the most recent live agents visible, adding a summary line for folded-away rows.
- Updated collapsed result rendering to preserve failed and aborted agents in the visible set while trimming other completions.
- Refreshed job polling text to document waiting on all running jobs when `poll` is omitted and added tests for both collapsed progress and result display behavior.
can1357