- Added a new built-in `title` model role with `hidden` metadata and updated role definitions and schema.
- Updated title generation to resolve models in `title`, `commit`, then `smol` order and added test coverage for that precedence.
- Filtered hidden roles from selector badges and documented the new built-in role in model/settings docs.
Read vLLM max_model_len and OpenAI-compatible context_length metadata during model discovery, route providers.vllm.baseUrl into built-in discovery before cached models exist, and avoid sending local placeholder bearer tokens.
Scope the vLLM model cache to the discovery base URL so endpoint changes refetch immediately, and add focused regression coverage for configured and built-in vLLM discovery.
- Tracked snapshot-safe boundaries to retain commit-stable streamed rows in scrollback.
- Computed durableBoundary from commit and snapshot ends to prevent row drop regressions.
- Updated audit-row handling so drifting durable rows were excluded from resync checks.
- Added regression tests for commit-stable and commit-unstable relayout streaming cases.
- agent-loop: raise repetition-detection floor to 180 chars and clear thinking
replay anchors when collapsing a detected loop.
- providers/google: ignore empty text parts, retain terminal thoughtSignatures,
and stop function-call signatures clobbering the prior block.
- autolearn: capture goal-mode at the turn boundary; harden managed-skill writes
against hard-links/symlinks (O_NOFOLLOW + nlink); refuse minting managed skills
whose name an authored skill already claims.
- eager tasks: thread agentKind through the session so a custom top-level agentId
still gets always-mode delegation; split Eager Tasks prompt into hard vs soft.
- title-generator: race the online title model against a local tiny-model fallback.
- eager-todo: keep the soft reminder aligned with the todo init schema.
- mcp/stdio: keep close() detaching the read loop instead of awaiting it.
- stream loop: fix collapsing and tool-call thought-signature handling.
- Added a space-hold gesture state machine in CustomEditor, tracking repeated spaces, detecting holds beyond SPACE_HOLD_THRESHOLD, and firing start/end callbacks via a release timer.
- Hooked editor space-hold callbacks in InputController so STT toggles on hold start and again on release when STT is enabled.
- Added tests for space-hold start/stop behavior and updated keybinding docs to describe the hold-to-record STT workflow.
- Updated JS eval helper option parsing to accept positional optional args or a trailing plain-object options argument, while rejecting mixed or invalid forms.
- Updated `read` to route non-`local://` URI paths through the `read` tool with line selectors so offset/limit slicing works for artifact-style resources.
- Expanded JS executor tests for positional reads, nullable slot skipping, and delegated URI read slicing.
- Updated the resize fast-path repaint to remove the terminal full-screen clear and instead overwrite the viewport in place at home, rewriting each row via `#lineRewriteSequence`.
- Passed the viewport width into `#emitResizeViewport` so each row self-clears only its tail with CSI K while resize drag remains active.
- Added coverage in `resize-viewport-defer.test.ts` confirming drag-time writes omit ED2/ED3 clears and that ED3 is emitted when the resize settles.
Add a default-off "auto-learn" loop. When `autolearn.enabled` is set, after the
agent stops a session controller nudges it to capture reusable lessons: durable
facts go to long-term memory and repeatable procedures become "managed skills" —
SKILL.md files written to an isolated ~/.omp/agent/managed-skills directory that is
discovered and surfaced like authored skills but never overwrites them.
Two tools back this:
- `manage_skill` — create/update/delete managed skills.
- `learn` — record a lesson, optionally minting/enhancing a managed skill in the
same call (requires a hindsight/mnemopi memory backend).
The nudge is passive by default (a hidden reminder rides the next turn);
`autolearn.autoContinue` instead auto-runs one capture turn at stop, and
`autolearn.minToolCalls` (default 5) gates trivial turns. Plan/goal-mode turns and
subagents are never nudged, and the controller re-checks the live setting at fire
time so a mid-session opt-out takes effect.
Isolation & precedence: managed skills are a separate lowest-priority discovery
provider, so an authored skill of the same name wins across every provider and
custom directory regardless of third-party toggles; a disabled higher-priority
authored skill can never hide a managed one, and managed never masks an enabled
authored skill. Managed names and descriptions are sanitized on both write and
read (control/format chars, angle brackets, and Markdown fences) before they render
into the system prompt, and the SKILL.md byte cap is enforced on the final
serialized file.
Default off → zero footprint when disabled.
- 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.
- docs/models.md: retitled the '/model and --list-models' section and
updated the bullet to describe 'omp models' plus 'omp models canonical'.
- docs/providers.md: updated the troubleshooting note to validate
models.yml with 'omp models' (and 'omp models find <substr>').
- packages/coding-agent/CHANGELOG.md: noted the doc fix under Unreleased.
Fixes#2458
- Documented built-in defaults in the settings precedence chain.
- Documented PI_CODING_AGENT_DIR migration of agent data to ~/.omp/agent.
- Documented legacy settings migration to config.yml and settings.json backup.
- Documented omp config merge behavior, global-only persistence, and YAML overlay hard-fails.
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
- 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
- Replaced the committed `template.generated.ts` with Bun text imports (`with { type: "text" }`) of `template.html/css/js` plus the gitignored `tool-views.generated.js`, composed in a memoized `getTemplate()` in `src/export/html/index.ts`.
- Deleted `scripts/generate-template.ts` and the unused `template.macro.ts`; removed the stale package-level `.gitignore` and the `biome.json` exclusion for the generated file.
- Wired root `prepare` to `generate-docs-index` + new `build-tool-views` script and coding-agent `prepack` to rebuild tool views before `bundle-dist`, so source runs and publishes never need a manual generate step.
- Added narrow ambient text-module declarations (`*.css`, `*/template.js`, `*.generated.js`) to `bun-imports.d.ts`; `*.html` stays untyped because bun-types claims it as `HTMLBundle`, so the import casts at the use site.
- Updated `DEVELOPMENT.md` and `docs/porting-from-pi-mono.md` references; the rewritten import block transiently carries `loadEntriesFromFile`, consumed by the next commit's sub-session loader.
- Added `packages/collab-web/src/tool-render/`: a per-tool React renderer suite (one view per built-in tool) with common `ToolView` chrome, a `tv-` CSS design system, a registry, and an `<omp-tool-view>` web-component wrapper (`element.tsx`, `standalone.tsx`).
- Switched collab-web transcript `ToolCard` to the per-tool renderers instead of the generic args/result JSON dump, and threaded a `ToolRenderHost` through `Transcript`/`AgentDrawer`/`app.tsx` so task-card agent chips drill into the matching subagent drawer.
- Added `scripts/build-tool-views.ts` plus the `build:tool-views` script bundling the renderers (React included, `</script` escaped) into the gitignored `coding-agent/src/export/html/tool-views.generated.js`.
- Modernized the coding-agent HTML export chrome in `template.html/css/js` to the tool-card design language and added the `<template-tool-views/>` injection point.
- Showed the standard done checkmark for completed rows in the `job` tool renderer; its changelog line shares a changed run with the restyle entries.
- The session-operations doc gained two adjacent lines; the subagent-transcript one belongs to the upcoming /share commit but is inseparable from the tool-view line.
- Added write-token generation and validation to distinguish writable and read-only guests.
- Added deep-link support using `https://<relay>/#<link>` with 32/48-byte collab secrets.
- Added full-link and key-only semantics where full links grant writes and key-only links are view-only.
- Added /collab view/status/stop command updates with read-only participant status and join hints.
Individual conflict resolution now bypasses the LSP writethrough to prevent formatting from corrupting other unresolved marker blocks and to avoid noisy diagnostics in partially resolved files.
- Implemented model-specific frame-size billing for Anthropic, OpenAI, and Google.
- Changed compaction shape resolution to bind model variants to ideal frame sizes.
- Updated tests and docs to reflect new frame-size and budget behavior.
- Adjusted snapcompact rendering to compute used rows from text, dim toggles, and doc line breaks, then derive output height from usedRows x lineRepeat x cellHeight.
- Updated indexed and RGB PNG encoders to accept explicit canvas width and height so native renders now emit non-square frames matching actual content.
- Expanded Rust and TypeScript tests and updated docs/changelogs to assert and describe variable-height frame behavior.
- Added support for `{api,id}` `ShapeTarget` in `resolveShape`, deriving variants from model IDs.
- Added provider budget APIs/constants and `providerFrameBudget` clamping with `MAX_FRAMES`.
- Added `Archive.textTail` and moved overflow pages into plain-text tail folding across frames.
- Updated summary prompt rendering to show continuation only when `textTail` exists and append it as text.
- Repointed `SHAPES.anthropic` and the `anthropic-messages`/unknown-API fallback in `resolveShape` at the `6x12-dim` variant: production mono eval on claude-fable scored f1 .840 vs .877 for the repeated grid (within noise at n=25) at 37% lower cost, with no refusals.
- Reworded the `snapcompact.shape` descriptions in `settings-schema.ts` to drop per-provider eval-winner claims from the variant help text.
- Updated `snapcompact.test.ts` (new `6x12-dim` default render/compact assertions, `8x8r-bw` exercised via `resolveShape`), `snapcompact-inline.test.ts` frame math for the new geometry, and the `docs/compaction.md` shape sentence.
- Amended the snapcompact `[Unreleased]` entry that said the Anthropic default stayed `8x8r-bw` and added the default-switch entry.
- Added a new `bench` CLI command with multi-model selectors and new options.
- Implemented `runBenchCommand` validation, per-run session handling, and failure exit reporting.
- Updated default compaction shapes to `8x8r-bw` and `doc-8on16-sent-dim` in code and schema.
- Documented `bench` flags, per-run errors, failure counts, and exit behavior.
- Resolved OpenAI shape resolution to `openai` and default to `8on16-bw`.
- Fixed catalog generation to collapse effort tiers before provider grouping.
- Updated help text and schemas to describe `8on16-bw` as the OpenAI auto default.
- Added production `render_pages` and `mono_prod` scripts for end-to-end QA output.
- Added the `6x12-dim`, `8x13-bw`, `8on16-bw`, `doc-8on16-bw`, `doc-8on16-sent`, and `doc-8on16-sent-dim` options to the `snapcompact.shape` enum in `settings-schema.ts` with per-variant descriptions naming each eval winner.
- Updated the `snapcompact.shape` paragraph in `docs/compaction.md` to list the new grid and two-column doc variants.
- Updated the coding-agent changelog: rewrote the `snapcompact.shape` Added entry for the new variants and recorded the Changed/Fixed entries for the already-landed variant-alias and pending-preview commits (one contiguous changelog run).
- Added snapcompact.shape setting with auto and variant options in agent config.
- Implemented resolveShape support for forced variants, auto provider winners, and repricing.
- Threaded resolved shape into compaction and inline-image flows for pricing and rendering.
- Removed the `note` operation from `TodoOp` validation and the `text` field from todo operation payloads.
- Deleted `TodoItem` note storage and stripped note-aware logic from execution, markdown round-trip helpers, summaries, and rendering.
- Updated todo docs and prompt schema text to remove `note` usage and keep the public operation set aligned.
- Updated block resolution to detect structural-closing-line anchors and convert unresolvable `insert after block` edits into plain `insert after` inserts while emitting a dedicated warning.
- Propagated these resolver warnings through `PatchSection` and `Patcher` results so parse and application callers receive them.
- Added tests covering the closer-anchor fallback and confirming non-closer unresolved block anchors still throw.
- Added `mnemopi.polyphonicRecall` and `mnemopi.enhancedRecall` boolean settings (default off) to `settings-schema.ts` and `loadMnemopiConfig`, applied via the new `configureRecallFeatures()` in `createScopedResources`.
- Made `polyphonicRecallEnabled()`, `enhancedRecallEnabled()`, and `isEnhancedRecallEnabled()` fall back to the configured defaults while `MNEMOPI_POLYPHONIC_RECALL` / `MNEMOPI_ENHANCED_RECALL` env vars still win when set.
- Exported `configureRecallFeatures`/`RecallFeatureFlags` from the package root and `core` barrels; documented the settings in `docs/mnemosyne-memory-backend.md`.
- Added `recall-feature-flags.test.ts` covering defaults, config enablement, and env precedence; the mnemopi changelog hunk also carries the adjacent #2322 entry (same contiguous run).
Fixes#2323: Mnemopi: MNEMOPI_POLYPHONIC_RECALL and MNEMOPI_ENHANCED_RECALL not configurable via config.yml
- Renamed all functions, types, and constants in @oh-my-pi/snapcompact to namespace-relative names (`snapcompactCompact` → `compact`, `renderSnapcompactFrames` → `renderMany`, `snapcompactFrameCount` → `frames`, `SnapcompactShape` → `Shape`, `SNAPCOMPACT_SHAPES` → `SHAPES`, …).
- Converted every consumer to `import * as snapcompact` member access: `agent/compaction.ts`, `coding-agent` `agent-session.ts`/`session-manager.ts`/`snapcompact-inline.ts`, and all affected tests.
- Renamed internal `geometry` locals to `geo` in `snapcompact.ts` to avoid TDZ collisions with the new `geometry` export.
- Updated `docs/compaction.md` prose and added a Breaking Changes entry to the snapcompact changelog documenting the full rename map.
can1357