Route '/data/workspaces/can1357__oh-my-pi__1863/.omp-session/2026-06-04T13-36-11-717Z_019e92d9-3fc5-7000-a66f-15cad94b7e75/local' plan artifacts through OMP's session-local storage instead of the editor writeTextFile bridge, preserving ACP bridge routing for regular editor-visible files.
Fixes#1863
- Converted compaction, branch, and handoff prompts to fragment voice.
- Replaced "You MUST" phrasing with bare "MUST" directives.
- Applied same rewrite to autoresearch and turn-aborted prompts.
MCP tool renderers now merge call and result components so completed blocks replace the pending call header with success or error status.
MCP protocol errors now preserve top-level isError so downstream render state can use the error status consistently.
Added renderer coverage for completed MCP success and error blocks.
Fixes#1855
Centralized append-only context auto-mode resolution so SDK sessions, interactive sessions, and the status display use the same provider checks. Auto mode now enables for Xiaomi/SGLang hosts and explicit stored-request compat signals while preserving DeepSeek behavior.
Added focused regression coverage for Xiaomi Token Plan SGLang HiCache endpoints and explicit on/off behavior.
Fixes#1851
Allowed OpenAI-compatible providers to opt into Anthropic cache_control markers via compat.cacheControlFormat while preserving OpenRouter Anthropic defaults.
Fixes#1845
Marketplace plugin toggles in Settings → Plugins wrote the installed-plugin
registry and then only requested a render through the settings callback. In a
live TUI session that left already-loaded slash commands, hooks, tools, agents,
and SSH tool state unchanged until the user manually reloaded plugins or
restarted.
Make the plugin-change callback awaitable and wire the settings selector to the
same reload pipeline used by the slash-command runtime: clear plugin-root caches
for the active project registry, refresh slash command state, refresh the SSH
tool, then request a render. Await the callback after npm and marketplace
registry writes so Settings → Plugins reflects live plugin state immediately.
Add a regression test proving a marketplace toggle calls setPluginEnabled before
the plugin-change reload callback resolves.
`MarketplacePluginDetailComponent` rendered the raw `installPath` from
the installed-plugin registry, which leaks the user's home directory
into the TUI when the plugin lives under `~/.omp/cache`. Route it
through `shortenPath` so $HOME becomes `~` before the value reaches
`Text`, matching the repo's TUI sanitization rules (per review on #1844).
`PluginSettingsComponent.#showPluginList()` only inspected the npm plugin
registry, so the TUI's `Settings → Plugins` panel rendered "No plugins
installed" whenever the user had no npm plugins — even when many
marketplace plugins were installed. The `/plugins list` slash command,
`omp plugin list` CLI, and the install/uninstall selectors already
merged `PluginManager.list()` with `MarketplaceManager.listInstalledPlugins()`;
the settings panel was the only surface that missed the marketplace
registry when it was added.
Extend the panel to consume both data sources:
- Replace `PluginListComponent`'s `InstalledPlugin[]` input with a tagged
union `PluginListEntry = { kind: "npm"; plugin: InstalledPlugin } | { kind:
"marketplace"; plugin: InstalledPluginSummary }`. Each row now carries an
`[npm]`/`[marketplace]` kind badge, a scope tag, and the shadow indicator
for user installs overridden by a project entry. Widen the SelectList
primary column so long `name@marketplace` ids stay readable.
- Add `MarketplacePluginDetailComponent`: single `Enabled` toggle plus the
read-only `InstalledPluginEntry` metadata (version, install path,
installed-at, last-updated, git commit SHA). The toggle calls
`MarketplaceManager.setPluginEnabled(pluginId, enabled, scope)` — same
path `/plugins enable|disable` uses.
- Update `PluginSettingsComponent` to await both `PluginManager.list()` and
`MarketplaceManager.listInstalledPlugins()` in parallel, build the merged
list, and route selection to the kind-specific detail view. The empty
state now lists both install commands (npm and marketplace).
Fixes#1842
The beam backend never invoked the embedding pipeline during normal
operation: `remember()`/`rememberBatch()`/`updateWorking()` skipped `embed()`
entirely and `recall()`/`recallEnhanced()` never called `embedQuery()` on
the query text. As a result `memory_embeddings` stayed empty in every
deployment and recall silently degraded to FTS-only regardless of the
configured provider (fastembed, OpenAI-compatible API, custom).
- Added `scheduleEmbedding` on `beam.pendingExtractions` (mirroring
`scheduleFactExtraction`) and wired it from `remember`, `rememberBatch`,
`updateWorking`, and `consolidateToEpisodic`. Writes
`INSERT OR REPLACE INTO memory_embeddings(memory_id, embedding_json, model)`
with the active runtime-options model, captured before the AsyncLocalStorage
scope exits and re-entered inside the task.
- Auto-derived `queryEmbedding` inside `recall()` via `embedQuery(query)` when
the caller did not pass one. `queryEmbedding: null` is preserved as the
explicit FTS-only opt-out; `undefined` triggers auto-derive.
- Propagated `queryEmbedding` through `Mnemopi`'s `toRecallOptions` so the
facade no longer strips the override on the way to the beam layer.
- Made `Mnemopi.recall`/`recallEnhanced`/`search`/`query`, the module-level
exports, `BeamMemory.recall`/`recallEnhanced`, the free `recall`/`recallEnhanced`,
and `orchestrateRecall` async. MCP `handleToolCall`/`callToolJson`/`handleJsonRpc`
follow suit so the recall handler can await.
- Fixed `withBeam`/`withSharedBeam` to defer `beam.close()` until the async
handler resolves; otherwise the new async recall hit
`RangeError: Cannot use a closed database`.
- Updated CLI, MCP entrypoints, coding-agent `MnemopiSessionState`, and every
affected test to await the new shapes.
Verified with a new regression suite (`test/issue-1832-embedding-population.test.ts`)
exercising both ends of the bug: empty `memory_embeddings` and zero
`dense_score`.
Fixes#1832
The SSH tool renderer fed the raw command into renderStatusLine's
description, so any newline in the remote command expanded the
single-line tool header — the bordered output block then opened
mid-command and the rest of the SSH cell rendered against a broken
frame.
The renderer now keeps only [host] in the header and renders the
full command (with a dim $ prefix and tab sanitization) as its own
framed section above Output, matching the bash renderer's shape.
renderStatusLine also flattens CR/LF in title, description, meta,
and badge labels so no future caller can accidentally produce a
multiline tool header.
Covered by:
- test/tools/ssh-render.test.ts: multiline command stays out of
the header and every command line is present in the body, for
both renderCall and renderResult.
- test/tui/status-line-newline-guard.test.ts: embedded LF, CRLF,
and lone CR in description/meta are flattened to spaces.
Fixes#1828
bun install -g <pkg>@<v> did not reliably re-resolve transitive
optionalDependencies, so @oh-my-pi/pi-natives and the platform leaf
@oh-my-pi/pi-natives-<tag> stayed at the previous version while
@oh-my-pi/pi-coding-agent moved. The loader’s validateLoadedBindings
then aborted because the .node file exposed the old
__piNativesV<old> sentinel instead of __piNativesV<new>.
buildBunInstallArgs now pins @oh-my-pi/pi-natives and (when the
running tag is one the release pipeline publishes) the platform
leaf to the same version it installs for @oh-my-pi/pi-coding-agent,
so bun replaces all three in lock-step. The leaf is gated by the
same SUPPORTED_PLATFORMS set the loader uses, so unsupported tags
still surface the original 'no matching version' diagnostic instead
of EBADPLATFORM.
Fixes#1824
The SlashCommandSpec handle/handleTui signatures and a test `populate`
callback relied on `() => void` being assignable to
`() => T | undefined`. The repo's own gate uses `tsgo`
(@typescript/native-preview) and TypeScript 6.x, both of which accept
that coercion, so `bun run check:ts` passed cleanly. TypeScript 5.x
does not, so `tsc --noEmit -p packages/coding-agent/tsconfig.json`
under 5.9.3 produced 56 errors (`builtin-registry.ts` x46 TS2322,
`agent-session-openai-responses-replay.test.ts` x10 TS2345).
Expressed the slot as a union of two function types — one returning
`SlashCommandResult`, one returning `void` — so the same handler
bodies typecheck under both compilers. `T | void` in a single
function-return position also trips Biome's `noConfusingVoidType`;
the siblings-of-function-types shape avoids that.
Verified:
- TypeScript 5.9.3: 0 errors (was 56)
- tsgo: 0 errors
- bun run check:ts: 0 errors workspace-wide
- packages/coding-agent test/slash-commands + agent-session-openai-responses-replay: 50/50 pass
The issue's other two categories (telemetry-export.ts x2, tui virtual-terminal.ts x1) did not reproduce on this checkout — the catalog
declares @opentelemetry/exporter-trace-otlp-proto,
@opentelemetry/sdk-trace-node, and ghostty-web and they install cleanly.
Fixes#1821
Move the color math added for the session-accent fix into the shared
@oh-my-pi/pi-utils color module instead of a coding-agent-local file:
- colorLuma, relativeLuminance, and hslToHex now live in
packages/utils/src/color.ts (hslToHex lifted out of session-color.ts).
- Drop the duplicate hex parser: toRgb reuses the existing hexToRgb and
paletteToRgb returns the shared RGB type, so hex parsing lives once.
- Delete packages/coding-agent/src/utils/color.ts; theme.ts and
session-color.ts import from @oh-my-pi/pi-utils.
- Move the color unit test into the utils package; repoint session-color
test imports.
No behavior change to accent luminance capping.
- Added `loadOverallPlanReference` to resolve a session plan reference from local storage and skip empty or missing files.
- Updated task execution to read the active plan reference (except in plan mode) and pass it into each spawned subagent.
- Extended the subagent system prompt and session SDK/tools plumbing so subagents receive and render the approved plan path and contents.
- Added TranscriptContainer that snapshots non-live blocks to avoid stale scrollback duplicates.
- Thawed snapshots at prompt-submit checkpoints for reconciliation.
- Repainted eager streaming tail on overflowing shrink to unfreeze UI (issue #1682).
- Added `selectionMarker`, `checkedIndices`, and `markableCount` options to render radio/checkbox glyphs per row.
- Moved checkbox rendering from inline label prefixes into the selector component.
- Kept trailing control rows like "Other"/"Done" on the plain cursor.
- Added `isReadOnlyAgent` and `READ_ONLY_TOOL_NAMES` to classify agents.
- Marked read-only agents and forbade edits, commands, and reasoning offload.
- Added tests for capability classification and description rendering.
The `search` tool required `paths` via a strict `union([string,
array.min(1)])`, so any call that omitted `paths` (or passed an empty
array) was rejected at schema validation with `paths: Invalid input`
and never ran — turning a recoverable "no scope given" into a fatal
tool-call failure.
Make `paths` optional and default an omitted/empty value to the
workspace root (`.`), matching the documented prompt contract. Behavior
is unchanged when paths are supplied. Adds regression coverage for the
omitted and empty-array cases.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Renamed `TodoWriteTool` to `TodoTool` and its source/prompt files.
- Updated tool registration, schema, renderers, and gating to `todo`.
- Adjusted cursor provider native tool names and tests to match.
- Renamed strike-animation constants and `todo-error-reminder` type.
- Wrapped plan content in `` tags for subagent handoff.
- Instructed agent never to read the plan path since content is inlined.
- Replaced collapsible details block in plan reference prompt.
- Added `IndexedSessionStorage` with `SessionStorageBackend` for index-based storage reads.
- Removed `readTextSync` from the public `SessionStorage` API and sync backends.
- Changed Redis and SQL backends to warm `{size, mtimeMs}` metadata and read via `readTextSlices`.
- Added per-path write queues and `drain()` to serialize operations and surface first failures.
- Classified each session's final message as done, interrupted, aborted, error, or pending from a 32 KiB tail read.
- Rendered the status as a colored segment on the session metadata line.
- Added `peekFileTail` and `readTextSuffix` across storage backends to read file tails in one pass.
- Simplified `MemorySessionStorage` to a string array mirror with a sidecar mtime map.
- Extended line selector parsing in path-utils to accept `..` as a forgiving alias for `-`, with `..` normalized during chunk parsing.
- Updated selector-matching regexes for file selectors and internal URL selectors to recognize alias-style ranges in single chunks and comma-separated lists.
- Added tests covering `N..M`, `N..`, mixed separators, inverted-range errors, and path-splitting behavior with `:N..M` selectors and `foo:../bar.ts` paths.
- Added a shared `renderAnswerOptions` helper that redrew answered options with markers, custom input, and cancellation state in-place.
- Set `mergeCallAndResult` to true so ask prompts now keep their question form visible while showing the final selection.
- Kept selection rendering consistent by preserving markers and option ordering while reusing the same layout for completed answers.
- Added `textSizing` terminal capability and `tui.textSizing` setting for Kitty OSC66 scaling.
- Updated OSC66 range and visible-width handling to preserve grapheme slice behavior.
- Updated markdown rendering to apply heading text sizing only when enabled.
- Fixed DECCARA trailing-background fill tracking and DECRPM status 3/4 recognition.
- Updated completion and ask notifications to pass structured payloads.
- Updated completion and ask notifications to include explicit message metadata fields.
- Adjusted abort-guard and retry-capability tests for the new notification/options behavior.
- Added debug menu options for terminal state and protocol checks with new handlers.
- Added terminal diagnostics models and collectors to report geometry, protocol flags, and multiplexer data.
- Added protocol-probe utilities to encode RGB PNGs, generate sample content, and render test panels.
- Added support components for verbatim line rendering and OSC66-scaled text rows.
- Added tests validating image encoding, OSC66 output, and terminal state formatting.
- Added kitty-graphics module with Unicode placeholder and temp-file APIs.
- Refined terminal image handling to use rendered placeholder lines and detect placeholder output.
- Raised the max inline-image default from 3 to 8 in schema and image constants.
- Refined terminal capability flow for Kitty support, including screen-to-scrollback and text-sizing handling.
- Added integration tests for kitty placeholders, virtual placement, and temp-file rendering.
roboomp