- Added preview title support and fallback handling across shape previews and status line segments.
- Refined session list sizing and line height budgets in the session selector component.
- Extracted session compaction method helpers and improved speculative compaction logic.
- Prevented armed LLM speculation results from overriding local snapshot compaction execution.
- Added new field, rail, and rule composer styles with accent and surface color support.
- Introduced runtime extension registration for custom composer shapes and styles.
- Updated status line rendering and theme adapters to support dynamic composer styling and gaps.
- Added comprehensive unit tests for new composer shapes, extension loading, and rendering behaviors.
- Enable stringification repairs for expected types in union branches.
- Update test to expect successful string coercion for objects in string union branches.
- Switch github file-read tool to request json contents and handle base64 encoding.
- Add support for parsing image attachments and detecting binary files from github contents.
- Added theme icons and formatting for subscription status and advisor tracking across status lines and footers.
- Implemented `isAdvisorUsingSubscription` and `isUsingSubscription` methods to check active models against OAuth usage.
- Updated status line model segments to display the new advisor icon instead of text badges.
- Added comprehensive tests covering subscription and advisor costs across multiple font presets.
- Introduced embedded mode and context gauge render options for the status line alongside boundary calculation helpers.
- Added pluggable composer styles with a style registry supporting box, claude, pi, and borderless layout rendering.
- Extracted speculation lead resolution into a dedicated shared module and added theme symbol definitions.
- Expanded test coverage for status line context gauge modes, composer shape previews, and editor style assertions.
- Extract foreground wait, notice formatting, and settlement racing logic into a shared module.
- Update async job type definitions to support eval jobs alongside bash and task jobs.
- Add configuration settings for eval auto-background thresholds.
- Moved the overall todo list progress indicator from a horizontal header bar into the tree spine and closing tail.
- Drains the accent fill upward along the spine path when tasks close rather than shrinking a progress bar.
- Add support for customizable composer shapes and editor border styles including box, claude, pi, and borderless.
- Introduce a setup wizard scene and settings selector integration for choosing and previewing composer shapes.
- Enhance status line rendering to support standalone placement and context usage percentage shading.
- Add comprehensive unit tests covering composer shape previews, editor border styles, and status line rendering.
- Prevent schema validation from applying lossy repairs such as container stringification and key deletion to values diagnosed within failed `anyOf` and `oneOf` branches.
- Remove the `coerceArguments` tool option and let repair provenance dictate whether lossy coercions are allowed.
- Introduce OverlayPanel and PanelDivider classes to standardize rounded-box inline overlays and section rules.
- Migrate various UI dialog, selector, and panel components to inherit from OverlayPanel instead of Container.
- Remove manual DynamicBorder elements and custom title/header components across migrated components.
- Update test helpers and assertions to match the new overlay panel structure and rendering methods.
- Added shared process data collection and table formatting helpers to support rendering.
- Added an interactive alt-screen TUI monitor for bare `omp ps` executions on TTYs.
- Added a `--plain` flag to force static process listing output.
- Added a new ps command to list, inspect, view logs, and control daemon processes.
- Implemented CLI handlers and help metadata supporting daemon process operations.
- Added helpers for managing daemon scope metadata, paths, and live broker PIDs.
- Added context length, max tokens, input modalities, and tool support flags to GET /v1/models response in auth gateway server.
- Updated auth gateway model list tests to verify catalog metadata fields in output rows.
- Added Tool.coerceArguments (default true); false skips every LLM-quirk
repair pass (object->string stringification, unrecognized-key deletion,
JSON-string parsing) so validation runs verbatim.
- YieldTool opts out: its args are the deliverable, and the repair layer
silently stringified object payloads into string-typed schema fields
while bypassing yield's own validate-and-retry loop.
- Losslessly salvaged weak-caller envelopes observed in session traces:
type:"result" without the result wrapper finalizes as last-turn,
top-level data/error are wrapped, and JSON-string result/data parse
before consuming a schema retry.
- Added scripts/gen-clippy-bazelrc.ts: emits bazel/clippy.bazelrc from
[workspace.lints] in Cargo.toml (groups by ascending priority, then
per-lint overrides, alphabetical within each tier); --check mode
verifies sync without writing.
- release.ts regenerates it alongside the lockfiles; the release_gate CD
job runs the --check so drift only blocks publishing, never ordinary
CI. Added the gen:clippy package script.
- Introduce CleanseBoardModel and clean up status board rendering logic.
- Decouple CLI and interactive modes with CleanseRunUi interface and core runner.
- Add CleansePanelComponent and controller to manage interactive cleanse overlay.
- Register builtin `/cleanse` slash command and integrate into interactive mode.
bazel/clippy.bazelrc lagged Cargo.toml [workspace.lints.clippy], so the
strict bazel clippy pass denied redundant_pub_crate on utok while cargo
clippy passed locally.
- Added compaction.asyncEnabled (Async Compaction, default on): when
context enters the pre-threshold band [threshold - lead, threshold)
with lead = clamp(threshold * 0.125, 8192, 32000), maintenance
speculatively summarizes in the background off a branch snapshot
(first configured LLM-backed method: remote, handoff, or soft) using
a side session id isolated from the live turn. Crossing the threshold
splices the armed result in instantly instead of blocking on a
summarization round-trip. Armed results are invalidated by branch
changes, reset boundaries, model switches that strand provider-native
replay payloads, and context growth past keepRecentTokens (which
re-speculates); extensions registering session_before_compact keep
exact blocking semantics (speculation disabled).
- Reworked handoff to commit in place: /handoff and the auto handoff
method now write the generated document as a regular compaction entry
on the current session (summary = document + <files> tag, cut from
prepareCompaction) instead of starting a new session. SessionHandoff
shrank to a document generator; session_before_switch/session_switch
no longer fire with reason "handoff"; mid-turn maintenance no longer
suppresses the handoff preference; overflow recovery can apply an
armed handoff result.
- Extracted the shared auto-compaction commit tail
(#commitAutoCompactionResult / #commitCompactionEntry) used by the
blocking production path, the armed speculative apply, manual
compaction, and manual handoff.
- Status line pulses the auto-compact icon while a speculation runs and
holds it in accent once a result is armed.
- Exported remotePreserveReusable from pi-agent-core/compaction for
apply-time validation of speculative remote results.
- Implement a live status board utility for transient multi-line CLI status displays with TTY fallback support.
- Add progress callback support and forward subagent progress events to runner hooks.
- Update cleanse execution flow to track checker runs, agent progress, and status rendering.
- Add comprehensive unit tests for live board repainting and cleanse progress assertions.
- Added `NodeSpan` struct and `nodeChainAt` function in `pi-ast` with native bindings to query AST node chains by line.
- Replaced regex-based annotation parsing with tree-sitter node queries and addedconstruct relocation validation.
- Implemented opener-escape landing correction for inserts anchored on block openers along with warning messages.
- Added comprehensive unit and integration tests covering node chain resolution and escape behavior.
- Introduced `StreamWriter` with configurable block and line buffering policies across builtins.
- Updated pipeline stages and compound commands to execute concurrently as tasks.
- Replaced Linux splice and local stream wrapping with generic `Write` streams and explicit flushing.
- Added regression and streaming smoke tests to verify concurrent output and prevent deadlocks.
- Implemented an animated collapse effect for the interactive mode todo header bar when tasks settle.
- Added timer management and render loop updates for the todo bar collapse transition.
- Replaced legacy `compaction.strategy` and `remoteEnabled` settings with `compaction.methodOrder` across session maintenance, schema, and tests.
- Added automatic fallback mechanism to try subsequent compaction methods upon failure or unsupported model capabilities.
- Added mouse drag-and-drop reordering support and click handlers to multi-select settings submenus.
- Updated documentation and test suites to reflect ordered compaction strategy preferences and fallback chains.
- Added long-context pricing tiers and billing policies for subscription Codex models in the catalog.
- Introduced the `extendedContext` configuration setting to control premium long-context windows.
- Implemented runtime policy refresh and model re-binding when context settings change.
- Added comprehensive unit tests for pricing tiers, context capping, and policy toggling behavior.
- Added annotation row detection to reject under-filled one-sided echoes on single-line replacement ranges.
- Raised default snapshot store path capacity from 30 to 256 to prevent early tags from aging out in wide sessions.
- Added comprehensive test suites verifying boundary repair for single-line annotations and snapshot LRU retention.
Addresses a broad audit of built-in shell utilities against their real counterparts: timeout gains signal delivery, -s/-k/--preserve-status/--foreground/-v, and GNU exit codes; diff defaults to normal format and gains -w/-b/-B/-i/-c/-x/-L/-s/--strip-trailing-cr and proper -r gating; find fixes -newerXY timestamp comparison direction, anchors -regex to whole paths, and gains BSD -perm +mode, -type lists, -size T/P suffixes, -E/-x/-s flags; date gains BSD -r epoch, -v adjustments, -j -f strptime, and non-greedy -I; tail/head accept obsolete -N/+N at any position with any file count; rg resolves case flags by last occurrence and gains --path-separator and clean -0 output; stat prints integer epochs for %X/%Y/%Z and gains BSD -s/-x/-t; cksum is registered as a builtin; truncate implements -o/--io-blocks and b/= size suffixes; sleep/timeout accept infinity; yes/errno/kill accept hyphen-prefixed operands; nohup -- cmd no longer runs --; which gains BSD -s.
- Replaced the stage-position counter in the todo HUD header with a summed progress bar counting closed and total tasks across all stages.
- Added a trailing overflow summary row to announce hidden stages past the collapsed cap.
- Introduced theme symbol support for filled and empty progress bar glyphs across unicode, nerd, and ascii presets.
- Replaced the `ctok` implementation with the `utok` universal tokenizer supporting multiple model families and UTF text encodings.
- Added tokenizer support and embedding data for Qwen3, DeepSeek V3, Kimi K2, and GLM-5 model variants.
- Added fixture generation scripts, vocabulary packers, and golden test suites for validating tokenization parity.
- Updated dependency requirements and Bazel workspace definitions for new crates and tools.
- Add `setPromptDropped` hook and `DroppedPrompt` type to return prompts that were cancelled during turn setup before dispatch.
- Restore dropped prompt text and image attachments to the interactive mode editor and remove the optimistic transcript row.
- Implemented the `ctok` Rust native tokenization engine with offline support for Claude V3, V47, V5, and V5Sonnet families.
- Replaced global token estimation with model-scoped `Tokenizer` instances and provider-anchored transcript accounting across packages.
- Added vocabulary generation scripts, test fixtures, and comprehensive unit tests for tokenizer routing and matching modes.
- Replace newline characters with visual indicators in subagent HUD descriptions and task previews.
- Add unit tests verifying multiline description and task rendering.
- Added `qwenTemplateReasoningEffort` model compatibility option to disable Qwen chat template kwargs for strict local servers.
- Implemented fallback handling to strip rejected `chat_template_kwargs.reasoning_effort` and hoist values to top-level fields.
- Added comprehensive test coverage for Qwen reasoning effort fallback and keyword rejections.
- Fixed `muse-spark-1.2` and `muse-spark-1.2-contributor` failing on tool-call turns by mapping them to `openai-responses` in `OPENCODE_GO_API_ID_OVERRIDES`.
- Added automatic fallback routing to borrow `openai-responses` routes from sibling gateways or billing-variant base IDs for gateway-first models.
- Configured `dropCachedModelIdsOnStaticMismatch` to ensure cached models holding stale static metadata are invalidated on discovery.
- Add support for risk notes and warning markers on setting items in the TUI settings list component.
- Update the external thinking setting schema and help command to include a warning about provider abuse enforcement.
- Added `fetchUsageData` and fleet token summation to aggregate token burn across clients.
- Changed window grouping logic from window labels to limit IDs for distinct separation.
- Updated `ProviderWindowInsight` properties and added tests for label suffixing and token summation.
The ask-card note renderer (#8786) grew tool-views.generated.js by 126 bytes; CI regenerates the asset so the byte-pinned template contract (bytes/chars/sha256) moved. Values verified identical between CI and a fresh local gen:tool-views.
bazel test sandboxes stage only the crate's declared inputs, so the repository sweep found zero sources and tripped its own evidence guard ('corpus sample too small to be evidence: 0'). Skip on a missing or empty corpus; any non-empty scan still enforces the >40-file evidence floor.
`resolveCliArgv` hoisted a subcommand hidden behind leading global launch
flags to the front and forwarded those flags to the subcommand's own
parser (#2970). Launch-shaped commands (`launch`/`acp`) share the launch
flag surface, but strict-parsing subcommands like `update` declare only
their own flags, so a leading `--cwd` reached `node:util.parseArgs` and
threw `Unknown option '--cwd'`. This bit users whose shell alias/wrapper
runs `omp --cwd <dir> update`.
Leading launch-global flags are now stripped when the hoisted subcommand
is not launch-shaped, and still forwarded for `launch`/`acp`. Shared the
launch-command set with the profile bootstrap to keep one source of truth.
Fixes#8891
parseFileDiffs split the captured `git diff --cached --binary` on
"
diff --git ", consuming the newline that terminates each file block, and
patch.join ended with `.replace(/\n+$/, "")`. Both dropped the blank line
that terminates a `GIT binary patch` block, so rebuilding a split-commit
patch produced a corrupt binary patch rejected by `git apply --binary`.
Split on a line-start lookahead so blocks keep their terminators verbatim,
and concatenate join parts without stripping trailing newlines. Both
trailing and mid-diff binary blocks now round-trip byte-exact.
Fixes#8899
can1357