- Updated type signature to show `paths` accepts `string | string[]` instead of only arrays.
- Clarified that single string paths are wrapped into a one-element list before resolution.
- Improved prompt instructions to explicitly show both string and array usage patterns.
- Removed per-session run queues from JS and Python backends, allowing async cells on the same session id to interleave.
- Introduced `getEvalSessionId` on ToolSession so subagents spawned via `task` inherit the parent's executor id and share JS VM and Python kernel state.
- Switched JS runtime state from module-level fields to AsyncLocalStorage so concurrent runs route output and tool calls to their own context.
- Changed Python runner to an asyncio event loop with per-request tasks and ContextVar-based run id tracking for concurrent execution.
- Added mtime-based module cache eviction to preserve singleton state across re-imports of unchanged local files.
- Replaced per-line hash anchors with file-level hash validation in hashline format, changing anchor syntax from LINE+HASH to bare LINE numbers.
- Simplified hashline line separator from pipe (|) to colon (:) and replaced replace operator (->) with colon, added delete operator (!) for explicit line deletion.
- Implemented file-read snapshot caching with multi-snapshot ring buffer per path and file-hash-based recovery to detect and recover from stale edits.
- Refactored hashline grammar, parser, and execution to support file-level hash binding, anchor-scoped validation, and structural bracket warnings for delete operations.
- Updated documentation and test fixtures to reflect new hashline syntax with file hashes, colon separators, and delete operator throughout.
- Removed vim edit mode and automatically map existing vim configurations to hashline mode.
- Deleted VimTool class, VimEngine implementation, and all vim-specific editing logic (2409 lines).
- Removed vim mode from EditMode union type, edit tool strategies, and configuration schemas.
- Deleted vim parser, command handler, buffer manager, and renderer modules.
- Updated documentation and tests to remove vim mode references and add deprecation mapping.
- Updated hashline markers to `¶` headers and `^/v/->` operators across constants, prompts, docs, and tests.
- Reworked hashline grammar and parser to support `ANCHOR<SIGIL>[INLINE_PAYLOAD]` with optional inline bodies and `A-B` ranges.
- Changed range and marker syntax from `..`/`"` to `-` and suffix `^/v/->` forms like `7v` and `A->`.
- Aligned `sameLineRange()` output and BOF/EOF handling so `|TEXT` remains cosmetic and payload now follows the op line.
- Centralized op-line detection by replacing local regex helpers with `isHashlineOpLineText` for payload terminator and bad-op checks.
`ref` is a JTD-reserved keyword (RFC 8927) used by the schema-reference
form, so the JTD-to-JSON-Schema converter on releases prior to 15.3.2
silently dropped it from the generated JSON Schema and required it at
the same time. Every explore-agent invocation then failed validation
with `schema_violation: files.0.ref: must not be present`.
The converter side was hardened in #1345 (shipped in 15.3.2). This
rename is defense-in-depth at the prompt level: the explore agent's
output contract no longer relies on the converter recognising a
user-named property that collides with a JTD keyword, and the field
name now matches what it actually carries.
Fixes#1379
Adds optional autoloadSkills field to agent frontmatter that automatically loads listed skills when a sub-agent is spawned. Uses the same buildSkillPromptMessage + sendCustomMessage mechanism as interactive skill loading, queued via sendCustomMessage({ triggerTurn: false }) before the first session.prompt(task). No extra agent turns, no new injection path. Skills stay in listing for sub-resource access. Compaction behavior matches manual loading. Unknown skill names silently skipped.
Lore-id: f85fdbdc
Constraint: autoload must use buildSkillPromptMessage + sendCustomMessage, never modify systemPrompt or use contextFiles
Constraint: triggerTurn must be false to avoid extra agent turns
Rejected: append to systemPrompt | agent cannot distinguish skill content from own instructions
Rejected: contextFiles injection | agent sees opaque file blob, cannot discover sub-resources
Rejected: promptCustomMessage per skill | N extra agent turns with model inference
Directive: autoload skill names are resolved against parent session skill list at spawn time in task/index.ts
Tested: TypeScript compiles clean with tsc --noEmit
Tested: parseAgentFields parses array and CSV string frontmatter
Tested: parseAgentFields returns undefined for absent and empty fields
Not-tested: bun test cannot run locally due to missing pi_natives native addon (requires Rust toolchain)
Confidence: high
Scope-risk: moderate
Reversibility: clean
- Changed hashline format to canonical `§` section headers and `"`/`"`/`≔` operations across grammar, parser, and docs.
- Reworked range and op parsing so single anchors are valid, legacy `-`/`-=` ops error, and empty `≔` payloads now delete ranges.
- Removed legacy `HL_EDIT_SEP`, `$HSEP$`, and `hsep` plumbing, adopting raw payload lines.
- Updated execution, input, renderer, and streaming flows to use `HL_FILE_PREFIX` and `HL_OP_CHARS` helpers.
- Updated session-stats parsing to `§`/`≔`/`"`/`"` format, patch envelopes, and bumped parser versions.
- Removed the hashline-separator benchmark script and its PI_HL_SEP job orchestration.
- Added optional `onBeforeYield` configuration and `setOnBeforeYield` in Agent, executed before follow-up checks.
- Added `YieldQueue` to `AgentSession`, with setup/teardown and streaming/idle flush via `setOnBeforeYield`.
- Replaced immediate async-result follow-up dispatch with queued batch entries, including stale-state suppression.
- Added MCP follow-up queueing in SDK, deduplicating updates by `serverName` and `uri`.
- Added changelog entries for `onBeforeYield`, async-result batching, MCP dedupe, and `display.shimmer` modes.
- Added yield queue unit tests for streaming emission, debounced idle batches, stale filtering, and error isolation.
- Added a new shimmerText helper that computes a moving accent shimmer band across characters.
- Updated the interactive mode loader and slash-command ASCII bar renderer to use shimmer styling, with interrupt hints kept dim.
- Added tests for shimmer-enabled progress rendering and verified the visible bar output remains correct.
- get op now returns paused goals (was returning null when enabled=false)
- complete op now works on paused goals; previously required enabled=true
which always failed after an interrupt set enabled=false
- create op now allowed after previous goal status is 'complete'; was
incorrectly blocked by the same guard as 'dropped' check
- goal tool is re-added to the active tool set on session reload when a
paused/active goal is persisted to disk; sdk.ts:1599 excludes 'goal'
from initial active tools unconditionally, so restoreModeFromSession
now re-adds it and saves #goalModePreviousTools for later cleanup
- goal_updated event for 'dropped' status now triggers #exitGoalMode
before clearing goalModeEnabled, ensuring the previous tool set is
restored when the agent drops a goal via the tool
- added 'resume' and 'drop' ops to goal tool schema and execute path
- updated goal.md prompt to document new ops and the paused-goal workflow
Fixes#1249
- Updated the oracle agent description to present it as a senior engineer who can either consult or execute when delegated.
- Removed the read-only mandate and added requirements to implement changes, run checks, and report completed work in delegation mode.
- Adjusted the procedure and decision guidance to distinguish consult versus implement paths while keeping the scope limited to requested tasks.
The timeout/async section is only meaningful when the async option is
exposed to the model. Wrap the new section in {{#if asyncEnabled}} to
match the existing async-bullet guard above.
Documents that async:true defers reporting but does not extend or
disable the timeout, so long-running daemons should pass a generous
timeout. Also notes the output minimizer may rewrite results and that
the full bytes are always available at the artifact:// footer.
- The plan-approval gate required extra.title but the wire schema only
declared an opaque additionalProperties record so codex/gpt-5.x could
not discover the field. Schema now declares title with a description
while still allowing passthrough for future per-context keys.
- resolve.md replaces the truncated "Schema depends on context:" line
with the actual enumeration.
- runResolveInvocation wraps apply() in try/catch; a thrown apply (e.g.
ast_edit overlap) requeues the resolve directive so the model can
discard or fix-and-retry instead of losing the preview.
- todo-write.md adds an explicit note that tasks are referenced by
verbatim content text; the tool never emits task-N IDs.
- resolveTaskOrError rejects ^task-\d+$ inputs with a clarifying error.
- execute sets isError:true when any op failed.
- appendItems short-circuits on the first "already exists" error so the
call no longer applies the prefix of a doomed batch.
- search.md no longer claims "full regex syntax". Engine is rust-regex
(RE2) so lookaround and backreferences are unsupported; the doc now
says so and points at the post-filter alternative.
- search.ts rejects array entries containing a top-level comma with an
actionable ToolError, instead of silently demoting to a footer note
and returning zero matches.
- Add a paths-as-array example to search.md.
- Expose optional timeoutMs (clamped 0.5..60s) and pipe through to the
native walker. Default stays at 5s.
- On timeout, drain accumulated matches and return them with
truncated:true plus a notice line instead of throwing.
- Add gitignore boolean to the schema so callers can opt out of the
default exclude when looking for .env/.jsonl/build artifacts.
- Reject comma-in-paths array entries with an actionable ToolError.
- Update find.md with the knobs and the array-shape example.
- Preserved launch and attach request failures when configurationDone also fails.
- Handled initial stop-outcome watcher rejections for failed launch and attach attempts.
- Rejected directory-valued debug launch programs before adapter selection and documented the debugpy launch shape.
Fixes#1187
- Added a new `oracle.md` prompt defining a read-only diagnostic, architecture, and debugging advisor.
- Imported `oracle.md` into the agent prompt loader in `packages/coding-agent/src/task/agents.ts`.
- Included `oracle.md` in `EMBEDDED_AGENT_DEFS` so the new agent is available at runtime.
- Guard renderInlineMarkdown against non-string input: partial JSON during
streaming can leave option label fields as undefined, causing marked.lexer
to throw 'undefined is not an object (evaluating e.replace)'. The ask tool
renderer now silently falls back to an empty string or baseColor output.
- Sanitize normalizePlanTitle instead of hard-rejecting: models that produce
natural-language plan titles like 'My Improvement Plan' were getting a
ToolError on every resolve call, causing an infinite retry loop. Spaces are
now converted to hyphens, remaining invalid chars are dropped, and only
truly unresolvable titles (empty after sanitization, path separators) throw.
- Fix ask.md prompt example: the example showed the legacy single-question
format (question/options/recommended at the top level) while the schema
requires questions: [{id, question, options}]. Models that follow examples
closely (Qwen3) generated calls that always failed schema validation.
Fixes#1176
Tightened the hashline prompt to forbid readability spaces after the payload separator.
Preserved parsed payload text verbatim and surfaced a warning when a payload block looks like separator padding was added across every line.
Fixes#1166
- Non-interrupting tool-source TTSR matches now prepend a system-reminder to the matched tool's `toolResult` content instead of queuing a loop-wide deferred follow-up turn.
- Text/thinking source matches retain the previous deferred-injection behavior.
- Added deduplication so one rule attaches to exactly one sibling tool call per batch.
- Stale per-tool injections are cleared on abort/error before tools produce results.
- Removed the legacy `parseEvalInput` parser module and `eval.lark`, eliminating `*** Cell` stream parsing.
- Replaced eval tool arguments from single `input` strings to ordered `cells` arrays in tool calls and schema.
- Updated execution to resolve language explicitly, map `py` to `python`, and apply timeout/reset defaults.
- Removed backend sniffing and `ABORT_WARNING` suffix handling, then updated docs and tests to the new JSON cells format.
- Replaced all StringEnum(...) usages with z.enum([...]) across tools, examples, and tests.
- Removed StringEnum re-export from @oh-my-pi/pi-coding-agent public API.
- Condensed verbose tool parameter descriptions to minimal lowercase phrases.
- Renamed AuthCredentialStore to SqliteAuthCredentialStore at usage sites.
- Renamed the internal URL protocol handler from `pi` to `omp` and updated the router export/import wiring to use `OmpProtocolHandler` with the `omp://` scheme.
- Updated embedded documentation link rendering and related validation/error messages in the protocol handler to reference `omp://` URLs.
- Adjusted tests and prompt/docs references so `read` examples and harness documentation guidance now use the renamed `omp://` scheme.
- Updated read-line selector parsing to accept line-range selectors ending with a trailing dash.
- Mapped selectors with a trailing dash to open-ended ranges that read from the start line onward without requiring an explicit end.
- Updated read tool documentation to document `:50-` as the shorthand for reading from line 50 onward.
- Updated the hashline prompt to state the tool should never be used for code reformatting tasks.
- Added guidance to run the project's formatter for whitespace, indentation, and style-only edits.
- Relocated compaction, branch-summarization, pruning, and utils from coding-agent to packages/agent/src/compaction.
- Moved OpenAI remote compaction helpers from packages/ai to the new compaction module.
- Added handoff.ts with extractHandoffDocument, createHandoffContext, and renderHandoffPrompt helpers.
- Exposed new entries.ts with standalone SessionEntry types so coding-agent no longer owns them.
- Added note to read tool prompt that the pipe after the hashline anchor is a
separator, not part of the file content.
- Added note to search tool prompt that the pipe before content is a separator.
- Added a `resolveSearchRepoScope` helper that uses an explicit `repo` when provided, skips defaulting when a query already contains a repo/org/user/owner scope qualifier, and otherwise resolves the current checkout via `resolveDefaultRepoMemoized`.
- Updated `search_issues`, `search_prs`, `search_code`, and `search_commits` to use the resolver before composing API queries, defaulting `repo` when omitted but silently falling back to an unscoped search on resolution failure.
- Documented the new search-repo defaulting rules in tool prompts, user docs, and the package changelog.
The previous examples used " • " in the source file and inserted "·"
as the new content. Some agents were copying the middle-dot literally
into real edits as if it were format scaffolding, since the demo
inserts were near-twins of the existing string.
The new example uses TITLE = "Mr" → "Mrs" with "Dr" inserts:
ASCII-only, clearly distinct from any payload separator, and obviously
domain content rather than punctuation the model could confuse for
syntax. Every original op shape is preserved (single-line replace,
multiline replace, insert AFTER/BEFORE, append, delete, blank, both
anti-patterns). Pure prompt change; parser/schema/runtime untouched.
- Updated shell minimizer line truncation to append `...[+N]` with the count of dropped Unicode scalars when truncation occurs.
- Updated read summary rendering to track `elidedLines`, include them in tool details, and append a recovery footer for `:raw` or line-range access whenever elided spans are present.
- Updated read-tool prompts/docs/tests to cover the new elision-footers and recovery guidance.
Fixes#1046
- Updated the hashline mismatch error to describe anchor mismatches against the current file.
- Rewrote hashline tool instructions to clarify insert payload rules, anchor usage, and avoidance of fabricated hashes.
- Expanded stale-edit detection and tests to recognize the revised anchor-mismatch rejection wording.
- Discouraged coreutils in favor of dedicated read/search/find/edit/write tools.
- Prohibited pipe truncation via head/tail since artifacts handle full output.
- Prohibited stderr redirection since stdout and stderr are already merged.
- Added GoalRuntime with wall-clock and token accounting, budget steering, and lifecycle operations (create, pause, resume, drop, complete).
- Exposed goal tool as a hidden agent tool, activated only when goal mode is enabled.
- Integrated goal continuation loop in InteractiveMode with auto-submit between turns.
- Added status line segment and theme icons for goal mode state.
- Expanded the hashline tool rules to state that patch payloads should only contain newly added lines and must not duplicate existing content.
- Clarified that insertion and replacement operations affect only their specified targets, with adjacent lines remaining unchanged.
- Reinforced widening edits to self-contained syntactic units before selecting the smallest patch operation.
- Extended selector regex and parser to accept ranges like `:5-16,960-973`.
- Ranges are sorted and merged automatically before reading.
- Out-of-bounds ranges surface as inline notices instead of errors.
- Added `#readLocalFileMultiRange` and `#buildInMemoryMultiRangeResult` for file, archive, notebook, and internal URL targets.
- Removed ExitPlanModeTool and deleted exit-plan-mode docs/tests, dropping the old approval contract outputs.
- Replaced plan-mode approval flow from exit_plan_mode to resolve across session, SDK, controllers, and discovery.
- Added standing resolve handler accessors and updated resolve routing for queued or standing approval handlers.
- Added PlanApprovalDetails and enforced normalized, validated approval titles with readable plan-file requirements.
- Extended resolve schema and invocation signatures with optional extra metadata and reason trimming behavior updates.
- Updated plan and resolve prompts and changelog guidance to require resolve action, reason, and extra.title for apply/discard.
- Drop duplicated op listing from the reminder; <ops> already defines
the four shapes one block above.
- Replace hardcoded `~` with the {{hsep}} helper so the reminder
tracks PI_HL_SEP / HL_EDIT_SEP overrides, matching the rest of
hashline.md and addressing Codex review on #1063.
- Shrink the WRONG/RIGHT example (smaller anchor, no padding runs)
since the reminder's only job is contrasting on-line vs next-line
payload placement.
Models frequently write '+ ANCHOR| CONTENT' instead of '+ ANCHOR'
followed by '~CONTENT' on the next line. Add a compact FORMAT block
between </ops> and <rules> with a WRONG/RIGHT example that directly
addresses this failure mode.
- Updated the task tool output to list newly started background jobs by live task id with optional descriptions.
- Extended the async task prompt guidance to distinguish IRC-enabled versus standard coordination and cancellation behavior.
- Revised the system prompt wording in collaboration guidance from absolute prohibitions to explicit "avoid" directives.
- Adjusted multiple policy lines to reduce rigid phrasing around handling difficult user proposals, harness docs, and unnecessary file reads.
- Kept the behavioral intent intact while making the instructions more nuanced in the high-reliability prompt text.
can1357