- Made `JsRuntime` track the realm globals it installs (`#globalOwner`, `#ownedGlobalKeys`, `PRELUDE_GLOBAL_KEYS`) and reclaim them in `dispose()`, re-binding ownership through `#activateGlobals()` on cwd/run-scope/run; disposing an older inline/direct runtime no longer deletes a newer runtime's helper globals, and overlapping same-realm runs are serialized via `enterGlobalRun`.
- Added `WorkerCore.dispose()` (rejects pending tool calls with `ToolError` and disposes the runtime) and invoked it from `spawnInlineWorker` teardown in `context-manager.ts`.
- Updated the `js-static-import-rewrite` test to snapshot and restore any pre-existing `__omp_import__` global instead of unconditionally deleting it.
- Added `runtime-global-dispose.test.ts` covering newer-runtime global survival, older-runtime reactivation, and cross-runtime mutation rejection.
- Clarified the `runWorkerEntrypoint` comment in `cli.ts` about `parentPort` sync-prefix buffering for tab/eval workers.
Register tree-sitter-elisp in the shared AST language registry so
.el files infer the emacs-lisp grammar across blockRangeAt,
summarizeCode, astGrep/astEdit, and native aliases.
This fixes edit-tool block operations on top-level Emacs Lisp forms
instead of returning unsupported-language block errors.
- Add canonical emacs-lisp aliases and .el extension inference.
- Teach summaries to fold Lisp forms without grouping arbitrary lists.
- Map .el rendering and highlighting aliases through coding-agent/native.
- Cover defun, ERT, use-package, with-eval-after-load, pcase,
summary, astMatch, astEdit, and edit-tool insertion paths.
- Document the language and update package changelogs.
- Renamed line and block patch op verbs to XCHG, DEL, and INS in parsing and formatting.
- Updated grammar and tokenizer to support XCHG.BLK, DEL.BLK, and INS.PRE/POST/HEAD/TAIL forms.
- Updated diagnostics, docs, prompts, tests, and changelog to use XCHG/DEL/INS-based operators.
- Expanded session-stats parsing to normalize legacy op aliases to compact IDs.
- Added a lifecycle test case verifying executePython retries execution with a fresh kernel when the prior session kernel dies during run.
- Removed the now-redundant python-executor-session.test.ts file that defined session lifecycle tests.
- 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.
- Added a shared `formatAnchoredContext` helper and switched mismatch formatting to use it.
- Extended unresolved block-edit errors to append nearby numbered context with `*`-marked anchor lines.
- Updated unit and integration tests and docs to reflect the new unresolved-block preview behavior.
Resolve the explicit interpreter from the session's Settings instance
(ToolSession.settings / AgentSession.settings) instead of re-reading the
process-global Settings.init() singleton, so project-scoped and cloned
session settings take effect. The availability cache is now keyed by
cwd + interpreter, and PythonKernel.start/executePython accept the
resolved interpreter as an option. Also expand home-relative paths
(~/...) before resolving against cwd, and document the contract of
resolveExplicitPythonRuntime.
Addresses review feedback on #2204.
Two pathologies surfaced in the same captured failure (#2081): a subagent
spent 16 minutes hammering 205 `edit` calls (182 byte-identical no-ops)
against a file that already matched its payload, while a sibling bash
invocation persisted 7.6MB of PowerShell rich-object metadata to
`~/.omp/agent/artifacts/<id>.bash.log` from what was intended as a small
tail. Both are addressed independently here:
- Hashline executor now consults a per-ToolSession `noopLoopGuard` that
hashes the raw patch input and tracks consecutive no-ops per canonical
path. After NOOP_HARD_LIMIT (3) repeats of the same payload the soft
"byte-identical" hint escalates to a thrown ToolError, which the agent
loop surfaces as a tool failure rather than success-with-text — far
more effective at breaking the loop than the soft hint alone. A
non-noop commit (or any variant payload) resets the counter; state is
isolated per ToolSession so subagents cannot inherit each other's
history.
- OutputSink artifact-on-disk writes are now bounded by
`artifactMaxBytes` (default 4 MiB = 3 MiB head + 1 MiB rolling tail).
Once the head budget is exhausted, subsequent chunks divert into a
fixed-size tail ring; `dump()` replays the ring behind a single
`[ARTIFACT TRUNCATED: kept first … + last … of …; … elided from the
middle]` notice before closing the sink. Setting `artifactMaxBytes: 0`
restores the historical unbounded behavior. Sized comfortably above
anything a model would reasonably scroll through via the artifact URL
scheme while preventing the captured 7.6MB spray from sitting on disk.
The terminal-typing lag the reporter observed has multiple compounding
causes (transcript-render freezing is disabled on win32; the bash result
renderer lacks the per-render cache that the eval renderer already has).
Those land in a follow-up — the loop guard + artifact cap address the
root pathologies that turned the session into a multi-MB transcript in
the first place.
Fixes#2081
- Added lazy async module loaders for @babel/parser, linkedom, puppeteer/browsers, @mozilla/readability, @xterm/headless, and mnemopi to avoid loading them during cold startup.
- Added an interactive startup splash before session construction and skipped it for resume/fork/continue, quiet mode, timing mode, or non-TTY runs.
- Updated JS import-rewrite and memory tests to match async parser loading and preloaded mnemopi modules for sync state helpers.
single OutputSink owner per cell artifact; JS parallel() honors its documented barrier (allSettled) instead of orphaning in-flight thunks; Python subprocesses no longer inherit the NDJSON frame pipe (stdout captured and forwarded); JS timeouts annotate the VM reset; console bridge implements dir/time/group/assert/trace; python availability probe cached; runner frames coalesce per write.
- Rewrote dynamic `import(...)` rewriting to emit a guarded callee that prefers `__omp_import__` and falls back to native `import` when the helper is unavailable.
- Added a shared shim constant and updated import-rewrite tests to verify routed dynamic imports work both with the injected helper and after serializing into a realm without it.
- Added status.done and tool.* symbols to theme mappings and presets.
- Replaced generic success glyphs with contextual +/-, tool icons, and warnings.
- Mapped tool/task/job completions to status.done or status.enabled with icon overrides.
- Triggered runtime provider refresh after extension registration and warned on failure.
- Substituted injected on-disk roots for `local://` in read/write/append (Python and JS).
- Pinned `local://` to the session's own root so eval writes land where reads resolve.
- Rejected path traversal and unknown `scheme://` paths instead of creating junk `local:` dirs.
- Added unit and integration tests covering resolution, guards, and plain-path passthrough.
- Removed the mid-skip placeholder line that was output when skipping lines in the middle of a diff, relying instead on the line number jump to convey the gap. Removed the corresponding placeholder-filtering logic from the hashline diff preview that was handling these placeholders.
- Modified buildCompactDiffPreview to omit removed lines from output while preserving removal counts for offset tracking.
- Added logic to collapse long contiguous added runs with +<lineNum>... elision marker, keeping configurable edge lines on each side via new maxAddedRunContext option.
- Removed context-gap placeholder rows (... or ...) from model-facing preview, relying on line-number jumps to convey elision.
- Reorganized test suite by moving core contract tests to dedicated core-contracts.test.ts file and diff-preview tests to diff-preview.test.ts for better separation of concerns.
- Added a BlockResolution type and `onResolved` callback so `resolveBlockEdits` reports each anchor's resolved span for `replace block`/`delete block` edits.
- Updated patch application to return those spans on hash-match applies and omit them during drift-recovery paths where line numbers no longer align.
- Propagated the surfaced spans through the edit tool output and added/updated tests covering replace/delete block echo and drift behavior.
- Coalesced concurrent JS and Python reset requests by awaiting in-flight promises instead of throwing.
- Aligned non-reset execution calls to wait for in-progress resets before running on a recreated session.
- Replace recursive stripLeadingHashlinePrefixes with single-pass
stripOneLeadingHashlinePrefix in #handleRaw to prevent over-stripping
content whose own text starts with digits:colon (e.g. YAML ports,
timestamps: 2:42:hello → 42:hello, not hello)
- Export stripOneLeadingHashlinePrefix from prefixes.ts
- Move hashline CHANGELOG entry to [Unreleased] section
- Add regression tests for nested N: prefix and +N: asymmetry
- Replaced `¶path#hash` prefix with `[path#hash]` delimiters across parser, tokenizer, and grammar.
- Updated prompts, docs, and recovery paths to the new bracketed form.
Worker-ready wait reused Bun's 5s default per-test timeout as its floor, so a slow cold-start under --isolate + high CI concurrency was aborted at 5s. The catch then terminate()s a still-initializing Bun worker -- the documented SIGILL/SIGTRAP crash trigger -- crashing the whole test file and intermittently failing unrelated PRs.
Introduce WORKER_INIT_TIMEOUT_MS=15s as a fixed infrastructure floor (independent of, still dominated by, a larger per-cell timeout) and set a 20s file-local setDefaultTimeout in js-executor/js-workflow-helpers tests so cold starts complete instead of being torn down.
- Aligned handoff, reminder, and system-prompt expectations with shortened copy.
- Added HTTP transport test for required initialize failures.
- Guarded SSE startup timeout against stale connection races.
- Updated the grammar to parse replace hunks with zero body lines.
- Changed empty replace execution to emit delete edits across the target range.
- Updated tests to verify empty replace syntax deletes lines while empty inserts still throw errors.
- Added +Nk/+Nm turn-budget parsing with whitespace-boundary matching, multipliers, and hard `!` indicator.
- Added per-turn budget lifecycle plus APIs (`getTurnBudget`, `recordEvalSubagentUsage`) and hard-cap checks in eval runs.
- Added hard budget observability in eval preludes and docs by exposing `budget.hard` and documenting ceiling modes.
- Fixed streaming preview stutter with max-row tracking and padding, with tests for preview height and budget parsing.
- Dropped `args` input from eval tool schema, JS/Python executors, and worker protocol.
- Removed per-call `args` injection from JS runtime and Python kernel/runner.
- Deleted related tests and updated docs to reflect removal.
- Replaced single-candidate resolution with `enumeratePythonRuntimes`, returning venv, managed env, and system interpreter in priority order.
- Availability check now probes each candidate and falls through to the first that executes, so a stale `uv`-managed Python no longer fails the whole session.
- Kernel spawn reuses the probed runtime from the availability result instead of re-resolving independently.
- Expanded test coverage for enumeration, fallback, and env isolation between candidates.
- Added `replace block N:` syntax in grammar/parser/tokenizer/types, emitting `kind: "block"` edits with empty-body checks.
- Added block-resolution in hashline apply/recovery, wiring `BlockResolver` to resolve edits with throw/drop unresolved behavior.
- Added native `blockRangeAt` support and exported block range/options types through pi-ast, pi-natives, and JS bindings.
- Added coding-agent resolver wiring plus internal visibility/exports updates and new parser, patcher, and setup-wizard tests.
- Updated local module loading to force TS syntax stripping for .ts/.tsx/.mts modules and use the matching Bun transpiler loader.
- Extended TypeScript stripping to detect `import type`/`export type` syntax and rewired wrapping to strip TS syntax after final-expression extraction with TypeScript-aware parsing.
- Added tests verifying type-only imports are handled correctly in evaluator modules and rewritten code no longer contains type-only import declarations.
- Added formatContextUsage to render context as `%/window` with `?` fallback across status and task views.
- Updated task renderCall to show dispatched agents as tree entries with `Tasks (2)` header and `#3` fallback.
- Capped task preview collapse at 12 entries and added `... N more agents` overflow messaging.
- Replaced hard-coded dot separators with `theme.sep.dot` in subagent cost and context output.
- Added tests for streaming task preview rendering and updated nested-live expectations for percent/context output.
- Rejected file creation via hashline and directed to write tool instead.
- Required snapshot tag in duplicate insert test setup.
- Added "irc" to expected subagent LSP tool names.
- Replaced snapshot internals with full-file records and removed contiguous/sparse snapshot APIs.
- Added file-hash normalization, computed `computeFileHash`, and updated grammar/messages to 4-hex tags.
- Simplified recovery by checking whole-file hashes first, then applying merge-replay fallback after mismatches.
- Updated coding-agent tools to use `record`/`recordFileSnapshot` and skip hash headers for unsnapshotted large files.
- Expanded patcher and snapshot tests to verify 4-hex anchors, hash deduplication, and cache-capped behavior.
- Replaced bare `A B` range headers with `replace N..M:`, `delete N..M`, `insert before N:`, `insert after N:`, `insert head:`, and `insert tail:`.
- Removed `&A..B` repeat rows; insert-before/after ops now express the same intent explicitly.
- Empty replace bodies now error instead of deleting; `delete` is the canonical deletion op.
- Updated grammar, prompt, docs, tests, and all call sites to the new syntax.
- Replacement hunks now drop duplicated closing delimiters restated in the payload but surviving just outside the range.
- Ranges that swallow a structural closer the payload omits now spare that closer instead of deleting it.
- Each repair surfaces a `delimiter-balance` warning through `ApplyResult.warnings`.
- Brackets inside strings, template literals, and comments are skipped to avoid false positives.
- Rejected bare `A` anchors; single-line ranges must now be spelled `A A`.
- Added a descriptive error for single-number headers to guide model output.
- Updated grammar, tokenizer, prompt docs, and tests to reflect the change.
- Redesigned hashline patch syntax from anchor-based (`A-B:`) to hunk-header format (`@@ A..B @@`) with unified-diff compatibility.
- Removed `autoDropPureInsertDuplicates` option and simplified apply behavior to preserve duplicated boundary and context lines.
- Changed repeat operator from `^A-B` to `&A..B` and range separator from `-` to `..` for consistency with hunk-header syntax.
- Added image resizing and dimension notes to eval tool output; improved write tool hashline header sanitation for legacy formats.
- Removed 521 lines of boundary-duplicate absorption code and simplified parser to auto-convert bare body rows and unified-diff contamination.
- Replaced 4-hex content-derived file hashes with 3-hex opaque tags minted by InMemorySnapshotStore, making tags session-bound pointers rather than content fingerprints.
- Removed lru-cache dependency; replaced LRU-bounded per-path rings with a flat 4096-slot global ring using a scrambled permutation to prevent LLM tag extrapolation.
- Made SnapshotStore required in Patcher (was optional); tag resolution now drives stale-anchor detection instead of recomputing hashes at apply time.
- Changed literal payload sigil from `|` to `+` and accepted `^A` shorthand for `^A-A`; added lenient recovery for bare bodies, lone `-` rows, and overlapping bare/concrete block pairs.
- Replaced anchor shorthand syntax with explicit range format (1: -> 1-1:) and removed ^/v sigils in favor of ^A-B repeat and A-B:- delete operations.
- Added repeat edit kind to support ^A-B syntax for copying lines A through B, and inline delete syntax A-B:- for range deletions.
- Removed after_anchor cursor kind and standalone delete rows; empty anchor blocks now produce blank-line replacements instead of deletions.
- Updated parser, tokenizer, and type system to discriminate literal and repeat payloads, and refactored apply/recovery logic to expand repeat edits into individual inserts.
- Updated coding-agent test fixtures and settings documentation to reflect new hashline syntax and behavior.
- Narrowed the xai-oauth bundled model cast to `Model<"openai-responses">` in its regression test.
- Changed hashline stale-recovery fixtures to use `repl(...)` for both line-replacement payloads instead of `extra(pl(...))`.
The recovery fallback that replays edits onto current text when the structured-patch 3-way merge refuses guarded only on line-count equality. If a prior in-session edit rewrote the very line a later stale-hash edit re-targets, replay overwrote the new content with the stale-anchored payload and emitted a 'Verify the diff matches your intent' warning that does not block the write.
Concrete window: v0 line 5 = 'L5', v1 = 'L5-CHANGED' (same line count). Edit E2 authored against H0 anchored at line 5 lands on v1 because the line-count gate passes, silently replacing L5-CHANGED with the model's L5-MODEL.
Add a verifyAnchorContent gate: walk every edit's anchors and require previousText[line] === currentText[line]. Any mismatch returns null so the caller raises MismatchError and the model re-reads. The success path now emits the standard RECOVERY_SESSION_CHAIN_WARNING (the hedged REPLAY_WARNING text was only sensible when content was partially aligned; that case is now unreachable, and the constant is removed).
Tests: packages/hashline/test/recovery-session-chain.test.ts pins both the corruption refusal and the safe-replay positive case (anchor on an unchanged line, 3-way merge fails on neighbouring rewritten context, replay succeeds with the standard chain warning). packages/coding-agent/test/core/hashline.test.ts adds an end-to-end through executeHashlineSingle so the production patcher path is covered too.
can1357