Commit Graph

49 Commits

Author SHA1 Message Date
can1357 7aef1f1cd5 fix(coding-agent): rewrite trailing return statement into final expression
A top-level `return value;` in a JS eval cell was previously swallowed:
returnFinalExpression only handled ExpressionStatement, so ReturnStatement
flipped the IIFE wrapper which discarded the value. Rewrite the trailing
return into __omp_set_final_expr__((expr)) so the existing
final-expression channel surfaces the value just like a trailing
expression.
2026-05-19 19:16:08 +09:00
can1357 226fe87345 fix(coding-agent/eval): hardened image display value coercion to strict base64
- Implemented strict base64 validation and normalization for image `displayValue` payloads in the JS runtime, supporting strict strings, `Uint8Array`, `Buffer`, `ArrayBuffer`, typed-array views, and JSON `Buffer` objects.
- Dropped unrecognized image payloads while emitting a warning and fallback text instead of forwarding malformed data.
- Added tests covering successful coercions and invalid image data rejection paths.
2026-05-19 04:36:30 +02:00
can1357 6db7d6af92 feat(ai): added auth-broker snapshot contract with generation checks
- Added generation-aware snapshot contracts with generation, serverNowMs, refresher, and rotatesInMs fields.
- Reworked /v1/snapshot serving and client fetching for If-None-Match long-poll with 304/200 status handling.
- Added status checks in remote-store and SDK/CLI snapshot paths, applying updates only when fetch returns 200.
- Added StreamOptions.onAuthError and stream one-shot 401 retry dispatch using refreshed credentials.
2026-05-17 04:54:30 +02:00
can1357 7901cecf80 feat(coding-agent): added module cache busting for local imports in JS runtime
- Appended a unique nonce query param to local file imports so Bun treats each reload as a fresh module record.
- Restricted cache busting to relative/absolute path specifiers; bare packages and built-ins are left unchanged.
2026-05-16 20:27:45 +02:00
can1357 84ec8fba49 feat(coding-agent/eval): implemented JSON cell-based eval tool inputs
- 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.
2026-05-16 19:33:44 +02:00
can1357 188711b858 fix(coding-agent/eval): close remaining Python dispose races
- disposeAllKernelSessions removes sessions from the registry before awaiting shutdown, preventing queued work from seeing a registered-but-disposing session and spawning a replacement kernel.
- replaceSessionKernel re-checks registry membership after old-kernel shutdown and after starting a replacement, shutting the replacement down if the session was disposed mid-replace.
- owner-scoped disposal now preserves ownerIds when shutdown is unconfirmed so a later disposeKernelSessionsByOwner(ownerId) can retry.
2026-05-15 18:31:12 +02:00
can1357 110a6a3244 fix(coding-agent): persisted bindings from async-wrapped cells via globalThis publish
- Detected async wrapper need via AST traversal instead of regex, enabling pre-demote analysis.
- Published demoted var bindings back to `this` (worker global) when inside the async wrapper, preventing function-scope from hiding them across cells.
- Added `collectBindingNames`/`getLexicalBindingNames` to extract names from destructured patterns.
2026-05-15 18:31:12 +02:00
can1357 dad6149393 fix(coding-agent/eval): fenced disposed Python sessions from queued work
- executeOnSession's runQueued callback now re-checks sessions.get(sessionId) === session at slot entry and before the dead-kernel replace retry; if the session was removed by disposeAllKernelSessions / disposeKernelSessionsByOwner / resetSession during the queue wait, the queued caller now rejects with PythonExecutionCancelledError instead of spawning an untracked replacement kernel on a stale session object.
- Both dispose paths now inspect KernelShutdownResult.confirmed and retain (or re-insert) sessions whose shutdown was unconfirmed or rejected, logging a warn so a later dispose can retry the kernel instead of orphaning the subprocess.
2026-05-15 17:48:36 +02:00
can1357 9a755822eb fix(coding-agent): resolved coding-agent SIGINT shutdown escalation path
- Added bounded SIGINT escalation with `requestCancel()` to force kernel shutdown after 2s.
- Removed executor idle-timeout, max-session, heartbeat, and deferred disposal-retry logic.
- Added per-session `runQueued()` execution and dead-kernel restart retry flow for owned sessions.
- Replaced kernel session tracking with reusable `sessions` map and `acquireSession()` ownership registration.
- Removed obsolete owner-cleanup session-capacity tests and updated dead-session mocks to resolver-based flow.
2026-05-15 14:46:54 +02:00
Parsifa1 cf22f02584 fix(coding-agent): add CONDA_PREFIX for python venv 2026-05-15 07:57:59 +00:00
can1357 7cd05c374c feat(coding-agent/eval): enabled top-level await execution in Python runner cells
- Added a persistent asyncio event loop and coroutine-aware compiled-code execution for runner cells.
- Enabled compiling notebook cells with top-level await flags and awaiting coroutine results before rendering.
- Added an integration test confirming top-level await works across kernel cells with preserved state.
2026-05-15 02:12:34 +02:00
can1357 f1f6516056 refactor: reorganized exports and removed obsolete helper branches
- Removed export leakage by demoting many helper and const symbols to module-local scope.
- Renamed underscore-prefixed internals and cache fields, then updated related references and `satisfies never` checks.
- Deleted obsolete logic branches and helpers, including harmony-stream interruption flow and unused benchmark runtime helpers.
- Updated Biome config and manifests by broadening lint coverage and removing an unused `@napi-rs/cli` dev dependency.
- Adjusted tests and utilities to use renamed test helpers and remove redundant private test-only helpers/locals.
2026-05-14 04:36:19 +02:00
can1357 28b9ce7a0c feat(coding-agent): added middle-elision caps to OutputSink truncation
- Added `tools.artifactHeadBytes` and `tools.outputMaxColumns` settings with defaults in `SETTINGS_SCHEMA`.
- Expanded `OutputSink` with `headBytes`/`maxColumns` and middle truncate logic with elision markers and tracking.
- Updated output-meta to resolve sink settings, emit truncation metrics, and use `truncateMiddle` for spills.
- Integrated head and column limits into JS/Python/Bash/SSH/read output flows, with `:raw` skipping read truncation.
- Documented new output middle-elision and column-cap behavior in `CHANGELOG.md`.
- Added truncation tests for `OutputSink`, `truncateMiddle`, and read-tool line handling.
2026-05-13 11:19:11 +02:00
can1357 db1a3fd7b1 fix(packages/coding-agent): corrected js import rewriting empty AST body
- Added guard for ASTs with no body and trimmed trailing EmptyStatement nodes before final-expression capture.
- Exposed wrapCode via context-manager export for external JS import-rewrite callers.
- Added regression test asserting final-expression wrapping when trailing semicolons follow await.
2026-05-13 05:24:33 +02:00
can1357 218fe8b892 fix(packages/coding-agent): resolved JS display fallback for noncloneable values
- Handled structured-clone failures in JsRuntime.display by falling back to text output.
- Added regression coverage for non-structured-cloneable JS display output.
2026-05-13 05:24:33 +02:00
can1357 1ccc56aca6 fix(coding-agent/eval): routed JS import calls through session-aware import helper
- Updated JS import rewriting to route top-level `import` declarations through `__omp_import__` with support for import attributes.
- Added AST traversal to replace `import(...)` call callee nodes with `__omp_import__` so dynamic imports resolve via session-aware helper.
- Updated runtime `__omp_import__` to accept an optional options object and pass it through to `import(target, options)`.
2026-05-13 04:47:49 +02:00
can1357 a6f80d6a86 Merge PR #1024: feat(coding-agent): return JS eval final expressions
Rewrites the final top-level expression statement to a runtime hook so
its value surfaces without an explicit return/display, while preserving
top-level binding lifetime across cells. Promise-valued and thenable
finals are awaited exactly once; import-only cells stay silent.

Closes #1024
2026-05-13 02:25:04 +02:00
jiwangyihao 56428618c2 fix(js-eval): 不捕获改写后的 import 表达式 2026-05-13 02:24:10 +02:00
jiwangyihao 370fda14ff fix(js-eval): 使用私有最终表达式槽 2026-05-13 02:24:10 +02:00
jiwangyihao 7855028814 fix(js-eval): 仅在重写后读取最终表达式标记 2026-05-13 02:24:10 +02:00
jiwangyihao 51234ad929 fix(js-eval): 忽略继承的最终表达式标记 2026-05-13 02:24:10 +02:00
jiwangyihao 1b0ed01d32 fix(coding-agent): 解析所有最终 Promise 表达式 2026-05-13 02:24:10 +02:00
jiwangyihao efbf6b3833 fix(coding-agent): 等待最终 Promise 表达式 2026-05-13 02:24:10 +02:00
jiwangyihao 3af9369536 fix(coding-agent): 保留 JS eval 顶层绑定 2026-05-13 02:24:10 +02:00
jiwangyihao c270e966ba feat(coding-agent): 返回 JS eval 最终表达式 2026-05-13 02:24:10 +02:00
jiwangyihao 0f73414d3b fix(coding-agent): 识别顶层工具错误标记 2026-05-13 02:18:56 +02:00
jiwangyihao e043125e11 fix(coding-agent): 标记 JS eval 工具错误结果 2026-05-13 02:18:56 +02:00
can1357 1cb451a071 fix(workers): replaced file-URL import pattern with compiled-binary-aware spawn
- Replaced `with { type: "file" }` worker imports with `isCompiledBinary()` hybrid: literal string for `--compile` static analysis, `new URL(import.meta.url)` for dev portability.
- Added worker entrypoints as explicit `--compile` args in `build-binary.ts` so Bun emits them into bunfs.
- Added `smokeTestSyncWorker` and `omp --smoke-test` to catch silent worker-load failures in compiled binaries (fixes #1011, #1027).
- Added `isCompiledBinary()` utility to `@oh-my-pi/pi-utils` detecting bunfs path markers.
2026-05-12 16:40:15 +02:00
can1357 028a442f18 feat(coding-agent): added parser support for t/rst in Cell eval
- Introduced canonical `*** Cell` headers with `t:` and `rst` attributes in eval prompts, schema, and docs.
- Updated parser and grammar to parse `*** Cell` blocks, stop on `*** End`/next header/EOF, and handle invalid `rst` with errors.
- Added quote-aware attribute tokenizers and split HTML eval parsing into `Cell` and legacy `Begin` handlers with `py` defaults.
- Expanded parsing behavior and tests for `rst` booleans, title aliases, abort boundaries, and stray-line skips between cells.
2026-05-12 10:01:56 +02:00
can1357 c562f4dc2a fix(coding-agent/eval): hardened eval parser against stray non-marker lines
- Updated parseEvalInput to verify begin-cell markers before dereferencing regex matches.
- Skipped stray non-marker lines between and after cells, preserving valid cells when model output is noisy.
- Added eval parse regression tests for stray content and trailing chatter, and kept abort-line handling explicit.
2026-05-12 09:41:06 +02:00
can1357 8d144e17ec feat(coding-agent/eval): added local python-runner subprocess execution
- Replaced Python execution with a local `python -u runner.py` subprocess and NDJSON stdin/stdout framing.
- Removed shared-gateway architecture, including coordinator lifecycle APIs, `useSharedGateway` wiring, and `jupyter` CLI/actions.
- Simplified setup checks to a plain Python 3 availability probe and removed automatic dependency-install fallbacks.
- Updated kernel cancellation and display processing to use status frames, SIGINT/SIGTERM escalation, and normalized output coercion.
- Added `python-runner` integration and display tests while deleting legacy websocket and kernel lifecycle test suites.
2026-05-12 09:09:24 +02:00
can1357 dcf3f1c8a3 feat(coding-agent): added tool.<name>(args) execution in Python prelude
- Added `tool.<name>(args)` execution in Python prelude and docs, enabling direct tool call syntax.
- Added per-execution Python tool-bridge registration, env wiring, and executor lifecycle management.
- Implemented authenticated loopback `/v1/tool` handling with session/name validation and structured responses.
- Updated runtime and lint handling to permit controlled global eval usage in indirect eval paths.
- Added tests for success, failures, invalid bodies, and `emitStatus` propagation in Python tool bridges.
2026-05-12 08:43:36 +02:00
can1357 2f7b2aaccd feat(coding-agent/eval): stripped TypeScript syntax before import rewrites
- Added a stripTypeScript pass that heuristically detects TypeScript-like syntax and transpiles it with Bun's ts loader before rewriting.
- Integrated the new pass into wrapCode so import and lexical rewrites operate on transpiled input.
- Added an executeJs test that verifies interfaces, type annotations, and type assertions execute to the expected numeric result.
2026-05-12 08:42:52 +02:00
can1357 2d4d70e47e feat(coding-agent): added shared JS runtime for worker execution
- Added shared JS runtime infrastructure with RuntimeHooks, RuntimeOptions, JsRuntime, and indirectEval-based execution.
- Reworked worker execution to use runtime.run, track active runs, and clean pending tool calls on close.
- Added tool-call and tool-reply message variants and wired supervisor/worker to route run-scoped calls.
- Added shared helper globals (read, writeFile, diff, tree, env) for browser-tab JS execution.
2026-05-12 08:42:30 +02:00
can1357 efbaa59a05 fix(coding-agent): routed rewritten static imports through cwd-aware helper
- Rewrote static import lowering to emit `__omp_import__` calls instead of direct `import(...)` so rewritten code routes through worker context helpers.
- Added a `__omp_import__` runtime helper in `WorkerCore` that resolves specifiers against the session cwd via `Bun.resolveSync` while passing through URL-like modules unchanged.
- Updated static import rewrite tests to expect the new helper-based `__omp_import__` form, including import attribute cases.
2026-05-12 08:22:55 +02:00
can1357 f56cbbf4c6 feat(stats): added frustration metrics to stats parser and charting
- Added new frustration and revised behavior metrics across stats types, parser mappings, and UI charts.
- Reworked session sync to fan out parsing across a capped worker pool with SyncOptions progress callbacks.
- Added worker-based parse messaging and throttled TTY progress rendering in the stats sync command.
- Updated behavior scoring to strip structured content, ignore noisy prompts, and fix profanity boundary regressions.
- Expanded user message schema and migrations, then repaired assistant model/provider links during sync backfill.
- Updated worker-import guidance in AGENTS.md and recorded sync-progress/metrics updates in package changelogs.
2026-05-12 07:55:23 +02:00
can1357 a7209c2b4f feat(coding-agent-eval): added worker-backed JS runtime with queued runs
- Added worker-backed JS runtime via Transport and WorkerCore, with queued runs, status/error output, and clean teardown.
- Refactored executeInVmContext to reuse worker sessions, route pending runs by id, and fallback inline on spawn failure.
- Added rewrite helpers to convert top-level imports and demote top-level const/let/class declarations for persistence.
- Handled aborts by canceling in-flight tool calls, hard-killing worker sessions, and dropping JS timeout enforcement.
2026-05-12 07:20:43 +02:00
can1357 7d233725b6 refactor(coding-agent/eval): removed eval shell run helpers from JS and Python preludes
- Removed the JS and Python eval prelude `run` helpers, including their shell execution and timeout/cwd option handling.
- Updated the JS VM helper set to expose `Bun` and removed the deleted `run` entry from the prelude.
- Revised eval docs to drop `run` from the helper surface and note the new JS `Bun` global.
2026-05-12 05:43:37 +02:00
can1357 9ed81977f7 feat(coding-agent): shared artifact manager and flat output directory across subagent sessions
- Added parent-to-subagent artifact manager adoption so subagents reuse the parent `ArtifactManager` and write artifacts into a shared directory with shared IDs.
- Passed the shared artifact manager through tool/session context into subagent executor startup and exposed it via `SessionManager` and `ToolSession` for lookup.
- Updated kernel environment and artifact-resolution paths to prefer `PI_ARTIFACTS_DIR`, falling back to existing session-file-based behavior when absent.
2026-05-12 05:17:53 +02:00
can1357 8b92ec937e feat: gpt-5 harmony errata fixes
- Replaced `===== ... =====` eval cell headers with `*** Begin ` / `*** End ` markers; legacy format remains renderable in HTML exports.
- Replaced hashline patch grammar with `*** Begin Patch` / `*** End Patch` envelope; old inputs without the envelope are still accepted.
- Extracted `sniffEvalLanguage` into a shared `sniff.ts` module reused by the parser and tool.
- Added `docs/ERRATA-GPT5-HARMONY.md` and `scripts/session-stats/harmony_backtest.py` documenting and backtesting the GPT-5 Harmony-header leak defect.
2026-05-10 19:52:44 +02:00
can1357 1802de9c0a fix(coding-agent): resolved eval context import rewrite via Babel AST
- Replaced regex-based import rewriting in `rewriteStaticImports` with Babel AST parsing.
- Handled default, namespace, named, and side-effect imports, preserving `import ... with` options.
- Returned original source on no top-level imports, parse failures, or unchanged non-import regions.
- Added `@babel/parser` dependency and tests/changelog coverage for top-level static-import rewrite behavior.
2026-05-09 23:10:15 +02:00
can1357 1e96e715e8 feat(coding-agent/eval): added a static-import rewriter that converts
- Added a static-import rewriter that converts common import clauses into dynamic `await import(...)` expressions before VM wrapping.
- Provided `require` and `createRequire` globals in the JS VM context using a cwd-based resolver.
- Added executor tests confirming rewritten imports run correctly and that `require`/`createRequire` are exposed with expected behavior.
2026-05-08 06:23:16 +02:00
Parsifa1 1b2b8f0991 fix(coding-agent): fix share lib error for python gateway
also fix correct position for python-gateway/ for xdg spec
2026-05-06 18:08:48 +02:00
can1357 627e655f43 fix(coding-agent/eval): enabled main-context dynamic imports in JS VM execution
- Added the main-context dynamic import loader option when running the JS prelude in VM state creation.
- Enabled the same `importModuleDynamically` setting during `executeInVmContext` execution so wrapped scripts use the shared dynamic import behavior.
- This ensures VM execution now uses the main context default loader for dynamic module imports.
2026-05-02 06:59:33 +02:00
can1357 d064170c56 fix: chatgpt really doesnt like sandwitching lark 2026-05-02 04:54:56 +02:00
can1357 9fc762cbad refactor(packages/coding-agent): reorganized eval helper APIs in prelude
- Removed deprecated file helper APIs (find, glob, grep, rgrep, sed, and stat) from JS and Python eval preludes.
- Removed status icons and formatting branches for find/grep/rgrep/glob/stat/sed from tools/eval.ts.
- Updated eval helper docs and Python prelude tests to match the reduced exposed helper surface.
2026-05-02 04:34:39 +02:00
can1357 ca84ee760d perf: optimized ai providers with lazy-loading imports and cached init
- Consolidated AI provider imports through register-builtins and moved Gemini/Antigravity header helpers to a shared module.
- Added lazy loading for heavy providers and SDK-backed modules with cached initialization to trim startup cost.
- Converted markdown conversion helpers to async and awaited htmlToBasicMarkdown in affected scraper and kernel output paths.
- Parsed bundled agent definitions on-demand and moved BrowserTool prompt rendering behind a memoized getter.
- Added cached validation/error handling paths by replacing AJV runtime checks with Value.Check and trimming validation error output.
2026-05-01 18:54:21 +02:00
can1357 6dccdf9193 refactor(coding-agent/eval): drop python warmup path
The warmup path no longer produces prelude docs, so the cached-session
warmup it implemented added no value over the create-on-first-execute
path that withKernelSession already covers. Remove warmPythonEnvironment,
the backend warm() hook, the eval-tool warmup loop, the createTools
warmup preflight, and the forcePythonWarmup option. Simplify
ExecutorBackendCallOptions into ExecutorBackendExecOptions since execute
is now the only consumer.
2026-05-01 15:27:40 +02:00
can1357 cf60e6df51 feat(coding-agent): implemented eval framework and replaced python tool
- Added a unified eval framework with parser grammar, backend interfaces, and JS/Python execution result types.
- Added eval tool docs and updated prompts for fenced cells, `eval.py`/`eval.js`, and fallback behavior.
- Replaced the built-in `python` tool with `eval` across registry, rendering, interactive modes, and tool settings.
- Migrated Python execution runtime from `src/ipy` to `src/eval/py`, renamed state fields, and removed legacy introspection.
- Refactored browser tooling from in-process VM helpers to worker-managed tab supervisors and protocol transport.
- Added eval parser fallback and JS tool-bridge tests, updated imports, and removed obsolete python-mode suites.
2026-04-30 18:08:37 +02:00