Commit Graph

13 Commits

Author SHA1 Message Date
can1357 c101452bb5 refactor: restructured and condensed agent prompts and system instructions
- Refactored and condensed numerous system prompts, agent instructions, and tool documentation files across packages.
- Streamlined workflow rules, formatting constraints, and execution guidelines for improved clarity and brevity.
- Updated discovery rules, recommendation criteria, and syntax standards in prompt templates.
2026-08-12 01:48:14 +02:00
can1357 5ea583e413 feat: replaced legacy editing commands with unified put and cut syntax
- Replaced legacy `SWAP`, `INS`, and `PASTE` commands with unified `PUT` and `CUT` hunks across parser, grammar, tokenizer, and test suites.
- Added support for named registers and span paste operations in clipboard and block execution logic.
- Implemented indentation repair and enhanced gap locator formatting for improved patch resilience.
- Updated documentation, system prompts, and session analysis scripts to reflect the new syntax and header shapes.
2026-07-31 00:19:52 +02:00
can1357 9856f904d7 feat(typescript-edit-benchmark): introduced empirical edit mutation planning
- Add new structural, multi-edit, and block-level mutation classes with updated category mappings.
- Introduce hunk extraction, placement, rendering, and solver utilities along with unit tests.
- Implement size-based mutation planning, prompt validation logic, and new prompt markdown templates.
- Update benchmark generation scripts and package configurations to support empirical edit shape statistics.
2026-07-30 07:45:01 +02:00
can1357 e05f229f43 refactor: standardized editing syntax by removing copy and delete operations
- Removed copy and delete operations across tokenizer, parser, grammar, and clipboard logic.
- Standardized line-editing operations and block resolvers to use cut exclusively.
- Updated documentation, prompts, and test suites to reflect the removal of copy and delete syntax.
2026-07-30 07:42:48 +02:00
can1357 4e5f480f14 feat(metaharness/adapters): implemented interactive cli runner and reporting
- Added comprehensive CLI arguments for thinking levels, timeouts, concurrency, and report formatting.
- Implemented real-time interactive terminal progress rendering and runtime statistics summary.
- Enhanced runner logic with tokenizer-based hashline operation detection and aggregated reporting.
- Added bench:edit script to package configuration and updated default report output paths.
2026-07-30 07:21:08 +02:00
can1357 d16a251777 chore: reorg tests 2026-07-27 16:43:53 +02:00
can1357 52ad6516ef feat(diff): implemented native UTF-16 diff processing and removed jsdiff
- Implemented native UTF-16 text processing in Rust diff module with support for unpaired surrogates.
- Removed `similar` crate from Rust workspace and `diff` npm package from coding-agent, hashline, and natives.
- Removed jsdiff fallback wrappers and `isWellFormed()` guards from TypeScript diff implementations.
- Added comprehensive test suite for native diff functions covering random inputs and edge cases including surrogates and emoji.
- Renamed model `codex-auto-review` to `gpt-5.3-codex-spark` with updated pricing and context window.
2026-07-23 01:35:31 +02:00
can1357 0002905ec5 chore: untrack node_modules symlinks and harden ignore pattern
- An eval-worktree cherry-pick swept 16 packages/*/node_modules symlinks into the index; 'node_modules/' with a trailing slash only matches directories, so symlinked installs bypassed the ignore. Dropped the slash and removed the tracked links.
2026-07-22 21:43:22 +02:00
can1357 b9072f1991 fix(extensibility): validate Type.Unsafe against the draft-2020-12 upgraded schema
Aligns the shim's runtime safeParse/__validator with the wire/tool-call
path, so legacy draft-07 documents (tuple items) accept the same values
validateToolArguments does. Adds a regression test.
2026-07-22 21:13:21 +02:00
can1357 8640c0dded refactor(python/robomp): renamed typecheck npm script to check:types
- Renamed `typecheck` script to `check:types` in the web package.
- Updated AGENTS.md documentation to reference the renamed script.
- Removed duplicate `start` script from metaharness package.json.
2026-07-18 19:26:41 +02:00
can1357 55f5ebec49 chore: reformat 2026-07-15 00:08:50 +02:00
can1357 8702a3f225 feat(metaharness/scripts): added trace-report generation for metaharness run traces
- Added `packages/metaharness/scripts/trace-report.ts` to generate markdown reports with turn logs and narratives.
- Implemented API loading of run traces and run metadata so each report includes run context and final assistant message.
- Added concurrency-limited turn mapping with retries, progress logs, and token usage tracking for model calls.
- Documented the new `trace-report` CLI, its flags, and invocation examples in `packages/metaharness/README.md`.
- Added `scripts/tsconfig.json`, integrated it into `check:types`, and added `@oh-my-pi/pi-catalog` dependency entries.
2026-07-14 02:01:27 +02:00
can1357 77f641268d feat(metaharness): migrated harbor-manager to metaharness and updated harness logic
- Renamed and migrated package-level artifacts from `harbor-manager` to `metaharness`.
- Updated metaharness core services (`server`, `runner`, `store`, `experiments`) with substantive logic edits.
- Synced CLI, local agent, and config wiring to align with the metaharness package structure.
- Refreshed benchmark-related documentation/prompts and expanded tests for the revised metaharness flow.
2026-07-14 01:30:40 +02:00