@weldr/runr 0.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +216 -0
- package/LICENSE +190 -0
- package/NOTICE +4 -0
- package/README.md +200 -0
- package/dist/cli.js +464 -0
- package/dist/commands/__tests__/report.test.js +202 -0
- package/dist/commands/compare.js +168 -0
- package/dist/commands/doctor.js +124 -0
- package/dist/commands/follow.js +251 -0
- package/dist/commands/gc.js +161 -0
- package/dist/commands/guards-only.js +89 -0
- package/dist/commands/metrics.js +441 -0
- package/dist/commands/orchestrate.js +800 -0
- package/dist/commands/paths.js +31 -0
- package/dist/commands/preflight.js +152 -0
- package/dist/commands/report.js +478 -0
- package/dist/commands/resume.js +149 -0
- package/dist/commands/run.js +538 -0
- package/dist/commands/status.js +189 -0
- package/dist/commands/summarize.js +220 -0
- package/dist/commands/version.js +82 -0
- package/dist/commands/wait.js +170 -0
- package/dist/config/__tests__/presets.test.js +104 -0
- package/dist/config/load.js +66 -0
- package/dist/config/schema.js +160 -0
- package/dist/context/__tests__/artifact.test.js +130 -0
- package/dist/context/__tests__/pack.test.js +191 -0
- package/dist/context/artifact.js +67 -0
- package/dist/context/index.js +2 -0
- package/dist/context/pack.js +273 -0
- package/dist/diagnosis/analyzer.js +678 -0
- package/dist/diagnosis/formatter.js +136 -0
- package/dist/diagnosis/index.js +6 -0
- package/dist/diagnosis/types.js +7 -0
- package/dist/env/__tests__/fingerprint.test.js +116 -0
- package/dist/env/fingerprint.js +111 -0
- package/dist/orchestrator/__tests__/policy.test.js +185 -0
- package/dist/orchestrator/__tests__/schema-version.test.js +65 -0
- package/dist/orchestrator/artifacts.js +405 -0
- package/dist/orchestrator/state-machine.js +646 -0
- package/dist/orchestrator/types.js +88 -0
- package/dist/ownership/normalize.js +45 -0
- package/dist/repo/context.js +90 -0
- package/dist/repo/git.js +13 -0
- package/dist/repo/worktree.js +239 -0
- package/dist/store/run-store.js +107 -0
- package/dist/store/run-utils.js +69 -0
- package/dist/store/runs-root.js +126 -0
- package/dist/supervisor/__tests__/evidence-gate.test.js +111 -0
- package/dist/supervisor/__tests__/ownership.test.js +103 -0
- package/dist/supervisor/__tests__/state-machine.test.js +290 -0
- package/dist/supervisor/collision.js +240 -0
- package/dist/supervisor/evidence-gate.js +98 -0
- package/dist/supervisor/planner.js +18 -0
- package/dist/supervisor/runner.js +1562 -0
- package/dist/supervisor/scope-guard.js +55 -0
- package/dist/supervisor/state-machine.js +121 -0
- package/dist/supervisor/verification-policy.js +64 -0
- package/dist/tasks/task-metadata.js +72 -0
- package/dist/types/schemas.js +1 -0
- package/dist/verification/engine.js +49 -0
- package/dist/workers/__tests__/claude.test.js +88 -0
- package/dist/workers/__tests__/codex.test.js +81 -0
- package/dist/workers/claude.js +119 -0
- package/dist/workers/codex.js +162 -0
- package/dist/workers/json.js +22 -0
- package/dist/workers/mock.js +193 -0
- package/dist/workers/prompts.js +98 -0
- package/dist/workers/schemas.js +39 -0
- package/package.json +47 -0
- package/templates/prompts/implementer.md +70 -0
- package/templates/prompts/planner.md +62 -0
- package/templates/prompts/reviewer.md +77 -0
package/CHANGELOG.md
ADDED
|
@@ -0,0 +1,216 @@
|
|
|
1
|
+
# Changelog
|
|
2
|
+
|
|
3
|
+
All notable changes to this project will be documented in this file.
|
|
4
|
+
|
|
5
|
+
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
|
|
6
|
+
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
|
7
|
+
|
|
8
|
+
## [Unreleased]
|
|
9
|
+
|
|
10
|
+
## [0.3.0] - 2026-01-01
|
|
11
|
+
|
|
12
|
+
**Renamed to Runr.** New identity, same reliability-first mission.
|
|
13
|
+
|
|
14
|
+
### Changed
|
|
15
|
+
|
|
16
|
+
- **Package renamed**: `agent-runner` → `@weldr/runr`
|
|
17
|
+
- **CLI renamed**: `agent` → `runr`
|
|
18
|
+
- **Directory renamed**: `.agent/` → `.runr/` (old location still works with deprecation warning)
|
|
19
|
+
- **Config renamed**: `agent.config.json` → `runr.config.json` (old name still works)
|
|
20
|
+
- **Worktrees renamed**: `.agent-worktrees/` → `.runr-worktrees/`
|
|
21
|
+
- **Env var renamed**: `AGENT_WORKTREES_DIR` → `RUNR_WORKTREES_DIR` (old var still works)
|
|
22
|
+
|
|
23
|
+
### Added
|
|
24
|
+
|
|
25
|
+
- **Fun CLI aliases**: `summon` (run), `resurrect` (resume), `scry` (status), `banish` (gc)
|
|
26
|
+
- **Deprecation warnings**: Clear messages when using old paths/names
|
|
27
|
+
- **Backwards compatibility**: Old locations and names work during transition period
|
|
28
|
+
|
|
29
|
+
### Migration
|
|
30
|
+
|
|
31
|
+
Both old and new paths are supported. To migrate:
|
|
32
|
+
|
|
33
|
+
1. Rename `.agent/` to `.runr/`
|
|
34
|
+
2. Rename `agent.config.json` to `runr.config.json`
|
|
35
|
+
3. Use `runr` instead of `agent` CLI
|
|
36
|
+
|
|
37
|
+
### Fixed
|
|
38
|
+
|
|
39
|
+
- **Guard violation diagnostics**: `stop.md` now includes specific files that caused the violation
|
|
40
|
+
- Scope violations list the exact files modified outside allowlist
|
|
41
|
+
- Lockfile violations list which lockfiles were changed
|
|
42
|
+
- Error message includes up to 5 file names for quick diagnosis
|
|
43
|
+
|
|
44
|
+
## [0.2.2] - 2025-12-31
|
|
45
|
+
|
|
46
|
+
Reliability release: fixes the worktree/denylist catch-22 that caused `implement_blocked` failures.
|
|
47
|
+
|
|
48
|
+
### Fixed
|
|
49
|
+
|
|
50
|
+
- **Worktrees moved out of `.agent/`**: Worktrees now created at `.agent-worktrees/<runId>/` instead of `.agent/worktrees/<runId>/`
|
|
51
|
+
- Prevents catch-22 where denylist patterns like `.agent/**` blocked worker operations
|
|
52
|
+
- Workers no longer see `.agent` in their absolute CWD path
|
|
53
|
+
- Override location with `AGENT_WORKTREES_DIR` env var
|
|
54
|
+
- GC command updated to scan both new and legacy locations
|
|
55
|
+
|
|
56
|
+
- **Auto-inject git excludes for agent artifacts**: `.agent/` and `.agent-worktrees/` now auto-added to `.git/info/exclude` at run start
|
|
57
|
+
- Fresh repos no longer need manual `.gitignore` entries for agent artifacts
|
|
58
|
+
- Prevents "dirty worktree" guard failures on first run
|
|
59
|
+
|
|
60
|
+
- **Guard failure diagnostics**: Full guard failure details now printed to console (not just `guard=fail`)
|
|
61
|
+
- Shows exact reasons, scope violations, lockfile violations, dirty files
|
|
62
|
+
- Makes debugging guard failures actionable
|
|
63
|
+
|
|
64
|
+
- **Built-in env_allowlist for agent artifacts**: `.agent/**` and `.agent-worktrees/**` now always treated as env noise
|
|
65
|
+
- Agent artifacts never trigger scope violations or dirty worktree errors
|
|
66
|
+
- Belt-and-suspenders with git exclude injection
|
|
67
|
+
|
|
68
|
+
- **Worktree exclude injection**: Fixed `node_modules` symlinks appearing as untracked files in worktrees
|
|
69
|
+
- Git only reads `.git/info/exclude` from the main repo, not worktree gitdirs
|
|
70
|
+
- Now writes exclude patterns to main repo's `.git/info/exclude`
|
|
71
|
+
- Prevents "worktree became dirty after env setup" errors
|
|
72
|
+
|
|
73
|
+
- **Tier escalation at final milestone**: `is_milestone_end` and `is_run_end` now correctly trigger at the last milestone
|
|
74
|
+
- Previously hardcoded to `false`, preventing tier1/tier2 from running
|
|
75
|
+
- Final milestone now runs all verification tiers (tier0 + tier1 + tier2)
|
|
76
|
+
- Fixes review loops caused by reviewer expecting `npm test` but verifier only running `npm run build`
|
|
77
|
+
|
|
78
|
+
### Added
|
|
79
|
+
|
|
80
|
+
- **Legacy worktree warning**: Warns on startup if old worktree locations are detected
|
|
81
|
+
- Helps users clean up after upgrade
|
|
82
|
+
- Points to `agent gc` for cleanup
|
|
83
|
+
|
|
84
|
+
- **Implementer prompt scope clarification**: Added note that scope patterns are repo-relative, not absolute paths
|
|
85
|
+
- Prevents worker confusion when CWD contains `.agent` substrings
|
|
86
|
+
|
|
87
|
+
- **Task ownership enforcement (Phase-2)**: Tasks with `owns:` frontmatter now enforce ownership at IMPLEMENT time
|
|
88
|
+
- Defensive normalization via shared `src/ownership/normalize.ts` module
|
|
89
|
+
- Renames count as touching both old and new paths (conservative rule)
|
|
90
|
+
- `ownership_violation` stop reason with actionable error message
|
|
91
|
+
|
|
92
|
+
### Testing
|
|
93
|
+
|
|
94
|
+
- **Acceptance tests for worktree fixes**: 9 tests covering auto-exclude, worktree location, and guard diagnostics
|
|
95
|
+
- Run with `npx vitest run test/acceptance/worktree-fixes.test.ts`
|
|
96
|
+
|
|
97
|
+
## [0.2.1] - 2025-12-29
|
|
98
|
+
|
|
99
|
+
Adoption improvements: scope presets, better diagnostics, and OSS packaging.
|
|
100
|
+
|
|
101
|
+
### Added
|
|
102
|
+
|
|
103
|
+
- **Scope presets**: Named pattern collections for popular frameworks
|
|
104
|
+
- 11 presets: `nextjs`, `react`, `drizzle`, `prisma`, `vitest`, `jest`, `playwright`, `typescript`, `tailwind`, `eslint`, `env`
|
|
105
|
+
- Use via `scope.presets: ["vitest", "nextjs"]` in config
|
|
106
|
+
- Patterns merged into allowlist at config load time
|
|
107
|
+
- Unknown presets warn but don't fail
|
|
108
|
+
|
|
109
|
+
- **Review digest artifact**: `review_digest.md` written when `review_loop_detected` stops a run
|
|
110
|
+
- Contains milestone context, review round count, full list of requested changes
|
|
111
|
+
- Makes debugging review loops much easier
|
|
112
|
+
|
|
113
|
+
- **Preset suggestions**: `plan_scope_violation` errors now suggest relevant presets
|
|
114
|
+
- e.g., "Try adding presets: [vitest] to scope.presets"
|
|
115
|
+
|
|
116
|
+
### Documentation
|
|
117
|
+
|
|
118
|
+
- **README.md**: Quick start, configuration, CLI reference, stop reasons
|
|
119
|
+
- **LICENSE**: Apache 2.0 license
|
|
120
|
+
- **CONTRIBUTING.md**: Development workflow, code style, PR process, architecture overview
|
|
121
|
+
- **docs/PILOT_PROGRAM.md**: Early adopter onboarding guide
|
|
122
|
+
|
|
123
|
+
### Improved
|
|
124
|
+
|
|
125
|
+
- Stop memo now includes descriptions and tips for `review_loop_detected` and `plan_scope_violation`
|
|
126
|
+
|
|
127
|
+
## [0.2.0] - 2025-12-28
|
|
128
|
+
|
|
129
|
+
Resilience improvements based on dogfooding feedback.
|
|
130
|
+
|
|
131
|
+
### Added
|
|
132
|
+
|
|
133
|
+
- **Review loop detection**: Prevents infinite IMPLEMENT→REVIEW cycles
|
|
134
|
+
- `max_review_rounds` config option (default: 2)
|
|
135
|
+
- Fingerprint-based detection for identical consecutive `request_changes`
|
|
136
|
+
- New stop reason: `review_loop_detected`
|
|
137
|
+
- Timeline event with diagnostic payload
|
|
138
|
+
|
|
139
|
+
### Fixed
|
|
140
|
+
|
|
141
|
+
- **ESM compatibility**: `agent orchestrate wait` no longer crashes under ESM / Node 22
|
|
142
|
+
- Replaced `require()` with proper ESM import
|
|
143
|
+
|
|
144
|
+
- **State sync**: Removed dead `'DONE'` phase check in orchestrator reconciliation
|
|
145
|
+
|
|
146
|
+
### Testing
|
|
147
|
+
|
|
148
|
+
- **Golden scenario 07**: `07-review-loop-detected` validates review loop detection
|
|
149
|
+
- **Mock worker**: New `review_always_request_changes` mode for testing
|
|
150
|
+
|
|
151
|
+
## [0.1.0] - 2025-12-27
|
|
152
|
+
|
|
153
|
+
Initial stable release with full dual-LLM orchestration and autonomy features.
|
|
154
|
+
|
|
155
|
+
### Added
|
|
156
|
+
|
|
157
|
+
- **Dual-LLM orchestration**: Claude for planning/review, Codex for implementation
|
|
158
|
+
- **Phase-based execution**: PLAN → IMPLEMENT → VERIFY → REVIEW → CHECKPOINT → FINALIZE
|
|
159
|
+
- **Safety guards**: Scope allowlist/denylist, lockfile protection, dirty worktree checks
|
|
160
|
+
- **Verification tiers**: Risk-based test selection with automatic retries
|
|
161
|
+
- **Worktree isolation**: Git worktrees for safe parallel runs
|
|
162
|
+
- **Auto-resume**: Automatic recovery from transient failures (stall timeout, worker timeout)
|
|
163
|
+
- **Evidence gate**: Requires proof for `no_changes_needed` claims
|
|
164
|
+
|
|
165
|
+
### Orchestrator
|
|
166
|
+
|
|
167
|
+
- **Multi-track orchestration**: Run parallel tracks of serial steps
|
|
168
|
+
- **Collision detection**: Prevent merge conflicts with allowlist overlap checking
|
|
169
|
+
- **Collision policies**: serialize, force, fail
|
|
170
|
+
- **Resume support**: Resume orchestrations from any state
|
|
171
|
+
- **Artifact schema versioning**: All outputs include `schema_version: 1`
|
|
172
|
+
|
|
173
|
+
### Commands
|
|
174
|
+
|
|
175
|
+
- `agent run` - Execute a task with full phase lifecycle
|
|
176
|
+
- `agent resume` - Resume a stopped run
|
|
177
|
+
- `agent status` - Show run status
|
|
178
|
+
- `agent report` - Generate run report
|
|
179
|
+
- `agent follow` - Tail run timeline in real-time
|
|
180
|
+
- `agent wait` - Block until run reaches terminal state
|
|
181
|
+
- `agent summarize` - Generate summary.json from run KPIs
|
|
182
|
+
- `agent compare` - Compare KPIs between two runs
|
|
183
|
+
- `agent doctor` - Check worker CLI availability
|
|
184
|
+
- `agent gc` - Clean up old worktree directories
|
|
185
|
+
- `agent paths` - Display canonical agent directory paths
|
|
186
|
+
- `agent metrics` - Show aggregated metrics across runs
|
|
187
|
+
- `agent version` - Show version information
|
|
188
|
+
- `agent orchestrate run` - Start multi-track orchestration
|
|
189
|
+
- `agent orchestrate resume` - Resume orchestration
|
|
190
|
+
- `agent orchestrate wait` - Wait for orchestration to complete
|
|
191
|
+
|
|
192
|
+
### Diagnostics
|
|
193
|
+
|
|
194
|
+
- **Auto-diagnose stop reasons**: 10 diagnostic rules with actionable guidance
|
|
195
|
+
- **Structured handoff artifacts**: `stop.json` and `stop.md` for stopped runs
|
|
196
|
+
- **Stop reason families**: guard, budget, verification, worker, stall, auth
|
|
197
|
+
|
|
198
|
+
### Testing
|
|
199
|
+
|
|
200
|
+
- **Golden scenario suite**: 6 deterministic integration tests
|
|
201
|
+
- **Mock worker modes**: delay, stall, timeout_once_then_ok, no_changes_no_evidence
|
|
202
|
+
- **Benchmark harness**: `scripts/bench.ts` with presets
|
|
203
|
+
|
|
204
|
+
### Documentation
|
|
205
|
+
|
|
206
|
+
- Full documentation in `docs/` directory
|
|
207
|
+
- TARGET_REPO_SETUP.md for using in other projects
|
|
208
|
+
- Worktree strategy documentation
|
|
209
|
+
- CLI reference
|
|
210
|
+
|
|
211
|
+
[Unreleased]: https://github.com/vonwao/runr/compare/v0.3.0...HEAD
|
|
212
|
+
[0.3.0]: https://github.com/vonwao/runr/compare/v0.2.2...v0.3.0
|
|
213
|
+
[0.2.2]: https://github.com/vonwao/runr/compare/v0.2.1...v0.2.2
|
|
214
|
+
[0.2.1]: https://github.com/vonwao/runr/compare/v0.2.0...v0.2.1
|
|
215
|
+
[0.2.0]: https://github.com/vonwao/runr/compare/v0.1.0...v0.2.0
|
|
216
|
+
[0.1.0]: https://github.com/vonwao/runr/releases/tag/v0.1.0
|
package/LICENSE
ADDED
|
@@ -0,0 +1,190 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to the Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
Copyright 2024 Agent Framework Contributors
|
|
179
|
+
|
|
180
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
181
|
+
you may not use this file except in compliance with the License.
|
|
182
|
+
You may obtain a copy of the License at
|
|
183
|
+
|
|
184
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
185
|
+
|
|
186
|
+
Unless required by applicable law or agreed to in writing, software
|
|
187
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
188
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
189
|
+
See the License for the specific language governing permissions and
|
|
190
|
+
limitations under the License.
|
package/NOTICE
ADDED
package/README.md
ADDED
|
@@ -0,0 +1,200 @@
|
|
|
1
|
+
# Runr
|
|
2
|
+
|
|
3
|
+
Phase-gated orchestration for agent tasks.
|
|
4
|
+
|
|
5
|
+
> **Status**: v0.3.0 — Renamed from `agent-runner`. Early, opinionated, evolving.
|
|
6
|
+
|
|
7
|
+
## The Problem
|
|
8
|
+
|
|
9
|
+
AI agents can write code. They can also:
|
|
10
|
+
- Claim success without verification
|
|
11
|
+
- Modify files they shouldn't touch
|
|
12
|
+
- Get stuck in infinite loops
|
|
13
|
+
- Fail in ways that are impossible to debug
|
|
14
|
+
|
|
15
|
+
**Runr doesn't make agents smarter. It makes them accountable.**
|
|
16
|
+
|
|
17
|
+
## What This Does
|
|
18
|
+
|
|
19
|
+
Runr orchestrates AI workers (Claude, Codex) through a phase-based workflow with hard gates:
|
|
20
|
+
|
|
21
|
+
```
|
|
22
|
+
PLAN → IMPLEMENT → VERIFY → REVIEW → CHECKPOINT → done
|
|
23
|
+
↑___________| (retry if needed)
|
|
24
|
+
```
|
|
25
|
+
|
|
26
|
+
Every phase has criteria. You don't advance without meeting them.
|
|
27
|
+
|
|
28
|
+
## Why Phase Gates?
|
|
29
|
+
|
|
30
|
+
Most agent tools optimize for speed. Runr optimizes for **trust**.
|
|
31
|
+
|
|
32
|
+
When a run fails (and it will), you get:
|
|
33
|
+
- **Structured diagnostics** — exactly why it stopped
|
|
34
|
+
- **Checkpoints** — resume from where it failed
|
|
35
|
+
- **Scope guards** — files it couldn't touch, it didn't touch
|
|
36
|
+
- **Evidence** — "done" means "proven done"
|
|
37
|
+
|
|
38
|
+
## Quick Start
|
|
39
|
+
|
|
40
|
+
```bash
|
|
41
|
+
# Install
|
|
42
|
+
git clone https://github.com/vonwao/runr.git
|
|
43
|
+
cd runr && npm install && npm run build && npm link
|
|
44
|
+
|
|
45
|
+
# Verify
|
|
46
|
+
runr version
|
|
47
|
+
runr doctor
|
|
48
|
+
|
|
49
|
+
# Run a task
|
|
50
|
+
cd /your/project
|
|
51
|
+
runr run --task .runr/tasks/my-task.md --worktree
|
|
52
|
+
```
|
|
53
|
+
|
|
54
|
+
> Not on npm yet. Coming soon as `@weldr/runr`.
|
|
55
|
+
|
|
56
|
+
## Configuration
|
|
57
|
+
|
|
58
|
+
Create `.runr/runr.config.json`:
|
|
59
|
+
|
|
60
|
+
```json
|
|
61
|
+
{
|
|
62
|
+
"agent": { "name": "my-project", "version": "1" },
|
|
63
|
+
"scope": {
|
|
64
|
+
"allowlist": ["src/**", "tests/**"],
|
|
65
|
+
"denylist": ["node_modules/**"],
|
|
66
|
+
"presets": ["vitest", "typescript"]
|
|
67
|
+
},
|
|
68
|
+
"verification": {
|
|
69
|
+
"tier0": ["npm run typecheck"],
|
|
70
|
+
"tier1": ["npm run build"],
|
|
71
|
+
"tier2": ["npm test"]
|
|
72
|
+
}
|
|
73
|
+
}
|
|
74
|
+
```
|
|
75
|
+
|
|
76
|
+
### Scope Presets
|
|
77
|
+
|
|
78
|
+
Don't write patterns by hand:
|
|
79
|
+
|
|
80
|
+
```json
|
|
81
|
+
{
|
|
82
|
+
"scope": {
|
|
83
|
+
"presets": ["nextjs", "vitest", "drizzle", "tailwind"]
|
|
84
|
+
}
|
|
85
|
+
}
|
|
86
|
+
```
|
|
87
|
+
|
|
88
|
+
Available: `nextjs`, `react`, `drizzle`, `prisma`, `vitest`, `jest`, `playwright`, `typescript`, `tailwind`, `eslint`, `env`
|
|
89
|
+
|
|
90
|
+
## CLI Reference
|
|
91
|
+
|
|
92
|
+
| Command | What it does |
|
|
93
|
+
|---------|--------------|
|
|
94
|
+
| `runr run --task <file>` | Start a task |
|
|
95
|
+
| `runr resume <id>` | Continue from checkpoint |
|
|
96
|
+
| `runr status [id]` | Show run state |
|
|
97
|
+
| `runr follow [id]` | Tail run progress |
|
|
98
|
+
| `runr report <id>` | Generate run report |
|
|
99
|
+
| `runr gc` | Clean up old runs |
|
|
100
|
+
| `runr doctor` | Check environment |
|
|
101
|
+
|
|
102
|
+
### The Fun Commands
|
|
103
|
+
|
|
104
|
+
Same functionality, different vibe:
|
|
105
|
+
|
|
106
|
+
```bash
|
|
107
|
+
runr summon --task task.md # run
|
|
108
|
+
runr resurrect <id> # resume
|
|
109
|
+
runr scry <id> # status
|
|
110
|
+
runr banish # gc
|
|
111
|
+
```
|
|
112
|
+
|
|
113
|
+
## Task Files
|
|
114
|
+
|
|
115
|
+
Tasks are markdown files:
|
|
116
|
+
|
|
117
|
+
```markdown
|
|
118
|
+
# Add user authentication
|
|
119
|
+
|
|
120
|
+
## Goal
|
|
121
|
+
OAuth2 login with Google.
|
|
122
|
+
|
|
123
|
+
## Requirements
|
|
124
|
+
- Session management
|
|
125
|
+
- Protected routes
|
|
126
|
+
- Logout functionality
|
|
127
|
+
|
|
128
|
+
## Success Criteria
|
|
129
|
+
- Users can log in with Google
|
|
130
|
+
- Session persists across refreshes
|
|
131
|
+
```
|
|
132
|
+
|
|
133
|
+
## Stop Reasons
|
|
134
|
+
|
|
135
|
+
When Runr stops, it tells you why:
|
|
136
|
+
|
|
137
|
+
| Reason | What happened |
|
|
138
|
+
|--------|---------------|
|
|
139
|
+
| `complete` | Task finished. Ship it. |
|
|
140
|
+
| `verification_failed_max_retries` | Tests failed too many times |
|
|
141
|
+
| `guard_violation` | Touched files outside scope |
|
|
142
|
+
| `review_loop_detected` | Reviewer kept requesting same changes |
|
|
143
|
+
| `time_budget_exceeded` | Ran out of time |
|
|
144
|
+
|
|
145
|
+
Every stop produces `stop.json` + `stop.md` with diagnostics.
|
|
146
|
+
|
|
147
|
+
## Philosophy
|
|
148
|
+
|
|
149
|
+
**This is not magic.** Runs fail. The goal is *understandable, resumable* failure.
|
|
150
|
+
|
|
151
|
+
**This is not a chatbot.** Task in, code out. No conversation.
|
|
152
|
+
|
|
153
|
+
**This is not a code generator.** It orchestrates generators. Different job.
|
|
154
|
+
|
|
155
|
+
**Agents lie. Logs don't.** If it can't prove it, it didn't do it.
|
|
156
|
+
|
|
157
|
+
## Migrating from agent-runner
|
|
158
|
+
|
|
159
|
+
If you're upgrading from `agent-runner`:
|
|
160
|
+
|
|
161
|
+
| Old | New |
|
|
162
|
+
|-----|-----|
|
|
163
|
+
| `agent` CLI | `runr` CLI |
|
|
164
|
+
| `.agent/` directory | `.runr/` directory |
|
|
165
|
+
| `agent.config.json` | `runr.config.json` |
|
|
166
|
+
| `.agent-worktrees/` | `.runr-worktrees/` |
|
|
167
|
+
|
|
168
|
+
Both old and new locations work during the transition period. You'll see deprecation warnings for old locations.
|
|
169
|
+
|
|
170
|
+
## Development
|
|
171
|
+
|
|
172
|
+
```bash
|
|
173
|
+
npm run build # compile
|
|
174
|
+
npm test # run tests
|
|
175
|
+
npm run dev -- run --task task.md # run from source
|
|
176
|
+
```
|
|
177
|
+
|
|
178
|
+
## Release History
|
|
179
|
+
|
|
180
|
+
| Version | Date | Highlights |
|
|
181
|
+
|---------|------|------------|
|
|
182
|
+
| v0.3.0 | 2026-01-01 | **Renamed to Runr**, new CLI, new directory structure |
|
|
183
|
+
| v0.2.2 | 2025-12-31 | Worktree location fix, guard diagnostics |
|
|
184
|
+
| v0.2.1 | 2025-12-29 | Scope presets, review digest |
|
|
185
|
+
| v0.2.0 | 2025-12-28 | Review loop detection |
|
|
186
|
+
| v0.1.0 | 2025-12-27 | Initial stable release |
|
|
187
|
+
|
|
188
|
+
See [CHANGELOG.md](CHANGELOG.md) for detailed release notes.
|
|
189
|
+
|
|
190
|
+
## Contributing
|
|
191
|
+
|
|
192
|
+
See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup and guidelines.
|
|
193
|
+
|
|
194
|
+
## License
|
|
195
|
+
|
|
196
|
+
Apache 2.0 — See [LICENSE](LICENSE)
|
|
197
|
+
|
|
198
|
+
---
|
|
199
|
+
|
|
200
|
+
<sub>Existence is pain, but shipping is relief.</sub>
|