@orkestrel/scaffold 0.0.111 → 0.0.112
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/dist/agents/templates/brief.md +1 -1
- package/dist/bin/main.js +1 -1
- package/dist/bin/main.js.map +1 -1
- package/dist/host/AGENTS.md +1 -1
- package/dist/host/agents/orchestration.md +1 -1
- package/dist/host/agents/skills/orkestrel-dispatch/SKILL.md +1 -1
- package/dist/host/agents/templates/brief.md +1 -1
- package/dist/host/claude/agents/verifier.md +1 -1
- package/dist/host/codex/agents/verifier.toml +2 -2
- package/dist/host/manifest.json +7 -7
- package/dist/src/core/index.cjs +1 -1
- package/dist/src/core/index.cjs.map +1 -1
- package/dist/src/core/index.js +1 -1
- package/dist/src/core/index.js.map +1 -1
- package/package.json +1 -1
package/dist/host/AGENTS.md
CHANGED
|
@@ -100,7 +100,7 @@ Test ladder, narrowest first; stop at the boundary the change size names:
|
|
|
100
100
|
3. The touched project: `npm run test:<project>`, plus the `check:` script for that project where `package.json` declares one.
|
|
101
101
|
4. Tree-wide gates, once, by `verifier`: `npm run format:check`, `npm run lint:check`, `npm run check`, `npm run build`, `npm test`.
|
|
102
102
|
|
|
103
|
-
-
|
|
103
|
+
- After every change, run the format check, lint, and type check over the changed scope before any test, build, or long run. They take seconds and catch what a slow run would report late; fix what they report, then climb the ladder. A guide check runs with the tests that prove the guide.
|
|
104
104
|
- Run the mutating `npm run lint` then `npm run format` only to converge before the non-mutating gates.
|
|
105
105
|
- A writing unit stops at the project boundary and reports the commands it ran. `verifier` runs the tree-wide gates when dispatched for them and edits no source.
|
|
106
106
|
- Never claim a gate passed without running it and reading its output bare, with no `| tail` or `| grep` behind it.
|
|
@@ -81,7 +81,7 @@ The harness's own engine orchestrates: Claude Fable 5.1 or Claude Opus 5.5 in Cl
|
|
|
81
81
|
|
|
82
82
|
- Spend process only where it changes a result. Launch, run, and report: no fixed clock windows, readiness-only turns, per-command acknowledgments, hash pins of a brief, or process queries beyond the recorded process ids.
|
|
83
83
|
- When a verifier lane fails in its harness rather than in the gate, run the gate once yourself and read its exit code; write no comparator, snapshot, or retry chain to obtain evidence.
|
|
84
|
-
- Keep valid receipts. Re-run a check only when its inputs, configuration, environment, or claim
|
|
84
|
+
- Keep valid receipts. Re-run a check only when a change to its inputs, configuration, environment, or claim could alter what it proved, and then run the narrowest check that covers the change. Never repeat a passing check to collect another receipt or to have every suite pass in one command; name the receipt that covers each check a brief does not rerun.
|
|
85
85
|
- Ask the user only for a decision that is theirs: scope, the spend ceiling and stop line § Hold the plan names, a conflicting ruling, a credential, publication, or a commit or push the law reserves. Decide routine matters yourself, such as time and lane allowances, retries, and order, and report them, with time in whole minutes.
|
|
86
86
|
- Never end a turn with work pending and nothing that will wake the session: run the work as a tracked background command or a child whose completion notifies, or schedule a wake. While a lane runs, continue independent work.
|
|
87
87
|
|
|
@@ -27,7 +27,7 @@ description: >-
|
|
|
27
27
|
1. A small native unit's brief is the dispatch message: scope, law references, expected result. Otherwise run `node .agents/skills/orkestrel-dispatch/scripts/brief.ts --unit <unit> --lane <lane>` and fill every section; write `none` in an empty one. A re-run takes the `-<n>` file the script writes; never edit a launched brief.
|
|
28
28
|
2. Back every fact the unit will act on with the command and output that established it. Check a fact against the tree, not against another artifact. A cross-process or filesystem brief carries a platform-facts table (operation, host, measured code, and the probe that measured it) and marks each unmeasured assumption. An investigation brief names the failing command and state, the candidate layers, the readings that distinguish them, the test that pins the existing behavior, the fix pre-approved for each confirmed reading, and the stop for every other outcome. A failure that passes alone but repeats in the sequence that produced it is an order-dependent defect to diagnose, never a timing miss to record, and an unchanged rerun of that sequence adds no evidence. A brief built on an earlier lane's evidence names what that evidence left unproven and schedules the cheapest run that covers the remainder before any long run. A brief carries the failure output it asks the unit to repair inline or under the unit's own checkout, never only as a path the unit may not reach.
|
|
29
29
|
3. Scope by what the change makes false: run the `orkestrel-scout` skill's `map.ts --refs` and `--census` for an existing member of any enumerated population the unit extends, and own every file that comes back, with the tests that pin the behavior, the fixtures derived from a constant, and the materialized copy of a template. A brief that prescribes a mechanism step by step lists the inherited operations that keep their behavior, so its stop line guards only what the prescription changes.
|
|
30
|
-
4. Order acceptance criteria cheap-first
|
|
30
|
+
4. Order acceptance criteria cheap-first, per `AGENTS.md` § Work loop: regenerate, then the format check, lint, and type check, then scoped tests. Name a timing-sensitive or tree-wide gate as an observation, not a criterion. Place a run whose cost outweighs the discrimination it adds after the cheap checks and after the inputs stabilize. Before a brief ships, run every acceptance check it states as a command's expected output against the destination tree and word the row from that reading.
|
|
31
31
|
5. State that the executor performs the work itself and spawns nothing. A bridge driver carries the brief unaltered and returns the journal path and session id.
|
|
32
32
|
6. Name the host conditions the unit will hit: shell, sandbox, network, files expected dirty, commands known to fail. Give absolute paths for work outside the session's root; a lane's shell can restart in another directory between calls. A brief that folds prepared work onto a checkout inventories the tracked, staged, and untracked inputs, checks the chosen patch method against the destination's actual state, and names the conflict precedence and a bounded recovery.
|
|
33
33
|
7. Fill each placeholder at its value sites only; a global replace also rewrites a stop clause that names the placeholder.
|
|
@@ -46,7 +46,7 @@ Stop and report (expected, found, evidence, done or not done, one hypothesis) on
|
|
|
46
46
|
|
|
47
47
|
## Acceptance criteria
|
|
48
48
|
|
|
49
|
-
1.
|
|
49
|
+
1. CHEAP_CHECKS (regeneration, then the format check, lint, and type check over the owned files)
|
|
50
50
|
2. SCOPED_TEST
|
|
51
51
|
3. ARTIFACT_CRITERION
|
|
52
52
|
|
|
@@ -12,7 +12,7 @@ On Claude Haiku 5.5, run the requested gates and report their results. Write onl
|
|
|
12
12
|
|
|
13
13
|
## Do
|
|
14
14
|
|
|
15
|
-
1. Run exactly the commands the dispatch names, in order. Default scoped sweep: the `check:` script and `test:` script of each project the dispatch names. Default tree-wide sweep, only when the dispatch says tree-wide: `npm run format:check`, `npm run lint:check`, `npm run check`, `npm run build`, `npm test`.
|
|
15
|
+
1. Run exactly the commands the dispatch names, in order. Default scoped sweep: the format check and lint over the changed files, then the `check:` script and `test:` script of each project the dispatch names. Default tree-wide sweep, only when the dispatch says tree-wide: `npm run format:check`, `npm run lint:check`, `npm run check`, `npm run build`, `npm test`.
|
|
16
16
|
2. Read each gate bare. Never pipe it through `tail` or `grep`.
|
|
17
17
|
3. Record each gate's outcome by exit code. A gate that "mostly passes" failed.
|
|
18
18
|
4. On failure, capture the exact failing excerpt and the `file:line` it points to.
|
|
@@ -9,8 +9,8 @@ outputs .agents/orchestration.md § Permission floor permits; never fix source.
|
|
|
9
9
|
runner, follow .agents/skills/orkestrel-parallel/SKILL.md for requests, holds, result publication,
|
|
10
10
|
and continuation. Never spawn another agent.
|
|
11
11
|
|
|
12
|
-
Run exactly the commands the dispatch names, in order. Default scoped sweep: the check
|
|
13
|
-
scripts of each named project. Default tree-wide sweep, only when the dispatch says tree-wide:
|
|
12
|
+
Run exactly the commands the dispatch names, in order. Default scoped sweep: the format check and
|
|
13
|
+
lint over the changed files, then the check: and test: scripts of each named project. Default tree-wide sweep, only when the dispatch says tree-wide:
|
|
14
14
|
npm run format:check; npm run lint:check; npm run check; npm run build; npm test. Read each gate
|
|
15
15
|
bare, never through tail or grep. Record each outcome by exit code; a gate that mostly passes
|
|
16
16
|
failed. On failure capture the exact excerpt and the file:line it points to. Report a failure that
|
package/dist/host/manifest.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
"storage": "AGENTS.md",
|
|
5
5
|
"destination": "AGENTS.md",
|
|
6
6
|
"executable": false,
|
|
7
|
-
"digest": "
|
|
7
|
+
"digest": "3d183e5cae674592a63f5ec38deb421fab480d408d2874a3040bacf2e4d20680"
|
|
8
8
|
},
|
|
9
9
|
{
|
|
10
10
|
"storage": "LICENSE",
|
|
@@ -16,7 +16,7 @@
|
|
|
16
16
|
"storage": "agents/orchestration.md",
|
|
17
17
|
"destination": ".agents/orchestration.md",
|
|
18
18
|
"executable": false,
|
|
19
|
-
"digest": "
|
|
19
|
+
"digest": "9f61611ce7f38a80d4070018884d6dfc9ca3791d51e561919489cc2fdb29965f"
|
|
20
20
|
},
|
|
21
21
|
{
|
|
22
22
|
"storage": "agents/platforms/posix.md",
|
|
@@ -160,7 +160,7 @@
|
|
|
160
160
|
"storage": "agents/skills/orkestrel-dispatch/SKILL.md",
|
|
161
161
|
"destination": ".agents/skills/orkestrel-dispatch/SKILL.md",
|
|
162
162
|
"executable": false,
|
|
163
|
-
"digest": "
|
|
163
|
+
"digest": "ec6f9888db5f24c8d07fa9516045b96ab3f38fe9fbb4ba0c827b675088235f49"
|
|
164
164
|
},
|
|
165
165
|
{
|
|
166
166
|
"storage": "agents/skills/orkestrel-dispatch/agents/openai.yaml",
|
|
@@ -532,7 +532,7 @@
|
|
|
532
532
|
"storage": "agents/templates/brief.md",
|
|
533
533
|
"destination": ".agents/templates/brief.md",
|
|
534
534
|
"executable": false,
|
|
535
|
-
"digest": "
|
|
535
|
+
"digest": "7dc057870174bda3f0aee305c0e8e86b9552ddf8f4f0e84ae66aba4fae45ab95"
|
|
536
536
|
},
|
|
537
537
|
{
|
|
538
538
|
"storage": "agents/transports/claude-cli.md",
|
|
@@ -634,7 +634,7 @@
|
|
|
634
634
|
"storage": "claude/agents/verifier.md",
|
|
635
635
|
"destination": ".claude/agents/verifier.md",
|
|
636
636
|
"executable": false,
|
|
637
|
-
"digest": "
|
|
637
|
+
"digest": "7b242f3dbb2b0407d4520e3cf6e1a426327ddb42013aeb816249efa9311660a3"
|
|
638
638
|
},
|
|
639
639
|
{
|
|
640
640
|
"storage": "claude/rules/application.md",
|
|
@@ -874,7 +874,7 @@
|
|
|
874
874
|
"storage": "codex/agents/verifier.toml",
|
|
875
875
|
"destination": ".codex/agents/verifier.toml",
|
|
876
876
|
"executable": false,
|
|
877
|
-
"digest": "
|
|
877
|
+
"digest": "476393f285521ccd341db919f1ec5155e7630de6e1b2a9183a1f2378e09809a3"
|
|
878
878
|
},
|
|
879
879
|
{
|
|
880
880
|
"storage": "codex/config.toml",
|
|
@@ -2141,5 +2141,5 @@
|
|
|
2141
2141
|
]
|
|
2142
2142
|
}
|
|
2143
2143
|
],
|
|
2144
|
-
"digest": "
|
|
2144
|
+
"digest": "a3c8bbe5bf6b648df8bae2b16eb53584423b05ac61c8a31a6d8af964d72929c1"
|
|
2145
2145
|
}
|
package/dist/src/core/index.cjs
CHANGED
|
@@ -4,7 +4,7 @@ let _orkestrel_template = require("@orkestrel/template");
|
|
|
4
4
|
let _orkestrel_emitter = require("@orkestrel/emitter");
|
|
5
5
|
var package_default = {
|
|
6
6
|
name: "@orkestrel/scaffold",
|
|
7
|
-
version: "0.0.
|
|
7
|
+
version: "0.0.112",
|
|
8
8
|
description: "Scaffold workspaces with commands: new, audit, repair, catalog, and overwrite.",
|
|
9
9
|
keywords: [
|
|
10
10
|
"audit",
|