@fro.bot/systematic 3.25.1 → 3.26.0
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/HARNESSES.md +49 -1
- package/README.md +1 -1
- package/dist/ce-review-validator.d.ts +22 -3
- package/dist/cli.js +69 -34
- package/dist/{index-bmsgc2em.js → index-1dyb2x0z.js} +1 -0
- package/dist/index.js +1 -1
- package/dist/lib/bundled-names.d.ts +1 -1
- package/dist/lib/review-artifact-path.d.ts +66 -0
- package/dist/lib/review-artifact-schema.d.ts +12 -0
- package/dist/lib/review-pipeline.d.ts +25 -17
- package/dist/lib/review-return-validator.d.ts +3 -6
- package/dist/pi.js +1 -0
- package/package.json +2 -1
- package/skills/ce-review/SKILL.md +2 -2
- package/skills/ce-review/references/pipeline-invocation.md +36 -1
- package/skills/ce-review/references/review-pipeline-schema.json +3 -3
- package/skills/ce-review/references/review-summary-schema.json +12 -12
- package/skills/ce-review/references/validator-template.md +12 -11
- package/skills/ce-review/scripts/validate-review.mjs +355 -136
- package/skills/git-commit-push-pr/SKILL.md +79 -6
- package/skills/pr-attachments/SKILL.md +764 -0
- package/skills/pr-attachments/scripts/pr-attachments.mjs +3140 -0
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@fro.bot/systematic",
|
|
3
|
-
"version": "3.
|
|
3
|
+
"version": "3.26.0",
|
|
4
4
|
"description": "Compound-engineering loops for OpenCode, Pi, and Claude Code",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"homepage": "https://fro.bot/systematic",
|
|
@@ -133,6 +133,7 @@
|
|
|
133
133
|
"brace-expansion": "^5.0.8",
|
|
134
134
|
"conventional-changelog-writer": ">=9",
|
|
135
135
|
"devalue": "^5.9.3",
|
|
136
|
+
"dompurify": "~3.4.17",
|
|
136
137
|
"fast-uri": "~3.1.7",
|
|
137
138
|
"markdown-it": "~14.3.3",
|
|
138
139
|
"smol-toml": "~1.9.0",
|
|
@@ -520,8 +520,8 @@ A helper failure (`prepare` or `merge` exiting 1 or 2) is never permission to ha
|
|
|
520
520
|
|
|
521
521
|
Dispatch validators for exactly the findings `merge`'s `validator_requests` names -- the P0/P1-or-`requires_verification` gating band is already computed; Stage 5b no longer identifies the gated set by hand.
|
|
522
522
|
|
|
523
|
-
1. For each entry in `validator_requests`, spawn one validator subagent in parallel using the validator template at `references/validator-template.md`. Look up that finding's full fields (title, why_it_matters, evidence, file, line, severity, autofix_class, owner, suggested_fix) from `merge`'s `merged_findings` by `finding_id`, and pass them along with the intent summary, file list, and full diff.
|
|
524
|
-
2. Collect `{outcome: 'true'|'false'|'failed'|'unavailable', reason?}` from each validator, keyed by `finding_id`. `outcome: 'true'` needs no reason; the other three outcomes each require one.
|
|
523
|
+
1. For each entry in `validator_requests`, spawn one validator subagent in parallel with the others in its batch, using the validator template at `references/validator-template.md`. Dispatch in bounded batches, sized to what the harness handles reliably. Each batch runs in parallel and finishes before the next starts. Look up that finding's full fields (title, why_it_matters, evidence, file, line, severity, autofix_class, owner, suggested_fix) from `merge`'s `merged_findings` by `finding_id`, and pass them along with the intent summary, file list, and full diff.
|
|
524
|
+
2. Collect `{outcome: 'true'|'false'|'failed'|'unavailable', reason?}` from each validator, keyed by `finding_id`. `outcome: 'true'` needs no reason; the other three outcomes each require one. Every request needs a result: a subagent that returns nothing, or an answer that is not one of these outcomes, is recorded as `unavailable` with a reason.
|
|
525
525
|
3. Carry every result forward as `validator_lifecycle_results` into `finalize` (Stage 6). Do not reconcile filtered findings, update ledger dispositions, or recompute the "Filtered (not validated)" group by hand -- `finalize` derives all of it from these results plus `merge`'s output.
|
|
526
526
|
|
|
527
527
|
**Outcome semantics** (enforced by `finalize`, not the model): `true` validates the finding -- it flows to Stage 6 unchanged. `false` filters the finding -- it drops out of the surviving/actioned set, receives disposition `filtered` with the validator's exact one-sentence reason, and appears in the "Filtered (not validated)" group. `failed` and `unavailable` leave the finding actionable and unvalidated (no `validated` annotation; it appears in the normal severity tables) but each records a lifecycle failure that marks the run `degraded` and blocks a clean verdict -- report the failed/unavailable validator in Coverage rather than silently treating it as validated.
|
|
@@ -23,10 +23,45 @@ exit 2 is a launch failure, not a payload problem. On exit 1 (the input
|
|
|
23
23
|
was structurally rejected), the parent may correct its own JSON envelope
|
|
24
24
|
exactly once -- fixing a genuine encoding mistake, never reshaping the
|
|
25
25
|
envelope to force acceptance -- and retry; a second exit 1 stops the run
|
|
26
|
-
visibly with degraded or abnormal status.
|
|
26
|
+
visibly with degraded or abnormal status. An exit 1 whose message says the
|
|
27
|
+
input exceeds the aggregate byte cap is not an encoding mistake: do not retry
|
|
28
|
+
the same bytes, and do not shrink the payload to fit. Stop visibly and report
|
|
29
|
+
the cap the message names. Never fall back to writing a
|
|
27
30
|
finding, a merged finding, a queue, a disposition count, or a report section
|
|
28
31
|
by hand because a phase call failed.
|
|
29
32
|
|
|
33
|
+
## Rejection output
|
|
34
|
+
|
|
35
|
+
An exit 1 from `prepare`, `merge` or `finalize` prints one of four shapes on
|
|
36
|
+
stderr:
|
|
37
|
+
|
|
38
|
+
- **Schema rejection.** `<phase> rejected the aggregate envelope: <reason>`,
|
|
39
|
+
then up to eight `path code` lines, then `… and N more` when more issues
|
|
40
|
+
were found.
|
|
41
|
+
- **Rejection of the content.** One line,
|
|
42
|
+
`<phase> rejected the aggregate envelope: <reason> at <path>`. Malformed JSON
|
|
43
|
+
is this shape too, with the reason `malformed JSON` and the path `$`.
|
|
44
|
+
- **Byte cap.** One bare line, `<phase> input exceeds the aggregate byte cap
|
|
45
|
+
(16842752 bytes)`. It names the cap and carries no reason or path.
|
|
46
|
+
- **Invalid UTF-8.** One bare line, `<phase> input is not valid UTF-8`.
|
|
47
|
+
|
|
48
|
+
`path` points into the envelope and `code` is a schema issue code. No payload
|
|
49
|
+
value, key name or issue message is printed, so the lines are safe to quote
|
|
50
|
+
in Coverage and are enough to locate the field to correct.
|
|
51
|
+
|
|
52
|
+
The artifact validators (`artifact` here, `validate-review-artifact` in the
|
|
53
|
+
CLI) print `Review artifact failed schema validation: N issue(s)` with the full
|
|
54
|
+
issue count, a `Schema:` line, and the same bounded `path code` lines, then
|
|
55
|
+
`… and N more` when more were found. An issue the schema authors wrote a
|
|
56
|
+
message for (a `custom` issue) carries that one authored message after its
|
|
57
|
+
code, as `path custom: <message>`; no other issue prints a message.
|
|
58
|
+
|
|
59
|
+
Validators installed before the run-level limits were raised reject artifacts
|
|
60
|
+
with more than 32 findings or other run-level entries. Schema version 1 is
|
|
61
|
+
unchanged, so an older artifact still validates. If an older external
|
|
62
|
+
validator rejects a large artifact on a count, that is a version mismatch to
|
|
63
|
+
report, not a malformed artifact: update the validator.
|
|
64
|
+
|
|
30
65
|
## screen
|
|
31
66
|
|
|
32
67
|
Structurally admits one persona's raw return and binds it to the dispatched
|
|
@@ -7,7 +7,7 @@
|
|
|
7
7
|
"type": "object",
|
|
8
8
|
"properties": {
|
|
9
9
|
"decisions": {
|
|
10
|
-
"maxItems":
|
|
10
|
+
"maxItems": 2048,
|
|
11
11
|
"type": "array",
|
|
12
12
|
"items": {
|
|
13
13
|
"oneOf": [
|
|
@@ -26,7 +26,7 @@
|
|
|
26
26
|
},
|
|
27
27
|
"input_finding_ids": {
|
|
28
28
|
"minItems": 2,
|
|
29
|
-
"maxItems":
|
|
29
|
+
"maxItems": 2048,
|
|
30
30
|
"type": "array",
|
|
31
31
|
"items": {
|
|
32
32
|
"type": "string",
|
|
@@ -363,7 +363,7 @@
|
|
|
363
363
|
"pattern": "\\S"
|
|
364
364
|
},
|
|
365
365
|
"results": {
|
|
366
|
-
"maxItems":
|
|
366
|
+
"maxItems": 2048,
|
|
367
367
|
"type": "array",
|
|
368
368
|
"items": {
|
|
369
369
|
"type": "object",
|
|
@@ -212,7 +212,7 @@
|
|
|
212
212
|
}
|
|
213
213
|
},
|
|
214
214
|
"findings": {
|
|
215
|
-
"maxItems":
|
|
215
|
+
"maxItems": 2048,
|
|
216
216
|
"type": "array",
|
|
217
217
|
"items": {
|
|
218
218
|
"type": "object",
|
|
@@ -350,7 +350,7 @@
|
|
|
350
350
|
},
|
|
351
351
|
"input_finding_ids": {
|
|
352
352
|
"minItems": 1,
|
|
353
|
-
"maxItems":
|
|
353
|
+
"maxItems": 2048,
|
|
354
354
|
"type": "array",
|
|
355
355
|
"items": {
|
|
356
356
|
"type": "string",
|
|
@@ -412,7 +412,7 @@
|
|
|
412
412
|
}
|
|
413
413
|
},
|
|
414
414
|
"declined_merges": {
|
|
415
|
-
"maxItems":
|
|
415
|
+
"maxItems": 2048,
|
|
416
416
|
"type": "array",
|
|
417
417
|
"items": {
|
|
418
418
|
"type": "object",
|
|
@@ -434,7 +434,7 @@
|
|
|
434
434
|
},
|
|
435
435
|
"input_finding_ids": {
|
|
436
436
|
"minItems": 2,
|
|
437
|
-
"maxItems":
|
|
437
|
+
"maxItems": 2048,
|
|
438
438
|
"type": "array",
|
|
439
439
|
"items": {
|
|
440
440
|
"type": "string",
|
|
@@ -517,7 +517,7 @@
|
|
|
517
517
|
"additionalProperties": false
|
|
518
518
|
},
|
|
519
519
|
"applied_fixes": {
|
|
520
|
-
"maxItems":
|
|
520
|
+
"maxItems": 2048,
|
|
521
521
|
"type": "array",
|
|
522
522
|
"items": {
|
|
523
523
|
"type": "string",
|
|
@@ -527,7 +527,7 @@
|
|
|
527
527
|
}
|
|
528
528
|
},
|
|
529
529
|
"residual_actionable_work": {
|
|
530
|
-
"maxItems":
|
|
530
|
+
"maxItems": 2048,
|
|
531
531
|
"type": "array",
|
|
532
532
|
"items": {
|
|
533
533
|
"type": "string",
|
|
@@ -537,7 +537,7 @@
|
|
|
537
537
|
}
|
|
538
538
|
},
|
|
539
539
|
"advisory_outputs": {
|
|
540
|
-
"maxItems":
|
|
540
|
+
"maxItems": 2048,
|
|
541
541
|
"type": "array",
|
|
542
542
|
"items": {
|
|
543
543
|
"type": "string",
|
|
@@ -557,10 +557,10 @@
|
|
|
557
557
|
"validators": {
|
|
558
558
|
"type": "integer",
|
|
559
559
|
"minimum": 0,
|
|
560
|
-
"maximum":
|
|
560
|
+
"maximum": 2048
|
|
561
561
|
},
|
|
562
562
|
"residual_risks": {
|
|
563
|
-
"maxItems":
|
|
563
|
+
"maxItems": 4096,
|
|
564
564
|
"type": "array",
|
|
565
565
|
"items": {
|
|
566
566
|
"type": "string",
|
|
@@ -570,7 +570,7 @@
|
|
|
570
570
|
}
|
|
571
571
|
},
|
|
572
572
|
"testing_gaps": {
|
|
573
|
-
"maxItems":
|
|
573
|
+
"maxItems": 4096,
|
|
574
574
|
"type": "array",
|
|
575
575
|
"items": {
|
|
576
576
|
"type": "string",
|
|
@@ -590,7 +590,7 @@
|
|
|
590
590
|
}
|
|
591
591
|
},
|
|
592
592
|
"validator_failures": {
|
|
593
|
-
"maxItems":
|
|
593
|
+
"maxItems": 2048,
|
|
594
594
|
"type": "array",
|
|
595
595
|
"items": {
|
|
596
596
|
"type": "string",
|
|
@@ -600,7 +600,7 @@
|
|
|
600
600
|
}
|
|
601
601
|
},
|
|
602
602
|
"intent_uncertainty": {
|
|
603
|
-
"maxItems":
|
|
603
|
+
"maxItems": 67584,
|
|
604
604
|
"type": "array",
|
|
605
605
|
"items": {
|
|
606
606
|
"type": "string",
|
|
@@ -17,16 +17,17 @@ Your sole job is to answer three questions about one specific finding and return
|
|
|
17
17
|
Return ONLY valid JSON matching this schema. No prose, no markdown, no explanation outside the JSON object.
|
|
18
18
|
|
|
19
19
|
{
|
|
20
|
-
"
|
|
21
|
-
"reason": "<one sentence
|
|
20
|
+
"outcome": "true" | "false" | "failed" | "unavailable",
|
|
21
|
+
"reason": "<one sentence; omit when outcome is true>"
|
|
22
22
|
}
|
|
23
23
|
|
|
24
24
|
Rules:
|
|
25
25
|
- You are a leaf validator inside an already-running review workflow. Do not invoke systematic skills or agents. Perform your analysis directly and return the JSON verdict only.
|
|
26
26
|
- You are operationally read-only. You may use non-mutating inspection tools (file reads, glob, grep, git log, git diff, git show, git blame, gh pr view) to examine the code. Do not edit project files, change branches, commit, push, create PRs, or otherwise mutate the checkout or repository state.
|
|
27
|
-
- Answer the three validation questions below. Set `
|
|
28
|
-
-
|
|
29
|
-
-
|
|
27
|
+
- Answer the three validation questions below. Set `outcome: "true"` only when all three answers are YES. Set `outcome: "false"` when any answer is NO.
|
|
28
|
+
- A `false` verdict needs a `reason` of one sentence. State the specific code evidence that drove your verdict (file name, function name, or line reference when relevant). Do not repeat the finding title verbatim. A `true` verdict carries no reason.
|
|
29
|
+
- Return `failed` with a reason when your analysis could not be completed, and `unavailable` with a reason when the code or tools you need could not be reached. Never guess a verdict to avoid either.
|
|
30
|
+
- Be conservative: when evidence is ambiguous, prefer `outcome: "true"` (keep the finding in the actioned set). A false negative that lets a real bug through is worse than a false positive that the human reviewer can dismiss.
|
|
30
31
|
- Do not validate based on general coding principles alone. Ground your verdict in the actual code as written in this diff and the surrounding context.
|
|
31
32
|
</output-contract>
|
|
32
33
|
|
|
@@ -42,8 +43,8 @@ Answer each question YES or NO based on the code evidence you find.
|
|
|
42
43
|
3. **Is the issue already handled elsewhere?**
|
|
43
44
|
Check whether the problem is already mitigated by a guard, middleware, framework behavior, type constraint, or other mechanism not visible at the cited line. A finding is not valid if the issue is fully handled at a higher or lower layer that the reviewer missed.
|
|
44
45
|
|
|
45
|
-
Set `
|
|
46
|
-
Set `
|
|
46
|
+
Set `outcome: "true"` only when: the issue is real (Q1 YES), introduced by this diff or newly relevant (Q2 YES), and not already handled elsewhere (Q3 YES).
|
|
47
|
+
Set `outcome: "false"` when any question is NO, and state which question failed and why in `reason`.
|
|
47
48
|
</validation-questions>
|
|
48
49
|
|
|
49
50
|
<finding>
|
|
@@ -89,8 +90,8 @@ Diff:
|
|
|
89
90
|
|
|
90
91
|
## Dispatch Notes
|
|
91
92
|
|
|
92
|
-
- Dispatch one validator subagent per gated finding
|
|
93
|
+
- Dispatch one validator subagent per gated finding. Run them in bounded batches, sized to what the harness handles reliably: the validators of a batch run in parallel, and a batch finishes before the next starts.
|
|
93
94
|
- Pass the full diff and file list so the validator can inspect surrounding context, not just the cited line.
|
|
94
|
-
- The validator returns `{
|
|
95
|
-
- **Never drop a finding based on the validator verdict.** A finding with `
|
|
96
|
-
- If a validator subagent fails
|
|
95
|
+
- The validator returns `{outcome, reason?}`. Record it as that finding's lifecycle result, keyed by `finding_id`, and carry it into `finalize` as `validator_lifecycle_results`.
|
|
96
|
+
- **Never drop a finding based on the validator verdict.** A finding with `outcome: "false"` moves to the "Filtered (not validated)" presentation group in Stage 6. It is never removed from the report.
|
|
97
|
+
- If a validator subagent fails, times out, or returns nothing, record `failed` or `unavailable` with a reason. The finding stays actionable and unvalidated, and `finalize` records a lifecycle failure that marks the run degraded. Report that validator in the Coverage section. Do not treat the finding as validated.
|