@codyswann/lisa 4.37.1 → 4.37.3
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/all/copy-contents/gitignore +6 -0
- package/all/copy-overwrite/scripts/check-third-party-action-pins.mjs +6 -2
- package/dist/core/lisa-owned-hash-ledger.d.ts.map +1 -1
- package/dist/core/lisa-owned-hash-ledger.js +14 -0
- package/dist/core/lisa-owned-hash-ledger.js.map +1 -1
- package/dist/core/nightly-e2e-guard-behavior-certificate.js +2 -2
- package/dist/core/upstream-evidence-manifest.d.ts.map +1 -1
- package/dist/core/upstream-evidence-manifest.js +39 -12
- package/dist/core/upstream-evidence-manifest.js.map +1 -1
- package/package.json +5 -4
- package/plugins/lisa/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa/.codex-plugin/plugin.json +1 -1
- package/plugins/lisa/.codex-plugin/skills/lisa-github-write-issue/SKILL.md +11 -0
- package/plugins/lisa/.codex-plugin/skills/lisa-jira-write-ticket/SKILL.md +11 -0
- package/plugins/lisa/.codex-plugin/skills/lisa-linear-write-issue/SKILL.md +11 -0
- package/plugins/lisa/.codex-plugin/skills/lisa-repair-intake/SKILL.md +30 -2
- package/plugins/lisa/hooks/inject-resolved-config.mjs +26 -7
- package/plugins/lisa/rules/eager/config-resolution.md +3 -1
- package/plugins/lisa/rules/reference/config-resolution.md +1 -1
- package/plugins/lisa/scripts/intake-blocker-reprobe.mjs +120 -3
- package/plugins/lisa/skills/lisa-github-write-issue/SKILL.md +11 -0
- package/plugins/lisa/skills/lisa-jira-write-ticket/SKILL.md +11 -0
- package/plugins/lisa/skills/lisa-linear-write-issue/SKILL.md +11 -0
- package/plugins/lisa/skills/lisa-repair-intake/SKILL.md +30 -2
- package/plugins/lisa-agy/plugin.json +1 -1
- package/plugins/lisa-agy/scripts/intake-blocker-reprobe.mjs +120 -3
- package/plugins/lisa-agy/skills/lisa-github-write-issue/SKILL.md +11 -0
- package/plugins/lisa-agy/skills/lisa-jira-write-ticket/SKILL.md +11 -0
- package/plugins/lisa-agy/skills/lisa-linear-write-issue/SKILL.md +11 -0
- package/plugins/lisa-agy/skills/lisa-repair-intake/SKILL.md +30 -2
- package/plugins/lisa-cdk/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-cdk/.codex-plugin/plugin.json +1 -1
- package/plugins/lisa-cdk-agy/plugin.json +1 -1
- package/plugins/lisa-cdk-copilot/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-cdk-cursor/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-copilot/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-copilot/hooks/inject-resolved-config.mjs +26 -7
- package/plugins/lisa-copilot/rules/eager/config-resolution.md +3 -1
- package/plugins/lisa-copilot/rules/reference/config-resolution.md +1 -1
- package/plugins/lisa-copilot/scripts/intake-blocker-reprobe.mjs +120 -3
- package/plugins/lisa-copilot/skills/lisa-github-write-issue/SKILL.md +11 -0
- package/plugins/lisa-copilot/skills/lisa-jira-write-ticket/SKILL.md +11 -0
- package/plugins/lisa-copilot/skills/lisa-linear-write-issue/SKILL.md +11 -0
- package/plugins/lisa-copilot/skills/lisa-repair-intake/SKILL.md +30 -2
- package/plugins/lisa-cursor/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-cursor/hooks/inject-resolved-config.mjs +26 -7
- package/plugins/lisa-cursor/rules/config-resolution-reference.mdc +1 -1
- package/plugins/lisa-cursor/rules/config-resolution.mdc +3 -1
- package/plugins/lisa-cursor/scripts/intake-blocker-reprobe.mjs +120 -3
- package/plugins/lisa-cursor/skills/lisa-github-write-issue/SKILL.md +11 -0
- package/plugins/lisa-cursor/skills/lisa-jira-write-ticket/SKILL.md +11 -0
- package/plugins/lisa-cursor/skills/lisa-linear-write-issue/SKILL.md +11 -0
- package/plugins/lisa-cursor/skills/lisa-repair-intake/SKILL.md +30 -2
- package/plugins/lisa-expo/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-expo/.codex-plugin/plugin.json +1 -1
- package/plugins/lisa-expo-agy/plugin.json +1 -1
- package/plugins/lisa-expo-copilot/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-expo-cursor/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-harper-fabric/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-harper-fabric/.codex-plugin/plugin.json +1 -1
- package/plugins/lisa-harper-fabric-agy/plugin.json +1 -1
- package/plugins/lisa-harper-fabric-copilot/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-harper-fabric-cursor/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-nestjs/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-nestjs/.codex-plugin/plugin.json +1 -1
- package/plugins/lisa-nestjs-agy/plugin.json +1 -1
- package/plugins/lisa-nestjs-copilot/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-nestjs-cursor/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-openclaw/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-openclaw/.codex-plugin/plugin.json +1 -1
- package/plugins/lisa-openclaw-agy/plugin.json +1 -1
- package/plugins/lisa-openclaw-copilot/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-openclaw-cursor/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-phaser/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-phaser/.codex-plugin/plugin.json +1 -1
- package/plugins/lisa-phaser-agy/plugin.json +1 -1
- package/plugins/lisa-phaser-copilot/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-phaser-cursor/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-rails/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-rails/.codex-plugin/plugin.json +1 -1
- package/plugins/lisa-rails-agy/plugin.json +1 -1
- package/plugins/lisa-rails-copilot/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-rails-cursor/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-typescript/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-typescript/.codex-plugin/plugin.json +1 -1
- package/plugins/lisa-typescript-agy/plugin.json +1 -1
- package/plugins/lisa-typescript-copilot/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-typescript-cursor/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-wiki/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-wiki/.codex-plugin/plugin.json +1 -1
- package/plugins/lisa-wiki-agy/plugin.json +1 -1
- package/plugins/lisa-wiki-copilot/.claude-plugin/plugin.json +1 -1
- package/plugins/lisa-wiki-cursor/.claude-plugin/plugin.json +1 -1
- package/plugins/src/base/hooks/inject-resolved-config.mjs +26 -7
- package/plugins/src/base/rules/eager/config-resolution.md +3 -1
- package/plugins/src/base/rules/reference/config-resolution.md +1 -1
- package/plugins/src/base/scripts/intake-blocker-reprobe.mjs +120 -3
- package/plugins/src/base/skills/lisa-github-write-issue/SKILL.md +11 -0
- package/plugins/src/base/skills/lisa-jira-write-ticket/SKILL.md +11 -0
- package/plugins/src/base/skills/lisa-linear-write-issue/SKILL.md +11 -0
- package/plugins/src/base/skills/lisa-repair-intake/SKILL.md +30 -2
- package/scripts/check-third-party-action-pins.mjs +6 -2
- package/scripts/measure-tmpdir-growth.mjs +925 -0
- package/typescript/copy-overwrite/scripts/check-skipped-required-checks.mjs +5 -3
package/package.json
CHANGED
|
@@ -83,6 +83,7 @@
|
|
|
83
83
|
"verify:packed-learnings-contract": "bun run build:dist && node scripts/verify-packed-learnings-contract.mjs",
|
|
84
84
|
"verify:health-agentic": "bun run build:dist && node scripts/verify-health-agentic-built.mjs",
|
|
85
85
|
"verify:health-consumer": "bun run build:dist && node scripts/verify-health-consumer-built.mjs",
|
|
86
|
+
"measure:tmpdir-growth": "node scripts/measure-tmpdir-growth.mjs",
|
|
86
87
|
"lint:staged": "lint-staged --config .lintstagedrc.json"
|
|
87
88
|
},
|
|
88
89
|
"engines": {
|
|
@@ -167,7 +168,7 @@
|
|
|
167
168
|
"zod-validation-error": "^4.0.0"
|
|
168
169
|
},
|
|
169
170
|
"name": "@codyswann/lisa",
|
|
170
|
-
"version": "4.37.
|
|
171
|
+
"version": "4.37.3",
|
|
171
172
|
"description": "Claude Code governance framework that applies guardrails, guidance, and automated enforcement to projects",
|
|
172
173
|
"main": "dist/index.js",
|
|
173
174
|
"exports": {
|
|
@@ -315,7 +316,7 @@
|
|
|
315
316
|
"test": "tests"
|
|
316
317
|
},
|
|
317
318
|
"types": "./dist/index.d.ts",
|
|
318
|
-
"lisaReleaseCommit": "
|
|
319
|
-
"gitHead": "
|
|
320
|
-
"lisaReleaseTag": "v4.37.
|
|
319
|
+
"lisaReleaseCommit": "3f7bdc84a24fe7f5b24973ced10b7dc57bfdd329",
|
|
320
|
+
"gitHead": "3f7bdc84a24fe7f5b24973ced10b7dc57bfdd329",
|
|
321
|
+
"lisaReleaseTag": "v4.37.3"
|
|
321
322
|
}
|
|
@@ -276,6 +276,17 @@ Held for a human product call: <reason>.
|
|
|
276
276
|
<!-- [lisa-human-gate] reason=<short-slug> -->
|
|
277
277
|
```
|
|
278
278
|
|
|
279
|
+
**Stamp both surfaces, not just the marker.** Also apply the configured `human_needed` marker
|
|
280
|
+
label (`github.labels.build.human_needed`, default `human-needed`) to the issue, via `gh issue edit`/`gh issue create --label`. The marker in the body and the label say the same thing,
|
|
281
|
+
and a filing that carries only one of them is a **half-armed gate**: sweeps that read the body
|
|
282
|
+
honour it, and sweeps that read labels do not. That is not hypothetical — the repair sweep that
|
|
283
|
+
normalizes items carrying no lifecycle label keys on the *absence* of `human_needed`, so a
|
|
284
|
+
marker-only hold was its population by construction and got promoted into the build queue (#3805).
|
|
285
|
+
The marker remains the authoritative declaration; the label is what makes the hold visible to a
|
|
286
|
+
person scanning a board and to any path that has not yet been routed through the shared reader.
|
|
287
|
+
If the label does not exist in the tracker, create it, or record that it could not be applied and
|
|
288
|
+
proceed — the marker still holds. Never file the label *instead of* the marker.
|
|
289
|
+
|
|
279
290
|
If a leaf arrives with `build_ready` omitted or `false` **and** no `human_gate`, do not create it: report the incomplete handoff and name both ways to resolve it (`build_ready: true`, or a `human_gate` reason). Containers are exempt — their state rolls up from children, so they need neither.
|
|
280
291
|
|
|
281
292
|
## Phase 5.5 — Validate (Pre-write Gate)
|
|
@@ -261,6 +261,17 @@ Held for a human product call: <reason>.
|
|
|
261
261
|
<!-- [lisa-human-gate] reason=<short-slug> -->
|
|
262
262
|
```
|
|
263
263
|
|
|
264
|
+
**Stamp both surfaces, not just the marker.** Also apply the configured `human_needed` marker
|
|
265
|
+
label (`jira.labels.human_needed`, default `Human Needed`) to the ticket, via the ticket's `labels` field. The marker in the body and the label say the same thing,
|
|
266
|
+
and a filing that carries only one of them is a **half-armed gate**: sweeps that read the body
|
|
267
|
+
honour it, and sweeps that read labels do not. That is not hypothetical — the repair sweep that
|
|
268
|
+
normalizes items carrying no lifecycle label keys on the *absence* of `human_needed`, so a
|
|
269
|
+
marker-only hold was its population by construction and got promoted into the build queue (#3805).
|
|
270
|
+
The marker remains the authoritative declaration; the label is what makes the hold visible to a
|
|
271
|
+
person scanning a board and to any path that has not yet been routed through the shared reader.
|
|
272
|
+
If the label does not exist in the tracker, create it, or record that it could not be applied and
|
|
273
|
+
proceed — the marker still holds. Never file the label *instead of* the marker.
|
|
274
|
+
|
|
264
275
|
If a leaf arrives with `build_ready` omitted or `false` **and** no `human_gate`, do not create it: report the incomplete handoff and name both ways to resolve it (`build_ready: true`, or a `human_gate` reason). Containers are exempt — their status rolls up from children, so they need neither.
|
|
265
276
|
|
|
266
277
|
## Phase 5.5 — Validate (Pre-write Gate)
|
|
@@ -280,6 +280,17 @@ Held for a human product call: <reason>.
|
|
|
280
280
|
<!-- [lisa-human-gate] reason=<short-slug> -->
|
|
281
281
|
```
|
|
282
282
|
|
|
283
|
+
**Stamp both surfaces, not just the marker.** Also apply the configured `human_needed` marker
|
|
284
|
+
label (`linear.labels.build.human_needed`, default `human-needed`) to the Issue, via the Issue's labels (create it via `create_issue_label` if absent). The marker in the body and the label say the same thing,
|
|
285
|
+
and a filing that carries only one of them is a **half-armed gate**: sweeps that read the body
|
|
286
|
+
honour it, and sweeps that read labels do not. That is not hypothetical — the repair sweep that
|
|
287
|
+
normalizes items carrying no lifecycle label keys on the *absence* of `human_needed`, so a
|
|
288
|
+
marker-only hold was its population by construction and got promoted into the build queue (#3805).
|
|
289
|
+
The marker remains the authoritative declaration; the label is what makes the hold visible to a
|
|
290
|
+
person scanning a board and to any path that has not yet been routed through the shared reader.
|
|
291
|
+
If the label does not exist in the tracker, create it, or record that it could not be applied and
|
|
292
|
+
proceed — the marker still holds. Never file the label *instead of* the marker.
|
|
293
|
+
|
|
283
294
|
If a leaf arrives with `build_ready` omitted or `false` **and** no `human_gate`, do not create it: report the incomplete handoff and name both ways to resolve it (`build_ready: true`, or a `human_gate` reason). Containers are exempt — their state rolls up from children, so they need neither.
|
|
284
295
|
|
|
285
296
|
## Phase 5.5 — Validate (Pre-write Gate)
|
|
@@ -951,6 +951,23 @@ with labels like `build-ready`, or with no Lisa status label at all, that are in
|
|
|
951
951
|
selected by `intake_mode`. If `intake_mode=prd`, only PRD-classified issues are normalized. If
|
|
952
952
|
`intake_mode=build`, every non-PRD issue is normalized as a build ticket. If `intake_mode=both`,
|
|
953
953
|
classify PRDs first and normalize all remaining issues as build tickets.
|
|
954
|
+
2a. **Ask whether a person is holding it, before anything else.** Call
|
|
955
|
+
`planLabelNormalization({ labels, body, humanNeededLabel, lifecycleLabels, readyLabel })` from
|
|
956
|
+
`scripts/intake-blocker-reprobe.mjs` for every candidate and apply exactly the verdict it
|
|
957
|
+
returns. Do **not** re-implement the test here and do **not** decide held-ness from labels
|
|
958
|
+
alone: the vendor writers stamp the `[lisa-human-gate]` marker into the body of a deliberate
|
|
959
|
+
hold, and `human_needed` is one of the lifecycle labels this sweep keys on the **absence** of —
|
|
960
|
+
so an item held exactly as the filing contract instructs is a member of this swept population by
|
|
961
|
+
construction, and a label-only read promoted it into the build queue (#3805). The
|
|
962
|
+
`[lisa-human-gate]` exclusion already existed in the read-only "Ungated non-ready filing" sweep
|
|
963
|
+
below; the one sweep that writes was the one that could not see it.
|
|
964
|
+
|
|
965
|
+
On `normalize: false` with reason `human-gate`, **stop for that item**: apply no label, do not
|
|
966
|
+
classify it, and report it read-only per step 5. Writing a label here — even the human-needed
|
|
967
|
+
marker — would turn a match into durable state on a second path, and the gate test is a plain
|
|
968
|
+
substring match whose precision is a separate open defect (#3815). Refusing and reporting is
|
|
969
|
+
the safe failure direction without the latch. Count these under `held_for_person`, never under
|
|
970
|
+
`normalized_ready`.
|
|
954
971
|
3. Classify the issue:
|
|
955
972
|
- **PRD** if it has PRD labels/markers (`prd`, `type:PRD`, `kind:prd`), PRD structure
|
|
956
973
|
(`## Problem`, `## Goals`, `## Validation Journey`, generated-work/backlink sections), or
|
|
@@ -964,7 +981,8 @@ with labels like `build-ready`, or with no Lisa status label at all, that are in
|
|
|
964
981
|
- **Ambiguous PRD/build** if strong PRD and build classifications both match. In `intake_mode=prd`
|
|
965
982
|
normalize as PRD; in `intake_mode=build` normalize as build; in `intake_mode=both`, prefer PRD
|
|
966
983
|
only when the body has PRD structure, otherwise build.
|
|
967
|
-
4. Apply exactly one configured ready label for the classified lifecycle
|
|
984
|
+
4. Apply exactly one configured ready label for the classified lifecycle — and only when step
|
|
985
|
+
2a returned `normalize: true`; its `actions.addReadyLabel` is the label to apply, verbatim:
|
|
968
986
|
- PRD → add the configured PRD `ready` label (default `prd-ready`).
|
|
969
987
|
- Build ticket → add the configured build `ready` label (default `status:ready`).
|
|
970
988
|
Keep any unofficial labels for auditability unless the project has explicitly configured one as a
|
|
@@ -972,7 +990,11 @@ with labels like `build-ready`, or with no Lisa status label at all, that are in
|
|
|
972
990
|
normalization makes the next normal `lisa-intake` run pick it up.
|
|
973
991
|
5. Post one idempotent `[lisa-repair-intake]` note naming the classification and the configured label
|
|
974
992
|
applied. Include the normalization result in the loop-prevention fingerprint so repeated repair
|
|
975
|
-
cycles do not spam comments.
|
|
993
|
+
cycles do not spam comments. For an item step 2a held, post `formatNormalizationHoldNote()`
|
|
994
|
+
instead — it says that nothing was changed and how a person resumes the item, which is the
|
|
995
|
+
opposite of what the reconciliation note says and must not be substituted for it. A promotion
|
|
996
|
+
declined silently is invisible, which is the quieter version of the failure this step exists to
|
|
997
|
+
prevent, so name every held item in the cycle summary via `summarizeHumanGateHolds([...])`.
|
|
976
998
|
|
|
977
999
|
### Ungated non-ready filing → surface as an incomplete handoff (read-only)
|
|
978
1000
|
|
|
@@ -1223,6 +1245,8 @@ It MAY:
|
|
|
1223
1245
|
Epic/Story container** from its hierarchy/body-parentage children — so rollup and the GitHub UI can
|
|
1224
1246
|
rely on the native graph. This repairs structure only; it does not ship, transition, or verify the
|
|
1225
1247
|
parent.
|
|
1248
|
+
- Leave a normalization candidate untouched and report it when it is held for a person — the
|
|
1249
|
+
human gate is consulted before classification and its refusal is absolute.
|
|
1226
1250
|
- Normalize a GitHub issue with no configured lifecycle label by adding the configured PRD or build
|
|
1227
1251
|
`ready` label after classifying the issue. This is a visibility repair, not a claim; the item
|
|
1228
1252
|
remains open and unclaimed for normal intake.
|
|
@@ -1305,6 +1329,10 @@ Report outcomes in these buckets:
|
|
|
1305
1329
|
from hierarchy/body-parentage) whose missing native sub-issue links were attached.
|
|
1306
1330
|
- `normalized_ready` — GitHub issues missing official lifecycle labels that were classified and
|
|
1307
1331
|
given the configured PRD/build `ready` label so normal intake can claim them.
|
|
1332
|
+
- `held_for_person` — normalization candidates left exactly as they were because a person is
|
|
1333
|
+
holding them, per the human gate in step 2a of that repair. Nothing was written to them. This
|
|
1334
|
+
bucket is never merged into `normalized_ready` or `errors`: "a person parked this and I honoured
|
|
1335
|
+
it" is a repair outcome, not a failure and not a promotion.
|
|
1308
1336
|
- `still_blocked` — examined and intentionally left `blocked`, with the active reason.
|
|
1309
1337
|
- `reversal_suppressed` — a repair this skill previously made was reversed by a human, so the
|
|
1310
1338
|
classification was **not** re-applied. Name the **reversed transition** (role, direction, and
|
|
@@ -51,7 +51,7 @@
|
|
|
51
51
|
* @module inject-resolved-config
|
|
52
52
|
*/
|
|
53
53
|
import { existsSync, readFileSync, realpathSync } from "node:fs";
|
|
54
|
-
import { join } from "node:path";
|
|
54
|
+
import { basename, join } from "node:path";
|
|
55
55
|
import { fileURLToPath } from "node:url";
|
|
56
56
|
|
|
57
57
|
/** Committed, project-wide configuration. */
|
|
@@ -799,13 +799,32 @@ export function buildContext(projectDir) {
|
|
|
799
799
|
? `${MAIN_CONFIG} + ${LOCAL_CONFIG} (local wins where they overlap)`
|
|
800
800
|
: `${MAIN_CONFIG} (no local override file)`;
|
|
801
801
|
|
|
802
|
+
// The block used to say "this project's" — a possessive with no referent
|
|
803
|
+
// anywhere in its text, so two repositories emitted blocks that were
|
|
804
|
+
// character-identical except for the values. An agent standing in one
|
|
805
|
+
// directory while doing work governed by another read something perfectly
|
|
806
|
+
// true about the directory and wrong about the work, and the next sentence
|
|
807
|
+
// told it not to open the files that would have shown the difference. Six
|
|
808
|
+
// independent agent cycles reached the same false conclusion from one such
|
|
809
|
+
// block (CodySwannGT/lisa#3765).
|
|
810
|
+
//
|
|
811
|
+
// `basename` rather than the git remote: naming the subject must not cost a
|
|
812
|
+
// subprocess on a hook that runs at every session and subagent start, and it
|
|
813
|
+
// must not fail in a directory that is not a git checkout. The absolute path
|
|
814
|
+
// beside it is the unambiguous identifier; the basename is the short name a
|
|
815
|
+
// reader actually compares against the work in front of them.
|
|
816
|
+
const subject = basename(projectDir) || projectDir;
|
|
817
|
+
|
|
802
818
|
return block(
|
|
803
|
-
`These are
|
|
804
|
-
`
|
|
805
|
-
`
|
|
806
|
-
`
|
|
807
|
-
`
|
|
808
|
-
`
|
|
819
|
+
`These are the EFFECTIVE Lisa configuration values for ${subject}, resolved from ${sources} ` +
|
|
820
|
+
`at ${projectDir}.\n` +
|
|
821
|
+
`Act on them directly and do not act against them. They describe THAT directory: if your ` +
|
|
822
|
+
`work targets a different repository, read that repository's config rather than these. For ` +
|
|
823
|
+
`work in ${subject}, do not re-read the config files to learn these values. A line marked ` +
|
|
824
|
+
`[Lisa built-in default] is NOT something ${subject} declared. A key whose NAME is identity- ` +
|
|
825
|
+
`or credential-shaped is withheld and counted, and a VALUE matching a known credential shape ` +
|
|
826
|
+
`is replaced with ${REDACTED}: a best-effort filter, not proof that anything it left alone ` +
|
|
827
|
+
`is safe to repeat.\n\n` +
|
|
809
828
|
renderBody(resolved)
|
|
810
829
|
);
|
|
811
830
|
}
|
|
@@ -1,6 +1,8 @@
|
|
|
1
1
|
# Config Resolution (load-bearing)
|
|
2
2
|
|
|
3
|
-
**The resolved configuration is already in your context.** `inject-resolved-config.sh` runs at every session and subagent start and injects the EFFECTIVE values — `.lisa.config.local.json` already merged over `.lisa.config.json` — inside a `<lisa-resolved-config>` block,
|
|
3
|
+
**The resolved configuration is already in your context.** `inject-resolved-config.sh` runs at every session and subagent start and injects the EFFECTIVE values — `.lisa.config.local.json` already merged over `.lisa.config.json` — inside a `<lisa-resolved-config>` block, which **names the directory it resolved for** and marks anything that is a Lisa built-in rather than something that directory declared. Read the values there and act on them, and do not act against them.
|
|
4
|
+
|
|
5
|
+
They are resolved for **that working directory only**. For work in it, do not re-derive them from the files — that is the saving this block exists for. If your work targets a **different** repository, the block does not describe it: read that repository's config instead. A block with no name on it is how six agent cycles acted on one repository's settings while doing another's work.
|
|
4
6
|
|
|
5
7
|
That block replaces the paragraph that used to sit here saying where configuration lives and which file wins. Restating it is what nine eager rules were already doing while agents acted against a config they never opened; if the block is ever missing, the two files are the source and the local one wins where they overlap.
|
|
6
8
|
|
|
@@ -505,7 +505,7 @@ Resolution keys:
|
|
|
505
505
|
- Linear: `linear.labels.build.human_needed` (default `human-needed`). Applied as a Linear **label**, for the same reason as JIRA — an Issue holds exactly one workflow state but any number of labels, so an additive marker cannot be a state. The `blocked` **state** still drives the lifecycle; `human_needed` is the marker on top of it. This is the only build-lane key left in `linear.labels`.
|
|
506
506
|
- `spec_defect` resolves the same way on each vendor — `jira.labels.spec_defect` (default `Spec Defect`), `github.labels.build.spec_defect` and `linear.labels.build.spec_defect` (default `blocked:spec-defect`).
|
|
507
507
|
|
|
508
|
-
**When to apply it.**
|
|
508
|
+
**When to apply it.** There are two application sites. The first is **at filing**: a leaf filed with a `human_gate` reason under `ready-role-filing` carries the `[lisa-human-gate]` body marker *and* this label, so the hold is legible to a path that reads bodies and to a path that reads labels alike. Such an item sits in no lifecycle role at all rather than in `blocked`, which is the one case where this marker stands beside no role — and it is deliberate: a hold recorded on only one surface is a half-armed gate, and the label-keyed sweeps promoted exactly that population into the build queue (#3805). The second site is a **block a human must clear**: apply `human_needed` only when a human must act before the item can move — the pre-flight gate failures that bounce a ticket back to its reporter are exactly this case, but **only after** the agent has run the `pre-flight-autofill` draft-then-block procedure (drafting the authorable gaps — acceptance criteria, validation journey, repository, relationship search, etc. — into the ticket as labeled assumptions). What then remains for the human is to **confirm those assumptions** or supply a genuinely human-only input (real missing credentials, an irreducible product/scoping decision). The marker means "a human must confirm or decide," not "a human must author from scratch."
|
|
509
509
|
|
|
510
510
|
**Why `spec_defect` is separate from `human_needed`.** Both name a hold a person must clear, but they are different asks and the rollup must not merge them. `human_needed` waits on an input from *outside* the item — a credential, an access grant, a product decision — and the item's own text is fine. `spec_defect` waits on the item's text being *rewritten*, and no external event will ever supply that. An item carrying `spec_defect` will sit forever until somebody edits it; that is exactly the class that accumulated silently when the rollup rendered both as plain `blocked` (issue #3045: 32 identical hold comments over six weeks on one Epic). Where both markers are present, `spec_defect` wins — it is the more specific record, and the only one carrying a judgment nothing else can supply.
|
|
511
511
|
|
|
@@ -38,10 +38,20 @@ function normalizeLabels(labels) {
|
|
|
38
38
|
}
|
|
39
39
|
|
|
40
40
|
/**
|
|
41
|
-
*
|
|
42
|
-
*
|
|
41
|
+
* Whether an item is held for a person, on either surface.
|
|
42
|
+
*
|
|
43
|
+
* Exported deliberately, and it is the ONLY answer to that question anywhere in
|
|
44
|
+
* the intake machinery. Every selection and promotion path calls this rather
|
|
45
|
+
* than inspecting labels itself, because the label surface alone is a partial
|
|
46
|
+
* answer: the vendor writers stamp the body marker on a deliberate hold, so an
|
|
47
|
+
* item held exactly as the filing contract instructs carries no label at all.
|
|
48
|
+
* A path that read labels alone judged such an item unheld and promoted it —
|
|
49
|
+
* which is #3805, and is why this is a shared function rather than a shared
|
|
50
|
+
* convention.
|
|
51
|
+
* @param {{ labels?: unknown, body?: unknown, humanNeededLabel?: unknown }} input - Candidate surfaces
|
|
52
|
+
* @returns {boolean} True when a person is holding this item
|
|
43
53
|
*/
|
|
44
|
-
function isHumanGated(input) {
|
|
54
|
+
export function isHumanGated(input) {
|
|
45
55
|
const configured = String(
|
|
46
56
|
input.humanNeededLabel ?? DEFAULT_HUMAN_NEEDED_LABEL
|
|
47
57
|
)
|
|
@@ -282,6 +292,113 @@ export function planHumanGateReconciliation(input = {}) {
|
|
|
282
292
|
};
|
|
283
293
|
}
|
|
284
294
|
|
|
295
|
+
/**
|
|
296
|
+
* Marker on the note the normalization sweep leaves, so a later cycle
|
|
297
|
+
* recognises its own work instead of commenting again.
|
|
298
|
+
*
|
|
299
|
+
* Deliberately NOT the hold marker and deliberately not a superstring of it:
|
|
300
|
+
* `HUMAN_GATE_MARKER` closes with `]`, so neither this nor
|
|
301
|
+
* `HUMAN_GATE_NOTE_MARKER` matches it. A note that read as a hold declaration
|
|
302
|
+
* would make every reported item look held to the next body-reading sweep,
|
|
303
|
+
* including items the report merely names.
|
|
304
|
+
*/
|
|
305
|
+
export const NORMALIZATION_HOLD_NOTE_MARKER =
|
|
306
|
+
"<!-- [lisa-human-gate-normalization-held] -->";
|
|
307
|
+
|
|
308
|
+
/**
|
|
309
|
+
* Decide whether an item carrying NO configured lifecycle label may be
|
|
310
|
+
* normalized into a ready lane.
|
|
311
|
+
*
|
|
312
|
+
* This is the promotion path, and it was keyed on labels alone. The configured
|
|
313
|
+
* `human_needed` label is one of the lifecycle labels whose *absence* the sweep
|
|
314
|
+
* enumerates on, so an item held only by the body marker was a member of the
|
|
315
|
+
* swept population by definition and got the build-ready label applied to it.
|
|
316
|
+
* The `[lisa-human-gate]` exclusion existed, in a different and read-only sweep
|
|
317
|
+
* further down the same contract: the one sweep that writes was the one that
|
|
318
|
+
* could not see the marker.
|
|
319
|
+
*
|
|
320
|
+
* Order is load-bearing for the same reason it is in `classifyPreWorkCandidate`:
|
|
321
|
+
* the hold is checked before lane membership and before any classification, so
|
|
322
|
+
* nothing downstream — however confident — can promote an item a person parked.
|
|
323
|
+
*
|
|
324
|
+
* On a match this plans NO write of its own. `planHumanGateReconciliation`
|
|
325
|
+
* turns a match into durable state, so a false positive there latches and every
|
|
326
|
+
* later cycle agrees with the first. The gate test is a plain substring match
|
|
327
|
+
* whose imprecision is tracked separately, so this path refuses and reports
|
|
328
|
+
* read-only instead — the same treatment the ungated-filing sweep already gives
|
|
329
|
+
* a hold it finds.
|
|
330
|
+
* @param {{
|
|
331
|
+
* labels?: unknown
|
|
332
|
+
* body?: unknown
|
|
333
|
+
* humanNeededLabel?: unknown
|
|
334
|
+
* lifecycleLabels?: unknown
|
|
335
|
+
* readyLabel?: unknown
|
|
336
|
+
* }} input - Candidate surfaces plus the configured lifecycle vocabulary
|
|
337
|
+
* @returns {{ normalize: boolean, reason: string, humanGated: boolean, actions: { addReadyLabel: string | null, reportHold: boolean } }} Normalization plan
|
|
338
|
+
*/
|
|
339
|
+
export function planLabelNormalization(input = {}) {
|
|
340
|
+
const idle = Object.freeze({ addReadyLabel: null, reportHold: false });
|
|
341
|
+
if (isHumanGated(input)) {
|
|
342
|
+
return {
|
|
343
|
+
normalize: false,
|
|
344
|
+
reason: "human-gate",
|
|
345
|
+
humanGated: true,
|
|
346
|
+
actions: Object.freeze({ addReadyLabel: null, reportHold: true }),
|
|
347
|
+
};
|
|
348
|
+
}
|
|
349
|
+
|
|
350
|
+
const labels = normalizeLabels(input.labels);
|
|
351
|
+
if (normalizeLabels(input.lifecycleLabels).some(l => labels.includes(l))) {
|
|
352
|
+
return {
|
|
353
|
+
normalize: false,
|
|
354
|
+
reason: "already-in-lifecycle",
|
|
355
|
+
humanGated: false,
|
|
356
|
+
actions: idle,
|
|
357
|
+
};
|
|
358
|
+
}
|
|
359
|
+
|
|
360
|
+
const ready = trimmedString(input.readyLabel);
|
|
361
|
+
if (ready.length === 0) {
|
|
362
|
+
return {
|
|
363
|
+
normalize: false,
|
|
364
|
+
reason: "no-ready-label",
|
|
365
|
+
humanGated: false,
|
|
366
|
+
actions: idle,
|
|
367
|
+
};
|
|
368
|
+
}
|
|
369
|
+
|
|
370
|
+
return {
|
|
371
|
+
normalize: true,
|
|
372
|
+
reason: "normalize",
|
|
373
|
+
humanGated: false,
|
|
374
|
+
actions: Object.freeze({ addReadyLabel: ready, reportHold: false }),
|
|
375
|
+
};
|
|
376
|
+
}
|
|
377
|
+
|
|
378
|
+
/**
|
|
379
|
+
* Render the notice for an item the normalization sweep left alone.
|
|
380
|
+
*
|
|
381
|
+
* Distinct from `formatHumanGateNote` because the two say opposite things
|
|
382
|
+
* about what happened: that one reports a lane that WAS changed, this one
|
|
383
|
+
* reports a promotion that was declined and nothing else. Reusing it would tell
|
|
384
|
+
* an operator their item had been moved when it had not.
|
|
385
|
+
* @returns {string} Comment body, carrying the marker that keeps a re-run quiet
|
|
386
|
+
*/
|
|
387
|
+
export function formatNormalizationHoldNote() {
|
|
388
|
+
return [
|
|
389
|
+
"**Left alone: a person is holding this**",
|
|
390
|
+
"",
|
|
391
|
+
"- What was found: the description says a person is holding this one, so " +
|
|
392
|
+
"it was not put into the queue that agents work from.",
|
|
393
|
+
"- What changed: nothing at all. It was left exactly as it is, and " +
|
|
394
|
+
"nothing will pick it up on its own.",
|
|
395
|
+
"- To resume it: remove the hold note from the description, then put it " +
|
|
396
|
+
"into the build queue.",
|
|
397
|
+
"",
|
|
398
|
+
NORMALIZATION_HOLD_NOTE_MARKER,
|
|
399
|
+
].join("\n");
|
|
400
|
+
}
|
|
401
|
+
|
|
285
402
|
/**
|
|
286
403
|
* Render the hold notice for a reader who does not know this subsystem.
|
|
287
404
|
*
|
|
@@ -276,6 +276,17 @@ Held for a human product call: <reason>.
|
|
|
276
276
|
<!-- [lisa-human-gate] reason=<short-slug> -->
|
|
277
277
|
```
|
|
278
278
|
|
|
279
|
+
**Stamp both surfaces, not just the marker.** Also apply the configured `human_needed` marker
|
|
280
|
+
label (`github.labels.build.human_needed`, default `human-needed`) to the issue, via `gh issue edit`/`gh issue create --label`. The marker in the body and the label say the same thing,
|
|
281
|
+
and a filing that carries only one of them is a **half-armed gate**: sweeps that read the body
|
|
282
|
+
honour it, and sweeps that read labels do not. That is not hypothetical — the repair sweep that
|
|
283
|
+
normalizes items carrying no lifecycle label keys on the *absence* of `human_needed`, so a
|
|
284
|
+
marker-only hold was its population by construction and got promoted into the build queue (#3805).
|
|
285
|
+
The marker remains the authoritative declaration; the label is what makes the hold visible to a
|
|
286
|
+
person scanning a board and to any path that has not yet been routed through the shared reader.
|
|
287
|
+
If the label does not exist in the tracker, create it, or record that it could not be applied and
|
|
288
|
+
proceed — the marker still holds. Never file the label *instead of* the marker.
|
|
289
|
+
|
|
279
290
|
If a leaf arrives with `build_ready` omitted or `false` **and** no `human_gate`, do not create it: report the incomplete handoff and name both ways to resolve it (`build_ready: true`, or a `human_gate` reason). Containers are exempt — their state rolls up from children, so they need neither.
|
|
280
291
|
|
|
281
292
|
## Phase 5.5 — Validate (Pre-write Gate)
|
|
@@ -261,6 +261,17 @@ Held for a human product call: <reason>.
|
|
|
261
261
|
<!-- [lisa-human-gate] reason=<short-slug> -->
|
|
262
262
|
```
|
|
263
263
|
|
|
264
|
+
**Stamp both surfaces, not just the marker.** Also apply the configured `human_needed` marker
|
|
265
|
+
label (`jira.labels.human_needed`, default `Human Needed`) to the ticket, via the ticket's `labels` field. The marker in the body and the label say the same thing,
|
|
266
|
+
and a filing that carries only one of them is a **half-armed gate**: sweeps that read the body
|
|
267
|
+
honour it, and sweeps that read labels do not. That is not hypothetical — the repair sweep that
|
|
268
|
+
normalizes items carrying no lifecycle label keys on the *absence* of `human_needed`, so a
|
|
269
|
+
marker-only hold was its population by construction and got promoted into the build queue (#3805).
|
|
270
|
+
The marker remains the authoritative declaration; the label is what makes the hold visible to a
|
|
271
|
+
person scanning a board and to any path that has not yet been routed through the shared reader.
|
|
272
|
+
If the label does not exist in the tracker, create it, or record that it could not be applied and
|
|
273
|
+
proceed — the marker still holds. Never file the label *instead of* the marker.
|
|
274
|
+
|
|
264
275
|
If a leaf arrives with `build_ready` omitted or `false` **and** no `human_gate`, do not create it: report the incomplete handoff and name both ways to resolve it (`build_ready: true`, or a `human_gate` reason). Containers are exempt — their status rolls up from children, so they need neither.
|
|
265
276
|
|
|
266
277
|
## Phase 5.5 — Validate (Pre-write Gate)
|
|
@@ -280,6 +280,17 @@ Held for a human product call: <reason>.
|
|
|
280
280
|
<!-- [lisa-human-gate] reason=<short-slug> -->
|
|
281
281
|
```
|
|
282
282
|
|
|
283
|
+
**Stamp both surfaces, not just the marker.** Also apply the configured `human_needed` marker
|
|
284
|
+
label (`linear.labels.build.human_needed`, default `human-needed`) to the Issue, via the Issue's labels (create it via `create_issue_label` if absent). The marker in the body and the label say the same thing,
|
|
285
|
+
and a filing that carries only one of them is a **half-armed gate**: sweeps that read the body
|
|
286
|
+
honour it, and sweeps that read labels do not. That is not hypothetical — the repair sweep that
|
|
287
|
+
normalizes items carrying no lifecycle label keys on the *absence* of `human_needed`, so a
|
|
288
|
+
marker-only hold was its population by construction and got promoted into the build queue (#3805).
|
|
289
|
+
The marker remains the authoritative declaration; the label is what makes the hold visible to a
|
|
290
|
+
person scanning a board and to any path that has not yet been routed through the shared reader.
|
|
291
|
+
If the label does not exist in the tracker, create it, or record that it could not be applied and
|
|
292
|
+
proceed — the marker still holds. Never file the label *instead of* the marker.
|
|
293
|
+
|
|
283
294
|
If a leaf arrives with `build_ready` omitted or `false` **and** no `human_gate`, do not create it: report the incomplete handoff and name both ways to resolve it (`build_ready: true`, or a `human_gate` reason). Containers are exempt — their state rolls up from children, so they need neither.
|
|
284
295
|
|
|
285
296
|
## Phase 5.5 — Validate (Pre-write Gate)
|
|
@@ -951,6 +951,23 @@ with labels like `build-ready`, or with no Lisa status label at all, that are in
|
|
|
951
951
|
selected by `intake_mode`. If `intake_mode=prd`, only PRD-classified issues are normalized. If
|
|
952
952
|
`intake_mode=build`, every non-PRD issue is normalized as a build ticket. If `intake_mode=both`,
|
|
953
953
|
classify PRDs first and normalize all remaining issues as build tickets.
|
|
954
|
+
2a. **Ask whether a person is holding it, before anything else.** Call
|
|
955
|
+
`planLabelNormalization({ labels, body, humanNeededLabel, lifecycleLabels, readyLabel })` from
|
|
956
|
+
`scripts/intake-blocker-reprobe.mjs` for every candidate and apply exactly the verdict it
|
|
957
|
+
returns. Do **not** re-implement the test here and do **not** decide held-ness from labels
|
|
958
|
+
alone: the vendor writers stamp the `[lisa-human-gate]` marker into the body of a deliberate
|
|
959
|
+
hold, and `human_needed` is one of the lifecycle labels this sweep keys on the **absence** of —
|
|
960
|
+
so an item held exactly as the filing contract instructs is a member of this swept population by
|
|
961
|
+
construction, and a label-only read promoted it into the build queue (#3805). The
|
|
962
|
+
`[lisa-human-gate]` exclusion already existed in the read-only "Ungated non-ready filing" sweep
|
|
963
|
+
below; the one sweep that writes was the one that could not see it.
|
|
964
|
+
|
|
965
|
+
On `normalize: false` with reason `human-gate`, **stop for that item**: apply no label, do not
|
|
966
|
+
classify it, and report it read-only per step 5. Writing a label here — even the human-needed
|
|
967
|
+
marker — would turn a match into durable state on a second path, and the gate test is a plain
|
|
968
|
+
substring match whose precision is a separate open defect (#3815). Refusing and reporting is
|
|
969
|
+
the safe failure direction without the latch. Count these under `held_for_person`, never under
|
|
970
|
+
`normalized_ready`.
|
|
954
971
|
3. Classify the issue:
|
|
955
972
|
- **PRD** if it has PRD labels/markers (`prd`, `type:PRD`, `kind:prd`), PRD structure
|
|
956
973
|
(`## Problem`, `## Goals`, `## Validation Journey`, generated-work/backlink sections), or
|
|
@@ -964,7 +981,8 @@ with labels like `build-ready`, or with no Lisa status label at all, that are in
|
|
|
964
981
|
- **Ambiguous PRD/build** if strong PRD and build classifications both match. In `intake_mode=prd`
|
|
965
982
|
normalize as PRD; in `intake_mode=build` normalize as build; in `intake_mode=both`, prefer PRD
|
|
966
983
|
only when the body has PRD structure, otherwise build.
|
|
967
|
-
4. Apply exactly one configured ready label for the classified lifecycle
|
|
984
|
+
4. Apply exactly one configured ready label for the classified lifecycle — and only when step
|
|
985
|
+
2a returned `normalize: true`; its `actions.addReadyLabel` is the label to apply, verbatim:
|
|
968
986
|
- PRD → add the configured PRD `ready` label (default `prd-ready`).
|
|
969
987
|
- Build ticket → add the configured build `ready` label (default `status:ready`).
|
|
970
988
|
Keep any unofficial labels for auditability unless the project has explicitly configured one as a
|
|
@@ -972,7 +990,11 @@ with labels like `build-ready`, or with no Lisa status label at all, that are in
|
|
|
972
990
|
normalization makes the next normal `lisa-intake` run pick it up.
|
|
973
991
|
5. Post one idempotent `[lisa-repair-intake]` note naming the classification and the configured label
|
|
974
992
|
applied. Include the normalization result in the loop-prevention fingerprint so repeated repair
|
|
975
|
-
cycles do not spam comments.
|
|
993
|
+
cycles do not spam comments. For an item step 2a held, post `formatNormalizationHoldNote()`
|
|
994
|
+
instead — it says that nothing was changed and how a person resumes the item, which is the
|
|
995
|
+
opposite of what the reconciliation note says and must not be substituted for it. A promotion
|
|
996
|
+
declined silently is invisible, which is the quieter version of the failure this step exists to
|
|
997
|
+
prevent, so name every held item in the cycle summary via `summarizeHumanGateHolds([...])`.
|
|
976
998
|
|
|
977
999
|
### Ungated non-ready filing → surface as an incomplete handoff (read-only)
|
|
978
1000
|
|
|
@@ -1223,6 +1245,8 @@ It MAY:
|
|
|
1223
1245
|
Epic/Story container** from its hierarchy/body-parentage children — so rollup and the GitHub UI can
|
|
1224
1246
|
rely on the native graph. This repairs structure only; it does not ship, transition, or verify the
|
|
1225
1247
|
parent.
|
|
1248
|
+
- Leave a normalization candidate untouched and report it when it is held for a person — the
|
|
1249
|
+
human gate is consulted before classification and its refusal is absolute.
|
|
1226
1250
|
- Normalize a GitHub issue with no configured lifecycle label by adding the configured PRD or build
|
|
1227
1251
|
`ready` label after classifying the issue. This is a visibility repair, not a claim; the item
|
|
1228
1252
|
remains open and unclaimed for normal intake.
|
|
@@ -1305,6 +1329,10 @@ Report outcomes in these buckets:
|
|
|
1305
1329
|
from hierarchy/body-parentage) whose missing native sub-issue links were attached.
|
|
1306
1330
|
- `normalized_ready` — GitHub issues missing official lifecycle labels that were classified and
|
|
1307
1331
|
given the configured PRD/build `ready` label so normal intake can claim them.
|
|
1332
|
+
- `held_for_person` — normalization candidates left exactly as they were because a person is
|
|
1333
|
+
holding them, per the human gate in step 2a of that repair. Nothing was written to them. This
|
|
1334
|
+
bucket is never merged into `normalized_ready` or `errors`: "a person parked this and I honoured
|
|
1335
|
+
it" is a repair outcome, not a failure and not a promotion.
|
|
1308
1336
|
- `still_blocked` — examined and intentionally left `blocked`, with the active reason.
|
|
1309
1337
|
- `reversal_suppressed` — a repair this skill previously made was reversed by a human, so the
|
|
1310
1338
|
classification was **not** re-applied. Name the **reversed transition** (role, direction, and
|