@skein-code/cli 0.3.16 → 0.3.17
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/README.md +5 -3
- package/dist/cli.js +48 -16
- package/dist/cli.js.map +1 -1
- package/docs/ARCHITECTURE.md +5 -3
- package/docs/NEXT_STEPS.md +11 -9
- package/package.json +5 -1
package/docs/ARCHITECTURE.md
CHANGED
|
@@ -53,7 +53,9 @@
|
|
|
53
53
|
generation. After the write succeeds, compare only newly added or at least
|
|
54
54
|
1.5x-expanded functions before refreshing changed index paths. Exact
|
|
55
55
|
normalized hashes identify Type-1/2 clones; winnowed 10-token shingles and
|
|
56
|
-
Jaccard similarity identify
|
|
56
|
+
Jaccard similarity identify Type-3 candidates. The repository-owned fixture
|
|
57
|
+
matrix calibrates threshold 0.55: unsuppressed Type-1/2 matches block the
|
|
58
|
+
existing completion gate, while Type-3 remains warning-only. Type-4 semantic
|
|
57
59
|
equivalence is explicitly outside this deterministic contract.
|
|
58
60
|
12. Run configured verification commands after changes. The completion gate accepts
|
|
59
61
|
only current successful test, typecheck, lint, build, check, or `git diff
|
|
@@ -99,8 +101,8 @@ build, targeted upsert, and deletion. Audit receipts never retain source,
|
|
|
99
101
|
normalized tokens, literal contents, prompts, or raw retrieval failures.
|
|
100
102
|
|
|
101
103
|
Duplication findings are folded into the existing completion record rather than
|
|
102
|
-
creating a parallel completion state.
|
|
103
|
-
|
|
104
|
+
creating a parallel completion state. Fixture benchmarks establish the required
|
|
105
|
+
precision for calibrated Type-1/2 blocking; Type-3 remains warning-only. Active
|
|
104
106
|
matches receive stable, bounded ids; the optional `duplication_audit` read tool
|
|
105
107
|
is exposed only while unsuppressed findings exist. Suppression is exact-match,
|
|
106
108
|
reason-coded, and persisted as a content-free audit receipt. Repaired/deleted/
|
package/docs/NEXT_STEPS.md
CHANGED
|
@@ -54,7 +54,7 @@ short-height case. The current full-suite count is recorded from the latest
|
|
|
54
54
|
|
|
55
55
|
## Recommended Order
|
|
56
56
|
|
|
57
|
-
### P0-D:
|
|
57
|
+
### P0-D: Repository reuse and calibrated duplication enforcement
|
|
58
58
|
|
|
59
59
|
Version `0.3.14` added the prompt ladder and pre-write `ReuseReceipt`. Version
|
|
60
60
|
`0.3.15` added a post-write deterministic audit for ordinary TS/TSX/JS/JSX/MJS/
|
|
@@ -66,14 +66,16 @@ renames, moves, deletions, small functions, tests, fixtures, generated/vendor/
|
|
|
66
66
|
dist/minified/declaration files, and failed writes stay quiet. Receipts expose
|
|
67
67
|
at most eight path/symbol/similarity matches through session, TUI, JSON, and
|
|
68
68
|
JSONL without storing source, normalized tokens, prompts, or raw index errors.
|
|
69
|
-
Type-
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
duplication summaries into the single completion
|
|
76
|
-
|
|
69
|
+
Type-3 remains warning-only and unavailable evidence is `unresolved`, never a
|
|
70
|
+
false pass. The repository-owned `duplication-benchmark-v1` fixture matrix
|
|
71
|
+
calibrated threshold `0.55` at 100% recall, 100% precision, and 0% legitimate
|
|
72
|
+
boundary false-positive rate. Unsuppressed Type-1/2 matches now block the
|
|
73
|
+
existing completion record; Type-4 semantic equivalence is not promised.
|
|
74
|
+
|
|
75
|
+
Version `0.3.16` integrated duplication summaries into the single completion
|
|
76
|
+
receipt and every output surface while keeping all matches warning-only. Version
|
|
77
|
+
`0.3.17` keeps Type-3 warning-only but promotes calibrated Type-1/2 matches to
|
|
78
|
+
the completion gate. Active matches receive stable 24-character ids. The read-only
|
|
77
79
|
`duplication_audit` tool is disclosed only when unsuppressed matches exist and
|
|
78
80
|
can suppress one exact match with a reason code plus a bounded explanation;
|
|
79
81
|
wildcard/global suppression, credentials, and code-block reasons are rejected.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@skein-code/cli",
|
|
3
|
-
"version": "0.3.
|
|
3
|
+
"version": "0.3.17",
|
|
4
4
|
"description": "A context-first, model-agnostic coding agent with an auditable terminal workspace.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "MIT",
|
|
@@ -16,6 +16,9 @@
|
|
|
16
16
|
},
|
|
17
17
|
"skein": {
|
|
18
18
|
"releaseNotes": [
|
|
19
|
+
"Calibrated Type-1/2 duplication matches now block completion until reuse or exact audited suppression",
|
|
20
|
+
"Type-3 duplication remains warning-only and Type-4 semantic equivalence remains explicitly unsupported",
|
|
21
|
+
"Duplication benchmark fixtures report deterministic recall, precision, false-positive rate, and latency",
|
|
19
22
|
"Duplication warnings now aggregate into the single completion receipt without changing verified status",
|
|
20
23
|
"Exact match ids support bounded, reason-coded suppression with audit and credential/code-block safeguards",
|
|
21
24
|
"Duplication audit tools are disclosed only when active warnings exist and repaired paths clear stale matches",
|
|
@@ -54,6 +57,7 @@
|
|
|
54
57
|
"pretest:pty": "npm run build",
|
|
55
58
|
"test:pty": "sh test/pty/run-visual.sh",
|
|
56
59
|
"benchmark:context": "tsx scripts/benchmark-local-index.ts",
|
|
60
|
+
"benchmark:duplication": "tsx scripts/benchmark-duplication.ts",
|
|
57
61
|
"verify:package": "node scripts/verify-package.mjs",
|
|
58
62
|
"release:verify": "npm run check && npm run verify:package --",
|
|
59
63
|
"typecheck": "tsc --noEmit",
|