@xera-ai/skills 0.11.1 → 0.11.3
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/CHANGELOG.md +8 -0
- package/package.json +1 -1
- package/xera-report.md +4 -3
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,13 @@
|
|
|
1
1
|
# @xera-ai/skills
|
|
2
2
|
|
|
3
|
+
## 0.11.3
|
|
4
|
+
|
|
5
|
+
## 0.11.2
|
|
6
|
+
|
|
7
|
+
### Patch Changes
|
|
8
|
+
|
|
9
|
+
- [#70](https://github.com/xera-ai/xera/pull/70) [`7374f86`](https://github.com/xera-ai/xera/commit/7374f869a0436301fb6517c32f984482b5bde501) Thanks [@thanhtrinity](https://github.com/thanhtrinity)! - fix(core,skills): `xera:graph-enrich` now checks the graph snapshot before the input file (so an un-fetched candidate gets the actionable `/xera-fetch <TICKET>` hint), and deletes `enrichment-input.json` after a successful enrich so stray re-invocations can't replay stale LLM output. The `/xera-report` lazy-similarity step now pre-validates the candidate is in the graph and notes that the Write tool auto-creates the candidate directory.
|
|
10
|
+
|
|
3
11
|
## 0.11.1
|
|
4
12
|
|
|
5
13
|
## 0.11.0
|
package/package.json
CHANGED
package/xera-report.md
CHANGED
|
@@ -65,14 +65,15 @@ For every scenario in `classifier-input.json` whose `outcome === "FAIL"`:
|
|
|
65
65
|
|
|
66
66
|
**If lazy similarity is needed** (a candidate ticket exists but has no `similar` edges and is hot for many scenarios):
|
|
67
67
|
|
|
68
|
-
1.
|
|
69
|
-
2.
|
|
68
|
+
1. **Pre-check**: confirm `<CANDIDATE>` is in the graph by running `bun run xera:graph-query --ticket <CANDIDATE> --format json`. If the response lacks a `tickets.<CANDIDATE>` entry, skip lazy similarity for this candidate — `xera:graph-enrich` will refuse a ticket that hasn't been fetched and will give you the actionable error directly.
|
|
69
|
+
2. Read `node_modules/@xera-ai/prompts/similarity-match.md`. Follow its rules to produce a JSON object `{ "similar": [{ "ticketId": "...", "confidence": 0.0–1.0, "reason": "..." }] }`. Use the **Write tool** to create `.xera/<CANDIDATE>/enrichment-input.json` (Write auto-creates parent directories — important because the candidate dir may not exist locally yet).
|
|
70
|
+
3. Then run:
|
|
70
71
|
|
|
71
72
|
```bash
|
|
72
73
|
bun run xera:graph-enrich --ticket <CANDIDATE>
|
|
73
74
|
```
|
|
74
75
|
|
|
75
|
-
This populates `similar` edges so future graph queries are richer. Skip
|
|
76
|
+
This populates `similar` edges so future graph queries are richer. The CLI deletes `enrichment-input.json` after a successful enrich, so stale similarity data can't accidentally re-drive enrich on a later invocation. Skip the entire lazy-similarity sub-flow if not needed.
|
|
76
77
|
|
|
77
78
|
4a. **Heal sub-flow (only if SELECTOR_DRIFT present).** If the user passed `--no-heal` in the invocation, skip this entire sub-flow and proceed directly to step 5.
|
|
78
79
|
|