clud-bug 0.6.15 → 0.6.16
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/lib/prompts.js
CHANGED
|
@@ -151,6 +151,16 @@ At the end of every review, append a single-line footer:
|
|
|
151
151
|
If you genuinely cited none, list "[none]" and explain why no
|
|
152
152
|
installed skill applied to this diff.
|
|
153
153
|
|
|
154
|
+
Output-token budget (v0.6.16 / 0.0.X):
|
|
155
|
+
Keep total output under ~600 tokens. Per finding:
|
|
156
|
+
- One-sentence claim
|
|
157
|
+
- <details>Reasoning</details> ≤ 80 words
|
|
158
|
+
- No code quotes > 2 lines
|
|
159
|
+
- Omit reasoning details that don't change the verdict
|
|
160
|
+
This isn't a hard cap — the SDK doesn't expose max_tokens — but a
|
|
161
|
+
discipline. Verbose output costs the consuming repo on every review;
|
|
162
|
+
brevity compounds across the org.
|
|
163
|
+
|
|
154
164
|
Incremental-diff handshake (v0.6.10+) — emit the SHA marker:
|
|
155
165
|
At the very end of the summary comment (after the Skills-referenced
|
|
156
166
|
footer, on its own line), append the HTML marker that the next
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "clud-bug",
|
|
3
|
-
"version": "0.6.
|
|
3
|
+
"version": "0.6.16",
|
|
4
4
|
"description": "Skill-driven Claude PR review. Ship a brand-voice skill, get brand reviews. Each finding cites the skill that motivated it. CLI installs the workflow + a baseline kit; add more from skills.sh.",
|
|
5
5
|
"homepage": "https://cludbug.dev",
|
|
6
6
|
"bugs": "https://github.com/thrillmade/clud-bug/issues",
|
|
@@ -156,6 +156,6 @@ jobs:
|
|
|
156
156
|
# Strict-mode gate — composite action; see workflow.yml.tmpl for design notes.
|
|
157
157
|
- name: Strict mode — fail check on critical findings
|
|
158
158
|
if: success()
|
|
159
|
-
uses: thrillmade/clud-bug/.github/actions/strict-mode-gate@v0.6.
|
|
159
|
+
uses: thrillmade/clud-bug/.github/actions/strict-mode-gate@v0.6.16
|
|
160
160
|
with:
|
|
161
161
|
github-token: ${{ secrets.GITHUB_TOKEN }}
|
|
@@ -156,6 +156,6 @@ jobs:
|
|
|
156
156
|
# Strict-mode gate — composite action; see workflow.yml.tmpl for design notes.
|
|
157
157
|
- name: Strict mode — fail check on critical findings
|
|
158
158
|
if: success()
|
|
159
|
-
uses: thrillmade/clud-bug/.github/actions/strict-mode-gate@v0.6.
|
|
159
|
+
uses: thrillmade/clud-bug/.github/actions/strict-mode-gate@v0.6.16
|
|
160
160
|
with:
|
|
161
161
|
github-token: ${{ secrets.GITHUB_TOKEN }}
|
|
@@ -247,6 +247,6 @@ jobs:
|
|
|
247
247
|
# Letting the action's own failure fail the check is louder and right.
|
|
248
248
|
- name: Strict mode — fail check on critical findings
|
|
249
249
|
if: success()
|
|
250
|
-
uses: thrillmade/clud-bug/.github/actions/strict-mode-gate@v0.6.
|
|
250
|
+
uses: thrillmade/clud-bug/.github/actions/strict-mode-gate@v0.6.16
|
|
251
251
|
with:
|
|
252
252
|
github-token: ${{ secrets.GITHUB_TOKEN }}
|