valent-pipeline 0.2.17 → 0.2.18

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.
Files changed (4) hide show
  1. package/package.json +1 -1
  2. package/pipeline/prompts/lead.md +1 -0
  3. package/pipeline/prompts/readiness.md +4 -1
  4. package/pipeline/steps/orchestration/sprint-groom.md +2 -1
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "valent-pipeline",
3
- "version": "0.2.17",
3
+ "version": "0.2.18",
4
4
  "description": "v3 multi-agent AI pipeline for software development lifecycle",
5
5
  "type": "module",
6
6
  "bin": {
package/pipeline/prompts/lead.md CHANGED
@@ -53,6 +53,7 @@ You receive many message types. Process each by type:
53
53
  Your outbound messages follow the same terse format:
54
54
  - `[SPAWN] Spawning {agent} for {story_id}. Role: {role}. Shared context: {story_output_dir}.`
55
55
  - `[CHECK-IN] {agent}: task {task} has been in_progress for {minutes}min. Status?`
56
+ - `[REVIEW-READY] Story {story_id}` — sent to READINESS immediately when a story reaches `readiness-review` during sprint grooming. Do not batch — send as soon as QA-A hands off each story.
56
57
  - `[TEARDOWN] Tearing down all teammates for {story_id}.`
57
58
  - `[ESCALATION] See escalation block below.`
58
59
 
package/pipeline/prompts/readiness.md CHANGED
@@ -12,7 +12,10 @@ Read `.valent-pipeline/steps/common/agent-protocol.md` for Communication Standar
12
12
 
13
13
  You are spawned at story kick-off but do NOT begin work immediately.
14
14
 
15
- - **Wait for:** `[HANDOFF]` from QA-A
15
+ **Standalone mode:** Wait for `[HANDOFF]` from QA-A, then review that story.
16
+
17
+ **Sprint mode (`{is_sprint_mode}` is true):** Lead sends you `[REVIEW-READY] Story {story_id}` each time a story reaches `readiness-review`. Begin reviewing that story immediately. When you finish (approve or reject), return to idle and wait for the next `[REVIEW-READY]` from Lead. You may receive the next signal while still reviewing — queue it and process sequentially.
18
+
16
19
  - **On approval:** Send `[READINESS-APPROVAL]` to BEND (and FEND if active). Send `[DONE]` to Lead. Mark task completed.
17
20
  - **On rejection:** Send `[READINESS-REJECTION]` to the **responsible agent** (REQS, UXA, or QA-A — see Rejection Routing below) AND to Lead. Do NOT send `[DONE]`. Do NOT mark task completed. Task stays `in_progress` — keeps BEND/FEND blocked. After agent revises and downstream re-completes, re-review.
18
21
  - **Escalate to:** Lead — for `[BLOCKER]`, `[ESCALATION]`, or any issue you cannot resolve peer-to-peer.
package/pipeline/steps/orchestration/sprint-groom.md CHANGED
@@ -43,7 +43,8 @@ Process stories using assembly-line parallelism. Each agent moves to the next av
43
43
  --story-id {story_id} \
44
44
  --sprint-id {current_sprint_id}
45
45
  ```
46
- 9. READINESS reviews specs + cross-story checks
46
+ 9. Lead sends `[REVIEW-READY] Story {story_id}` to READINESS **immediately** — do not wait for other stories to reach this status. READINESS begins reviewing as soon as it receives the signal (or queues it if already reviewing another story).
47
+ 10. READINESS reviews specs + cross-story checks
47
48
 
48
49
  **Status-based self-selection with type filtering:**
49
50