valent-pipeline 0.2.3 → 0.2.5

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "valent-pipeline",
-  "version": "0.2.3",
+  "version": "0.2.5",
   "description": "v3 multi-agent AI pipeline for software development lifecycle",
   "type": "module",
   "bin": {

package/pipeline/prompts/lead.md

@@ -8,6 +8,18 @@ The story is your unit of work. The cycle is: **kick off story team -> monitor -
 
 You operate like a good manager: always able to answer "what is happening right now," accountable for the story shipping, but not micromanaging the work. Pipeline structure (task dependencies, quality gates, handoff contracts) enforces the rules -- you watch the board.
 
+## Agent Teams (CRITICAL)
+
+**You MUST use Claude Code's Agent Teams to spawn teammates.** Do NOT use subagents. The pipeline requires persistent, named teammates that communicate via inbox — subagents cannot do this.
+
+The correct pattern:
+1. `TeamCreate` to create the team (once per story or epic)
+2. **Agent tool** with `name` parameter to spawn each teammate onto the team. The `name` becomes the teammate's addressable identity for inbox messaging.
+3. `SendMessage` to communicate with living teammates by name
+4. `shutdown_request` via SendMessage to tear down individual teammates
+
+**NEVER** spawn pipeline agents as anonymous subagents. Every agent must be a named teammate on the team so it can send and receive inbox messages with other teammates.
+
 ## Core Operating Principles
 
 These override all other instructions when in conflict:

package/pipeline/steps/orchestration/adopt-lead-and-create-team.md

@@ -73,13 +73,17 @@ This file is appended to incrementally during monitoring as agents complete phas
 
 ## 7. Spawn Agents
 
+**IMPORTANT: Use the Agent tool to spawn teammates onto the team — NOT subagents.** Every pipeline agent must be a named teammate so it can send and receive inbox messages with other teammates. Use the `name` parameter on the Agent tool to set the teammate's addressable name (e.g., `name: "REQS"`).
+
 Read the spawn templates:
 - `.valent-pipeline/spawn-templates/knowledge-spawn.template.md` -- for the Knowledge Agent
 - `.valent-pipeline/spawn-templates/agent-spawn.template.md` -- for all other agents
 
-**Wave 1: Knowledge Agent first.** If `{is_epic_run}` is true and a Knowledge teammate already exists in the current team, skip the spawn. Instead, send a `[STORY-RESET]` message via inbox: `[STORY-RESET] story_id={story_id}, pipeline_context={story_output_dir}/pipeline-context.md`. Wait for `[KNOWLEDGE-READY]` response before proceeding.
+Substitute all `{{variables}}` in the template with resolved values, then pass the filled template as the `prompt` parameter to the Agent tool. Set `name` to the agent's name from the manifest (e.g., `"REQS"`, `"UXA"`, `"Knowledge"`). Set `run_in_background: true` so agents work autonomously.
+
+**Wave 1: Knowledge Agent first.** If `{is_epic_run}` is true and a Knowledge teammate already exists in the current team, skip the spawn. Instead, send a `[STORY-RESET]` message via `SendMessage(to: "Knowledge")`: `[STORY-RESET] story_id={story_id}, pipeline_context={story_output_dir}/pipeline-context.md`. Wait for `[KNOWLEDGE-READY]` response before proceeding.
 
-Otherwise, substitute variables in the knowledge spawn template (`{{story_id}}`, `{{story_output_dir}}`, knowledge config). Spawn with `run_in_background: true`. Wait for ready notification.
+Otherwise, substitute variables in the knowledge spawn template (`{{story_id}}`, `{{story_output_dir}}`, knowledge config). Spawn as a named teammate with `run_in_background: true`. Wait for ready notification.
 
 **Wave 1 timestamp capture:** Before spawning each Wave 1 agent (except Knowledge), capture the start timestamp via `date -u +%Y-%m-%dT%H:%M:%SZ`. Record it as that agent's phase start time for `phase-timing.md`. Knowledge is excluded from phase timing (reactive service).
 
@@ -99,7 +103,7 @@ When spawning a later-wave agent:
 - Substitute all variables as for wave 1 agents
 - For agents with two task refs: populate `{{additional_task_ids}}` with the second task
 - Use the `model` from `pipeline-config.yaml` `models` section (match agent name to tier)
-- Spawn with `run_in_background: true`
+- **Spawn as a named teammate** using the Agent tool with `name` set to the agent's name (e.g., `name: "BEND"`). Set `run_in_background: true`. Do NOT use subagents.
 
 ## 8. Enter Monitoring Mode
 

package/skills/valent-configure/SKILL.md

@@ -78,6 +78,21 @@ Present defaults and let the user adjust:
 | `retrospective_every_n_stories` | `5` | How often the Retrospective Agent runs (range: 3-10) |
 | `stall_threshold_minutes` | `15` | Minutes before a stalled agent gets a check-in (range: 5-30) |
 
+### Step 4b: Sprint Planning
+
+Present defaults and let the user adjust. These settings control sprint-based planning in epic and project runs:
+
+| Setting | Default | Description |
+|---------|---------|-------------|
+| `duration_minutes` | `480` | Sprint time budget in minutes (480 = 8 hours, "overnight") |
+| `initial_velocity_points` | `60` | Bootstrap velocity until first sprint completes (range: 20-120) |
+| `estimation_model` | `calibrated` | `calibrated` uses retro history for estimates; `baseline` estimates from specs only |
+| `auto_plan` | `true` | Enable sprint planning in epic/project runs |
+| `fibonacci_scale` | `[1, 2, 3, 5, 8, 13, 21]` | Point scale for story sizing (standard Fibonacci) |
+| `max_groom_batch_size` | `10` | Kill and respawn Phase 1 agents after this many stories to manage context |
+
+Note: Sprint config only affects `valent-run-epic` and `valent-run-project`. Standalone `valent-run-story` ignores it.
+
 ### Step 5: Knowledge Store Mode
 
 Ask the user to pick one:

package/src/commands/init.js

@@ -205,6 +205,34 @@ async function runWizard() {
     config.knowledge.chromadb_host = chromadbHost;
   }
 
+  // Sprint planning
+  const { sprintDuration } = await inquirer.prompt([{
+    type: 'input', name: 'sprintDuration',
+    message: 'Sprint duration (minutes, for epic/project runs):',
+    default: '480',
+    validate: v => !isNaN(parseInt(v)) || 'Must be a number',
+  }]);
+  config.sprint.duration_minutes = parseInt(sprintDuration);
+
+  const { initialVelocity } = await inquirer.prompt([{
+    type: 'input', name: 'initialVelocity',
+    message: 'Initial velocity (story points per sprint):',
+    default: '60',
+    validate: v => !isNaN(parseInt(v)) || 'Must be a number',
+  }]);
+  config.sprint.initial_velocity_points = parseInt(initialVelocity);
+
+  const { estimationModel } = await inquirer.prompt([{
+    type: 'list', name: 'estimationModel',
+    message: 'Estimation model:',
+    choices: [
+      { name: 'Calibrated (uses historical data from retros)', value: 'calibrated' },
+      { name: 'Baseline (estimates from specs only, no history)', value: 'baseline' },
+    ],
+    default: 'calibrated',
+  }]);
+  config.sprint.estimation_model = estimationModel;
+
   return config;
 }
 
@@ -256,6 +284,14 @@ ${config.knowledge.mode === 'sqlite' ? `  sqlite_db_path: "${config.knowledge.sq
   curated_files_path: "${config.knowledge.curated_files_path}"
   correction_directives_path: "${config.knowledge.correction_directives_path}"
 
+sprint:
+  duration_minutes: ${config.sprint?.duration_minutes ?? 480}
+  initial_velocity_points: ${config.sprint?.initial_velocity_points ?? 60}
+  estimation_model: "${config.sprint?.estimation_model ?? 'calibrated'}"
+  auto_plan: ${config.sprint?.auto_plan ?? true}
+  fibonacci_scale: [${(config.sprint?.fibonacci_scale ?? [1, 2, 3, 5, 8, 13, 21]).join(', ')}]
+  max_groom_batch_size: ${config.sprint?.max_groom_batch_size ?? 10}
+
 orchestration:
   recommended_context_window: "${config.orchestration?.recommended_context_window || '200k'}"
   epic_progress_path: "${config.orchestration?.epic_progress_path || './epic-progress.md'}"

package/src/commands/upgrade.js

@@ -73,6 +73,24 @@ export async function upgrade(options = {}) {
     console.log('Updated skills in .claude/skills/');
   }
 
+  // Migrate config: add sprint section if missing
+  const configPath = join(projectRoot, '.valent-pipeline', 'pipeline-config.yaml');
+  if (fileExists(configPath)) {
+    let configContent = readFile(configPath);
+    if (!configContent.includes('sprint:')) {
+      // Insert sprint section before orchestration (or at end if orchestration not found)
+      const sprintBlock = `\nsprint:\n  duration_minutes: 480\n  initial_velocity_points: 60\n  estimation_model: "calibrated"\n  auto_plan: true\n  fibonacci_scale: [1, 2, 3, 5, 8, 13, 21]\n  max_groom_batch_size: 10\n`;
+      const insertPoint = configContent.indexOf('\norchestration:');
+      if (insertPoint !== -1) {
+        configContent = configContent.slice(0, insertPoint) + sprintBlock + configContent.slice(insertPoint);
+      } else {
+        configContent += sprintBlock;
+      }
+      writeFileSafe(configPath, configContent);
+      console.log('Migrated pipeline-config.yaml: added sprint section');
+    }
+  }
+
   // Update version file
   writeFileSafe(versionFile, packageVersion);
   console.log(`Updated .valent-pipeline/.valent-version to ${packageVersion}`);

package/src/commands/validate.js

@@ -75,10 +75,18 @@ function parseSimpleYaml(content) {
           if ((s.startsWith('"') && s.endsWith('"')) || (s.startsWith("'") && s.endsWith("'"))) {
             s = s.slice(1, -1);
           }
+          // Parse numeric array elements
+          if (/^\d+(\.\d+)?$/.test(s)) {
+            return parseFloat(s);
+          }
           return s;
-        }).filter(s => s.length > 0);
+        }).filter(s => s !== '');
       }
 
+      // Parse booleans
+      if (typeof value === 'string' && value === 'true') value = true;
+      if (typeof value === 'string' && value === 'false') value = false;
+
       // Parse numbers
       if (typeof value === 'string' && /^\d+$/.test(value)) {
         value = parseInt(value, 10);