@xn-intenton-z2a/agentic-lib 7.4.40 → 7.4.42

package/.github/agents/agent-report.md

@@ -0,0 +1,100 @@
+---
+description: Generate enriched benchmark reports by analysing mechanically gathered pipeline data
+---
+
+You are a benchmark analyst for an autonomous coding pipeline. You have been given a comprehensive mechanical data dump covering a specific time period for a single repository. Your job is to enrich this data into a structured benchmark report with analysis, verified acceptance criteria, and recommendations.
+
+## Available Tools
+
+- `read_file` — Read any file in the repository. Use this to verify acceptance criteria by reading source code, check test implementations, read configuration, and examine mission files.
+- `list_files` — Browse the repository directory structure to discover additional source files, test files, and feature documents.
+- `list_issues` / `get_issue` — Query open and closed issues to understand what work was done, trace issues to features and code changes, and identify issue churn.
+- `list_prs` — Query pull requests (open, closed, merged) to trace code changes back to issues and understand the transformation pipeline.
+- `git_diff` / `git_status` — View the current state of the working tree.
+- `report_analysis` — **Required.** Call this exactly once to record your enriched analysis. Pass a JSON object with all required fields.
+
+> **Use tools aggressively.** The mechanical data gives you the overview — your job is to dig deeper. Read source code to verify acceptance criteria. Read issues and PRs to understand the narrative of what happened. Read commits to trace changes. Don't just trust issue titles — read the bodies and the actual code.
+
+## Context Provided (Mechanical Data)
+
+The task handler has already gathered and included in the prompt:
+
+- **MISSION.md** — full mission text with extracted acceptance criteria
+- **agentic-lib.toml** — full configuration snapshot (model, profile, budget, paths, tuning)
+- **agentic-lib-state.toml** — full persistent state snapshot (counters, budget, status flags)
+- **Workflow runs** — all runs in the period with name, conclusion, timing, duration, and URLs
+- **Pull requests** — merged and open PRs with branch, title, additions/deletions, file count
+- **Commits** — all commits with SHA, message, author, timestamp
+- **Issues** — open and recently closed issues with labels, title, body excerpts
+- **Source code** — full contents of all source files (src/lib/*.js), not just line counts
+- **Test files** — full contents of all test files, not just filenames
+- **Agent log excerpts** — narrative excerpts from the most recent agent log files
+- **Website HTML** — text summary of the GitHub Pages website content
+- **Screenshot** — whether SCREENSHOT_INDEX.png was captured (available as artifact)
+- **README.md** — repository README content
+- **Mission status** — whether MISSION_COMPLETE.md or MISSION_FAILED.md exist, with contents
+
+## Your Task
+
+### 1. Verify Acceptance Criteria (CRITICAL)
+
+For each criterion extracted from MISSION.md:
+- Use `read_file` to check source code for evidence of implementation
+- Use `list_issues` / `get_issue` to find related issues that addressed it
+- Mark each criterion as **PASS**, **FAIL**, or **NOT TESTED** with specific evidence (file path, line number, function name, or issue number)
+- Don't trust issue titles — verify in the actual code
+
+### 2. Build Iteration Narrative
+
+For each workflow run in the period:
+- Was it an init run, a supervisor run, or a manual dispatch?
+- Did it produce a transform? (Check: was a PR merged in the same time window?)
+- What did the supervisor/director decide? (Check agent logs)
+- Map runs to PRs to commits to understand the transformation chain
+
+Write this as the `iteration_narrative` field — a clear prose timeline of what happened.
+
+### 3. Assess Code Quality
+
+Read the source code included in the mechanical data:
+- Is the implementation correct and complete?
+- Are the tests meaningful (testing real behaviour) or trivial (testing existence)?
+- Are there TODO comments or incomplete implementations?
+- Does the code structure match what the mission asked for?
+
+### 4. Identify Findings
+
+Each finding should be categorised as:
+- **POSITIVE** — something that worked well
+- **CONCERN** — something that needs attention
+- **REGRESSION** — something that got worse compared to expected behaviour
+
+Every finding must cite evidence (file path, issue number, commit SHA, or workflow run ID).
+
+### 5. Produce Scenario Summary
+
+Fill in the `scenario_summary` object:
+- `total_iterations`: total workflow runs
+- `transforms`: how many produced merged PRs with code changes
+- `convergence_iteration`: which iteration reached mission-complete (0 if not)
+- `final_source_lines`: line count of main source file
+- `final_test_count`: number of test files
+- `acceptance_pass_count`: e.g. "7/8 PASS"
+- `total_tokens`: from state file counters
+
+### 6. Make Recommendations
+
+Actionable next steps for improving the pipeline, the mission, or the code. Be specific.
+
+### 7. Call `report_analysis`
+
+Record your complete analysis as a structured JSON object. This is mandatory — the report cannot be enriched without it.
+
+## Report Quality Standards
+
+- Every claim must cite evidence
+- Acceptance criteria assessment must read the actual source code
+- Compare state file counters with observed workflow runs for consistency
+- Note any discrepancies between what the pipeline reports and what actually happened
+- Be honest about failures — a clear failure report is more valuable than a vague success report
+- Include the iteration narrative as prose, not just a table

package/.github/workflows/agentic-lib-bot.yml

@@ -84,27 +84,49 @@ env:
 jobs:
   params:
     runs-on: ubuntu-latest
+    outputs:
+      model: ${{ steps.resolve.outputs.model }}
+      dry-run: ${{ steps.resolve.outputs.dry-run }}
+      discussion-url: ${{ steps.resolve.outputs.discussion-url }}
+      message: ${{ steps.resolve.outputs.message }}
     steps:
       - uses: actions/checkout@v6
         with:
           ref: ${{ inputs.ref || github.ref }}
           sparse-checkout: ${{ env.configPath }}
           sparse-checkout-cone-mode: false
-      - name: Normalise params
-        id: normalise
-        shell: bash
-        run: |
-          MODEL='${{ inputs.model }}'
-          if [ -z "$MODEL" ] && [ -f "${{ env.configPath }}" ]; then
-            TOML_MODEL=$(grep '^\s*model' "${{ env.configPath }}" | head -1 | sed 's/.*= *"\([^"]*\)".*/\1/')
-            MODEL="${TOML_MODEL}"
-          fi
-          echo "model=${MODEL:-gpt-5-mini}" >> $GITHUB_OUTPUT
-          DRY_RUN='${{ inputs.dry-run }}'
-          echo "dry-run=${DRY_RUN:-true}" >> $GITHUB_OUTPUT
-    outputs:
-      model: ${{ steps.normalise.outputs.model }}
-      dry-run: ${{ steps.normalise.outputs.dry-run }}
+      - id: resolve
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const fs = require('fs');
+            const configPath = '${{ env.configPath }}';
+            let toml = '';
+            if (fs.existsSync(configPath)) toml = fs.readFileSync(configPath, 'utf8');
+            const readToml = (key) => {
+              const m = toml.match(new RegExp(`^\\s*${key}\\s*=\\s*"([^"]*)"`, 'm'));
+              return m ? m[1] : '';
+            };
+            const resolve = (name, input, configKey, defaultValue) => {
+              let value = input || '';
+              let source = 'input';
+              if (!value && configKey) {
+                value = readToml(configKey);
+                source = value ? 'config' : '';
+              }
+              if (!value) {
+                value = defaultValue;
+                source = 'default';
+              }
+              const configVal = configKey ? readToml(configKey) : 'N/A';
+              core.info(`param ${name}: input='${input}' config='${configVal}' default='${defaultValue}' → '${value}' (source: ${source})`);
+              core.setOutput(name, value);
+              return value;
+            };
+            resolve('model', '${{ inputs.model }}', 'model', 'gpt-5-mini');
+            resolve('dry-run', '${{ inputs.dry-run }}', null, 'true');
+            resolve('discussion-url', '${{ inputs.discussion-url }}', null, '');
+            resolve('message', '${{ inputs.message }}', null, '');
 
   respond:
     needs: params

package/.github/workflows/agentic-lib-flow.yml

@@ -11,6 +11,64 @@ name: agentic-lib-flow
 run-name: "agentic-lib-flow [${{ github.ref_name }}] ${{ inputs.mission-seed }} (${{ inputs.workflow-runs }} runs)"
 
 on:
+  workflow_call:
+    inputs:
+      mode:
+        type: string
+        required: false
+        default: "purge"
+      mission-seed:
+        type: string
+        required: false
+        default: "7-kyu-understand-fizz-buzz"
+      model:
+        type: string
+        required: false
+        default: "gpt-5-mini"
+      profile:
+        type: string
+        required: false
+        default: "max"
+      workflow-runs:
+        type: string
+        required: false
+        default: "4"
+      schedule:
+        type: string
+        required: false
+        default: "off"
+      dry-run:
+        type: string
+        required: false
+        default: "false"
+      message:
+        type: string
+        required: false
+        default: ""
+      config-path:
+        type: string
+        required: false
+        default: ""
+      skipMaintain:
+        type: string
+        required: false
+        default: "false"
+      mission-text:
+        type: string
+        required: false
+        default: ""
+      create-seed-issues:
+        type: string
+        required: false
+        default: "false"
+      skip-tests:
+        type: string
+        required: false
+        default: "true"
+      generate-report:
+        type: string
+        required: false
+        default: "false"
   workflow_dispatch:
     inputs:
       mode:
@@ -88,29 +146,120 @@ on:
           - "weekly"
           - "daily"
           - "hourly"
+      dry-run:
+        description: "Skip all push/PR/merge operations"
+        type: boolean
+        required: false
+        default: false
+      message:
+        description: "Context message for supervisor/bot"
+        type: string
+        required: false
+        default: ""
+      config-path:
+        description: "Config file path (default: agentic-lib.toml)"
+        type: string
+        required: false
+        default: ""
+      generate-report:
+        description: "Generate enriched benchmark report after flow"
+        type: boolean
+        required: false
+        default: false
 
 permissions: write-all
 
 jobs:
+  # ── Params: normalise all inputs ─────────────────────────────────
+  params:
+    runs-on: ubuntu-latest
+    outputs:
+      mode: ${{ steps.resolve.outputs.mode }}
+      mission-seed: ${{ steps.resolve.outputs.mission-seed }}
+      mission-text: ${{ steps.resolve.outputs.mission-text }}
+      model: ${{ steps.resolve.outputs.model }}
+      profile: ${{ steps.resolve.outputs.profile }}
+      workflow-runs: ${{ steps.resolve.outputs.workflow-runs }}
+      schedule: ${{ steps.resolve.outputs.schedule }}
+      dry-run: ${{ steps.resolve.outputs.dry-run }}
+      message: ${{ steps.resolve.outputs.message }}
+      config-path: ${{ steps.resolve.outputs.config-path }}
+      skipMaintain: ${{ steps.resolve.outputs.skipMaintain }}
+      create-seed-issues: ${{ steps.resolve.outputs.create-seed-issues }}
+      skip-tests: ${{ steps.resolve.outputs.skip-tests }}
+      generate-report: ${{ steps.resolve.outputs.generate-report }}
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          sparse-checkout: agentic-lib.toml
+          sparse-checkout-cone-mode: false
+      - id: resolve
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const fs = require('fs');
+            const configPath = 'agentic-lib.toml';
+            let toml = '';
+            if (fs.existsSync(configPath)) toml = fs.readFileSync(configPath, 'utf8');
+            const readToml = (key) => {
+              const m = toml.match(new RegExp(`^\\s*${key}\\s*=\\s*"([^"]*)"`, 'm'));
+              return m ? m[1] : '';
+            };
+            const resolve = (name, input, configKey, defaultValue) => {
+              let value = input || '';
+              let source = 'input';
+              if (!value && configKey) {
+                value = readToml(configKey);
+                source = value ? 'config' : '';
+              }
+              if (!value) {
+                value = defaultValue;
+                source = 'default';
+              }
+              const configVal = configKey ? readToml(configKey) : 'N/A';
+              core.info(`param ${name}: input='${input}' config='${configVal}' default='${defaultValue}' → '${value}' (source: ${source})`);
+              core.setOutput(name, value);
+              return value;
+            };
+            resolve('mode', '${{ inputs.mode }}', null, 'purge');
+            resolve('mission-seed', '${{ inputs.mission-seed }}', null, '7-kyu-understand-fizz-buzz');
+            resolve('mission-text', '${{ inputs.mission-text }}', null, '');
+            resolve('model', '${{ inputs.model }}', 'model', 'gpt-5-mini');
+            resolve('profile', '${{ inputs.profile }}', 'profile', 'max');
+            resolve('workflow-runs', '${{ inputs.workflow-runs }}', null, '4');
+            resolve('schedule', '${{ inputs.schedule }}', null, 'off');
+            resolve('dry-run', '${{ inputs.dry-run }}', null, 'false');
+            resolve('message', '${{ inputs.message }}', null, '');
+            resolve('config-path', '${{ inputs.config-path }}', null, 'agentic-lib.toml');
+            resolve('skipMaintain', '${{ inputs.skipMaintain }}', null, 'false');
+            resolve('create-seed-issues', '${{ inputs.create-seed-issues }}', null, 'false');
+            resolve('skip-tests', '${{ inputs.skip-tests }}', null, 'true');
+            resolve('generate-report', '${{ inputs.generate-report }}', null, 'false');
+
   # ── Phase 0: Update agentic-lib package ────────────────────────────
   update:
-    if: inputs.mode != 'skip'
+    needs: [params]
+    if: needs.params.outputs.mode != 'skip'
     uses: ./.github/workflows/agentic-lib-update.yml
     with:
-      skip-tests: 'true'
+      skip-tests: ${{ needs.params.outputs.skip-tests }}
+      dry-run: ${{ needs.params.outputs.dry-run }}
     secrets: inherit
 
   # ── Phase 0b: Init (purge/reseed/update) ───────────────────────────
   init:
-    needs: [update]
-    if: always() && inputs.mode != 'skip' && (needs.update.result == 'success' || needs.update.result == 'skipped')
+    needs: [params, update]
+    if: always() && needs.params.outputs.mode != 'skip' && (needs.update.result == 'success' || needs.update.result == 'skipped')
     uses: ./.github/workflows/agentic-lib-init.yml
     with:
-      mode: ${{ inputs.mode }}
-      mission-seed: ${{ inputs.mission-seed }}
-      model: ${{ inputs.model }}
-      profile: ${{ inputs.profile }}
-      schedule: ${{ inputs.schedule }}
+      mode: ${{ needs.params.outputs.mode }}
+      mission-seed: ${{ needs.params.outputs.mission-seed }}
+      mission-text: ${{ needs.params.outputs.mission-text }}
+      model: ${{ needs.params.outputs.model }}
+      profile: ${{ needs.params.outputs.profile }}
+      schedule: ${{ needs.params.outputs.schedule }}
+      dry-run: ${{ needs.params.outputs.dry-run }}
+      create-seed-issues: ${{ needs.params.outputs.create-seed-issues }}
     secrets: inherit
 
   # ── Round 1: test + bot + up to 4 workflow runs ────────────────────
@@ -124,6 +273,9 @@ jobs:
     needs: [test-1]
     if: always() && needs.test-1.result == 'success'
     uses: ./.github/workflows/agentic-lib-bot.yml
+    with:
+      model: ${{ inputs.model }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-1:
@@ -150,6 +302,13 @@ jobs:
     needs: [check-1]
     if: always() && needs.check-1.result == 'success' && needs.check-1.outputs.mission-over != 'true' && inputs.workflow-runs >= 1
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-2:
@@ -175,6 +334,13 @@ jobs:
     needs: [check-2]
     if: always() && needs.check-2.result == 'success' && needs.check-2.outputs.mission-over != 'true' && inputs.workflow-runs >= 2
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-3:
@@ -200,6 +366,13 @@ jobs:
     needs: [check-3]
     if: always() && needs.check-3.result == 'success' && needs.check-3.outputs.mission-over != 'true' && inputs.workflow-runs >= 3
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-4:
@@ -225,6 +398,13 @@ jobs:
     needs: [check-4]
     if: always() && needs.check-4.result == 'success' && needs.check-4.outputs.mission-over != 'true' && inputs.workflow-runs >= 4
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   # ── Round 2: test + bot + up to 4 more workflow runs ───────────────
@@ -238,6 +418,9 @@ jobs:
     needs: [test-2]
     if: always() && needs.test-2.result == 'success'
     uses: ./.github/workflows/agentic-lib-bot.yml
+    with:
+      model: ${{ inputs.model }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-5:
@@ -263,6 +446,13 @@ jobs:
     needs: [check-5]
     if: always() && needs.check-5.result == 'success' && needs.check-5.outputs.mission-over != 'true' && inputs.workflow-runs >= 5
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-6:
@@ -288,6 +478,13 @@ jobs:
     needs: [check-6]
     if: always() && needs.check-6.result == 'success' && needs.check-6.outputs.mission-over != 'true' && inputs.workflow-runs >= 6
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-7:
@@ -313,6 +510,13 @@ jobs:
     needs: [check-7]
     if: always() && needs.check-7.result == 'success' && needs.check-7.outputs.mission-over != 'true' && inputs.workflow-runs >= 7
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-8:
@@ -338,6 +542,13 @@ jobs:
     needs: [check-8]
     if: always() && needs.check-8.result == 'success' && needs.check-8.outputs.mission-over != 'true' && inputs.workflow-runs >= 8
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   # ── Round 3: test + bot + up to 4 more workflow runs ───────────────
@@ -351,6 +562,9 @@ jobs:
     needs: [test-3]
     if: always() && needs.test-3.result == 'success'
     uses: ./.github/workflows/agentic-lib-bot.yml
+    with:
+      model: ${{ inputs.model }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-9:
@@ -376,6 +590,13 @@ jobs:
     needs: [check-9]
     if: always() && needs.check-9.result == 'success' && needs.check-9.outputs.mission-over != 'true' && inputs.workflow-runs >= 9
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-10:
@@ -401,6 +622,13 @@ jobs:
     needs: [check-10]
     if: always() && needs.check-10.result == 'success' && needs.check-10.outputs.mission-over != 'true' && inputs.workflow-runs >= 10
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-11:
@@ -426,6 +654,13 @@ jobs:
     needs: [check-11]
     if: always() && needs.check-11.result == 'success' && needs.check-11.outputs.mission-over != 'true' && inputs.workflow-runs >= 11
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-12:
@@ -451,6 +686,13 @@ jobs:
     needs: [check-12]
     if: always() && needs.check-12.result == 'success' && needs.check-12.outputs.mission-over != 'true' && inputs.workflow-runs >= 12
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   # ── Round 4: test + bot + up to 4 more workflow runs ───────────────
@@ -464,6 +706,9 @@ jobs:
     needs: [test-4]
     if: always() && needs.test-4.result == 'success'
     uses: ./.github/workflows/agentic-lib-bot.yml
+    with:
+      model: ${{ inputs.model }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-13:
@@ -489,6 +734,13 @@ jobs:
     needs: [check-13]
     if: always() && needs.check-13.result == 'success' && needs.check-13.outputs.mission-over != 'true' && inputs.workflow-runs >= 13
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-14:
@@ -514,6 +766,13 @@ jobs:
     needs: [check-14]
     if: always() && needs.check-14.result == 'success' && needs.check-14.outputs.mission-over != 'true' && inputs.workflow-runs >= 14
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-15:
@@ -539,6 +798,13 @@ jobs:
     needs: [check-15]
     if: always() && needs.check-15.result == 'success' && needs.check-15.outputs.mission-over != 'true' && inputs.workflow-runs >= 15
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   check-16:
@@ -564,6 +830,13 @@ jobs:
     needs: [check-16]
     if: always() && needs.check-16.result == 'success' && needs.check-16.outputs.mission-over != 'true' && inputs.workflow-runs >= 16
     uses: ./.github/workflows/agentic-lib-workflow.yml
+    with:
+      model: ${{ inputs.model }}
+      profile: ${{ inputs.profile }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+      skipMaintain: ${{ inputs.skipMaintain || 'false' }}
+      config-path: ${{ inputs.config-path }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   # ── Final: test + bot (always runs) ────────────────────────────────
@@ -577,6 +850,9 @@ jobs:
     needs: [test-final]
     if: always() && needs.test-final.result == 'success'
     uses: ./.github/workflows/agentic-lib-bot.yml
+    with:
+      model: ${{ inputs.model }}
+      message: ${{ inputs.message }}
     secrets: inherit
 
   # ── Verify: MISSION_COMPLETE.md must exist ─────────────────────────
@@ -737,3 +1013,14 @@ jobs:
         with:
           name: benchmark-report
           path: BENCHMARK_REPORT_FLOW_*.md
+
+  # ── Enriched benchmark report (opt-in) ──────────────────────────
+  enriched-report:
+    needs: [params, generate-report]
+    if: always() && needs.params.outputs.generate-report == 'true'
+    uses: ./.github/workflows/agentic-lib-report.yml
+    with:
+      model: ${{ inputs.model }}
+      config-path: ${{ inputs.config-path }}
+      dry-run: ${{ inputs.dry-run || 'false' }}
+    secrets: inherit