claude-mpm 4.3.4__py3-none-any.whl → 4.3.6__py3-none-any.whl

claude_mpm/VERSION

@@ -1 +1 @@
-4.3.4
+4.3.6

claude_mpm/agents/PM_INSTRUCTIONS.md

@@ -26,6 +26,7 @@
 | deploy, infrastructure | Ops | - |
 | GCP, Cloud Run | gcp-ops-agent | Ops |
 | Vercel, edge | vercel-ops-agent | Ops |
+| Railway deploy | railway-ops-agent | Ops |
 | security, auth | Security | - |
 | document, docs | Documentation | - |
 | git, commit | version-control | - |
@@ -45,10 +46,11 @@ START → Research → Code Analyzer → Implementation → Site Deployment →
 1. **Research**: Requirements analysis, success criteria, risks
 2. **Code Analyzer**: Solution review (APPROVED/NEEDS_IMPROVEMENT/BLOCKED)
 3. **Implementation**: Selected agent builds complete solution
-4. **Site Deployment** (for web projects):
-   - **MANDATORY**: Deploy stable instance using PM2 when working on sites
-   - Delegate to Ops agent: "Deploy site with PM2 for testing"
-   - Ensure site is accessible before proceeding to QA
+4. **Deployment & Verification** (MANDATORY for all deployments):
+   - **Step 1**: Deploy using appropriate ops agent
+   - **Step 2**: MUST verify deployment with same ops agent
+   - **Step 3**: Ops agent MUST check logs, use fetch/Playwright for validation
+   - **FAILURE TO VERIFY = DEPLOYMENT INCOMPLETE**
 5. **QA**: Real-world testing with evidence (MANDATORY)
    - **Web UI Work**: MUST use Playwright for browser testing
    - **API Work**: Use web-qa for fetch testing
@@ -60,6 +62,38 @@ START → Research → Code Analyzer → Implementation → Site Deployment →
 - Attempt 2: Escalate to Research
 - Attempt 3: Block, require user input
 
+## Deployment Verification Matrix
+
+**MANDATORY**: Every deployment MUST be verified by the appropriate ops agent
+
+| Deployment Type | Ops Agent | Required Verifications |
+|----------------|-----------|------------------------|
+| Local Dev (PM2, Docker) | Ops | Read logs, check process status, fetch endpoint, Playwright if UI |
+| Vercel | vercel-ops-agent | Read build logs, fetch deployment URL, check function logs, Playwright for pages |
+| Railway | railway-ops-agent | Read deployment logs, check health endpoint, verify database connections |
+| GCP/Cloud Run | gcp-ops-agent | Check Cloud Run logs, verify service status, test endpoints |
+| AWS | aws-ops-agent | CloudWatch logs, Lambda status, API Gateway tests |
+| Heroku | Ops (generic) | Read app logs, check dyno status, test endpoints |
+| Netlify | Ops (generic) | Build logs, function logs, deployment URL tests |
+
+**Verification Requirements**:
+1. **Logs**: Agent MUST read deployment/server logs for errors
+2. **Fetch Tests**: Agent MUST use fetch to verify API endpoints return expected status
+3. **UI Tests**: For web apps, agent MUST use Playwright to verify page loads
+4. **Health Checks**: Agent MUST verify health/status endpoints if available
+5. **Database**: If applicable, agent MUST verify database connectivity
+
+**Verification Template for Ops Agents**:
+```
+Task: Verify [platform] deployment
+Requirements:
+1. Read deployment/build logs - identify any errors or warnings
+2. Test primary endpoint with fetch - verify HTTP 200/expected response
+3. If UI: Use Playwright to verify homepage loads and key elements present
+4. Check server/function logs for runtime errors
+5. Report: "Deployment VERIFIED" or "Deployment FAILED: [specific issues]"
+```
+
 ## QA Requirements
 
 **Rule**: No QA = Work incomplete
@@ -74,9 +108,12 @@ START → Research → Code Analyzer → Implementation → Site Deployment →
 |------|-------------|----------|----------------|
 | API | HTTP calls | curl/fetch output | web-qa (MANDATORY) |
 | Web UI | Browser automation | Playwright results | web-qa with Playwright |
-| Site Deploy | PM2 status | Process running | Ops → web-qa verify |
+| Local Deploy | PM2/Docker status + fetch/Playwright | Logs + endpoint tests | Ops (MUST verify) |
+| Vercel Deploy | Build success + fetch/Playwright | Deployment URL active | vercel-ops-agent (MUST verify) |
+| Railway Deploy | Service healthy + fetch tests | Logs + endpoint response | railway-ops-agent (MUST verify) |
+| GCP Deploy | Cloud Run active + endpoint tests | Service logs + HTTP 200 | gcp-ops-agent (MUST verify) |
 | Database | Query execution | SELECT results | QA |
-| Deploy | Live URL | HTTP 200 | web-qa |
+| Any Deploy | Live URL + server logs + fetch | Full verification suite | Appropriate ops agent |
 
 **Reject if**: "should work", "looks correct", "theoretically"
 **Accept if**: "tested with output:", "verification shows:", "actual results:"
@@ -123,8 +160,13 @@ Override? → YES → PM executes
   ↓ NO
 Research → Code Analyzer → Implementation →
   ↓
-Is Site? → YES → PM2 Deploy (Ops)
-  ↓ NO
+Needs Deploy? → YES → Deploy (Appropriate Ops Agent) →
+  ↓                    ↓
+  NO              VERIFY (Same Ops Agent):
+  ↓                - Read logs
+  ↓                - Fetch tests
+  ↓                - Playwright if UI
+  ↓                    ↓
 QA Verification (MANDATORY):
   - web-qa for ALL projects (fetch tests)
   - Playwright for Web UI
@@ -133,12 +175,13 @@ Documentation → Report
 ```
 
 ### Common Patterns
-- Full Stack: Research → Analyzer → react-engineer + Engineer → Ops (PM2) → api-qa + web-qa (Playwright) → Docs
-- API: Research → Analyzer → Engineer → web-qa (fetch tests) → Docs
-- Web UI: Research → Analyzer → web-ui/react-engineer → Ops (PM2) → web-qa (Playwright) → Docs
-- Site Project: Research → Analyzer → Engineer → Ops (PM2 deploy) → web-qa (verify deployment) → Docs
-- Deploy: Research → Ops (PM2 for sites) → web-qa (verify accessible) → Docs
-- Bug Fix: Research → Analyzer → Engineer → web-qa (regression test) → version-control
+- Full Stack: Research → Analyzer → react-engineer + Engineer → Ops (deploy) → Ops (VERIFY) → api-qa + web-qa → Docs
+- API: Research → Analyzer → Engineer → Deploy (if needed) → Ops (VERIFY) → web-qa (fetch tests) → Docs
+- Web UI: Research → Analyzer → web-ui/react-engineer → Ops (deploy) → Ops (VERIFY with Playwright) → web-qa → Docs
+- Vercel Site: Research → Analyzer → Engineer → vercel-ops (deploy) → vercel-ops (VERIFY) → web-qa → Docs
+- Railway App: Research → Analyzer → Engineer → railway-ops (deploy) → railway-ops (VERIFY) → api-qa → Docs
+- Local Dev: Research → Analyzer → Engineer → Ops (PM2/Docker) → Ops (VERIFY logs+fetch) → QA → Docs
+- Bug Fix: Research → Analyzer → Engineer → Deploy → Ops (VERIFY) → web-qa (regression) → version-control
 
 ### Success Criteria
 ✅ Measurable: "API returns 200", "Tests pass 80%+"

claude_mpm/services/agents/deployment/multi_source_deployment_service.py

@@ -199,9 +199,12 @@ class MultiSourceAgentDeploymentService:
                                     f"Project agent '{agent_name}' v{other_agent['version']} "
                                     f"overridden by higher system version v{highest_version_agent['version']}"
                                 )
-                            elif other_agent["source"] == "user" and highest_version_agent[
+                            elif other_agent[
                                 "source"
-                            ] in ["system", "project"]:
+                            ] == "user" and highest_version_agent["source"] in [
+                                "system",
+                                "project",
+                            ]:
                                 self.logger.warning(
                                     f"User agent '{agent_name}' v{other_agent['version']} "
                                     f"overridden by higher {highest_version_agent['source']} version v{highest_version_agent['version']}"

{claude_mpm-4.3.4.dist-info → claude_mpm-4.3.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: claude-mpm
-Version: 4.3.4
+Version: 4.3.6
 Summary: Claude Multi-Agent Project Manager - Orchestrate Claude with agent delegation and ticket tracking
 Author-email: Bob Matsuoka <bob@matsuoka.com>
 Maintainer: Claude MPM Team

{claude_mpm-4.3.4.dist-info → claude_mpm-4.3.6.dist-info}/RECORD

@@ -1,5 +1,5 @@
 claude_mpm/BUILD_NUMBER,sha256=toytnNjkIKPgQaGwDqQdC1rpNTAdSEc6Vja50d7Ovug,4
-claude_mpm/VERSION,sha256=o_KX93dYgQAeUlvYMW1sYfnWMQ1_4M4ZGDDpbNctSho,6
+claude_mpm/VERSION,sha256=oKf8LmEL2ljWmqB_HQ624StYNfAD_9xr3PUlN9ch6rk,6
 claude_mpm/__init__.py,sha256=lyTZAYGH4DTaFGLRNWJKk5Q5oTjzN5I6AXmfVX-Jff0,1512
 claude_mpm/__main__.py,sha256=Ro5UBWBoQaSAIoSqWAr7zkbLyvi4sSy28WShqAhKJG0,723
 claude_mpm/constants.py,sha256=xnjYxUUVufwp4fIMpAwKiMC5MP14-c2HSAz5R9O3G-U,5927
@@ -15,7 +15,7 @@ claude_mpm/agents/BASE_RESEARCH.md,sha256=2DZhDd5XxWWtsyNTBIwvtNWBu1JpFy5R5SAZDH
 claude_mpm/agents/INSTRUCTIONS_OLD_DEPRECATED.md,sha256=zQZhrhVq9NLCtSjVX-aC0xcgueemSuPhKyv0SjEOyIQ,25852
 claude_mpm/agents/MEMORY.md,sha256=KbRwY_RYdOvTvFC2DD-ATfwjHkQWJ5PIjlGws_7RmjI,3307
 claude_mpm/agents/OUTPUT_STYLE.md,sha256=IYbo4jmICihrfnChbdrRpwVk4VobCcNyYqZqd53VXMk,533
-claude_mpm/agents/PM_INSTRUCTIONS.md,sha256=H4ghtT8D8JdevQx_vvklRm-MBLAz7oXSbO2emiEuxnI,4836
+claude_mpm/agents/PM_INSTRUCTIONS.md,sha256=uUD8ypYygQ3jJARZKQRApwvhNNjorjv0LXtAW-TP5HE,7563
 claude_mpm/agents/WORKFLOW.md,sha256=Dvy4Io3vr1V0WRINTPRuzSOIciwOl-d7fwO2PtXtvGs,2638
 claude_mpm/agents/__init__.py,sha256=jRFxvV_DIZ-NdENa-703Xu3YpwvlQj6yv-mQ6FgmldM,3220
 claude_mpm/agents/agent-template.yaml,sha256=mRlz5Yd0SmknTeoJWgFkZXzEF5T7OmGBJGs2-KPT93k,1969
@@ -436,7 +436,7 @@ claude_mpm/services/agents/deployment/interface_adapter.py,sha256=mOsQ5IJHLEezq8
 claude_mpm/services/agents/deployment/lifecycle_health_checker.py,sha256=2dphAvYRABNlsvi3XfVwS8kvv-YURNEwPBVtCc1g3Zc,3164
 claude_mpm/services/agents/deployment/lifecycle_performance_tracker.py,sha256=lK_yg0uRL55opUoecOJBL83Tjj6Pu_z4-4EYWPeN6tM,4336
 claude_mpm/services/agents/deployment/local_template_deployment.py,sha256=VgvmfT8dYaH1KUDMO04EsAQ-XBf_X8u1JlQ_ZGtjDWk,12966
-claude_mpm/services/agents/deployment/multi_source_deployment_service.py,sha256=RMmeKmn917NKtyvGRWNfrduQPama5nhqqIqAxJ1c9Ls,43237
+claude_mpm/services/agents/deployment/multi_source_deployment_service.py,sha256=0qyWrYaL7CFi5M8yqVhLgMKnIM8nIctKVjfpnAi4f9A,43332
 claude_mpm/services/agents/deployment/refactored_agent_deployment_service.py,sha256=5-StpaZYqVvm-WrmLMsoIp85WFYL2p0VLWQOfZEn8jU,11707
 claude_mpm/services/agents/deployment/single_agent_deployer.py,sha256=6QtHP-y4T_-UXYXYvdQgdIooOfjnC5NArlbkUo4EPl0,11492
 claude_mpm/services/agents/deployment/system_instructions_deployer.py,sha256=SCBBXleIn322X_w-swOHjO22J3HCxSHGkd3V-rSbbOs,4060
@@ -714,9 +714,9 @@ claude_mpm/utils/subprocess_utils.py,sha256=zgiwLqh_17WxHpySvUPH65pb4bzIeUGOAYUJ
 claude_mpm/validation/__init__.py,sha256=YZhwE3mhit-lslvRLuwfX82xJ_k4haZeKmh4IWaVwtk,156
 claude_mpm/validation/agent_validator.py,sha256=3Lo6LK-Mw9IdnL_bd3zl_R6FkgSVDYKUUM7EeVVD3jc,20865
 claude_mpm/validation/frontmatter_validator.py,sha256=u8g4Eyd_9O6ugj7Un47oSGh3kqv4wMkuks2i_CtWRvM,7028
-claude_mpm-4.3.4.dist-info/licenses/LICENSE,sha256=lpaivOlPuBZW1ds05uQLJJswy8Rp_HMNieJEbFlqvLk,1072
-claude_mpm-4.3.4.dist-info/METADATA,sha256=abw8FbY3jwaD4Sk3pC8Lr5vj-Rv-_T-yzL3W_3TYZIw,14882
-claude_mpm-4.3.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-claude_mpm-4.3.4.dist-info/entry_points.txt,sha256=FDPZgz8JOvD-6iuXY2l9Zbo9zYVRuE4uz4Qr0vLeGOk,471
-claude_mpm-4.3.4.dist-info/top_level.txt,sha256=1nUg3FEaBySgm8t-s54jK5zoPnu3_eY6EP6IOlekyHA,11
-claude_mpm-4.3.4.dist-info/RECORD,,
+claude_mpm-4.3.6.dist-info/licenses/LICENSE,sha256=lpaivOlPuBZW1ds05uQLJJswy8Rp_HMNieJEbFlqvLk,1072
+claude_mpm-4.3.6.dist-info/METADATA,sha256=G7SCcqBeLewGx3ai5QlKaWqh_j8ZAsOQ_pj369PBDbI,14882
+claude_mpm-4.3.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+claude_mpm-4.3.6.dist-info/entry_points.txt,sha256=FDPZgz8JOvD-6iuXY2l9Zbo9zYVRuE4uz4Qr0vLeGOk,471
+claude_mpm-4.3.6.dist-info/top_level.txt,sha256=1nUg3FEaBySgm8t-s54jK5zoPnu3_eY6EP6IOlekyHA,11
+claude_mpm-4.3.6.dist-info/RECORD,,