@pjmendonca/devflow 1.13.1 → 1.18.0

package/tooling/.automation/agents/maintainer.md

@@ -95,3 +95,22 @@ Brownfield development - working with existing, production code. Your approach i
 - **Quick fixes**: Sonnet (simple changes)
 - **Refactoring**: Opus (careful changes needed)
 - **Migrations**: Opus (complex, high-risk)
+
+## Context Management
+
+When investigating existing codebases:
+
+1. **Read strategically** - Focus on relevant files, don't load entire codebase
+2. **Create checkpoints** before starting large investigations
+3. **Document findings incrementally** - Don't wait until the end
+4. **Summarize learnings** - Keep notes for context preservation
+
+## When Complete
+
+After completing maintenance work:
+
+1. Document what was changed and why in commit messages
+2. Update any affected documentation
+3. Create fix summary if applicable (for bugs)
+4. Update sprint-status.yaml with new status
+5. Note any remaining technical debt or follow-up items

package/tooling/.automation/agents/pm.md

@@ -114,3 +114,22 @@ For releases:
 - **Feature Adoption**: Usage of key features
 - **Performance**: App load times, crash rates
 - **Satisfaction**: App store ratings, NPS
+
+## Context Management
+
+When planning and prioritizing:
+
+1. **Keep roadmaps focused** - Don't load entire product history
+2. **Create checkpoints** before strategic planning sessions
+3. **Summarize decisions** - Document rationale concisely
+4. **Link to details** - Reference full docs instead of copying
+
+## When Complete
+
+After completing product management work:
+
+1. Update roadmap and epic documentation
+2. Ensure sprint-status.yaml reflects current priorities
+3. Create clear handoff notes for BA and SM agents
+4. Document any scope changes or pivots
+5. Update stakeholder communication as needed

package/tooling/.automation/agents/reviewer.md

@@ -112,7 +112,7 @@ Location: path/to/file.dart:42
 
 ## Rules
 
-1. **No rubber stamping** - Every review must find at least one improvement opportunity
+1. **Thorough reviews** - Identify all legitimate issues; approve only when code genuinely meets standards
 2. **Be specific** - Vague feedback is useless; explain WHY and suggest HOW to fix
 3. **Prioritize by risk** - Security > Reliability > Correctness > Style
 4. **Check the tests** - Missing tests for critical paths is a blocking issue

package/tooling/.automation/agents/writer.md

@@ -191,3 +191,22 @@ Before finalizing documentation:
 - [ ] Links are valid
 - [ ] Code examples work
 - [ ] Screenshots are current (if applicable)
+
+## Context Management
+
+When writing documentation:
+
+1. **Read source first** - Understand before documenting
+2. **Create checkpoints** before large documentation efforts
+3. **Write incrementally** - Save sections as you complete them
+4. **Keep examples minimal** - Use the simplest code that illustrates the point
+
+## When Complete
+
+After completing documentation work:
+
+1. Save documentation to the appropriate working directory
+2. Verify all links and references are valid
+3. Update any related README files
+4. Update sprint-status.yaml if documenting a story
+5. Note any areas needing future documentation updates

package/tooling/.automation/benchmarks/benchmark_20251230_100119.json

@@ -0,0 +1,314 @@
+[
+  {
+    "test_id": "sim_20251230_100119",
+    "task": "Design a secure authentication system with OAuth2 and JWT",
+    "agents": [
+      "ARCHITECT",
+      "DEV",
+      "REVIEWER"
+    ],
+    "personas_used": [
+      "Enterprise Architect",
+      "Cloud Native",
+      "Pragmatic Minimalist"
+    ],
+    "total_rounds": 5,
+    "termination_reason": "max_rounds",
+    "final_agreement_score": 0.4152174154581419,
+    "total_tokens": 4674,
+    "total_cost_usd": 0.046740000000000004,
+    "timestamp": "2025-12-30T10:01:19.418096",
+    "duration_seconds": 0.0007348060607910156,
+    "rounds": [
+      {
+        "round_num": 0,
+        "new_arguments": 4,
+        "challenges_raised": 4,
+        "concessions_made": 0,
+        "agreement_score": 0.16548581440877563,
+        "agreement_delta": 0.16548581440877563,
+        "unique_issues": 8,
+        "tokens_used": 639,
+        "cost_usd": 0.006390000000000001,
+        "positions_changed": 1
+      },
+      {
+        "round_num": 1,
+        "new_arguments": 5,
+        "challenges_raised": 2,
+        "concessions_made": 0,
+        "agreement_score": 0.2572500710936962,
+        "agreement_delta": 0.09176425668492055,
+        "unique_issues": 4,
+        "tokens_used": 923,
+        "cost_usd": 0.00923,
+        "positions_changed": 1
+      },
+      {
+        "round_num": 2,
+        "new_arguments": 2,
+        "challenges_raised": 0,
+        "concessions_made": 1,
+        "agreement_score": 0.32163266454672484,
+        "agreement_delta": 0.06438259345302866,
+        "unique_issues": 2,
+        "tokens_used": 1405,
+        "cost_usd": 0.014050000000000002,
+        "positions_changed": 0
+      },
+      {
+        "round_num": 3,
+        "new_arguments": 3,
+        "challenges_raised": 1,
+        "concessions_made": 2,
+        "agreement_score": 0.3887506875113108,
+        "agreement_delta": 0.06711802296458597,
+        "unique_issues": 1,
+        "tokens_used": 887,
+        "cost_usd": 0.008870000000000001,
+        "positions_changed": 0
+      },
+      {
+        "round_num": 4,
+        "new_arguments": 2,
+        "challenges_raised": 1,
+        "concessions_made": 2,
+        "agreement_score": 0.4152174154581419,
+        "agreement_delta": 0.02646672794683108,
+        "unique_issues": 0,
+        "tokens_used": 820,
+        "cost_usd": 0.0082,
+        "positions_changed": 0
+      }
+    ],
+    "arguments_per_round": [
+      4,
+      5,
+      2,
+      3,
+      2
+    ],
+    "agreement_progression": [
+      0.16548581440877563,
+      0.2572500710936962,
+      0.32163266454672484,
+      0.3887506875113108,
+      0.4152174154581419
+    ],
+    "marginal_value": [
+      15.109324169151417,
+      8.578160960833376,
+      1.8817266437937983,
+      5.2662685790821415,
+      3.981301560327209
+    ]
+  },
+  {
+    "test_id": "sim_20251230_100119",
+    "task": "Implement a caching layer for the API with Redis",
+    "agents": [
+      "DEV",
+      "REVIEWER",
+      "SECURITY"
+    ],
+    "personas_used": [
+      "Enterprise Architect",
+      "Cloud Native",
+      "Legacy Steward"
+    ],
+    "total_rounds": 5,
+    "termination_reason": "max_rounds",
+    "final_agreement_score": 0.633611109969572,
+    "total_tokens": 5717,
+    "total_cost_usd": 0.057170000000000006,
+    "timestamp": "2025-12-30T10:01:19.418465",
+    "duration_seconds": 0.00034999847412109375,
+    "rounds": [
+      {
+        "round_num": 0,
+        "new_arguments": 6,
+        "challenges_raised": 4,
+        "concessions_made": 0,
+        "agreement_score": 0.24779613641768966,
+        "agreement_delta": 0.24779613641768966,
+        "unique_issues": 8,
+        "tokens_used": 896,
+        "cost_usd": 0.008960000000000001,
+        "positions_changed": 1
+      },
+      {
+        "round_num": 1,
+        "new_arguments": 6,
+        "challenges_raised": 2,
+        "concessions_made": 0,
+        "agreement_score": 0.4224856503032449,
+        "agreement_delta": 0.17468951388555526,
+        "unique_issues": 4,
+        "tokens_used": 745,
+        "cost_usd": 0.007450000000000001,
+        "positions_changed": 1
+      },
+      {
+        "round_num": 2,
+        "new_arguments": 2,
+        "challenges_raised": 1,
+        "concessions_made": 1,
+        "agreement_score": 0.49914978983499475,
+        "agreement_delta": 0.07666413953174983,
+        "unique_issues": 2,
+        "tokens_used": 1241,
+        "cost_usd": 0.012410000000000001,
+        "positions_changed": 0
+      },
+      {
+        "round_num": 3,
+        "new_arguments": 3,
+        "challenges_raised": 0,
+        "concessions_made": 1,
+        "agreement_score": 0.5746733088536397,
+        "agreement_delta": 0.0755235190186449,
+        "unique_issues": 1,
+        "tokens_used": 1454,
+        "cost_usd": 0.01454,
+        "positions_changed": 0
+      },
+      {
+        "round_num": 4,
+        "new_arguments": 1,
+        "challenges_raised": 0,
+        "concessions_made": 3,
+        "agreement_score": 0.633611109969572,
+        "agreement_delta": 0.05893780111593239,
+        "unique_issues": 0,
+        "tokens_used": 1381,
+        "cost_usd": 0.013810000000000001,
+        "positions_changed": 0
+      }
+    ],
+    "arguments_per_round": [
+      6,
+      6,
+      2,
+      3,
+      1
+    ],
+    "agreement_progression": [
+      0.24779613641768966,
+      0.4224856503032449,
+      0.49914978983499475,
+      0.5746733088536397,
+      0.633611109969572
+    ],
+    "marginal_value": [
+      13.926296165376002,
+      13.083080723296044,
+      3.03516631371273,
+      2.582692703016815,
+      1.1508892187974828
+    ]
+  },
+  {
+    "test_id": "sim_20251230_100119",
+    "task": "Refactor the monolith into microservices",
+    "agents": [
+      "ARCHITECT",
+      "DEV",
+      "MAINTAINER"
+    ],
+    "personas_used": [
+      "Enterprise Architect",
+      "Cloud Native",
+      "Pragmatic Minimalist"
+    ],
+    "total_rounds": 5,
+    "termination_reason": "max_rounds",
+    "final_agreement_score": 0.6020975857005524,
+    "total_tokens": 6145,
+    "total_cost_usd": 0.061450000000000005,
+    "timestamp": "2025-12-30T10:01:19.418781",
+    "duration_seconds": 0.0003027915954589844,
+    "rounds": [
+      {
+        "round_num": 0,
+        "new_arguments": 7,
+        "challenges_raised": 2,
+        "concessions_made": 0,
+        "agreement_score": 0.21906235961694137,
+        "agreement_delta": 0.21906235961694137,
+        "unique_issues": 8,
+        "tokens_used": 1410,
+        "cost_usd": 0.014100000000000001,
+        "positions_changed": 1
+      },
+      {
+        "round_num": 1,
+        "new_arguments": 4,
+        "challenges_raised": 1,
+        "concessions_made": 1,
+        "agreement_score": 0.3745279924008167,
+        "agreement_delta": 0.15546563278387532,
+        "unique_issues": 4,
+        "tokens_used": 1452,
+        "cost_usd": 0.014520000000000002,
+        "positions_changed": 1
+      },
+      {
+        "round_num": 2,
+        "new_arguments": 2,
+        "challenges_raised": 1,
+        "concessions_made": 2,
+        "agreement_score": 0.49082614889689385,
+        "agreement_delta": 0.11629815649607717,
+        "unique_issues": 2,
+        "tokens_used": 1190,
+        "cost_usd": 0.0119,
+        "positions_changed": 0
+      },
+      {
+        "round_num": 3,
+        "new_arguments": 2,
+        "challenges_raised": 1,
+        "concessions_made": 1,
+        "agreement_score": 0.5596567470953212,
+        "agreement_delta": 0.06883059819842735,
+        "unique_issues": 1,
+        "tokens_used": 736,
+        "cost_usd": 0.00736,
+        "positions_changed": 0
+      },
+      {
+        "round_num": 4,
+        "new_arguments": 2,
+        "challenges_raised": 0,
+        "concessions_made": 2,
+        "agreement_score": 0.6020975857005524,
+        "agreement_delta": 0.04244083860523118,
+        "unique_issues": 0,
+        "tokens_used": 1357,
+        "cost_usd": 0.01357,
+        "positions_changed": 0
+      }
+    ],
+    "arguments_per_round": [
+      7,
+      4,
+      2,
+      2,
+      2
+    ],
+    "agreement_progression": [
+      0.21906235961694137,
+      0.3745279924008167,
+      0.49082614889689385,
+      0.5596567470953212,
+      0.6020975857005524
+    ],
+    "marginal_value": [
+      7.9366124795527755,
+      4.5142261211010695,
+      3.498303836101489,
+      5.0112853016090675,
+      1.786594241748203
+    ]
+  }
+]

package/tooling/.automation/benchmarks/benchmark_20251230_100216.json

@@ -0,0 +1,314 @@
+[
+  {
+    "test_id": "sim_20251230_100216",
+    "task": "Design a secure authentication system with OAuth2 and JWT",
+    "agents": [
+      "ARCHITECT",
+      "DEV",
+      "REVIEWER"
+    ],
+    "personas_used": [
+      "Cloud Native",
+      "Security Focused",
+      "Thorough Critic"
+    ],
+    "total_rounds": 5,
+    "termination_reason": "max_rounds",
+    "final_agreement_score": 0.49019387935470854,
+    "total_tokens": 5893,
+    "total_cost_usd": 0.05893,
+    "timestamp": "2025-12-30T10:02:16.339232",
+    "duration_seconds": 0.0005037784576416016,
+    "rounds": [
+      {
+        "round_num": 0,
+        "new_arguments": 7,
+        "challenges_raised": 3,
+        "concessions_made": 0,
+        "agreement_score": 0.23946842194910561,
+        "agreement_delta": 0.23946842194910561,
+        "unique_issues": 8,
+        "tokens_used": 1291,
+        "cost_usd": 0.012910000000000001,
+        "positions_changed": 1
+      },
+      {
+        "round_num": 1,
+        "new_arguments": 3,
+        "challenges_raised": 1,
+        "concessions_made": 1,
+        "agreement_score": 0.3293716905425653,
+        "agreement_delta": 0.0899032685934597,
+        "unique_issues": 4,
+        "tokens_used": 1125,
+        "cost_usd": 0.011250000000000001,
+        "positions_changed": 1
+      },
+      {
+        "round_num": 2,
+        "new_arguments": 2,
+        "challenges_raised": 0,
+        "concessions_made": 1,
+        "agreement_score": 0.40130710727763447,
+        "agreement_delta": 0.07193541673506915,
+        "unique_issues": 2,
+        "tokens_used": 1083,
+        "cost_usd": 0.010830000000000001,
+        "positions_changed": 0
+      },
+      {
+        "round_num": 3,
+        "new_arguments": 3,
+        "challenges_raised": 1,
+        "concessions_made": 2,
+        "agreement_score": 0.4535129062771106,
+        "agreement_delta": 0.05220579899947614,
+        "unique_issues": 1,
+        "tokens_used": 1165,
+        "cost_usd": 0.01165,
+        "positions_changed": 0
+      },
+      {
+        "round_num": 4,
+        "new_arguments": 1,
+        "challenges_raised": 0,
+        "concessions_made": 2,
+        "agreement_score": 0.49019387935470854,
+        "agreement_delta": 0.036680973077597934,
+        "unique_issues": 0,
+        "tokens_used": 1229,
+        "cost_usd": 0.01229,
+        "positions_changed": 0
+      }
+    ],
+    "arguments_per_round": [
+      7,
+      3,
+      2,
+      3,
+      1
+    ],
+    "agreement_progression": [
+      0.23946842194910561,
+      0.3293716905425653,
+      0.40130710727763447,
+      0.4535129062771106,
+      0.49019387935470854
+    ],
+    "marginal_value": [
+      9.600839829195241,
+      4.354695720830753,
+      2.510945676224092,
+      3.8815948411972196,
+      1.1121315954239048
+    ]
+  },
+  {
+    "test_id": "sim_20251230_100216",
+    "task": "Implement a caching layer for the API with Redis",
+    "agents": [
+      "DEV",
+      "REVIEWER",
+      "SECURITY"
+    ],
+    "personas_used": [
+      "Rapid Prototyper",
+      "Mentoring Reviewer",
+      "Rapid Prototyper"
+    ],
+    "total_rounds": 5,
+    "termination_reason": "max_rounds",
+    "final_agreement_score": 0.4806110932047149,
+    "total_tokens": 4080,
+    "total_cost_usd": 0.0408,
+    "timestamp": "2025-12-30T10:02:16.339666",
+    "duration_seconds": 0.00041294097900390625,
+    "rounds": [
+      {
+        "round_num": 0,
+        "new_arguments": 4,
+        "challenges_raised": 3,
+        "concessions_made": 0,
+        "agreement_score": 0.2191275323905167,
+        "agreement_delta": 0.2191275323905167,
+        "unique_issues": 8,
+        "tokens_used": 813,
+        "cost_usd": 0.00813,
+        "positions_changed": 1
+      },
+      {
+        "round_num": 1,
+        "new_arguments": 3,
+        "challenges_raised": 2,
+        "concessions_made": 0,
+        "agreement_score": 0.2900503554649009,
+        "agreement_delta": 0.07092282307438419,
+        "unique_issues": 4,
+        "tokens_used": 909,
+        "cost_usd": 0.00909,
+        "positions_changed": 1
+      },
+      {
+        "round_num": 2,
+        "new_arguments": 4,
+        "challenges_raised": 0,
+        "concessions_made": 2,
+        "agreement_score": 0.37485556301934597,
+        "agreement_delta": 0.0848052075544451,
+        "unique_issues": 2,
+        "tokens_used": 1141,
+        "cost_usd": 0.011410000000000002,
+        "positions_changed": 0
+      },
+      {
+        "round_num": 3,
+        "new_arguments": 2,
+        "challenges_raised": 1,
+        "concessions_made": 1,
+        "agreement_score": 0.4334768125736834,
+        "agreement_delta": 0.05862124955433745,
+        "unique_issues": 1,
+        "tokens_used": 626,
+        "cost_usd": 0.006260000000000001,
+        "positions_changed": 0
+      },
+      {
+        "round_num": 4,
+        "new_arguments": 2,
+        "challenges_raised": 1,
+        "concessions_made": 3,
+        "agreement_score": 0.4806110932047149,
+        "agreement_delta": 0.04713428063103148,
+        "unique_issues": 0,
+        "tokens_used": 591,
+        "cost_usd": 0.00591,
+        "positions_changed": 0
+      }
+    ],
+    "arguments_per_round": [
+      4,
+      3,
+      4,
+      2,
+      2
+    ],
+    "agreement_progression": [
+      0.2191275323905167,
+      0.2900503554649009,
+      0.37485556301934597,
+      0.4334768125736834,
+      0.4806110932047149
+    ],
+    "marginal_value": [
+      11.305381702220378,
+      6.280779131731399,
+      4.248950110030194,
+      5.728773954542132,
+      5.8736764912188075
+    ]
+  },
+  {
+    "test_id": "sim_20251230_100216",
+    "task": "Refactor the monolith into microservices",
+    "agents": [
+      "ARCHITECT",
+      "DEV",
+      "MAINTAINER"
+    ],
+    "personas_used": [
+      "Cloud Native",
+      "Senior Fullstack",
+      "Devops Maintainer"
+    ],
+    "total_rounds": 5,
+    "termination_reason": "max_rounds",
+    "final_agreement_score": 0.4522478003296368,
+    "total_tokens": 3943,
+    "total_cost_usd": 0.03943,
+    "timestamp": "2025-12-30T10:02:16.339945",
+    "duration_seconds": 0.00026607513427734375,
+    "rounds": [
+      {
+        "round_num": 0,
+        "new_arguments": 6,
+        "challenges_raised": 4,
+        "concessions_made": 0,
+        "agreement_score": 0.1356175692422249,
+        "agreement_delta": 0.1356175692422249,
+        "unique_issues": 8,
+        "tokens_used": 544,
+        "cost_usd": 0.00544,
+        "positions_changed": 1
+      },
+      {
+        "round_num": 1,
+        "new_arguments": 3,
+        "challenges_raised": 1,
+        "concessions_made": 1,
+        "agreement_score": 0.2755513560908879,
+        "agreement_delta": 0.13993378684866298,
+        "unique_issues": 4,
+        "tokens_used": 702,
+        "cost_usd": 0.00702,
+        "positions_changed": 1
+      },
+      {
+        "round_num": 2,
+        "new_arguments": 3,
+        "challenges_raised": 1,
+        "concessions_made": 1,
+        "agreement_score": 0.3457996988404968,
+        "agreement_delta": 0.07024834274960895,
+        "unique_issues": 2,
+        "tokens_used": 923,
+        "cost_usd": 0.00923,
+        "positions_changed": 0
+      },
+      {
+        "round_num": 3,
+        "new_arguments": 3,
+        "challenges_raised": 0,
+        "concessions_made": 2,
+        "agreement_score": 0.4094348887759161,
+        "agreement_delta": 0.06363518993541928,
+        "unique_issues": 1,
+        "tokens_used": 1227,
+        "cost_usd": 0.012270000000000001,
+        "positions_changed": 0
+      },
+      {
+        "round_num": 4,
+        "new_arguments": 1,
+        "challenges_raised": 0,
+        "concessions_made": 3,
+        "agreement_score": 0.4522478003296368,
+        "agreement_delta": 0.04281291155372069,
+        "unique_issues": 0,
+        "tokens_used": 547,
+        "cost_usd": 0.00547,
+        "positions_changed": 0
+      }
+    ],
+    "arguments_per_round": [
+      6,
+      3,
+      3,
+      3,
+      1
+    ],
+    "agreement_progression": [
+      0.1356175692422249,
+      0.2755513560908879,
+      0.3457996988404968,
+      0.4094348887759161,
+      0.4522478003296368
+    ],
+    "marginal_value": [
+      20.875322964011488,
+      7.691364485023689,
+      5.094781611588395,
+      2.9636119799137672,
+      2.6108393337060454
+    ]
+  }
+]