Commit graph

8 commits

Author SHA1 Message Date
Eric Garcia
b8337c43a2 feat: RFC 0057 Judge Convergence Discipline (Phases 1-7)
Fixes convergence discipline with four core changes:

1. Velocity redefined: velocity = open_tensions + new_perspectives
   (work remaining, not score delta)

2. Unanimous convergence: 100% of experts must signal [MOVE:CONVERGE]

3. Both conditions required: velocity=0 AND converge=100%

4. Dialogues persist: stored in .blue/dialogues/<ISO>-<name>/

Database schema updates:
- Added score component columns (W/C/T/R breakdown)
- Added convergence tracking columns
- Created alignment_convergence_signals table
- Created alignment_scoreboard view

MCP tool updates:
- round_register accepts new metrics
- round_context returns convergence status
- verdict_register gates on convergence criteria
- dialogue_create outputs to .blue/dialogues/
- dialogue_export includes full scoreboard

Judge protocol updated with new scoreboard format and max_rounds=10.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-03 10:08:00 -05:00
Eric Garcia
49ac8f7a78 feat: RFC 0051 Phase 2-5 implementation
Phase 2 (MCP Tools):
- blue_dialogue_round_context - bulk fetch context for prompt building
- blue_dialogue_expert_create - create experts mid-dialogue
- blue_dialogue_round_register - bulk register perspectives, tensions, refs
- blue_dialogue_verdict_register - register interim/final/minority verdicts
- blue_dialogue_export - export dialogue to JSON with provenance

Phase 2c (Validation Layer):
- ValidationError struct with code, message, field, suggestion, context
- ValidationCollector for batch error collection
- Semantic constraints: resolve/address/reopen → Tension, refine → same-type
- validate_round_register_inputs() returns all errors before DB operations
- 8 new validation tests (20 total alignment_db tests)

Phase 5 (Skills):
- Updated alignment-play skill with DB-backed workflow
- Two-phase ID system documentation
- Cross-references alignment-expert skill for marker syntax

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-02 17:15:52 -05:00
Eric Garcia
401a6b1a45 feat: RFC 0051 Phase 1 - global perspective & tension tracking schema
RFC 0051 accepted and initial implementation:

- Added alignment_dialogues, alignment_experts, alignment_rounds tables
- Added alignment_perspectives, alignment_tensions with event tracking
- Added alignment_recommendations, alignment_evidence, alignment_claims
- Added alignment_refs table for cross-entity references
- Added alignment_verdicts table for final/interim/minority verdicts
- Created alignment_db.rs module with database operations
- Created alignment-expert skill with marker syntax reference

Schema version bumped from 8 to 9.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-02 15:13:41 -05:00
Eric Garcia
47edb7509f feat: RFC 0050 graduated panel rotation implementation
Judge-driven panel evolution for alignment dialogues:

- Add `Graduated` as default rotation mode
- New `blue_dialogue_evolve_panel` tool for panel specification
- Panel sampling is now a suggestion (`suggested_panel`) not mandate
- Judge can override Round 0 panel before spawning agents
- Fresh experts (pool/created) get automatic context briefs
- Support for on-demand expert creation with focus areas
- Track panel history with source counts (retained/pool/created)

Key workflow changes:
- Phase 1: Review suggested panel, override if needed
- Phase 2+: Evolve panel based on dialogue dynamics
- `expert_source` param in round_prompt for context brief generation

Updates skill documentation with graduated rotation guidelines and
7 key rules including "REVIEW THE SUGGESTED PANEL".

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-02 08:08:31 -05:00
Eric Garcia
d7db9c667d feat: RFC 0048 expert pool implementation and documentation batch
## RFC 0048 Expert Pool Implementation
- Added tiered expert pools (Core/Adjacent/Wildcard) to dialogue handlers
- Implemented weighted random sampling for panel selection
- Added blue_dialogue_sample_panel MCP tool for manual round control
- Updated alignment-play skill with pool design instructions

## New RFCs
- 0044: RFC matching and auto-status (draft)
- 0045: MCP tool enforcement (draft)
- 0046: Judge-defined expert panels (superseded)
- 0047: Expert pool sampling architecture (superseded)
- 0048: Alignment expert pools (implemented)
- 0050: Graduated panel rotation (draft)

## Dialogues Recorded
- 2026-02-01T2026Z: Test expert pool feature
- 2026-02-01T2105Z: SQLite vs flat files
- 2026-02-01T2214Z: Guard command architecture

## Other Changes
- Added TODO.md for tracking work
- Updated expert-pools.md knowledge doc
- Removed deprecated alignment-expert agent
- Added spikes for SQLite assets and SDLC workflow gaps

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-01 19:26:41 -05:00
Eric Garcia
71c3d3caa9 chore: dialogue handler improvements and config updates
- blue-mcp: dialogue handler enhancements (280+ lines)
- blue-mcp: server updates
- config.yaml updates
- alignment-play skill tweak
- spike: expert context and archival simplification

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-30 19:05:53 -05:00
Eric Garcia
02901dfec7 chore: batch commit - ADRs, RFCs, dialogues, spikes, and code updates
ADRs:
- Update 0008-honor, 0009-courage, 0013-overflow, 0015-plausibility
- Add 0017-hosted-coding-assistant-architecture

RFCs:
- 0032: per-repo AWS profile configuration (draft)
- 0033: round-scoped dialogue files (impl + plan)
- 0034: comprehensive config architecture (accepted)
- 0036: expert output discipline (impl)
- 0037: single source protocol authority (draft)
- 0038: SDLC workflow discipline (draft)
- 0039: ADR architecture greenfield clarifications (impl)
- 0040: divorce financial analysis (draft)
- 0042: alignment dialogue defensive publication (draft)

Spikes:
- Read tool token limit on assembled dialogues
- RFC ID collision root cause
- Expert agent output too long
- Judge writes expert outputs
- Blue MCP server on superviber infrastructure
- Playwright MCP multiple window isolation

Dialogues: 16 alignment dialogue records

Code:
- blue-core: forge module enhancements
- blue-mcp: env handlers and server updates
- alignment-expert agent improvements
- alignment-play skill refinements
- install.sh script

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-30 16:28:31 -05:00
Eric Garcia
a5b142299d feat: context injection architecture via 12-expert alignment dialogue
RFC 0016 drafted from alignment dialogue achieving 95% convergence:
- Three-tier model: Identity (fixed) / Workflow (session) / Reference (on-demand)
- Manifest-driven injection via .blue/context.manifest.yaml
- URI addressing: blue://docs/, blue://context/, blue://state/
- Hooks push URIs, MCP resolves content
- Progressive visibility: blue context show

New ADRs ported from coherence-mcp:
- 0014: Alignment Dialogue Agents (renamed from 0006)
- 0015: Plausibility
- 0016: You Know Who You Are

Knowledge injection system:
- hooks/session-start for SessionStart injection
- knowledge/*.md files for global context
- Expert pools with domain-specific relevance tiers
- Updated /alignment-play skill with full scoring

Spikes completed:
- Context injection mechanisms (7 mechanisms designed)
- ADR porting inventory (17 Blue ADRs mapped)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-25 16:16:11 -05:00