continuous-intelligence/ci
2
0
Fork 0
Code Issues Pull Requests 3 Actions Packages Projects Releases 29 Wiki Activity
37 Commits 4 Branches 29 Tags
8e50049ba52f27a6aaa005cbd527fadce66e41d4
Commit Graph

8 Commits

Author SHA1 Message Date
Jon Chery 8e50049ba5 feat(P01): add ideation engine + ciagent ideate command — IDEATE-01,02,03,17 + MULTI-01 
---ci---
phase: 1
milestone: v0.10
status: execute
decisions:
  - id: D-080
    decision: Three-tier ideation (mechanical, backend-enriched, cross-project)
    rationale: Mechanical tier always produces output without backend
    confidence: 0.92
  - id: D-089
    decision: No separate codebase map command
    rationale: Git-native + .ciagent/ covers mapping; avoids tree-sitter dep
    confidence: 0.88
requirements:
  covered:
    - IDEATE-01
    - IDEATE-02
    - IDEATE-03
    - IDEATE-17
    - MULTI-01
---/ci---

Add IdeationEngine core module with 15 signal collectors:
- Uncovered/partial requirements from REQUIREMENTS.md
- Coverage gaps (documented but unimplemented agents)
- Repeated lessons from git history
- Low-confidence decisions from ---ci--- blocks
- Escalation patterns from git history
- Compound solution patterns
- Architecture drift (ARCHITECTURE.md vs src/)
- Verification inversion (missing test files)
- Improvement patterns (cross-referencing lessons + requirements)
- Spec ambiguity (should/could/might patterns)
- Spec missing (common requirement categories)
- Cascade impact (--affected from git diff)
- External signals (npm audit, dependency staleness)
- Cross-project lesson mining

Add ciagent ideate CLI command with flags:
--category, --affected, --spec, --external, --cross-project, --output

Add active_projects to CIAgentConfig (backwards compatible with active_project).
Add IDEATE pipeline stage between RESEARCH and PLAN.
Update IdeationAgent to delegate to IdeationEngine.

533 tests passing.
 2026-05-30 20:13:43 +00:00
Jon Chery a8b50f5109 feat(ci): v0.9.0 — Distribution & Expansion milestone complete
CI / build-and-test (push) Has been cancelled
Details
Publish to npm / publish (push) Has been cancelled
Details 
---ci---
project: ci
phase: 6
milestone: v0.9
status: complete
artifacts:
  tags: [v0.9.0]
decisions:
  - id: D-047
    decision: v0.9 theme = Distribution & Expansion
    rationale: npm publish + OpenAI/Anthropic backends + agent flesh + parallel execution
    confidence: 0.92
  - id: D-049
    decision: Feature milestone — patch tags v0.8.1-v0.8.6 then v0.9.0
    rationale: OpenAI backend, agent flesh, npm publish all feat
    confidence: 0.95
  - id: D-059
    decision: Rename OllamaBaseBackend to LLMBaseBackend + thin OllamaBaseBackend subclass
    rationale: 15 of 17 methods backend-agnostic
    confidence: 0.92
  - id: D-060
    decision: OpenAI/Anthropic backends use native fetch() not SDK packages
    rationale: No dependency bloat; fetch native in Node 18+
    confidence: 0.85
  - id: D-066
    decision: Concurrency limiter internal (no p-limit dependency)
    rationale: 15 lines; avoids dependency for trivial feature
    confidence: 0.90
  - id: D-067
    decision: Promise.allSettled for review agents at orchestrator lines 373-400
    rationale: Current sequential loop replaced with parallel execution
    confidence: 0.88
requirements:
  covered: [PUBLISH-01, PUBLISH-02, PUBLISH-03, PUBLISH-04, OPENAI-01, OPENAI-02, OPENAI-03, OPENAI-04, OPENAI-05, FLESH-01, FLESH-02, FLESH-03, FLESH-04, FLESH-05, ANTHROPIC-01, ANTHROPIC-02, FLESH-06, FLESH-07, NPM-01, NPM-02, PARALLEL-01, PARALLEL-02, PARALLEL-03, INTEG-01, INTEG-02, INTEG-03, INTEG-04, INTEG-05]
---/ci---

6 phases, 28 tasks, 4077 net lines added, 57 test suites, 527 tests, zero stub agents
 2026-05-30 02:19:44 +00:00
Jon Chery e8c6c5c917 feat(P05): ship infrastructure — Gitea API client, release notes, npm publishConfig, ciagent projects cmd, --project flag 
---ci---
phase: 5
milestone: v1.0
plan: 05
task: SHIP-01-04 MULTI-01 MULTI-02
status: execute
---/ci---
 2026-05-29 18:15:58 +00:00
Jon Chery 4a58aa1657 refactor(rebrand): rename & rebrand CI → CIAgent across all source and test files 
- Type renames: CIConfig → CIAgentConfig, DEFAULT_CI_CONFIG → DEFAULT_CIAGENT_CONFIG
- Type renames: CiMetadata → CIAgentMetadata, ParsedCiCommit → ParsedCIAgentCommit
- Function renames: initCI → initCIAgent, isCIInitialized → isCIAgentInitialized
- Function renames: extractCiBlock → extractCIAgentBlock, parseCiBlock → parseCIAgentBlock
- Class renames: CiFiles → CIAgentFiles
- Import paths: ci-files.js → ciagent-files.js
- Directory paths: .ci/ → .ciagent/ across all source and test files
- Check names: ".ci directory exists" → ".ciagent directory exists"
- Check names: "CI config valid" → "CIAgent config valid"
- Temp dir names: ci-*-test- → ciagent-*-test-
- CLI examples: "ci init" → "ciagent init"
- Fix deepMerge infinite recursion bug in config.ts
- ---ci---/---/ci--- block markers preserved unchanged
- All 31 test suites, 370 tests passing

---ci---
phase: 1
milestone: v0.5
plan: 07
task: 07-01-01
status: execute
---/ci---
 2026-05-29 18:01:13 +00:00
Jon Chery ab6af144b7 feat(P06): 3-tier versioning, branch hierarchy enforcement, ARCHITECTURE-PLAN synthesis 
---ci---
phase: 6
milestone: v0.5
status: complete
decisions:
  - id: D-006
    decision: Research as intermediate work product
    rationale: Conclusions update .ci/ files; full research doc intentionally not preserved
    confidence: 0.90
  - id: D-007
    decision: Branch hierarchy enforcement: main > milestone > phase
    rationale: Prevents out-of-order merges and semantically wrong tags
    confidence: 0.92
  - id: D-008
    decision: 3-tier versioning: NFR/feature/schema-breaking
    rationale: Patch per phase (NFR/feature) or minor per phase (schema-breaking); milestone gets minor (feature) or major (schema-breaking)
    confidence: 0.95
requirements:
  covered: [VER-06, BRANCH-01, BRANCH-02, ARCH-01]
---/ci---

- Synthesize ARCHITECTURE-PLAN.md into .ci/ci/ARCHITECTURE.md (expanded 51→230 lines)
- Add D-006/D-007/D-008 to .ci/ci/PROJECT.md key decisions table
- Delete ARCHITECTURE-PLAN.md after synthesis
- Rewrite ship.md with 3-tier versioning model + branch hierarchy merge flows
- Rewrite branch-strategy.md with 3-tier versioning + branch hierarchy + version validation
- Add MilestoneType to config types
- Replace isNfrMilestone() with getMilestoneType() returning nfr|feature|schema-breaking
- Add validateMergeOrder(), mergeMilestoneBranch(), computeMilestoneTag() to GitBranch
- Add computeShipVersion(), validateVersionOrder(), resolveMergeTarget() to ship command
- Remove hardcoded v0.5. from error-recovery rollback
- Create .githooks/pre-push for semver ordering + branch hierarchy validation
- Add 15 new tests (370 total, all passing)
 2026-05-29 17:18:10 +00:00
CI 940b85bfae feat(backends): multi-backend intelligence layer — LLM + Agent backends, persona-loading agents, honest CLI commands 
Add IntelligenceBackend abstraction with two categories:
- LLMBackend (OllamaLocal, OllamaCloud): CI runs tool loop, provides tools, constructs prompts
- AgentBackend (Opencode): agent runs own tool loop, CI serializes request

Refactor all 18 agents from hardcoded stubs to persona loaders that delegate
to the active backend or fail honestly when no backend is available.

Refactor OrchestratorAgent.executeStage() from monolithic switch to agent
delegation via STAGE_AGENT_MAP for intelligent stages (research, plan, execute,
verify), with mechanical stages (specify, clarify, complete) staying inline.

Wire CLI commands with --backend flag and auto-detection (opencode →
ollama-local → ollama-cloud). Harden rollback/ship with real git operations.
No command returns fake success.
 2026-05-29 15:58:34 +00:00
CI ddf04792c7 feat(P03): multi-project support, NFR milestone versioning, phase context reset, install scripts (v0.3.0) 2026-05-29 15:13:45 +00:00
CI 9cf5c000d9 feat: implement CI (Continuous Intelligence) autonomous engineering harness 
Implements the full PRD for CI - a fully autonomous AI-driven software
engineering harness derived from Learnship's architecture.

Core components:
- CI Orchestrator agent with autonomous pipeline (SPECIFY → CLARIFY →
  RESEARCH → PLAN → EXECUTE → VERIFY → COMPLETE)
- Decision Engine with confidence thresholds (high/medium/low)
- Clarify Phase with question budget and default acceptance
- Escalation Protocol with timeout auto-proceed
- Audit Trail system (.ci/audit/) for post-hoc review
- Error Recovery with retry, plan revision, and rollback

18 agents (all Learnship agents + Orchestrator):
- Autonomous behavioral modifications per PRD §7.1
- Agent registry with factory pattern

11 CLI commands:
- ci init, ci run, ci quick, ci debug, ci verify
- ci review, ci status, ci audit, ci clarify
- ci rollback, ci ship

4-layer verification system:
- Structural, Behavioral, Security, Code Quality

3 autonomy levels: full, supervised, guided
Compatible with Learnship artifact schemas (.planning/)
 2026-05-28 23:24:42 +00:00