---ci---
phase: 5
milestone: v0.10
status: execute
decisions:
- id: MULTI-03
decision: Parallel project execution via OrchestratorAgent.runForAllProjects
rationale: Sequential by default, parallel when parallelization.enabled with max_concurrent_projects limit
confidence: 0.85
alternatives: [single-project-only, manual-iteration]
- id: MULTI-05
decision: ideate --project all iterates all active_projects with deduplication
rationale: Each project gets its own IdeationEngine; ideas deduplicated by project:title key
confidence: 0.90
alternatives: [single-project-only, merge-all-ideas]
- id: MULTI-07
decision: project field in ---ci--- commit blocks and CommitScope for multi-project tracking
rationale: CIAgentMetadata.project and CommitScope.project fields propagated through all commit builders
confidence: 0.92
alternatives: [separate-repos-only, branch-prefix-only]
requirements:
covered: [MULTI-03, MULTI-05, MULTI-07]
partial: []
---/ci---
- Add max_concurrent_projects to ParallelizationConfig (default: 3)
- Add AgentContext.project_slug optional field for multi-project pipeline tracking
- Implement OrchestratorAgent.runForProject() for single-project execution
- Implement OrchestratorAgent.runForAllProjects() for multi-project iteration
- Sequential execution by default
- Parallel when parallelization.enabled with limitConcurrency batching
- Add --project flag to createRunCommand for targeted project execution
- --project all triggers multi-project pipeline
- --project slug1,slug2 for comma-separated projects
- Enhance createIdeateCommand --project all support
- Iterates all active projects from config
- Deduplicates findings by project:title key
- Per-project idea acceptance via separate IdeationEngine instances
- Markdown table output for multi-project results
- Propagate project slug through orchestrator pipeline commits
- Specify stage: project field in CIAgentMetadata init commit
- Ideate stage: project field in task commit via buildTaskCommit
- Orchestrator sets ciFiles with project slug for per-project .ciagent dirs
- 19 new tests covering MULTI-03, MULTI-05, MULTI-07 functionality
- All 561 tests pass, typecheck clean
---ci---
project: ci
phase: 1
milestone: v0.8
status: in_progress
decisions:
- id: D-022
decision: Validate BackendResult at boundary with Zod schema
rationale: External backend output is untrusted; runtime validation prevents corrupt commit streams
confidence: 0.92
- id: D-023
decision: opencode parseResult returns success:false on malformed JSON
rationale: Silent success:true on parse failure masks backend errors; fail loudly instead
confidence: 0.95
requirements:
covered: [FIX-02, FIX-03]
---/ci---
FIX-02: Add Zod BackendResultSchema and validateBackendResult() in
backends/types.ts. backendResultToAgentResult() in base.ts now validates
before passing through. Invalid results produce success:false with error
detail. Path traversal protection: artifact paths with '..' or leading '/'
are rejected.
FIX-03: opencode.ts parseResult() no longer defaults to success:true when
JSON parsing fails entirely. Both the inner parse error and the no-JSON
match case now return emptyBackendResult() with descriptive error messages.
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.
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/)
Jon Chery