2dabf8ef03
Phase 1-3: Add memory, skills, and improvement systems
...
- memory/: cross-session project memory with decisions, lessons, failures,
architecture, and sessions categories. Each has format templates and
lifecycle documentation.
- skills/: 12 reusable specialized methodologies (tdd, systematic-debugging,
architecture-design, code-review, security-review, repository-analysis,
failure-analysis, refactoring, test-analysis, incident-investigation,
browser-automation, research). Each has frontmatter and methodology sections.
- improvements/: proposal-based improvement system requiring human approval.
- scripts/memory-lifecycle.sh: deterministic memory operations (recall, store,
list, search, sessions, cleanup).
- scripts/test-memory-system.sh: 12 structural tests for all new systems.
- orchestrator.md: added Memory Recall stage, Learning and Memory Storage
stage, Improvement Proposals workflow, memory/skills rules, and 3 new
actions (A23-A27) to the action catalog. Updated behavioral acceptance test
and state separation model.
- All 12 subagents: added Memory & Skills Awareness sections with recall
and store instructions.
- docs/AGENT_ARCHITECTURE.md: documented memory, skills, and improvements
systems (sections 12-14). Updated action count (27), state model, and
remaining weaknesses.
- README.md: documented new systems, updated repository layout, added
test-memory-system.sh documentation.
All 39 tests pass (16 architecture + 12 memory + 11 bootstrap).
2026-09-08 04:31:40 -04:00
fb9d91e510
Add adaptive, evidence-driven architecture upgrade: decision-loop orchestrator, action catalog, evidence-state handoffs, process quality, stop conditions
...
- Orchestrator: linear flow replaced by adaptive decision loop
(UNDERSTAND→ESTIMATE→LOAD CONTEXT→CHOOSE ACTION→EXECUTE→VERIFY→RE-PLAN/STOP→LEARN)
- New sections: Task Complexity Estimation (ESTIMATE→EXECUTE→EXPAND),
Action Catalog with 24 tool-card actions, Evidence-First State and Handoff
Discipline (9-field state records, state separation, long-horizon persistence),
Process Quality anti-patterns, Cost and Token Awareness, Stop Conditions,
adaptive planning + failure recovery (7 failure types), lightweight quality gates
- All 13 agents preserved; 12 subagents gain role-adapted Evidence & Handoffs
sections (evidence product, stop, escalation) after Repository Intelligence
- Repository Intelligence Bootstrap extended with Knowledge Lifecycle rules;
.opencode structure unchanged (knowledge/state dirs intentionally not added)
- New docs: AGENT_ARCHITECTURE.md (full architecture incl. simple/complex
execution traces, ownership table, weaknesses) and EVALUATION_SCENARIOS.md
(12 runtime scenarios + scoring rubric)
- New test: scripts/test-agent-architecture.sh (16 structural checks)
- Validation: 16/16 architecture tests PASS, 11/11 bootstrap tests PASS,
install 13/13 + permission verifier PASS, live config synced byte-identical
2026-09-07 12:53:30 -04:00
c1f5f939ad
Add Repository Intelligence Bootstrap: repo-bootstrap.sh, all 13 agents updated, docs, tests
...
- scripts/repo-bootstrap.sh: generic idempotent bootstrap tool (status/bootstrap/refresh)
- creates .opencode/ with repo-context, architecture, build-and-test, conventions, deployment skills
- relevance-based skill generation (only creates what the repo actually has)
- staleness detection via .bootstrap-meta (key=value, SHA-256 fingerprints)
- marker-based manual protection (never overwrites unmarked files)
- accepts --root flag for explicit repo targeting
- scripts/test-repo-bootstrap.sh: 11 tests covering all 10 acceptance criteria
- creation, idempotency, manual preservation, relevance detection
- orchestrator/agent structural checks, staleness, genericness
- install.sh workflow compatibility, malformed handling
- agents/orchestrator.md: first-class Repository Intelligence Bootstrap stage
- 10-step workflow, ownership rules table, staleness signals
- consumption rules, backward compatibility, fallback procedure
- All 12 subagent files: role-adapted Repository Intelligence section
- architect: owns architecture skill
- builder/tester: own build-and-test skill (shared)
- explorer: owns repo-context skill
- maintainer: owns conventions skill + audits .opencode/
- reviewer: validates consistency (consumer/reporter)
- designer/detective/philosopher/toolsmith/workflow-architect/writer: consume-only
- docs/REPOSITORY_INTELLIGENCE.md: full architecture documentation
- README.md: updated layout, bootstrap usage, requirements
- 13/13 agents installed, permission-engine verifier PASS
2026-09-07 12:10:25 -04:00
36caa15959
Unify all agent write permissions; reconcile read-only prompt text
...
All 13 agents now use a uniform writable permission model
(edit: allow, bash: allow) so every agent can persist its deliverables
and artifacts instead of being sandbox-denied on project writes.
Orchestrator retains task: allow for dispatching.
Reconciled the three agents (explorer, detective, reviewer) that still
carried a 'Hard Read-Only Boundary' and read-only role-fence wording
which contradicted the new permissions and caused self-censoring:
rewritten as role fences (investigate/diagnose/review != implement/fix),
keeping the report IS the deliverable boundary and UNVERIFIED handoff.
Builder/tester/maintainer were already writable and unchanged.
2026-09-07 07:30:00 -04:00
Your Name