gitea-admin/CASAN
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: align all documentation with the new repo structure

Browse Source 
Update agent protocols (.claude/agents, .github/agents), guides, runbooks and READMEs
to the post-restructure layout: .specify/{scripts,tests,security,config,templates,
governance,memory,level5-config} -> packages/casan-harness/...; docs/input +
golden-runs + traceability-map -> apps/okr/domain/...; drop AINative_OKR_CASAN5/ prefix.
Runtime-state paths (.specify/logs, .specify/agentops, .specify/level5/central-governance)
kept as-is. Historical evidence under docs/output/ left untouched (immutable run records).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
thanhnv
2026-07-08 14:36:27 +09:00
co-authored by Claude Opus 4.8
parent 36a4812ef3
commit 18997caf49
53 changed files with 167 additions and 167 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude/agents/protocols/casan-harness-protocol.md
+10 -10
View File
@@ -10,38 +10,38 @@ Raise the SDD Speckit OKR pipeline from CASAN Level 3 to Level 4 by making Secur
| Harness | Runtime control | Script | Evidence |
|---|---|---|---|
| H4 Security | Prompt injection block, PII masking, secret redaction, output filtering | `.specify/scripts/bash/security-check.sh` | `.specify/logs/trace/security-*.json`, `.specify/logs/audit/security.jsonl` |
| H5 Governance | Risk scoring, non-interactive approval policy, append-only hash-chain audit | `.specify/scripts/bash/governance-check.sh` | `.specify/logs/trace/governance-*.json`, `.specify/logs/audit/audit.jsonl` |
| H6 AgentOps | Latency, retry, token, cost, status, alert tracking | `.specify/scripts/bash/agent-metrics.sh` | `.specify/logs/trace/agentops-*.json`, `.specify/logs/cost/metrics.jsonl`, `.specify/agentops/alerts.log` |
| H2 Tool Registry | Side-effect registry, idempotency key, per-call audit | `.specify/scripts/bash/tool-registry-gate.sh` | `.specify/logs/level5/tool-registry.jsonl`, `.specify/logs/audit/tool-calls.jsonl` |
| H4 Security | Prompt injection block, PII masking, secret redaction, output filtering | `packages/casan-harness/scripts/bash/security-check.sh` | `.specify/logs/trace/security-*.json`, `.specify/logs/audit/security.jsonl` |
| H5 Governance | Risk scoring, non-interactive approval policy, append-only hash-chain audit | `packages/casan-harness/scripts/bash/governance-check.sh` | `.specify/logs/trace/governance-*.json`, `.specify/logs/audit/audit.jsonl` |
| H6 AgentOps | Latency, retry, token, cost, status, alert tracking | `packages/casan-harness/scripts/bash/agent-metrics.sh` | `.specify/logs/trace/agentops-*.json`, `.specify/logs/cost/metrics.jsonl`, `.specify/agentops/alerts.log` |
| H2 Tool Registry | Side-effect registry, idempotency key, per-call audit | `packages/casan-harness/scripts/bash/tool-registry-gate.sh` | `.specify/logs/level5/tool-registry.jsonl`, `.specify/logs/audit/tool-calls.jsonl` |
## Mandatory Gate Pattern
Before every delegated step:
```bash
.specify/scripts/bash/security-check.sh "$STEP_INPUT" "$SAFE_INPUT" input
.specify/scripts/bash/governance-check.sh "$SAFE_INPUT" "$APPROVED_INPUT" "$ACTION_NAME"
packages/casan-harness/scripts/bash/security-check.sh "$STEP_INPUT" "$SAFE_INPUT" input
packages/casan-harness/scripts/bash/governance-check.sh "$SAFE_INPUT" "$APPROVED_INPUT" "$ACTION_NAME"
```
Around every execution or agent/tool invocation:
```bash
CASAN_AGENT_NAME="<agent>" CASAN_STEP_NAME="<step>" \
.specify/scripts/bash/agent-metrics.sh "$APPROVED_INPUT" "$RAW_OUTPUT" -- <real command>
packages/casan-harness/scripts/bash/agent-metrics.sh "$APPROVED_INPUT" "$RAW_OUTPUT" -- <real command>
```
After every generated artifact or agent response:
```bash
.specify/scripts/bash/security-check.sh "$RAW_OUTPUT" "$FINAL_OUTPUT" output
packages/casan-harness/scripts/bash/security-check.sh "$RAW_OUTPUT" "$FINAL_OUTPUT" output
```
When a step can be represented as a single command, Boss MAY use the wrapper:
```bash
CASAN_AGENT_NAME="<agent>" CASAN_STEP_NAME="<step>" \
.specify/scripts/bash/casan-harness.sh "$STEP_INPUT" "$FINAL_OUTPUT" "$ACTION_NAME" -- <real command>
packages/casan-harness/scripts/bash/casan-harness.sh "$STEP_INPUT" "$FINAL_OUTPUT" "$ACTION_NAME" -- <real command>
```
Cache hits MUST NOT bypass CASAN evidence. A cached wrapper run still has to produce fresh H4 input, H5 governance, H6 metrics, and H4 output traces for the current execution.
@@ -105,4 +105,4 @@ Boss orchestrator also enforces:
1. **Self-Security Audit:** Every agent reads `protocols/agent-self-security-rules.md` before output is accepted.
2. **Self-Governance Audit:** Every agent reads `protocols/governance-risk-policy.md` before high-risk action planning.
3. **Hallucination Checklist:** Every review agent reads `protocols/hallucination-prevention-checklist.md` during review gates.
4. **Tool Registry Policy:** Every side-effecting tool is checked against `protocols/tool-registry-policy.md` and `.specify/level5/tool-registry.yaml`.
4. **Tool Registry Policy:** Every side-effecting tool is checked against `protocols/tool-registry-policy.md` and `packages/casan-harness/level5/tool-registry.yaml`.