Files
CASAN/packages/casan-devkit/templates/claude/README.md
T
thanhnvandClaude Opus 4.8 4bb184b935 feat(harness): implement Plan-20 transparent agentic client bridge
Wave 0 + Wave 1 core of the transparent agentic-client integration: a
developer types prompts normally in Claude Code / Codex while every
certified turn still carries a full H1->H7 trace and an H6 record.

- agentic_bridge.py: stdlib-only lifecycle state machine (begin/pre-tool/
  post-tool/telemetry/finalize/abort + report/doctor). Single-model
  invariant (never calls a model), fail-closed at the side-effect point,
  admission TTL + canonical-project/session binding, atomic state under
  .specify/state/agentic-sessions/, secret redaction, null-not-zero H6.
- agentic-lifecycle.schema.json: client-agnostic JSON contract.
- adapters/claude-code + adapters/codex: thin hook renderers + config
  templates that call the core bridge.
- phase-agentic-bridge-tests.sh: C1-C12 acceptance + threat suite (30/30).
- devkit templates/{claude,codex} + windows/install-agentic.ps1
  (install/doctor/uninstall with manifest, path-safe).
- docs/casan Windows + security/bypass guides; plan status -> IMPLEMENTED.
- harden generate-agentops-dashboard.py aggregation against null H6 costs.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-23 20:44:07 +07:00

37 lines
1.8 KiB
Markdown

# CASAN Claude Code adoption template (Plan-20)
Drop `settings.json` into the target repo as `.claude/settings.json` (the
installer does this). It wires the four Claude Code lifecycle hooks
(`UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `Stop`) to the CASAN agentic
bridge so a developer can type prompts normally while every certified turn still
carries an H1→H7 trace and an H6 record.
- The hook command resolves the repo root via `$CLAUDE_PROJECT_DIR`, so **no
machine-specific path is committed**.
- It invokes `packages/casan-harness/adapters/claude-code/claude_hook.py`, a thin
renderer that calls the core bridge. The bridge **never runs a model** — Claude
remains the sole model executor (single-model invariant).
- This is a **`project_hook`** integration: strong for a trusted project, but a
member who can edit `.claude/settings.json` can disable it. For organization
enforcement use a managed/pinned deployment (`managed_hook`) — see
`docs/casan/CASAN_AGENTIC_CLIENT_SECURITY.md`.
## Install (cross-platform)
```bash
packages/casan-devkit/install.sh --target <repo> --project <id>
# then enable the agentic client hooks:
cp packages/casan-devkit/templates/claude/settings.json <repo>/.claude/settings.json
```
Windows: use `packages/casan-devkit/windows/install-agentic.ps1 -Client claude`.
## Feature flags (environment)
| Variable | Default | Meaning |
|---|---|---|
| `CASAN_AGENTIC_BRIDGE_ENABLED` | `1` | Master on/off. |
| `CASAN_AGENTIC_ENFORCEMENT_MODE` | `observe` | `observe` (telemetry-only, never certified) → `enforce` (gates + certification). |
| `CASAN_AGENTIC_INTEGRATION_MODE` | `project_hook` | `project_hook` / `managed_hook` / `casan_owned`. |
| `CASAN_AGENTIC_CLIENT_ALLOWLIST` | (unset) | Comma list; clients outside it are `observed_only`. |