Files

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

1.8 KiB

Raw Blame History

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)

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`.

1.8 KiB Raw Blame History

CASAN Claude Code adoption template (Plan-20)

Install (cross-platform)

Feature flags (environment)

1.8 KiB

Raw Blame History