Files
AutoGPT/autogpt_platform/backend/backend/copilot/sdk/env.py
Zamil Majdy f115607779 fix(copilot): recognize Agent tool name and route CLI state into workspace (#12635)
### Why / What / How

**Why:** The Claude Agent SDK CLI renamed the sub-agent tool from
`"Task"` to `"Agent"` in v2.x. Our security hooks only checked for
`"Task"`, so all sub-agent security controls were silently bypassed on
production: concurrency limiting didn't apply, and slot tracking was
broken. This was discovered via Langfuse trace analysis of session
`62b1b2b9` where background sub-agents ran unchecked.

Additionally, the CLI writes sub-agent output to `/tmp/claude-<uid>/`
and project state to `$HOME/.claude/` — both outside the per-session
workspace (`/tmp/copilot-<session>/`). This caused `PermissionError` in
E2B sandboxes and silently lost sub-agent results.

The frontend also had no rendering for the `Agent` / `TaskOutput` SDK
built-in tools — they fell through to the generic "other" category with
no context-aware display.

**What:**
1. Fix the sub-agent tool name recognition (`"Task"` → `{"Task",
"Agent"}`)
2. Allow `run_in_background` — the SDK handles async lifecycle cleanly
(returns `isAsync:true`, model polls via `TaskOutput`)
3. Route CLI state into the workspace via `CLAUDE_CODE_TMPDIR` and
`HOME` env vars
4. Add lifecycle hooks (`SubagentStart`/`SubagentStop`) for
observability
5. Add frontend `"agent"` tool category with proper UI rendering

**How:**
- Security hooks check `tool_name in _SUBAGENT_TOOLS` (frozenset of
`"Task"` and `"Agent"`)
- Background agents are allowed but still count against `max_subtasks`
concurrency limit
- Frontend detects `isAsync: true` output → shows "Agent started
(background)" not "Agent completed"
- `TaskOutput` tool shows retrieval status and collected results
- Robot icon and agent-specific accordion rendering for both foreground
and background agents

### Changes 🏗️

**Backend:**
- **`security_hooks.py`**: Replace `tool_name == "Task"` with `tool_name
in _SUBAGENT_TOOLS`. Remove `run_in_background` deny block (SDK handles
async lifecycle). Add `SubagentStart`/`SubagentStop` hooks.
- **`tool_adapter.py`**: Add `"Agent"` to `_SDK_BUILTIN_ALWAYS` list
alongside `"Task"`.
- **`service.py`**: Set `CLAUDE_CODE_TMPDIR=sdk_cwd` and `HOME=sdk_cwd`
in SDK subprocess env.
- **`security_hooks_test.py`**: Update background tests (allowed, not
blocked). Add test for background agents counting against concurrency
limit.

**Frontend:**
- **`GenericTool/helpers.ts`**: Add `"agent"` tool category for `Agent`,
`Task`, `TaskOutput`. Agent-specific animation text detecting `isAsync`
output. Input summaries from description/prompt fields.
- **`GenericTool/GenericTool.tsx`**: Add `RobotIcon` for agent category.
Add `getAgentAccordionData()` with async-aware title/content.
`TaskOutput` shows retrieval status.
- **`useChatSession.ts`**: Fix pre-existing TS error (void mutation
body).

### Checklist 📋

#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] All security hooks tests pass (background allowed + limit
enforced)
  - [x] Pre-commit hooks (ruff, black, isort, pyright, tsc) all pass
  - [x] E2E test: copilot agent create+run scenario PASS
- [ ] Deploy to dev and test copilot sub-agent spawning with background
mode

#### For configuration changes:
- [x] `.env.default` is updated or already compatible
- [x] `docker-compose.yml` is updated or already compatible
2026-04-03 00:09:19 +07:00

83 lines
2.8 KiB
Python

"""SDK environment variable builder — importable without circular deps.
Extracted from ``service.py`` so that ``backend.blocks.orchestrator``
can reuse the same subscription / OpenRouter / direct-Anthropic logic
without pulling in the full copilot service module (which would create a
circular import through ``executor`` → ``credit`` → ``block_cost_config``).
"""
from __future__ import annotations
from backend.copilot.config import ChatConfig
from backend.copilot.sdk.subscription import validate_subscription
# ChatConfig is stateless (reads env vars) — a separate instance is fine.
# A singleton would require importing service.py which causes the circular dep
# this module was created to avoid.
config = ChatConfig()
def build_sdk_env(
session_id: str | None = None,
user_id: str | None = None,
sdk_cwd: str | None = None,
) -> dict[str, str]:
"""Build env vars for the SDK CLI subprocess.
Three modes (checked in order):
1. **Subscription** — clears all keys; CLI uses ``claude login`` auth.
2. **Direct Anthropic** — returns ``{}``; subprocess inherits
``ANTHROPIC_API_KEY`` from the parent environment.
3. **OpenRouter** (default) — overrides base URL and auth token to
route through the proxy, with Langfuse trace headers.
When *sdk_cwd* is provided, ``CLAUDE_CODE_TMPDIR`` is set so that
the CLI writes temp/sub-agent output inside the per-session workspace
directory rather than an inaccessible system temp path.
"""
# --- Mode 1: Claude Code subscription auth ---
if config.use_claude_code_subscription:
validate_subscription()
env: dict[str, str] = {
"ANTHROPIC_API_KEY": "",
"ANTHROPIC_AUTH_TOKEN": "",
"ANTHROPIC_BASE_URL": "",
}
if sdk_cwd:
env["CLAUDE_CODE_TMPDIR"] = sdk_cwd
return env
# --- Mode 2: Direct Anthropic (no proxy hop) ---
if not config.openrouter_active:
env = {}
if sdk_cwd:
env["CLAUDE_CODE_TMPDIR"] = sdk_cwd
return env
# --- Mode 3: OpenRouter proxy ---
base = (config.base_url or "").rstrip("/")
if base.endswith("/v1"):
base = base[:-3]
env = {
"ANTHROPIC_BASE_URL": base,
"ANTHROPIC_AUTH_TOKEN": config.api_key or "",
"ANTHROPIC_API_KEY": "", # force CLI to use AUTH_TOKEN
}
# Inject broadcast headers so OpenRouter forwards traces to Langfuse.
def _safe(v: str) -> str:
return v.replace("\r", "").replace("\n", "").strip()[:128]
parts = []
if session_id:
parts.append(f"x-session-id: {_safe(session_id)}")
if user_id:
parts.append(f"x-user-id: {_safe(user_id)}")
if parts:
env["ANTHROPIC_CUSTOM_HEADERS"] = "\n".join(parts)
if sdk_cwd:
env["CLAUDE_CODE_TMPDIR"] = sdk_cwd
return env