feat: claude code runner (#9)

This commit is contained in:
banteg
2026-01-01 17:04:49 +04:00
committed by GitHub
parent 4885e3b878
commit 936ea5109b
30 changed files with 2259 additions and 382 deletions
+122
View File
@@ -0,0 +1,122 @@
# Adding a Runner
This guide walks through adding a new engine to Takopi without changing the
domain model. Use the existing runners (Codex/Claude) as references.
## Quick checklist
1. Implement `Runner` in `src/takopi/runners/<engine>.py`.
2. Emit Takopi events from `takopi.model` and implement resume helpers
(`format_resume`, `extract_resume`, `is_resume_line`).
3. Register an `EngineBackend` in `src/takopi/engines.py` with setup checks
and runner construction.
4. Add CLI subcommand in `src/takopi/cli.py`.
5. Extend tests (runner contract + engine-specific translation tests).
---
## Example: adding a `pi` engine
This is a concrete walkthrough for an imaginary CLI called `pi`. The goal is to
make it easy to drop in another engine without changing the Takopi domain model.
### 1) Decide engine identity + resume format
- Engine id: `"pi"` (used in config, resume tokens, and CLI subcommand).
- Canonical resume line: the engines own CLI resume command, e.g.
`` `pi --resume <session_id>` ``.
- If your engine uses the standard `"<engine> resume <token>"` format, you can
reuse `compile_resume_pattern()`. Otherwise, define a custom regex in the
runner (like Claude does).
### 2) Implement `src/takopi/runners/pi.py`
Skeleton outline:
```py
ENGINE: EngineId = "pi"
_RESUME_RE = re.compile(r"(?im)^\s*`?pi\s+--resume\s+(?P<token>[^`\\s]+)`?\\s*$")
@dataclass
class PiRunner(SessionLockMixin, ResumeTokenMixin, Runner):
engine: EngineId = ENGINE
resume_re: re.Pattern[str] = _RESUME_RE
pi_cmd: str = "pi"
model: str | None = None
allowed_tools: list[str] | None = None
def _build_args(self, prompt: str, resume: ResumeToken | None) -> list[str]:
args = ["--jsonl"]
if resume is not None:
args.extend(["--resume", resume.value])
if self.model is not None:
args.extend(["--model", self.model])
if self.allowed_tools:
args.extend(["--allowed-tools", ",".join(self.allowed_tools)])
args.append("--")
args.append(prompt)
return args
async def run(
self, prompt: str, resume: ResumeToken | None
) -> AsyncIterator[TakopiEvent]:
async for evt in self._run_with_resume_lock(prompt, resume, self._run):
yield evt
```
Key implementation notes:
- Use `SessionLockMixin` to enforce per-session serialization.
- Use `ResumeTokenMixin` for `format_resume` / `extract_resume` / `is_resume_line`.
- Use `iter_jsonl(...)` + `drain_stderr(...)` from `takopi.utils.streams`.
- **Do not truncate** tool outputs in the runner; pass full strings into events.
Truncation belongs in renderers.
### 3) Map Pi JSONL → Takopi events
Example Pi lines (imaginary):
```json
{"type":"session.start","session_id":"pi_01","model":"pi-large"}
{"type":"tool.use","id":"toolu_1","name":"Bash","input":{"command":"ls"}}
{"type":"tool.result","tool_use_id":"toolu_1","content":"ok","is_error":false}
{"type":"final","session_id":"pi_01","ok":true,"answer":"Done."}
```
Mapping guidance:
- `session.start``StartedEvent(engine="pi", resume=<session_id>, title=<model>)`
- `tool.use``ActionEvent(phase="started")`
- `tool.result``ActionEvent(phase="completed")` and **pop** pending actions
- `final``CompletedEvent(ok, answer, resume)` (emit **exactly one**)
If Pi emits warnings/errors before the final event, surface them as completed
`ActionEvent`s (e.g., `kind="warning"`).
### 4) Register engine in `src/takopi/engines.py`
Add:
- `_pi_check_setup()` that verifies `pi` exists on PATH
- `_pi_build_runner()` that reads `[pi]` config and returns `PiRunner`
- A new `EngineBackend(id="pi", display_name="Pi", ...)` entry
Example config (minimal):
```toml
[pi]
model = "pi-large"
allowed_tools = ["Bash", "Read"]
```
### 5) Add CLI subcommand
Expose `takopi pi` alongside `takopi codex` / `takopi claude` by adding a new
`@app.command()` in `src/takopi/cli.py`.
### 6) Tests + fixtures
- Add `tests/test_pi_runner.py` for translation behavior.
- Reuse `tests/test_runner_contract.py` to ensure lock/resume invariants.
- Add JSONL fixtures under `tests/fixtures/` for the Pi stream.