Sync requests-based SDK in clients/python/. Wraps /healthz, /run, /files, and /admin/tokens behind a Forge class with typed exceptions (ForgeError + Transport/API/Auth subclasses) and dataclass response shapes (RunResult, FileToken, AppToken). HTTP timeout = run timeout + 30s margin, matching the pattern cauldron has been running inline. No retries — caller's job since /run isn't idempotent. 24 unit tests via responses, all passing. Install with pip install -e clients/python/.
171 lines
6.3 KiB
Markdown
171 lines
6.3 KiB
Markdown
# clawdforge — Python SDK
|
|
|
|
Sync Python client for the [clawdforge](http://192.168.0.5:3001/Sulkta-Coop/clawdforge) HTTP service. Wraps the bearer-token-gated REST API behind a typed dataclass surface so other Sulkta apps (cauldron, petalparse, johnny5) don't have to hand-roll `requests` calls.
|
|
|
|
## Install
|
|
|
|
```bash
|
|
pip install -e clients/python/
|
|
```
|
|
|
|
(LAN-only, not on PyPI.)
|
|
|
|
## Quickstart
|
|
|
|
```python
|
|
from clawdforge import Forge
|
|
|
|
forge = Forge(base_url="http://192.168.0.5:8800", token="cf_...")
|
|
|
|
print(forge.healthz())
|
|
# {'ok': True, 'claude_present': True, 'claude_version': '1.x.y'}
|
|
|
|
r = forge.run(prompt='Reply with JSON: {"hello": "world"}')
|
|
print(r.result) # {'hello': 'world'}
|
|
print(r.duration_ms) # 4321
|
|
print(r.stop_reason) # 'end_turn'
|
|
```
|
|
|
|
`Forge` is also a context manager — preferred when you have a script-shaped lifetime:
|
|
|
|
```python
|
|
with Forge(base_url="...", token="...") as forge:
|
|
forge.run(prompt="...")
|
|
```
|
|
|
|
## Construction
|
|
|
|
```python
|
|
Forge(
|
|
*,
|
|
base_url: str,
|
|
token: str,
|
|
default_model: str = "sonnet",
|
|
default_timeout_secs: int = 120,
|
|
http_timeout_margin: int = 30,
|
|
session: requests.Session | None = None,
|
|
)
|
|
```
|
|
|
|
- `base_url` — `http://host:port`. Trailing slash stripped.
|
|
- `token` — bearer. App token (`cf_...`) for `/run` and `/files`; admin bootstrap token for `/admin/*`.
|
|
- `default_model` — passed to `/run` when caller doesn't override. Server default is also `sonnet` so this matches.
|
|
- `default_timeout_secs` — `timeout_secs` for `/run` when caller doesn't override.
|
|
- `http_timeout_margin` — seconds added to the run subprocess timeout to derive the HTTP-level timeout. The HTTP deadline must outlast the server's subprocess deadline so we don't bail while clawdforge is still doing legitimate work for us. Default 30s — same pattern cauldron has been running inline.
|
|
- `session` — bring your own `requests.Session` if you want shared connection-pooling across multiple Forges. If omitted, the Forge owns one and closes it on exit.
|
|
|
|
## Methods
|
|
|
|
### `healthz() -> dict`
|
|
|
|
```python
|
|
forge.healthz()
|
|
# {'ok': True, 'claude_present': True, 'claude_version': '1.x.y'}
|
|
```
|
|
|
|
### `run(prompt, *, model=None, system=None, files=None, timeout_secs=None) -> RunResult`
|
|
|
|
```python
|
|
r = forge.run(
|
|
prompt="Sterilize this ingredient line: 'about 2 cups of cooked white rice'",
|
|
model="sonnet", # optional, defaults to forge.default_model
|
|
system="You are a precise recipe parser. Always reply with valid JSON.",
|
|
files=["ff_..."], # optional file tokens from upload_file()
|
|
timeout_secs=60, # optional, 5..600, defaults to forge.default_timeout_secs
|
|
)
|
|
|
|
r.ok # True
|
|
r.result # parsed JSON when claude returned valid JSON, else str
|
|
r.duration_ms # 4321
|
|
r.stop_reason # 'end_turn' | 'timeout' | 'error' | ...
|
|
```
|
|
|
|
### `upload_file(path_or_fileobj, *, ttl_secs=3600, filename=None, content_type=None) -> FileToken`
|
|
|
|
Either path-like or a binary file-object:
|
|
|
|
```python
|
|
ft = forge.upload_file("/path/to/recipe.png", ttl_secs=3600)
|
|
# FileToken(file_token='ff_...', ttl_secs=3600, size=12345)
|
|
|
|
# Or from a buffer:
|
|
import io
|
|
ft = forge.upload_file(io.BytesIO(b"..."), filename="snippet.txt")
|
|
|
|
r = forge.run(prompt="Extract recipe data", files=[ft.file_token])
|
|
```
|
|
|
|
The server enforces `60 <= ttl_secs <= 86400` and returns 400 for out-of-range values, surfaced as `ForgeAPIError`.
|
|
|
|
### Admin (admin-bootstrap-token gated)
|
|
|
|
```python
|
|
admin = Forge(base_url="http://192.168.0.5:8800", token=ADMIN_BOOTSTRAP_TOKEN)
|
|
|
|
t = admin.create_token("cauldron", ip_cidrs=["172.24.0.0/16"])
|
|
# AppToken(name='cauldron', token='cf_brandnew_xxx', ip_cidrs=['172.24.0.0/16'], ...)
|
|
# t.token is the plaintext bearer — store it now, the server only keeps a hash.
|
|
|
|
admin.list_tokens()
|
|
# [AppToken(name='cauldron', token=None, ip_cidrs=['172.24.0.0/16'], created_at=..., last_used=..., enabled=True), ...]
|
|
|
|
admin.revoke_token("cauldron") # True on success; raises ForgeAPIError(404) if no such token
|
|
```
|
|
|
|
## Errors
|
|
|
|
Everything the SDK raises descends from `ForgeError`:
|
|
|
|
```
|
|
ForgeError
|
|
├── ForgeTransportError — connection/TCP-timeout failures (server never responded)
|
|
└── ForgeAPIError — server returned 4xx/5xx; .status_code, .body available
|
|
└── ForgeAuthError — 401 or 403 specifically
|
|
```
|
|
|
|
`ForgeAPIError` carries:
|
|
- `.status_code: int`
|
|
- `.body: dict | str | None` — parsed JSON if available, else text
|
|
- `.message: str` — short summary
|
|
|
|
Typical pattern:
|
|
|
|
```python
|
|
from clawdforge import Forge, ForgeAuthError, ForgeAPIError, ForgeTransportError
|
|
|
|
try:
|
|
r = forge.run(prompt="...")
|
|
except ForgeAuthError:
|
|
# Re-mint your token, or check the IP allowlist.
|
|
raise
|
|
except ForgeAPIError as e:
|
|
if e.status_code == 502 and isinstance(e.body, dict):
|
|
# Subprocess failed/timed out. e.body has 'error', 'stderr',
|
|
# 'duration_ms', 'stop_reason'.
|
|
log.warning("clawdforge run failed: %s", e.body.get("error"))
|
|
raise
|
|
except ForgeTransportError:
|
|
# Network blip — clawdforge is down or unreachable. Caller decides
|
|
# whether to retry; the SDK does not retry.
|
|
raise
|
|
```
|
|
|
|
## No retries by default
|
|
|
|
Clawdforge runs are not idempotent — each `/run` spawns a real `claude -p` subprocess that costs tokens and time. If you want retries, wrap calls with whatever retry policy fits your call-site (tenacity, backoff, hand-rolled). The SDK won't double-charge you behind your back.
|
|
|
|
## Tests
|
|
|
|
```bash
|
|
cd clients/python
|
|
pip install -e .[test]
|
|
python -m unittest discover tests
|
|
```
|
|
|
|
Tests use `responses` to intercept HTTP calls — no live network, no live clawdforge.
|
|
|
|
## Notes
|
|
|
|
- The `result` field of `RunResult` matches whatever the server's `runner` parsed out of `claude -p --output-format json`: a dict when the prompt asked for JSON and the model complied, a string otherwise. The SDK passes it through as-is — your prompt determines the shape.
|
|
- The server's `GET /admin/tokens` returns `ip_cidrs` as a comma-joined string (it's stored that way in SQLite). The SDK normalizes that to `list[str]` on `AppToken`. The create response already returns a list, so both shapes round-trip cleanly.
|
|
- `revoke_token` on a non-existent name raises `ForgeAPIError(404)` rather than returning `False`. That matches the server's contract and lets callers distinguish "didn't exist" from "was disabled".
|