feat: implement raycast backend

This commit is contained in:
hh
2026-05-19 21:06:01 +02:00
parent 221e660c5c
commit 757065f21c
16 changed files with 1415 additions and 31 deletions
+468
View File
@@ -0,0 +1,468 @@
"""Raycast backend adapter.
Translates between Anthropic's ``/v1/messages`` wire vocabulary (incoming
``MessageParam`` history, outgoing ``MessageStreamEvent`` SSE) and the
``raycast-api`` SDK (``Message`` history, ``ChatStreamChunk`` SSE).
Two halves live here:
* :func:`_to_raycast_messages` — pure conversion of an Anthropic message
list into ``list[raycast_api.Message]``. ``tool_result`` blocks carry no
tool name in Anthropic; we recover it by remembering each ``tool_use``
id we saw upstream.
* :meth:`RaycastBackend.complete` — opens a ``client.chat.stream`` and
walks chunks through a tiny block-state machine. The state machine
exists only because Raycast streams ``tool_calls`` in three phases
(open with id+name, deltas with empty id, final summary with the full
``arguments``) — Anthropic wants one ``content_block_start`` → deltas
→ ``content_block_stop`` per block, so we de-duplicate the final
summary against the per-delta increments already emitted.
"""
from __future__ import annotations
import json
import uuid
from typing import TYPE_CHECKING, Any, cast
from raycast_api import Message as RaycastMessage
from raycast_api import RemoteTool, Tool, ToolCall
from beaver_gateway.agents.raycast import RaycastAgent
from beaver_gateway.core.events import (
StopReason,
build_content_block_stop,
build_input_json_delta,
build_message_delta,
build_message_start,
build_message_stop,
build_text_block_start,
build_text_delta,
build_thinking_block_start,
build_thinking_delta,
build_tool_use_block_start,
)
if TYPE_CHECKING:
from collections.abc import AsyncIterator, Iterable, Mapping, Sequence
from anthropic.types import MessageParam
from raycast_api import ChatStreamChunk, Client
from beaver_gateway.agents.base import BaseAgent
from beaver_gateway.core.events import MessageStreamEvent
else:
from collections.abc import Mapping
__all__ = ["RaycastBackend"]
_RAYCAST_TO_ANTHROPIC_STOP: dict[str, StopReason] = {
"stop": "end_turn",
"STOP": "end_turn",
"end_turn": "end_turn",
"tool_calls": "tool_use",
"tool_use": "tool_use",
"length": "max_tokens",
"max_tokens": "max_tokens",
"stop_sequence": "stop_sequence",
}
def _first_set[T](*values: T | None) -> T | None:
"""Return the first value that isn't ``None``, else ``None``.
Used to layer per-request options over per-agent defaults: a real
``0.0`` temperature on the request must override the agent's
``None``, but the agent's value must take effect when the request
omits it. ``or``-chaining is wrong here because ``0.0`` / ``""`` are
legitimate values and falsy.
"""
for v in values:
if v is not None:
return v
return None
def _map_stop_reason(raw: str | None) -> StopReason:
"""Map Raycast ``finish_reason`` strings into Anthropic stop reasons.
Unknown values collapse to ``end_turn`` — Anthropic clients treat that
as a clean finish, which is the right user-visible behaviour when the
upstream simply went off-vocabulary.
"""
if raw is None:
return "end_turn"
return _RAYCAST_TO_ANTHROPIC_STOP.get(raw, "end_turn")
def _as_mapping(block: object) -> Mapping[str, Any] | None:
"""Narrow a block param (TypedDict | dict | anything) to a read-only mapping.
ty refuses to assign a TypedDict to ``dict[str, Any]`` (TypedDicts are
not freely-mutable dicts in its model), and our access pattern is
strictly read-only — so we go through ``Mapping``.
"""
if isinstance(block, Mapping):
return cast("Mapping[str, Any]", block)
return None
def _extract_tool_result_text(content: object) -> str:
"""Flatten an Anthropic ``tool_result`` block's content into plain text.
Anthropic accepts either a string or a list of typed blocks (text /
image / etc.). Raycast only carries text in tool results, so we keep
text blocks and JSON-encode anything richer rather than dropping it.
"""
if isinstance(content, str):
return content
if isinstance(content, list):
parts: list[str] = []
for block in content:
block_map = _as_mapping(block)
if block_map is not None and block_map.get("type") == "text":
parts.append(str(block_map.get("text", "")))
else:
parts.append(
json.dumps(block, separators=(",", ":"), ensure_ascii=False)
)
return "\n".join(parts)
return json.dumps(content, separators=(",", ":"), ensure_ascii=False)
def _to_raycast_messages(
messages: Iterable[MessageParam],
) -> list[RaycastMessage]:
"""Convert an Anthropic message history into a Raycast one.
``tool_use_id → name`` is tracked across the iteration so that
Raycast ``tool`` messages — which require a tool name the Anthropic
side does not carry on ``tool_result`` blocks — can be reconstructed.
"""
out: list[RaycastMessage] = []
tool_use_names: dict[str, str] = {}
for msg in messages:
role = msg["role"]
content = msg.get("content", "")
if isinstance(content, str):
if role == "user":
out.append(RaycastMessage.user(content))
else:
out.append(RaycastMessage.assistant(text=content))
continue
if role == "user":
text_parts: list[str] = []
tool_results: list[Mapping[str, Any]] = []
for block in content:
block_map = _as_mapping(block)
if block_map is None:
continue
btype = block_map.get("type")
if btype == "text":
text_parts.append(str(block_map.get("text", "")))
elif btype == "tool_result":
tool_results.append(block_map)
if text_parts:
out.append(RaycastMessage.user("\n".join(text_parts)))
for tr in tool_results:
tool_use_id = str(tr.get("tool_use_id", ""))
out.append(
RaycastMessage.tool(
tool_call_id=tool_use_id,
name=tool_use_names.get(tool_use_id, ""),
result=_extract_tool_result_text(tr.get("content", "")),
)
)
continue
text_parts = []
tool_calls: list[ToolCall] = []
for block in content:
block_map = _as_mapping(block)
if block_map is None:
continue
btype = block_map.get("type")
if btype == "text":
text_parts.append(str(block_map.get("text", "")))
elif btype == "tool_use":
tu_id = str(block_map.get("id", ""))
tu_name = str(block_map.get("name", ""))
tool_use_names[tu_id] = tu_name
tool_calls.append(
ToolCall(
id=tu_id,
name=tu_name,
arguments=json.dumps(
block_map.get("input", {}),
separators=(",", ":"),
ensure_ascii=False,
),
)
)
out.append(
RaycastMessage.assistant(
text="\n".join(text_parts),
tool_calls=tool_calls or None,
)
)
return out
def _build_tool_list(
agent: RaycastAgent,
) -> list[Tool | RemoteTool | str] | None:
"""Wrap each native-tool name as a Raycast remote tool.
Phase 1.2 scope: only the three model-agnostic remote tools
(`web_search`, `search_images`, `read_page`). Client-defined tools
coming through the Anthropic body's ``tools`` field stay out — that's
Phase 1.3+ alongside ``accept_client_tools``.
"""
if not agent.available_native_tools:
return None
return [Tool.remote(name) for name in agent.available_native_tools]
class _BlockState:
"""Tracks the currently-open Anthropic content block, if any.
Anthropic events are sequential per block (``content_block_start`` →
deltas → ``content_block_stop``). Raycast streams text and tool_calls
interleaved across chunks; we keep one slot open at a time and close
it whenever the kind changes.
Tool-call routing needs two side tables because Raycast streams ids
in phase 1 only and ``index`` in every chunk: ``tool_id_to_block``
keys by Raycast tool-call id, ``tool_idx_to_id`` resolves chunk
indices back to that id for the no-id delta chunks.
"""
__slots__ = ("index", "kind", "tool_id_to_block", "tool_idx_to_id")
def __init__(self) -> None:
self.index: int = -1
self.kind: str | None = None # "text" | "thinking" | "tool_use" | None
self.tool_id_to_block: dict[str, int] = {}
self.tool_idx_to_id: dict[int, str] = {}
class RaycastBackend:
"""Adapter from ``raycast-api`` chat streams to Anthropic stream events.
Construction takes a long-lived :class:`raycast_api.Client` (one per
gateway — bearer + device_id are process-wide). Each
:meth:`complete` call opens one ``chat.stream`` and yields a fully
Anthropic-shaped event sequence.
"""
def __init__(self, client: Client) -> None:
self._client = client
async def complete(
self,
*,
agent: BaseAgent,
messages: Iterable[MessageParam],
system: str | None = None,
**options: Any,
) -> AsyncIterator[MessageStreamEvent]:
if not isinstance(agent, RaycastAgent):
msg = f"RaycastBackend requires RaycastAgent, got {type(agent).__name__}"
raise TypeError(msg)
raycast_messages = _to_raycast_messages(messages)
tools = _build_tool_list(agent)
# On the wire Raycast uses ``system_instructions`` as a format
# marker (``"markdown"`` for AI_CHAT, ``"plain"`` otherwise —
# filled in by the SDK from the source default when we pass
# ``None``) and ``additional_system_instructions`` as the actual
# prompt content. So our ``system_prompt`` (or the per-request
# Anthropic ``system``, if present) flows into the *additional*
# slot. The SDK still prepends ``<user-preferences>`` to whatever
# we hand it via ``_build_preamble``.
prompt_content = system if system is not None else agent.system_prompt
# Per-request options win over agent defaults; agent defaults
# win over Raycast SDK defaults. ``None`` means "fall back".
async for event in self._stream(
agent=agent,
raycast_messages=raycast_messages,
tools=tools,
prompt_content=prompt_content,
temperature=_first_set(options.get("temperature"), agent.temperature),
reasoning_effort=_first_set(
options.get("reasoning_effort"), agent.reasoning_effort
),
tool_choice=_first_set(options.get("tool_choice"), agent.tool_choice),
):
yield event
async def _stream(
self,
*,
agent: RaycastAgent,
raycast_messages: Sequence[RaycastMessage],
tools: list[Tool | RemoteTool | str] | None,
prompt_content: str | None,
temperature: float | None,
reasoning_effort: str | None,
tool_choice: str | None,
) -> AsyncIterator[MessageStreamEvent]:
message_id = f"msg_{uuid.uuid4().hex}"
yield build_message_start(message_id=message_id, model=agent.model)
state = _BlockState()
final_finish: str | None = None
final_usage: dict[str, int] | None = None
stream = self._client.chat.stream(
model=agent.model,
messages=list(raycast_messages),
source=agent.source,
# ``system_instructions=None`` → SDK substitutes the source
# default (``"markdown"`` / ``"plain"``). Real prompt goes
# into ``additional_system_instructions``.
additional_system_instructions=prompt_content,
user_preferences=agent.user_preferences,
tools=tools,
tool_choice=tool_choice,
temperature=temperature,
reasoning_effort=reasoning_effort,
)
async for chunk in stream:
for event in self._handle_chunk(chunk, state):
yield event
if chunk.finish_reason:
final_finish = chunk.finish_reason
if chunk.usage:
final_usage = chunk.usage
# Close whatever block is still open before the message delta.
if state.kind is not None:
yield build_content_block_stop(state.index)
state.kind = None
yield build_message_delta(
stop_reason=_map_stop_reason(final_finish),
usage=final_usage,
)
yield build_message_stop()
def _handle_chunk(
self, chunk: ChatStreamChunk, state: _BlockState
) -> Iterable[MessageStreamEvent]:
"""Translate one Raycast chunk into zero or more Anthropic events.
Branch order matters: we close the previous block kind before
opening a new one (text → tool_use, tool_use → text, etc.) and we
intentionally fall through ``tool_calls`` only if there's a real
delta — the final-summary chunk re-sends the full arguments
string we've already streamed delta-by-delta.
"""
events: list[MessageStreamEvent] = []
is_final_summary = chunk.finish_reason is not None
if chunk.text:
events.extend(self._ensure_kind(state, "text"))
events.append(build_text_delta(state.index, chunk.text))
if chunk.reasoning:
events.extend(self._ensure_kind(state, "thinking"))
events.append(build_thinking_delta(state.index, chunk.reasoning))
if chunk.tool_calls:
events.extend(
self._handle_tool_calls(chunk, state, is_final_summary=is_final_summary)
)
return events
def _ensure_kind(
self, state: _BlockState, kind: str
) -> Iterable[MessageStreamEvent]:
"""Open a block of ``kind``, closing any current block first."""
if state.kind == kind:
return []
events: list[MessageStreamEvent] = []
if state.kind is not None:
events.append(build_content_block_stop(state.index))
state.index += 1
state.kind = kind
if kind == "text":
events.append(build_text_block_start(state.index))
elif kind == "thinking":
events.append(build_thinking_block_start(state.index))
else:
msg = f"unexpected block kind: {kind!r}"
raise ValueError(msg)
return events
def _handle_tool_calls(
self,
chunk: ChatStreamChunk,
state: _BlockState,
*,
is_final_summary: bool,
) -> Iterable[MessageStreamEvent]:
"""Translate one chunk's ``tool_calls`` payload into Anthropic events.
Mirrors the keying logic of ``raycast_api.ChatResult._merge_tool_calls``
so the same dedupe behaviour lands here: tool calls are tracked
by id when present, otherwise by their wire ``index`` field, and
the final-summary chunk's arguments string is dropped because the
deltas already streamed it.
"""
events: list[MessageStreamEvent] = []
raw_tcs = chunk.raw.get("tool_calls") or []
for i, tc in enumerate(chunk.tool_calls or []):
raw_tc = raw_tcs[i] if i < len(raw_tcs) else {}
idx_field = raw_tc.get("index") if isinstance(raw_tc, dict) else None
# Resolve this entry to a tool-id key, mirroring
# `raycast_api.ChatResult._merge_tool_calls`. Phase 1 carries
# id+index, phase 2 only index, phase 3 only id.
tool_id: str | None = None
if tc.id:
tool_id = tc.id
if isinstance(idx_field, int):
state.tool_idx_to_id[idx_field] = tc.id
elif isinstance(idx_field, int):
tool_id = state.tool_idx_to_id.get(idx_field)
if tool_id is None:
continue
block_idx = state.tool_id_to_block.get(tool_id)
if block_idx is None:
# New tool_use block. Close any open text/thinking block first.
if state.kind is not None:
events.append(build_content_block_stop(state.index))
state.index += 1
state.kind = "tool_use"
block_idx = state.index
state.tool_id_to_block[tool_id] = block_idx
events.append(
build_tool_use_block_start(
block_idx, tool_use_id=tool_id, name=tc.name or ""
)
)
if tc.arguments and not is_final_summary:
events.append(build_input_json_delta(block_idx, tc.arguments))
continue
# Existing block. Skip args on the final summary — they're a
# full restatement of what's already been delta'd.
if is_final_summary:
continue
if tc.arguments:
events.append(build_input_json_delta(block_idx, tc.arguments))
return events