mirror of
https://github.com/Significant-Gravitas/AutoGPT.git
synced 2026-04-08 03:00:28 -04:00
37d9863552
## Summary
- Adds `ExecutionMode` enum with `BUILT_IN` (default built-in tool-call
loop) and `EXTENDED_THINKING` (delegates to Claude Agent SDK for richer
reasoning)
- Extracts shared `tool_call_loop` into `backend/util/tool_call_loop.py`
— reusable by both OrchestratorBlock agent mode and copilot baseline
- Refactors copilot baseline to use the shared `tool_call_loop` with
callback-driven iteration
## ExecutionMode enum
`ExecutionMode` (`backend/blocks/orchestrator.py`) controls how
OrchestratorBlock executes tool calls:
- **`BUILT_IN`** — Default mode. Runs the built-in tool-call loop
(supports all LLM providers).
- **`EXTENDED_THINKING`** — Delegates to the Claude Agent SDK for
extended thinking and multi-step planning. Requires Anthropic-compatible
providers (`anthropic` / `open_router`) and direct API credentials
(subscription mode not supported). Validates both provider and model
name at runtime.
## Shared tool_call_loop
`backend/util/tool_call_loop.py` provides a generic, provider-agnostic
conversation loop:
1. Call LLM with tools → 2. Extract tool calls → 3. Execute tools → 4.
Update conversation → 5. Repeat
Callers provide three callbacks:
- `llm_call`: wraps any LLM provider (OpenAI streaming, Anthropic,
llm.llm_call, etc.)
- `execute_tool`: wraps any tool execution (TOOL_REGISTRY, graph block
execution, etc.)
- `update_conversation`: formats messages for the specific protocol
## OrchestratorBlock EXTENDED_THINKING mode
- `_create_graph_mcp_server()` converts graph-connected blocks to MCP
tools
- `_execute_tools_sdk_mode()` runs `ClaudeSDKClient` with those MCP
tools
- Agent mode refactored to use shared `tool_call_loop`
## Copilot baseline refactored
- Streaming callbacks buffer `Stream*` events during loop execution
- Events are drained after `tool_call_loop` returns
- Same conversation logic, less code duplication
## SDK environment builder extraction
- `build_sdk_env()` extracted to `backend/copilot/sdk/env.py` for reuse
by both copilot SDK service and OrchestratorBlock
## Provider validation
EXTENDED_THINKING mode validates `provider in ('anthropic',
'open_router')` and `model_name.startswith('claude')` because the Claude
Agent SDK requires an Anthropic API key or OpenRouter key. Subscription
mode is not supported — it uses the platform's internal credit system
which doesn't provide raw API keys needed by the SDK. The validation
raises a clear `ValueError` if an unsupported provider or model is used.
## PR Dependencies
This PR builds on #12511 (Claude SDK client). It can be reviewed
independently — #12511 only adds the SDK client module which this PR
imports. If #12511 merges first, this PR will have no conflicts.
### 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 pre-commit hooks pass (typecheck, lint, format)
- [x] Existing OrchestratorBlock tests still pass
- [x] Copilot baseline behavior unchanged (same stream events, same tool
execution)
- [x] Manual: OrchestratorBlock with execution_mode=EXTENDED_THINKING +
downstream blocks → SDK calls tools
- [x] Agent mode regression test (non-SDK path works as before)
- [x] SDK mode error handling (invalid provider raises ValueError)
56 lines
2.1 KiB
Docker
56 lines
2.1 KiB
Docker
# Base stage for both dev and prod
|
|
FROM node:22.22-alpine3.23 AS base
|
|
WORKDIR /app
|
|
RUN corepack enable
|
|
COPY autogpt_platform/frontend/package.json autogpt_platform/frontend/pnpm-lock.yaml ./
|
|
RUN --mount=type=cache,target=/root/.local/share/pnpm pnpm install --frozen-lockfile
|
|
|
|
# Build stage for prod
|
|
FROM base AS build
|
|
|
|
COPY autogpt_platform/frontend/ .
|
|
# Allow CI to opt-in to Playwright test build-time flags
|
|
ARG NEXT_PUBLIC_PW_TEST="false"
|
|
ENV NEXT_PUBLIC_PW_TEST=$NEXT_PUBLIC_PW_TEST
|
|
ENV NODE_ENV="production"
|
|
# Merge env files appropriately based on environment
|
|
RUN if [ -f .env.production ]; then \
|
|
# In CI/CD: merge defaults with production (production takes precedence)
|
|
cat .env.default .env.production > .env.merged && mv .env.merged .env.production; \
|
|
elif [ -f .env ]; then \
|
|
# Local with custom .env: merge defaults with .env
|
|
cat .env.default .env > .env.merged && mv .env.merged .env; \
|
|
else \
|
|
# Local without custom .env: use defaults
|
|
cp .env.default .env; \
|
|
fi
|
|
RUN pnpm run generate:api
|
|
# Disable source-map generation in Docker builds to halve webpack memory usage.
|
|
# Source maps are only useful when SENTRY_AUTH_TOKEN is set (Vercel deploys);
|
|
# the Docker image never uploads them, so generating them just wastes RAM.
|
|
ENV NEXT_PUBLIC_SOURCEMAPS="false"
|
|
# In CI, we want NEXT_PUBLIC_PW_TEST=true during build so Next.js inlines it
|
|
RUN if [ "$NEXT_PUBLIC_PW_TEST" = "true" ]; then NEXT_PUBLIC_PW_TEST=true NODE_OPTIONS="--max-old-space-size=8192" pnpm build; else NODE_OPTIONS="--max-old-space-size=8192" pnpm build; fi
|
|
|
|
# Prod stage - based on NextJS reference Dockerfile https://github.com/vercel/next.js/blob/64271354533ed16da51be5dce85f0dbd15f17517/examples/with-docker/Dockerfile
|
|
FROM node:22.22-alpine3.23 AS prod
|
|
ENV NODE_ENV=production
|
|
ENV HOSTNAME=0.0.0.0
|
|
WORKDIR /app
|
|
|
|
RUN addgroup --system --gid 1001 nodejs
|
|
RUN adduser --system --uid 1001 nextjs
|
|
|
|
RUN mkdir .next
|
|
RUN chown nextjs:nodejs .next
|
|
|
|
COPY --from=build --chown=nextjs:nodejs /app/.next/standalone ./
|
|
COPY --from=build --chown=nextjs:nodejs /app/.next/static ./.next/static
|
|
|
|
COPY --from=build /app/public ./public
|
|
|
|
USER nextjs
|
|
|
|
EXPOSE 3000
|
|
CMD ["node", "server.js"]
|