mirror of
https://github.com/Significant-Gravitas/AutoGPT.git
synced 2026-04-08 03:00:28 -04:00
5a29de0e0e
## Summary When the Claude SDK returns a prompt-too-long error (e.g. transcript + query exceeds the model's context window), the streaming loop now retries with escalating fallbacks instead of failing immediately: 1. **Attempt 1**: Use the transcript as-is (normal path) 2. **Attempt 2**: Compact the transcript via LLM summarization (`compact_transcript`) and retry 3. **Attempt 3**: Drop the transcript entirely and fall back to DB-reconstructed context (`_build_query_message`) If all 3 attempts fail, a `StreamError(code="prompt_too_long")` is yielded to the frontend. ### Key changes **`service.py`** - Add `_is_prompt_too_long(err)` — pattern-matches SDK exceptions for prompt-length errors (`prompt is too long`, `prompt_too_long`, `context_length_exceeded`, `request too large`) - Wrap `async with ClaudeSDKClient` in a 3-attempt retry `for` loop with compaction/fallback logic - Move `current_message`, `_build_query_message`, and `_prepare_file_attachments` before the retry loop (computed once, reused) - Skip transcript upload in `finally` when `transcript_caused_error` (avoids persisting a broken/empty transcript) - Reset `stream_completed` between retry iterations - Document outer-scope variable contract in `_run_stream_attempt` closure (which variables are reassigned between retries vs read-only) **`transcript.py`** - Add `compact_transcript(content, log_prefix, model)` — converts JSONL → messages → `compress_context` (LLM summarization with truncation fallback) → JSONL - Add helpers: `_flatten_assistant_content`, `_flatten_tool_result_content`, `_transcript_to_messages`, `_messages_to_transcript`, `_run_compression` - Returns `None` when compaction fails or transcript is already within budget (signals caller to fall through to DB fallback) - Truncation fallback wrapped in 30s timeout to prevent unbounded CPU time on large transcripts - Accepts `model` parameter to avoid creating a new `ChatConfig()` on every call **`util/prompt.py`** - Fix `_truncate_middle_tokens` edge case: returns empty string when `max_tok < 1`, properly handles `max_tok < 3` **`config.py`** - E2B sandbox timeout raised from 5 min to 15 min to accommodate compaction retries **`prompt_too_long_test.py`** (new, 45 tests) - `_is_prompt_too_long` positive/negative patterns, case sensitivity, BaseException handling - Flatten helpers for assistant/tool_result content blocks - `_transcript_to_messages` / `_messages_to_transcript` roundtrip, strippable types, empty content - `compact_transcript` async tests: too few messages, not compacted, successful compaction, compression failure **`retry_scenarios_test.py`** (new, 27 tests) - Full retry state machine simulation covering all 8 scenarios: 1. Normal flow (no retry) 2. Compact succeeds → retry succeeds 3. Compact fails → DB fallback succeeds 4. No transcript → DB fallback succeeds 5. Double fail → DB fallback on attempt 3 6. All 3 attempts exhausted 7. Non-prompt-too-long error (no retry) 8. Compaction returns identical content → DB fallback - Edge cases: nested exceptions, case insensitivity, unicode content, large transcripts, resume-after-compaction flow **Shared test fixtures** (`conftest.py`) - Extracted `build_test_transcript` helper used across 3 test files to eliminate duplication ## Test plan - [x] `_is_prompt_too_long` correctly identifies prompt-length errors (8 positive, 5 negative patterns) - [x] `compact_transcript` compacts oversized transcripts via LLM summarization - [x] `compact_transcript` returns `None` on failure or when already within budget - [x] Retry loop state machine: all 8 scenarios verified with state assertions - [x] `TranscriptBuilder` works correctly after loading compacted transcripts - [x] `_messages_to_transcript` roundtrip preserves content including unicode - [x] `transcript_caused_error` prevents stale transcript upload - [x] Truncation timeout prevents unbounded CPU time - [x] All 139 unit tests pass locally - [x] CI green (tests 3.11/3.12/3.13, types, CodeQL, linting)
167 lines
4.4 KiB
TOML
167 lines
4.4 KiB
TOML
[tool.poetry]
|
|
name = "autogpt-platform-backend"
|
|
version = "0.6.22"
|
|
description = "A platform for building AI-powered agentic workflows"
|
|
authors = ["AutoGPT <info@agpt.co>"]
|
|
readme = "README.md"
|
|
packages = [{ include = "backend", format = "sdist" }]
|
|
|
|
|
|
[tool.poetry.dependencies]
|
|
python = ">=3.10,<3.14"
|
|
aio-pika = "^9.5.5"
|
|
aiohttp = "^3.10.0"
|
|
aiodns = "^3.5.0"
|
|
agentmail = "^0.4.5"
|
|
anthropic = "^0.79.0"
|
|
apscheduler = "^3.11.1"
|
|
autogpt-libs = { path = "../autogpt_libs", develop = true }
|
|
bleach = { extras = ["css"], version = "^6.2.0" }
|
|
claude-agent-sdk = "0.1.45" # see copilot/sdk/sdk_compat_test.py for capability checks
|
|
click = "^8.2.0"
|
|
cryptography = "^46.0"
|
|
discord-py = "^2.5.2"
|
|
e2b = "^2.15.2"
|
|
e2b-code-interpreter = "^2.0"
|
|
elevenlabs = "^1.50.0"
|
|
fastapi = "^0.128.6"
|
|
feedparser = "^6.0.11"
|
|
flake8 = "^7.3.0"
|
|
google-api-python-client = "^2.177.0"
|
|
google-auth-oauthlib = "^1.2.2"
|
|
google-cloud-storage = "^3.2.0"
|
|
googlemaps = "^4.10.0"
|
|
gravitasml = "^0.1.4"
|
|
groq = "^0.30.0"
|
|
html2text = "^2024.2.26"
|
|
jinja2 = "^3.1.6"
|
|
jsonref = "^1.1.0"
|
|
jsonschema = "^4.25.0"
|
|
langfuse = "^3.14.1"
|
|
launchdarkly-server-sdk = "^9.14.1"
|
|
mem0ai = "^0.1.115"
|
|
moviepy = "^2.1.2"
|
|
ollama = "^0.6.1"
|
|
openai = "^1.97.1"
|
|
orjson = "^3.10.0"
|
|
pika = "^1.3.2"
|
|
pinecone = "^7.3.0"
|
|
poetry = "2.2.1" # CHECK DEPENDABOT SUPPORT BEFORE UPGRADING
|
|
postmarker = "^1.0"
|
|
praw = "~7.8.1"
|
|
prisma = "^0.15.0"
|
|
rank-bm25 = "^0.2.2"
|
|
prometheus-client = "^0.24.1"
|
|
prometheus-fastapi-instrumentator = "^7.0.0"
|
|
psutil = "^7.0.0"
|
|
psycopg2-binary = "^2.9.10"
|
|
pydantic = { extras = ["email"], version = "^2.12.5" }
|
|
pydantic-settings = "^2.12.0"
|
|
pytest = "^8.4.1"
|
|
pytest-asyncio = "^1.1.0"
|
|
python-dotenv = "^1.1.1"
|
|
python-multipart = "^0.0.22"
|
|
redis = "^6.2.0"
|
|
regex = "^2025.9.18"
|
|
replicate = "^1.0.6"
|
|
sentry-sdk = {extras = ["anthropic", "fastapi", "launchdarkly", "openai", "sqlalchemy"], version = "^2.44.0"}
|
|
sqlalchemy = "^2.0.40"
|
|
strenum = "^0.4.9"
|
|
stripe = "^11.5.0"
|
|
supabase = "2.28.0"
|
|
tenacity = "^9.1.4"
|
|
todoist-api-python = "^2.1.7"
|
|
tweepy = "^4.16.0"
|
|
uvicorn = { extras = ["standard"], version = "^0.40.0" }
|
|
websockets = "^15.0"
|
|
youtube-transcript-api = "^1.2.1"
|
|
yt-dlp = "2025.12.08"
|
|
zerobouncesdk = "^1.1.2"
|
|
# NOTE: please insert new dependencies in their alphabetical location
|
|
pytest-snapshot = "^0.9.0"
|
|
aiofiles = "^25.1.0"
|
|
tiktoken = "^0.12.0"
|
|
aioclamd = "^1.0.0"
|
|
setuptools = "^80.9.0"
|
|
gcloud-aio-storage = "^9.5.0"
|
|
pandas = "^2.3.1"
|
|
firecrawl-py = "^4.3.6"
|
|
exa-py = "^1.14.20"
|
|
croniter = "^6.0.0"
|
|
stagehand = "^0.5.1"
|
|
gravitas-md2gdocs = "^0.1.0"
|
|
posthog = "^7.6.0"
|
|
fpdf2 = "^2.8.6"
|
|
langsmith = "^0.7.7"
|
|
openpyxl = "^3.1.5"
|
|
pyarrow = "^23.0.0"
|
|
|
|
[tool.poetry.group.dev.dependencies]
|
|
aiohappyeyeballs = "^2.6.1"
|
|
black = "^24.10.0"
|
|
faker = "^38.2.0"
|
|
httpx = "^0.28.1"
|
|
isort = "^5.13.2"
|
|
poethepoet = "^0.41.0"
|
|
pre-commit = "^4.4.0"
|
|
pyright = "^1.1.407"
|
|
pytest-mock = "^3.15.1"
|
|
pytest-watcher = "^0.6.3"
|
|
requests = "^2.32.5"
|
|
ruff = "^0.15.0"
|
|
# NOTE: please insert new dependencies in their alphabetical location
|
|
|
|
[build-system]
|
|
requires = ["poetry-core"]
|
|
build-backend = "poetry.core.masonry.api"
|
|
|
|
[tool.poetry.scripts]
|
|
app = "backend.app:main"
|
|
rest = "backend.rest:main"
|
|
db = "backend.db:main"
|
|
ws = "backend.ws:main"
|
|
scheduler = "backend.scheduler:main"
|
|
notification = "backend.notification:main"
|
|
executor = "backend.exec:main"
|
|
analytics-setup = "scripts.generate_views:main_setup"
|
|
analytics-views = "scripts.generate_views:main_views"
|
|
copilot-executor = "backend.copilot.executor.__main__:main"
|
|
cli = "backend.cli:main"
|
|
format = "scripts.linter:format"
|
|
lint = "scripts.linter:lint"
|
|
test = "scripts.run_tests:test"
|
|
load-store-agents = "test.load_store_agents:run"
|
|
export-api-schema = "backend.cli.generate_openapi_json:main"
|
|
gen-prisma-stub = "scripts.gen_prisma_types_stub:main"
|
|
oauth-tool = "backend.cli.oauth_tool:cli"
|
|
|
|
[tool.isort]
|
|
profile = "black"
|
|
|
|
[tool.pytest-watcher]
|
|
now = false
|
|
clear = true
|
|
delay = 0.2
|
|
runner = "pytest"
|
|
runner_args = []
|
|
patterns = ["*.py"]
|
|
ignore_patterns = []
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
asyncio_default_fixture_loop_scope = "session"
|
|
# Disable syrupy plugin to avoid conflict with pytest-snapshot
|
|
# Both provide --snapshot-update argument causing ArgumentError
|
|
addopts = "-p no:syrupy"
|
|
markers = [
|
|
"supplementary: tests kept for coverage but superseded by integration tests",
|
|
]
|
|
filterwarnings = [
|
|
"ignore:'audioop' is deprecated:DeprecationWarning:discord.player",
|
|
"ignore:invalid escape sequence:DeprecationWarning:tweepy.api",
|
|
]
|
|
|
|
[tool.ruff]
|
|
target-version = "py310"
|
|
|