Include config:challenge:attempt and timestamp in completion block
header for easier debugging and log correlation.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove selenium.py and test_selenium.py
- Add playwright_browser.py with WebPlaywrightComponent
- Update web component exports to use Playwright
- Update dependencies in pyproject.toml/poetry.lock
- Minor agent and reflexion strategy improvements
- Update CLAUDE.md documentation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously cost was hardcoded to 0.0. Now extracts cumulative cost
from MultiProvider.get_incurred_cost() after each step execution.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Benchmarks now automatically save progress and resume from where they
left off. State is persisted to .benchmark_state.json in reports dir.
Features:
- Auto-resume: runs skip already-completed challenges
- --fresh: clear all state and start over
- --retry-failures: re-run only failed challenges
- --reset-strategy/model/challenge: selective resets
- `state show/clear/reset` subcommands for state management
- Config mismatch detection with auto-reset
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add --ci flag that disables Rich Live display while preserving
completion blocks. Auto-detects CI environment via CI env var or
non-TTY stdout. Prints progress every 10 completions for visibility.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Calculate max columns based on terminal width (up to 10)
- Reduced panel width from 35 to 30 chars to fit more
- Wider terminals can now show more parallel runs side-by-side
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Fixes:
- Use run_key (config:challenge) instead of just config_name for tracking
active runs - allows multiple challenges from same config to run in parallel
- Add asyncio.sleep(0) yields to let multiple tasks acquire semaphore
and start before any proceed with work
- Always print completion blocks (not just failures) for visibility
This should properly show 8/8 active runs when running with --parallel 8.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
UI improvements:
- Multi-column layout: each active config gets its own panel showing
challenge name and step history (last 6 steps with status)
- Copy-paste completion blocks: when a challenge finishes (especially
failures), prints a detailed block with all steps for easy debugging
- Configurable logging: suppresses noisy LLM provider warnings unless
--debug flag is set
- Pass debug flag through harness to UI
Example active runs panel:
┌─ one_shot/claude ─┬─ rewoo/claude ────┐
│ ReadFile │ WriteFile │
│ ✓ #1 read_file │ ✓ #1 think │
│ ✓ #2 write_file │ ✓ #2 plan │
│ ● step 3: ... │ ● step 3: ... │
└───────────────────┴───────────────────┘
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add step callback to AgentRunner for real-time step logging
- BenchmarkUI now shows:
- Active runs with current step info
- Recent steps panel with colored config prefixes
- Proper Live display refresh (implements __rich_console__)
- Each config gets a distinct color for easy identification
- Verbose mode prints step logs immediately with config prefix
- Fix Live display not updating (pass UI object, not rendered content)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove vcrpy and pytest-recording dependencies
- Remove tests/vcr/ directory and vcr_cassettes submodule
- Remove .gitmodules (only had cassette submodule)
- Simplify CI workflow - no more cassette checkout/push/PAT_REVIEW
- Tests requiring API keys now skip if not set (fork PRs)
- Update CLAUDE.md files to remove cassette references
- Fix broken agbenchmark path in pyproject.toml
Security improvement: removes need for PAT with cross-repo write access.
Fork PRs will have API-dependent tests skipped (GitHub protects secrets).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove old benchmark/ folder with agbenchmark framework
- Move challenges to direct_benchmark/challenges/
- Move analysis tools (analyze_reports.py, analyze_failures.py) to direct_benchmark/
- Move challenges_already_beaten.json to direct_benchmark/
- Update CI workflow to use direct_benchmark
- Update CLAUDE.md files with new benchmarking instructions
- Add benchmarking section to original_autogpt/CLAUDE.md
The direct_benchmark harness directly instantiates agents without HTTP
server overhead, enabling parallel execution with asyncio semaphore.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add NONINTERACTIVE_MODE env var support to AppConfig for disabling
user interaction during automated runs
- Benchmark harness now sets NONINTERACTIVE_MODE=True when starting agents
- Add agent configuration logging at server startup (model, strategy, etc.)
- Harness logs env vars being passed to agent for verification
- Add --agent-output flag to show full agent server output for debugging
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add model comparison support to test harness (claude, openai, gpt5, opus presets)
- Add --models, --smart-llm, --fast-llm, --list-models CLI args
- Add real-time logging with timestamps and progress indicators
- Fix success parsing bug: read results[0].success instead of non-existent metrics.success
- Fix agbenchmark TestResult validation: use exception typename when value is empty
- Fix WebArena challenge validation: use strings instead of integers in instantiation_dict
- Fix Agent type annotations: create AnyActionProposal union for all prompt strategies
- Add pytest integration tests for the strategy benchmark harness
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When tool calls fail validation, the error messages now include:
- What arguments were actually provided
- The expected parameter schema with types and required/optional indicators
This helps LLMs understand and fix their mistakes when retrying,
rather than just being told a parameter is missing.
Example improved error:
Invalid function call for write_file: 'contents' is a required property
You provided: {"filename": 'story.txt'}
Expected parameters: {"filename": string (required), "contents": string (required)}
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add WebFetchComponent for fast HTTP-based page fetching without browser
overhead. Uses trafilatura for intelligent content extraction.
Commands:
- fetch_webpage: Extract main content as text/markdown/xml
- Removes navigation, ads, boilerplate automatically
- Extracts page metadata (title, description, author, date)
- Extracts and lists page links
- Much faster than Selenium-based read_webpage
- fetch_raw_html: Get raw HTML for structure inspection
- Optional truncation for large pages
Features:
- Trafilatura-powered content extraction (best-in-class accuracy)
- Automatic link extraction with relative URL resolution
- Page metadata extraction (OG tags, meta tags)
- Configurable timeout, max content length, max links
- Proper error handling for timeouts and HTTP errors
- 19 comprehensive tests
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Extract _get_tool_error_message helper method
- Replace 20+ levels of nesting with simple for loop
- Improve readability of tool_result construction
- Update benchmark poetry.lock
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace basic DuckDuckGo-only search with a modern tiered system:
1. Tavily (primary) - AI-optimized results with content extraction
- AI-generated answer summaries
- Relevance scoring
- Full page content extraction via search_and_extract command
2. Serper (secondary) - Fast, cheap Google SERP results
- $0.30-1.00 per 1K queries
- Real Google results without scraping
3. DDGS multi-engine (fallback) - Free, no API key required
- Automatic fallback chain: DuckDuckGo → Bing → Brave → Google → etc.
- 8 search backends supported
Key changes:
- Upgrade duckduckgo-search to ddgs v9.10 (renamed successor package)
- Add Tavily and Serper API integrations
- Implement automatic provider selection and fallback chain
- Add search_and_extract command for research with content extraction
- Add TAVILY_API_KEY and SERPER_API_KEY to env templates
- Update benchmark httpx constraint for ddgs compatibility
- 23 comprehensive tests for all providers and fallback scenarios
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Change Agent class to use ActionProposal instead of OneShotAgentActionProposal
to support multiple prompt strategy types
- Widen display_thoughts parameter type from AssistantThoughts to ModelWithSummary
- Fix speak attribute access in agent_protocol_server with hasattr check
- Add type: ignore comments for intentional thoughts field overrides in strategies
- Remove unused OneShotAgentActionProposal import
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix 32+ flake8 E501 (line too long) errors by shortening descriptions
- Remove unused import in todo.py
- Fix test_todo.py argument order (config= keyword)
- Add type annotations to fix pyright errors where straightforward
- Add noqa comments for flake8 false positives in __init__.py
- Remove unused nonlocal declarations in main.py
- Run black and isort to fix formatting
- Update CLAUDE.md with improved linting commands
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously, when a user selected "Once" or "Always" with feedback (via Tab),
the command was NOT executed because UserFeedbackProvided was raised before
checking the approval scope. This fix changes the architecture from
exception-based to return-value-based.
Changes:
- Add PermissionCheckResult class with allowed, scope, and feedback fields
- Change check_command() to return PermissionCheckResult instead of bool
- Update prompt_fn signature to return (ApprovalScope, feedback) tuple
- Add pending_user_feedback mechanism to EpisodicActionHistory
- Update execute() to handle feedback after successful command execution
- Feedback message explicitly states "Command executed successfully"
- Add on_auto_approve callback for displaying auto-approved commands
- Add comprehensive tests for approval/denial with feedback scenarios
Behavior:
- Once + feedback → Execute command, then send feedback to agent
- Always + feedback → Execute command, save permission, send feedback
- Deny + feedback → Don't execute, send feedback to agent
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds a custom Rich-based interactive selector for the command approval
workflow. Features include:
- Arrow key navigation for selecting approval options
- Tab to add context to any selection (e.g., "Once + also check file x")
- Dedicated inline feedback option with shadow placeholder text
- Quick select with number keys 1-5
- Works within existing asyncio event loop (no prompt_toolkit dependency)
Also adds UIProvider abstraction pattern for future UI implementations.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The strategy was stuck in a loop because it tracked plan steps but never
advanced them - the record_step_success() method existed but was never
called by the agent's execution loop.
Fix by using a _pending_step_advance flag to track when an action has
been proposed. On the next parse_response_content() call, advance the
previous step before processing the new response. This keeps step
tracking self-contained in the strategy without requiring agent changes.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement four new prompt strategies based on research papers:
- ReWOO: Reasoning Without Observation (5x token efficiency)
- Plan-and-Execute: Separate planning from execution phases
- Reflexion: Verbal reinforcement learning with episodic memory
- Tree of Thoughts: Deliberate problem solving with tree search
Each strategy extends a new BaseMultiStepPromptStrategy base class
with shared utilities. Strategies are selectable via PROMPT_STRATEGY
environment variable or config.prompt_strategy setting.
Fix JSONSchema generation issue where Optional/Union types created
anyOf schemas without direct type field - resolved by storing
plan/phase state in strategy instances rather than ActionProposal.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove openai_functions config option - native tool calling is now always enabled
- Remove use_functions_api from BaseAgentConfiguration and prompt strategy
- Add use_prefill config to disable prefill for Anthropic (prefill + tools incompatible)
- Update anthropic dependency to ^0.45.0 for tools API support
- Simplify prompt strategy to always expect tool_calls from LLM response
This fixes the N/A command loop bug where models would output "N/A" as a
command name when function calling was disabled. With native tool calling
always enabled, models are forced to pick from valid tools only.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update gitignore to use glob pattern for settings.local.json files
in any .claude directory. Also untrack the existing file.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove asctime from log formats since terminal output already has
timestamps from the logging infrastructure. Makes logs cleaner
and easier to read.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Environment loading:
- Search for .env in multiple locations (cwd, ~/.autogpt, ~/.config/autogpt)
- Allows running autogpt from any directory
- Document search order in .env.template
Setup simplification:
- Remove interactive AI settings revision (was broken/unused)
- Simplify to just printing current settings
- Clean up unused imports
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add specialized exception classes for better error reporting:
- CodeTimeoutError: For code execution timeouts
- HTTPError: For HTTP request failures with status code/URL
- DataProcessingError: For JSON/CSV processing errors
Each exception includes helpful hints for users.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add a task management component modeled after Claude Code's TodoWrite:
- TodoItem with recursive sub_items for hierarchical task structure
- todo_write: atomic list replacement with sub-items support
- todo_read: retrieve current todos with nested structure
- todo_clear: clear all todos
- todo_decompose: use smart LLM to break down tasks into sub-steps
Features:
- Hierarchical task tracking with independent status per sub-item
- MessageProvider shows todos in LLM context with proper indentation
- DirectiveProvider adds best practices for task management
- Graceful fallback when LLM provider not configured
Integrates with:
- original_autogpt Agent (full LLM decomposition support)
- ForgeAgent (basic task tracking, no decomposition)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove references to deleted files (./run, cli.py, setup.py, frontend/)
from CI workflows. Replace ./run agent start with direct poetry commands
to start agent servers in background.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The .autogpt/ directory is where AutoGPT stores agent data when running
from any directory. This should not be committed to version control.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add --workspace option to CLI that defaults to current working directory,
allowing users to run `autogpt` from any folder. Agent data is now stored
in `.autogpt/` subdirectory of the workspace instead of a hardcoded path.
Changes:
- Add -w/--workspace CLI option to run and serve commands
- Remove dependency on forge package location for PROJECT_ROOT
- Update config to use workspace instead of project_root
- Store agent data in .autogpt/ within workspace directory
- Update pyproject.toml files with proper PyPI metadata
- Fix outdated tests to match current implementation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Claude 3.5 v2, Claude 4 Sonnet, Claude 4 Opus, and Claude 4.5 Opus models
- Add rolling aliases (CLAUDE_SONNET, CLAUDE_OPUS, CLAUDE_HAIKU)
- Fix deprecated beta.tools.messages.create API call to use standard messages.create
- Update anthropic SDK from ^0.25.1 to >=0.40,<1.0
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
These models have become deprecated
- deepseek-r1-distill-llama-70b
- gemma2-9b-it
- llama3-70b-8192
- llama3-8b-8192
- google/gemini-flash-1.5
I have removed them and setup a migration, the migration is to convert
all the old versions of the model to new versions, the model changes
will happen like so
- llama3-70b-8192 → llama-3.3-70b-versatile
- llama3-8b-8192 → llama-3.1-8b-instant
- google/gemini-flash-1.5 → google/gemini-2.5-flash
- deepseek-r1-distill-llama-70b → gpt-5-chat-latest
- gemma2-9b-it → gpt-5-chat-latest
### Changes 🏗️
<!-- Concisely describe all of the changes made in this pull request:
-->
### 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:
<!-- Put your test plan here: -->
- [x] Check to see if old models where removed
- [x] Check to see if migration worked and converted old models to new
one in graph
This small PR resolves the deprecation warnings of the `logger` library:
```
DeprecationWarning: The 'warn' method is deprecated, use 'warning' instead
```
Make all changes necessary to make everything work with Poetry v2.0.0.
- Resolves#9196
## Changes
- Removed `--no-update` flag from `poetry lock` command in codebase
- Removed extra path arguments from `poetry -C [path] run [command]`
occurrences
- Regenerated all lock files in hierarchical order
- Added workaround for Poetry bug where `packages.[i].format` is now
suddenly required
Additionally:
- Fixed up .dockerignore
- Fixes .venv being erroneously copied over from local
- Fixes build context bloat (300MB -> 2.5MB)
- Fixed warnings about entrypoint script not being installed in docker
builds
### Relevant (breaking) changes in v2.0.0
- `--no-update` flag no longer exists for `poetry lock` as it has become
default behavior
- The `-C` option now actually changes the directory, so any path
arguments in `poetry run` commands can/must be removed
- Poetry v2.0.0 uses the new v2.1 lock file spec, so all lock files have
to be regenerated to avoid false-positive lock file updates and checks
on future PRs
- **BUG:** when specifying `poetry.tool.packages`, `format` is required
now
- python-poetry/poetry#9961
Full Poetry v2.0.0 release notes and change log:
https://python-poetry.org/blog/announcing-poetry-2.0.0
<!-- Clearly explain the need for these changes: -->
Nick wants others to be able to write tests besides Nick
### Changes 🏗️
<!-- Concisely describe all of the changes made in this pull request:
-->
- Fixes various import errors across the docs to fix dead links
- Adds Docs for making and debugging your own tests
---------
Co-authored-by: Swifty <craigswift13@gmail.com>
