docs: document --cap-add NET_ADMIN as required for WAA container networking#165
Merged
docs: document --cap-add NET_ADMIN as required for WAA container networking#165
Conversation
Add two scripts implementing Phase 1 of the distillation pipeline: - collect_distillation_data.py: Runs a frontier model (GPT-5.4, Claude, etc.) as teacher on WAA tasks, saving successful (screenshot, action) trajectories as SFT-ready JSONL + PNGs via PlannerTrajectoryLogger. Supports resume, cost tracking, task filtering, and --max-tasks for cost-limited testing. - finetune_distilled.py: Fine-tunes a student VLM (Qwen3.5-9B or any HuggingFace model) with LoRA on the collected trajectories using TRL SFTTrainer. Supports Unsloth for 2x speedup, 4-bit quantization, and a --mock mode that validates the full pipeline without GPU. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…orking Without this flag, the container falls back to user-mode networking and cannot reach the Windows QEMU guest at 20.20.20.21. Port 5050 (evaluate server on Linux side) works fine, making the failure confusing — but port 5000 (WAA Flask server inside Windows) is unreachable. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
abrichr
added a commit
that referenced
this pull request
Mar 20, 2026
…, and demo-guided execution Add detailed usage documentation for all major features added in PRs #134-#165: - Docker/WAA Container: --cap-add NET_ADMIN requirement, full docker run command, boot timeline, port reference - Full Evaluation Runner (run_full_eval.py): all flags with defaults, example commands for smoke test, resume, parallel, HTTP grounder - Distillation Pipeline: two-step workflow (collect_distillation_data.py + finetune_distilled.py), all flags, mock validation mode - Demo-Guided Execution: DemoLibrary API, DemoGuidedAgent with self- verification, recording workflow - Task Setup Config Types: all 15 supported types with example params - Strict Mode: ScrubMiddleware, workflow pipeline, WAALiveAdapter - Pool Execution: external agent_factory support via PoolManager.run() - Updated Quick Start with copy-pasteable sequence - Updated Architecture tree with new files (demo_library, demo_guided_agent, scripts/) - Updated Key Files table with new entries Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
3 tasks
abrichr
added a commit
that referenced
this pull request
Mar 20, 2026
…, and demo-guided execution (#166) Add detailed usage documentation for all major features added in PRs #134-#165: - Docker/WAA Container: --cap-add NET_ADMIN requirement, full docker run command, boot timeline, port reference - Full Evaluation Runner (run_full_eval.py): all flags with defaults, example commands for smoke test, resume, parallel, HTTP grounder - Distillation Pipeline: two-step workflow (collect_distillation_data.py + finetune_distilled.py), all flags, mock validation mode - Demo-Guided Execution: DemoLibrary API, DemoGuidedAgent with self- verification, recording workflow - Task Setup Config Types: all 15 supported types with example params - Strict Mode: ScrubMiddleware, workflow pipeline, WAALiveAdapter - Pool Execution: external agent_factory support via PoolManager.run() - Updated Quick Start with copy-pasteable sequence - Updated Architecture tree with new files (demo_library, demo_guided_agent, scripts/) - Updated Key Files table with new entries Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Documents that
--cap-add NET_ADMINis REQUIRED when running the WAA container. Without it, the container can't create a network bridge to the Windows QEMU guest, making port 5000 unreachable while port 5050 works fine (confusing failure mode).Tested and confirmed on live Azure VM — adding this flag fixes the "WAA server not starting" issue.
🤖 Generated with Claude Code