Meta-process scaffolding refresh (pr-auto + dead-code)#19
Open
BrianMills2718 wants to merge 17 commits intoShinMegamiBoson:mainfrom
Open
Meta-process scaffolding refresh (pr-auto + dead-code)#19BrianMills2718 wants to merge 17 commits intoShinMegamiBoson:mainfrom
BrianMills2718 wants to merge 17 commits intoShinMegamiBoson:mainfrom
Conversation
… and tests New data sources cataloged with fetch scripts and validation tests: - FEC federal campaign finance (API + bulk) - USASpending.gov federal contracts (API) - SAM.gov contractor registrations (API) - SEC EDGAR public company filings (API) - FDIC BankFind institution data (API) - ProPublica Nonprofit Explorer / IRS 990 (API) - Senate lobbying disclosures LD-1/LD-2 (bulk XML) - EPA ECHO enforcement & compliance (API) - OSHA inspection data (API) - OFAC SDN sanctions list (bulk CSV) - ICIJ Offshore Leaks database (bulk CSV) - US Census Bureau ACS (API) All scripts use Python stdlib only. 104 new tests pass (18 skip without API keys or network). Wiki index updated with new categories.
- Replace _ThinkingDisplay with _ActivityDisplay supporting three modes: thinking (cyan), streaming response (green), tool execution (yellow) - Auto-transition from thinking→streaming on first text delta - Show step counter (Step N/max) in activity spinner - Show tool name and key argument during tool execution - Add engine cancellation via threading.Event (_cancel flag) - Run agent in background thread so user can type next question - Queue typed input during agent execution (FIFO) - ESC key binding cancels the running agent - Add 13 tests covering ActivityDisplay, cancellation, and queuing
Extends ToolResult with optional ImageData payload and adds a read_image tool that reads PNG/JPEG/GIF/WebP files, base64-encodes them, and passes them through to the model layer in provider-specific formats (Anthropic content blocks, OpenAI data URI in user messages).
Add 5 reusable analysis scripts: - quickstart_investigation.py: starter template for investigations - scripts/entity_resolution.py: entity linking pipeline - scripts/cross_link_analysis.py: cross-referencing engine - scripts/build_findings_json.py: report synthesis utility - scripts/timing_analysis.py: statistical timing correlation Fix TUI flicker by making _ActivityDisplay a Rich renderable (__rich__ protocol) so Live's 8fps auto-refresh polls state instead of feed() forcing update() on every token delta.
Tell the agent about replay.jsonl, events.jsonl, and state.json in its session directory so it can read its own prior transcripts and recall earlier work within a session.
…ape sequences Root cause: prompt_toolkit's patch_stdout() wraps sys.stdout with StdoutProxy which corrupts Rich's ANSI escape sequences — replacing ESC bytes (0x1b) with '?' (0x3f). This caused raw escape codes like ?[2K?[1A?[2K to appear as visible text instead of being interpreted by the terminal. Fix: scope patch_stdout() to only wrap session.prompt(), not the entire main loop. During agent execution, Rich's Live writes directly to the real stdout with correct escape sequences. Also remove the secondary prompt loop (which compounded the issue) and switch cancellation from ESC to Ctrl+C. Verified via PTY test: 36 correct ESC sequences, 0 corrupted (was 0/16).
Three fixes to the TUI secondary prompt:
1. patch_stdout(raw=True): preserves Rich's ANSI escape sequences instead
of stripping ESC bytes (0x1b -> 0x3f). Root cause of visible ?[2K?[1A
garbage.
2. Slash commands at the secondary prompt are dispatched immediately:
/quit cancels the agent and exits, /help /status /model etc. run
in-place. Only non-slash input is queued.
3. app.exit("") called from _run_agent's finally block unblocks the
secondary prompt when the agent finishes, so the result is displayed
immediately without the user having to press Enter.
After each agent turn, generate a lightweight summary (objective, result preview, metadata) and persist it to state.json. On subsequent turns, inject the list of prior turn summaries into the initial message so the agent knows what it did before without re-reading full transcripts.
Forward tool_call_start and tool_call_args deltas from both OpenAI and Anthropic streaming paths to the TUI _ActivityDisplay. The display now shows a "Generating write_file..." header with a live content preview extracted from the partial JSON buffer, instead of stale thinking text.
The attribute was used in run() and slash-command handling but never initialized, causing an AttributeError on startup.
The function was called in the queued-input prompt but never defined, causing a NameError when the agent was running and accepting queued input.
…h commands Covers _queue_prompt_style, __init__ attributes, _on_event dispatching, _on_step state management, _on_content_delta delegation, run loop (empty input, quit, help, queued input, KeyboardInterrupt, agent execution), and dispatch_slash_command for all command types.
Batch install of meta-process --minimal: commit-msg hooks (YAML-driven prefix validation), pre-commit checks, plan workflow templates, and pattern documentation. Hooks gracefully degrade when optional scripts are missing. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Codex CLI reads AGENTS.md, Claude Code reads CLAUDE.md. Previously these diverged silently. Now both tools read identical content. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Disable unused features (claims, worktrees, acceptance_gates, messaging). Keep commit prefix validation and plan workflow. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Install full meta-process with claims, worktree hooks, and coordination scripts. Add Multi-Agent Coordination instructions to CLAUDE.md. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Masoud9215
approved these changes
Feb 27, 2026
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
3 participants
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.
This PR applies the latest meta-process scaffolding refresh:
scripts/meta/pr_auto.py)scripts/meta/check_dead_code.py)Makefileand hook wiringNo product logic changes are intended in this refresh.