3 fronts, 3 phases, 31 tasks, 12 verification criteria. Based on 3
parallel explore-agent audits of the live codebase.
Front A — Gemini CLI Adapter Removal: delete src/gemini_cli_adapter.py
+ 7 test files; edit ai_client.py (3 functions + 8 dispatch branches +
PROVIDERS 8->7); edit app_controller.py (~11 sites) + gui_2.py (2 blocks)
+ project_manager.py + api_hooks.py; introduce a mock provider that
routes to tests/mock_gemini_cli.py so the 9 live_gui sim tests switch
from gemini_cli to mock without losing their mock-LLM mechanism; update
7 docs + 5 conductor docs.
Front B — Test Suite Cleanup (410 files, 2,133 tests, ~45-60 files
downsizable): delete 2 guaranteed-broken chronology tests (import from
deleted scripts.audit.*); consolidate 7 test_scavenge_*.py tautologies
into 1 test_directive_structure.py; review deprecated-module tests;
consolidate ~15 test_*_phase*.py one-offs; migrate 27 src.models shim
importers to direct subsystem imports; extract shared mock_controller
fixture from ~8 boilerplate-patch files; fix 3 fix-not-skip candidates
(Gemini 503 in summarize.summarise_file); audit the 120KB
test_gui_2_result.py (9.4% of suite line count in one file).
Front C — Metadata-Type Reduction: flip the 38-site MCP dispatch
inversion (dispatch()+22 consumers still call str wrappers, not the
_result variants); migrate app_controller.py's ~40 in-memory Metadata
state sites to typed per-aggregate dataclasses; fix aggregate.py
file_items: list[Metadata] -> list[FileItem]; delete dead code
(openai_schemas.to_legacy_dict, app_controller._push_mma_state_update).
Out of scope: GEMINI_CLI_HOOK_CONTEXT env var + cli_tool_bridge.py +
mma_exec.py (meta-tooling, not the provider — separate follow-up if
user wants to purge naming).
Scripts + workflow for extracting Twitter/X posts and threads into
Markdown with associated media. Mirrors the scripts/video_analysis/
pattern. Standalone requirement: zero imports from src/, conductor/,
or scripts.video_analysis — copy-pasteable to another repo with only
gallery-dl as the external dep.
5 modules: __init__.py, error_types.py (Result[T, ErrorInfo] +
ThreadData/PostData typed dataclasses), fetch_thread.py (gallery-dl
subprocess for URLs + html.parser fallback for local HTML),
download_media.py (stdlib urllib, idempotent), render_markdown.py
(YAML front-matter + per-post sections + ./media/ links).
Reference project: C:\projects\forth\bootslop — the corpus feeds
bootslop's scripts and reference-generation pipeline. Acceptance
corpus: 8 threads (@NOTimothyLottes x6 + @VPCOMPRESSB x2) extracted
to tests/artifacts/twitter_threads_corpus/. The ?s=20 quote-share
suffix on the @VPCOMPRESSB URLs must be stripped by fetch_thread.py
before acquisition (added to FR2 as URL normalization).
5 phases / 23 tasks. 8 verification criteria (VC1-VC8). TDD red-first
on the pure-function modules (render_markdown, types, media naming).
ed