ducoterra e0f11e7aa8 phase: 126_pdf_support ...

All gates verified green — no code changes were needed on this pass. Final report:

## Phase 126 — PDF support: final verification pass

**Verified (all tasks 01–05 already complete in working tree):**
- `pymupdf` dep in `pyproject.toml`/`uv.lock`; `.env.example` documents the `pdf` token
- `app/rag/pdf.py` (text + image extraction, MIME mapping), page-aware `_chunk_pdf`, importer `_index_pdf_file` + embedded-image pass, archives covered via extension walk

**Test / lint / coverage results:**
- `uv run pytest` → 2997 passed
- `uv run pytest tests/e2e/test_pdf_support.py -v --no-cov` (isolation) → 6 passed
- `uv run pytest --cov=app --cov-report=term-missing` → TOTAL **99%** (>90% gate), 2997 passed
- `uv run ruff check . && uv run pyright` → clean (0 errors)

**Completion criteria:**
1. PDF → doc with text/chunks/embedding/summary — ✅ (integration + E2E Sources-page tests)
2. `BOR_IMAGES=true`: embedded images → standalone image docs — ✅ (integration + E2E chat-chip test)
3. `BOR_IMAGES=false`: images skipped, text indexed — ✅ (both suites)
4. PDF renders as extracted text in viewer — ✅ (E2E)
5. Test/coverage/lint gates — ✅ (above)
6. Commit + phase move — harness handles (per protocol, no `git` on this pass)

**Decisions:** none new; inline `[Embedded image: …]` placeholders were a documented task-04 deviation (simplified spec wins) — not a defect. No defects found; repo left functional with changes in the working tree.

**Next pending phase:** none — `todo/` is empty once 126 is moved.

2026-09-27 09:36:40 -04:00

..

__init__.py

phase: 82_security_headers

2026-09-07 23:54:41 -04:00

test_agent_short_lived_sessions.py

phase: 110_fix_sse_db_pool_exhaustion

2026-09-14 15:55:13 -04:00

test_agent.py

phase: 119_name_signal_read_chips

2026-09-16 15:50:48 -04:00

test_api_tokens_model.py

feat: phases 77–80 — navbar view refresh, static background, API tokens, history suggestion chips

2026-09-07 12:39:01 -04:00

test_archive_upload_dates.py

phase: 106_document_dates

2026-09-13 19:28:05 -04:00

test_archive_upload.py

feat(sources): upload tarball/zipfile archives as sources — unpack, scan, and replace in place

2026-08-28 15:57:59 -04:00

test_auth.py

feat: phases 77–80 — navbar view refresh, static background, API tokens, history suggestion chips

2026-09-07 12:39:01 -04:00

test_background_no_motion.py

phase: 92_theme_save_and_coverage

2026-09-10 00:23:08 -04:00

test_big_read_progress.py

fix(chat): render typing-indicator elapsed hint as horizontal text

2026-09-08 10:03:10 -04:00

test_caching.py

phase: 92_theme_save_and_coverage

2026-09-10 00:23:08 -04:00

test_chat_cancel.py

phase: 119_name_signal_read_chips

2026-09-16 15:50:48 -04:00

test_chat_gate.py

phase: 119_name_signal_read_chips

2026-09-16 15:50:48 -04:00

test_chat_image_questions.py

phase: 123_chat_image_questions

2026-09-25 05:19:18 -04:00

test_chat_message_failed.py

phase: 120_failed_turn_retry

2026-09-24 18:50:36 -04:00

test_chat_persistence.py

phase: 123_chat_image_questions

2026-09-25 05:19:18 -04:00

test_chip_sizing_question_cap.py

phase: 104_chip_sizing_question_cap

2026-09-12 19:45:00 -04:00

test_chunker.py

phase: 126_pdf_support

2026-09-27 09:36:40 -04:00

test_config.py

phase: 119_name_signal_read_chips

2026-09-16 15:50:48 -04:00

test_date_editor.py

phase: 106_document_dates

2026-09-13 19:28:05 -04:00

test_db_pool_config.py

phase: 110_fix_sse_db_pool_exhaustion

2026-09-14 15:55:13 -04:00

test_db.py

feat: scaffold Brain of Reese — FastAPI RAG chat over Postgres 17 + pgvector

2026-08-21 13:42:21 -04:00

test_debugging.py

feat: scaffold Brain of Reese — FastAPI RAG chat over Postgres 17 + pgvector

2026-08-21 13:42:21 -04:00

test_doc_dates.py

phase: 106_document_dates

2026-09-13 19:28:05 -04:00

test_doc_edit_screen.py

phase: 100_page_width_consistency

2026-09-12 13:37:19 -04:00

test_docs_push.py

feat(docs): save chat answers as docs — edit screen, commit + push to the .env docs branch

2026-09-01 03:52:03 -04:00

test_document_viewer.py

phase: 122_image_documents

2026-09-25 01:54:23 -04:00

test_embed_question_length.py

phase: 119_name_signal_read_chips

2026-09-16 15:50:48 -04:00

test_error_sanitization.py

phase: 84_docs_push_error_sanitization

2026-09-08 01:11:45 -04:00

test_folder_summaries.py

feat(rag): summarize single-document folders (MIN_DOCS_PER_FOLDER 2 → 1)

2026-09-14 08:57:57 -04:00

test_frontend_banner_retry.py

phase: 111_chat_banner_retry

2026-09-14 23:07:56 -04:00

test_frontend_brand.py

phase: 91_admin_theme_tab

2026-09-09 17:22:24 -04:00

test_frontend_doc_draft_discard.py

phase: 115_doc_draft_discard

2026-09-15 05:35:05 -04:00

test_frontend_failed_turn.py

phase: 120_failed_turn_retry

2026-09-24 18:50:36 -04:00

test_frontend_feedback.py

phase: 123_chat_image_questions

2026-09-25 05:19:18 -04:00

test_frontend_hidden_tab.py

fix(chat): raise pre-token guard from 120 s to 300 s

2026-09-08 09:37:33 -04:00

test_frontend_router.py

phase: 99_kb_tree_table_and_back_nav

2026-09-13 01:57:40 -04:00

test_frontend_scroll.py

phase: 123_chat_image_questions

2026-09-25 05:19:18 -04:00

test_frontend_sync_upload.py

phase: 98_sync_summary_visibility

2026-09-13 00:23:05 -04:00

test_frontend_tool_states.py

phase: 117_tool_call_compact

2026-09-15 18:26:38 -04:00

test_frontend_turn_loader.py

feat(ui): swap the in-turn loader for a brain-wave sweep left of the send button

2026-09-15 11:55:59 -04:00

test_gate_header_stacking.py

phase: 85_mobile_menu_gate_overlap

2026-09-08 01:56:37 -04:00

test_git_source_token.py

phase: 121_git_source_tokens

2026-09-24 20:51:39 -04:00

test_git_sources.py

feat(admin): local directory sources — kind/path on git_sources, combined sync + import, page form + badges

2026-08-27 01:04:16 -04:00

test_git_sync.py

phase: 107_git_full_history_dates

2026-09-13 23:21:39 -04:00

test_hamburger_nav.py

fix(ui): bind the shared header controls on explicit init, not at module import

2026-09-08 22:31:45 -04:00

test_header_bindings_once_per_document.py

fix(ui): bind the shared header controls on explicit init, not at module import

2026-09-08 22:31:45 -04:00

test_hidden_folders_toggle.py

phase: 105_hidden_folders_toggle

2026-09-12 21:26:30 -04:00

test_history_copy.py

fix(chat): keep in-flight answers alive across in-app view switches

2026-09-06 06:31:31 -04:00

test_history_page.py

fix(chat): keep in-flight answers alive across in-app view switches

2026-09-06 06:31:31 -04:00

test_history.py

phase: 108_history_wire_check

2026-09-13 23:57:54 -04:00

test_image_anchor_context.py

phase: 125_image_anchor_context

2026-09-27 05:53:12 -04:00

test_image_chips_and_answers.py

phase: 124_image_chips_and_answers

2026-09-26 17:06:09 -04:00

test_image_documents.py

phase: 125_image_anchor_context

2026-09-27 05:53:12 -04:00

test_importer_dates.py

phase: 106_document_dates

2026-09-13 19:28:05 -04:00

test_importer_ignore.py

phase: 89_source_ignore_paths

2026-09-09 01:45:42 -04:00

test_importer_include_hidden.py

phase: 105_hidden_folders_toggle

2026-09-12 21:26:30 -04:00

test_importer.py

phase: 122_image_documents

2026-09-25 01:54:23 -04:00

test_kb_tree_builder.py

phase: 122_image_documents

2026-09-25 01:54:23 -04:00

test_kb_tree_ui.py

phase: 106_document_dates

2026-09-13 19:28:05 -04:00

test_llm_client.py

phase: 96_oneshot_resilience

2026-09-11 13:16:20 -04:00

test_llm_probe.py

feat(rag): agent document tools — list/read tools with env-tuned budgets, SSE tool events + "calling tool" UI

2026-08-26 22:39:14 -04:00

test_llm_stream_teardown.py

feat(agent): align the document tools with the harness-trained shape — ls, read(path), grep(pattern, path?)

2026-09-03 11:17:47 -04:00

test_main.py

perf(ui): cache busting — HTML no-cache + versioned asset URLs (?v=) with immutable 1y asset caching

2026-08-25 22:42:10 -04:00

test_markdown_tables.py

phase: 100_page_width_consistency

2026-09-12 13:37:19 -04:00

test_md_images.py

phase: 125_image_anchor_context

2026-09-27 05:53:12 -04:00

test_mobile_chat_hamburger_boot.py

fix(ui): bind the shared header controls on explicit init, not at module import

2026-09-08 22:31:45 -04:00

test_mock_tool_flow.py

phase: 94_ls_tree_drilldown

2026-09-11 00:59:35 -04:00

test_models.py

phase: 125_image_anchor_context

2026-09-27 05:53:12 -04:00

test_overview.py

feat(rag): lite-generated KB overview in the system prompt — stored single row, regenerated on import, <knowledge_base> section in HIGH+LOW prompts

2026-08-25 20:22:51 -04:00

test_page_head_panel.py

phase: 93_theme_semantic_completion

2026-09-10 16:43:08 -04:00

test_pdf.py

phase: 126_pdf_support

2026-09-27 09:36:40 -04:00

test_pinned_composer.py

phase: 123_chat_image_questions

2026-09-25 05:19:18 -04:00

test_prompt_lock.py

phase: 119_name_signal_read_chips

2026-09-16 15:50:48 -04:00

test_prompts_dates.py

phase: 118_summary_seed_context

2026-09-16 06:57:49 -04:00

test_prompts.py

phase: 125_image_anchor_context

2026-09-27 05:53:12 -04:00

test_rate_limit.py

phase: 81_login_rate_limit

2026-09-07 23:08:46 -04:00

test_read_truncation_frontend.py

phase: 95_read_truncation_cap

2026-09-11 03:42:51 -04:00

test_remove_confirm_modal.py

phase: 100_page_width_consistency

2026-09-12 13:37:19 -04:00

test_retriever_recency.py

phase: 106_document_dates

2026-09-13 19:28:05 -04:00

test_retriever.py

phase: 119_name_signal_read_chips

2026-09-16 15:50:48 -04:00

test_save_as_doc_button.py

phase: 122_image_documents

2026-09-25 01:54:23 -04:00

test_save_chat_ui.py

phase: 123_chat_image_questions

2026-09-25 05:19:18 -04:00

test_scaffolding_filter.py

feat(agent): strip raw tool-scaffolding from streamed answers — deterministic filter with one bounded recovery

2026-09-03 13:39:15 -04:00

test_schemas.py

phase: 120_failed_turn_retry

2026-09-24 18:50:36 -04:00

test_security_headers.py

phase: 123_chat_image_questions

2026-09-25 05:19:18 -04:00

test_shared_header.py

fix(ui): bind the shared header controls on explicit init, not at module import

2026-09-08 22:31:45 -04:00

test_shared_page.py

phase: 100_page_width_consistency

2026-09-12 13:37:19 -04:00

test_source_chip_quality.py

phase: 119_name_signal_read_chips

2026-09-16 15:50:48 -04:00

test_source_ignore_paths.py

phase: 121_git_source_tokens

2026-09-24 20:51:39 -04:00

test_source_removal.py

feat(sources): removing a source deletes its files and index entries behind a confirmation modal

2026-09-02 15:55:33 -04:00

test_sources_dates.py

phase: 106_document_dates

2026-09-13 19:28:05 -04:00

test_sources_meta.py

feat(chat): invalidate saved chats on sources sync — versioned stamps, stale marker, Regenerate against the new index

2026-08-30 23:39:15 -04:00

test_sources_midstream.py

phase: 123_chat_image_questions

2026-09-25 05:19:18 -04:00

test_sse_events.py

phase: 114_embed_question_length

2026-09-15 04:16:55 -04:00

test_stale_ui_copy.py

fix(chat): keep in-flight answers alive across in-app view switches

2026-09-06 06:31:31 -04:00

test_steering_prompts.py

phase: 106_document_dates

2026-09-13 19:28:05 -04:00

test_steering_toggle_removal.py

fix(chat): keep in-flight answers alive across in-app view switches

2026-09-06 06:31:31 -04:00

test_steering.py

feat(rag): global tuning manager — /tuning.html + PUT /api/steering/{id}: create, edit, list, delete steering notes without a chat

2026-08-25 13:46:32 -04:00

test_sticky_header.py

fix(web): keep the navbar stuck to the top — drop the body height cap on the sticky range

2026-09-01 04:20:26 -04:00

test_summarizer.py

feat(rag): lite-model document summaries — non-markdown docs summarized at import, summary chunk retrieves and resolves to the full source doc

2026-08-25 17:48:37 -04:00

test_summary_edit_ui.py

phase: 106_document_dates

2026-09-13 19:28:05 -04:00

test_sync_button.py

phase: 106_document_dates

2026-09-13 19:28:05 -04:00

test_sync_model_probe.py

feat(sync): fail fast with a modal when a model is unavailable

2026-08-27 23:44:35 -04:00

test_table_wrap_stacking.py

phase: 86_history_page_width

2026-09-08 02:38:45 -04:00

test_theme_frontend.py

phase: 93_theme_semantic_completion

2026-09-10 16:43:08 -04:00

test_theming.py

phase: 93_theme_semantic_completion

2026-09-10 16:43:08 -04:00

test_thinking_scroll.py

fix(chat): stop the submit up-hop and keep the thinking pin alive across paragraph breaks

2026-08-28 17:10:02 -04:00

test_token_gate.py

feat: phases 77–80 — navbar view refresh, static background, API tokens, history suggestion chips

2026-09-07 12:39:01 -04:00

test_tokens.py

phase: 101_tokens_page_overhaul

2026-09-12 15:16:02 -04:00

test_tool_call_compact.py

phase: 117_tool_call_compact

2026-09-15 18:26:38 -04:00

test_ui_settings.py

phase: 93_theme_semantic_completion

2026-09-10 16:43:08 -04:00

test_wide_column_css.py

phase: 122_image_documents

2026-09-25 01:54:23 -04:00