Alexandre Teixeira 2790708b19 feat(benchmarks): add offline evidence integrity auditor (#7030) ...

* feat(benchmarks): add offline C5 evidence auditor

* fix(benchmarks): prevent sensitive data in audit logs

* fix(benchmarks): prevent Markdown report injection

* fix(benchmarks): prevent Markdown inline injection

* fix(benchmarks): secure GFM report rendering

* ci(benchmarks): gate rendered GFM security regressions

2026-11-02 23:07:56 +00:00

..

_completion

Odysseus v1.0

2026-05-31 23:58:26 +09:00

_lib

Odysseus v1.0

2026-05-31 23:58:26 +09:00

demo_email

fix(email): serialize default-account mutations (#5805)

2026-08-12 04:59:46 +01:00

add_hwfit_models.py

chore(publication): close pre-integration release blockers

2026-10-05 01:37:49 +01:00

agent_migration_manifest.py

docs: add agent migration manifest helper (#3028)

2026-06-15 15:57:33 +09:00

analyze_odysseus_eval_targets.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

assemble_sft_clean_corpus.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

audit_c5_benchmark_evidence.py

feat(benchmarks): add offline evidence integrity auditor (#7030)

2026-11-02 23:07:56 +00:00

audit_email_sft_with_deepseek.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

audit_historical_tool_routing.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

audit_search_pipeline.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

audit_sft_corpus_with_deepseek.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

audit_typo_tool_routing.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

backfill_model_release_dates.py

chore(publication): close pre-integration release blockers

2026-10-05 01:37:49 +01:00

build_frontend.py

refactor(frontend): establish source ownership and architecture gates (#6701)

2026-10-13 21:03:48 +01:00

build_historical_harness_queue.py

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

build_odysseus_everyday_deepseek_heldout_cases.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_odysseus_everyday_deepseek_heldout_v3_cases.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_odysseus_realistic_web_synthesis_rows.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_odysseus_search_teacher_edited_rows.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_odysseus_sft_repair_manifest.py

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

build_odysseus_tool_efficiency_sft_slice.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_odysseus_v54_live_gap_teacher_sft.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_odysseus_v55_web_synthesis_teacher_sft.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_odysseus_v56_broad_web_teacher_sft.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_odysseus_v61_app_route_web_rows.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_odysseus_v62_teacher_trace_web_rows.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_odysseus_web_teacher_sft.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_odysseus_web_v53_repair_sft.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_sft_environment_inventories.py

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

build_sft_expansion_manifest.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_sft_expansion_splits.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

build_v66_calendar_heldout_cases.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

check_brotli.py

fix(docker): require the patched Debian Brotli decoder (#6956)

2026-10-29 15:05:58 +01:00

check_ca_trust.py

fix(security): verify deployed trust before dependency work

2026-10-21 21:40:05 +00:00

check_frontend.mjs

refactor(frontend): establish source ownership and architecture gates (#6701)

2026-10-13 21:03:48 +01:00

check-docker-amd-gpu.sh

Parse all AMD GPU check args (#1586)

2026-06-03 08:56:48 +09:00

check-docker-gpu.sh

docs(docker): polish WSL2 snap GPU guidance

2026-07-08 19:30:41 +00:00

claim_ownerless.py

Reject blank ownerless claim owner (#4929)

2026-06-28 10:57:11 +01:00

compare_compact_tool_inventory.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

compare_reference_strategies.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

compare_schema_thinking.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

compare_tool_routing.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

cook_sft_alex_conversations.py

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

css_snapshot.py

test: stabilize final PR 40 validation gates

2026-10-01 06:39:22 +01:00

curate_public_search_seed_cases.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

curate_sft_trace_run.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

diffusion_server.py

Merge verified Odysseus fixes

2026-07-23 14:49:02 +00:00

encode_previews.sh

refactor(docs): separate Pages site source (#6176)

2026-08-27 10:20:36 +02:00

eval_ajax_basic_tools.py

Preserve preview harness, editor, email and task improvements

2026-10-01 01:34:26 +00:00

eval_exact_file_routing.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

eval_followup_domain_continuity.py

Harden maintainer-preview harness and review fixes

2026-09-21 06:54:03 +00:00

eval_odysseus_app_route_smoke.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

eval_odysseus_contextual_tool_use.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

eval_odysseus_crud.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

eval_odysseus_everyday_live_hard.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

eval_odysseus_live_hard_direct.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

eval_odysseus_live_hard_examples.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

eval_odysseus_tool_use.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

eval_qwen35_document_shape_direct.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

eval_qwen35_implicit_memory.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

eval_qwen35_tool_router_extended.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

eval_qwen_tool_groups_stream.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

filter_sft_seed_hygiene.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

fix_paths.py

Odysseus v1.0

2026-05-31 23:58:26 +09:00

generate_env_reference.py

feat(mcp): let a deployment declare local MCP tools (#6330)

2026-11-01 03:19:59 +00:00

generate_sft_environment_expansion.py

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

generate_sft_flow_variants_with_kimi.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

hf_download.py

Odysseus v1.0

2026-05-31 23:58:26 +09:00

import_from_vllm_recipes.py

chore(publication): close pre-integration release blockers

2026-10-05 01:37:49 +01:00

index_documents.py

refactor(constants): single source of truth for data dir (#3368)

2026-06-08 09:58:52 +02:00

judge_seeded_harness_replay.py

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

manage_sft_fixture_state.py

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

migrate_faiss_to_chroma.py

refactor(constants): single source of truth for data dir (#3368)

2026-06-08 09:58:52 +02:00

migrate_searxng_settings.py

fix(docker): migrate retained SearXNG settings (#6055)

2026-08-16 04:17:58 +02:00

mlx_image_server.py

Merge commit from fork

2026-08-24 17:38:40 +02:00

note_test_oracle.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

ody_eval_email_fixture.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

odysseus

Require runnable dispatcher subcommands (#1585)

2026-06-03 08:56:56 +09:00

odysseus_conversation_qa.py

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

odysseus_domain_audit.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

odysseus_related_flow_audit.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

odysseus_remaining_tool_audit.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

odysseus-backup

Skip vanished backup list entries (#2006)

2026-07-11 05:26:42 +01:00

odysseus-calendar

Fix odysseus-calendar list dropping in-progress / multi-day events (#2065)

2026-06-16 14:04:56 +02:00

odysseus-contacts

Skip invalid contacts CLI rows (#1569)

2026-06-03 14:11:21 +09:00

odysseus-cookbook

fix(platform): Improve WSL SSH remote compatibility (#3316)

2026-06-08 00:33:50 +02:00

odysseus-dev

feat(scripts): add odysseus-dev, a per-worktree isolated boot

2026-09-25 17:35:47 +02:00

odysseus-docs

Ignore non-string docs CLI content lengths (#1561)

2026-06-03 14:06:46 +09:00

odysseus-gallery

fix(gallery): match stacked CLI filters against AI tags

2026-10-28 14:33:23 +03:00

odysseus-logs

fix: logs CLI _resolve crashes on a non-string name (#1631)

2026-06-03 08:59:30 +09:00

odysseus-mail

fix(mail): sort CLI message batches by UTC date

2026-10-28 14:39:41 +03:00

odysseus-mcp

Normalize stored MCP CLI JSON (#1554)

2026-06-03 14:11:35 +09:00

odysseus-memory

fix: odysseus-memory cmd_add crashes on non-dict existing memory row (#2091)

2026-07-11 03:05:17 +01:00

odysseus-notes

Skip invalid notes CLI item rows (#2005)

2026-06-29 14:26:46 +01:00

odysseus-personal

Skip invalid personal CLI index rows (#1571)

2026-06-03 14:06:42 +09:00

odysseus-preset

Let preset set replace corrupt entries (#1650)

2026-06-03 14:10:58 +09:00

odysseus-research

Research CLI: alias --status complete to the stored done value (#2515)

2026-06-05 08:50:33 +01:00

odysseus-sessions

Normalize session CLI counters (#1578)

2026-06-03 08:57:41 +09:00

odysseus-signature

Reject non-PNG signature export data (#1651)

2026-06-03 14:10:54 +09:00

odysseus-skills

Skip invalid skills CLI rows (#1553)

2026-06-03 14:11:38 +09:00

odysseus-smoke

test(smoke): add a release smoke suite over every advertised feature area

2026-09-30 12:12:58 +02:00

odysseus-tasks

Ignore non-string task CLI previews (#1559)

2026-06-03 14:06:49 +09:00

odysseus-theme

Reject invalid theme CLI prefs (#1396)

2026-06-03 14:12:35 +09:00

odysseus-webhook

fix(cli): generate live task webhook URLs (#5956)

2026-08-16 23:28:26 +01:00

pr_blocker_audit.py

tools: add read-only PR blocker audit helper

2026-06-04 12:51:48 +01:00

probe_browser_budget.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

probe_empty_search_recovery.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

probe_fixed_search_evidence.py

Record wording robustness probes and source-loss replay evidence

2026-09-17 22:02:34 +00:00

probe_reference_resolution.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

probe_search_synthesis.mjs

Validate clarification and correct context-test setup; record rejected prompt experiment

2026-09-17 21:49:00 +00:00

probe_search_tool_choice.mjs

Record controlled missing-referent and schema-omission diagnostics

2026-09-17 21:44:46 +00:00

ref_parity_audit.py

chore(tools): add a read-only ref-to-ref parity audit

2026-09-30 11:53:31 +02:00

repair_email_sft_with_kimi.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

repair_sft_corpus_with_kimi.py

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

rerun_qwen35_v31_odysseus_surface.sh

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

review_sft_environment_expansion.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

run_odysseus_cases_chunked.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

run_odysseus_search_teacher_pipeline.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

run_regular_local_epictetus_full_matrix.sh

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

run_sft_environment_expansion.py

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

run_sft_maya_overnight.sh

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

run_sft_overnight_fixture_flows.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

run_sft_overnight.sh

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

sanitize_trace_artifacts.py

feat(editor): harden photo editor security and interactions

2026-10-28 17:37:10 +00:00

select_sft_expansion_seeds.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

serve_ajax_preheretic.sh

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

sft_email_overseer.py

Harden maintainer-preview harness and review fixes

2026-09-21 06:54:03 +00:00

summarize_odysseus_eval_delta.py

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

summarize_reference_strategies.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

summarize_result_format.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

summarize_schema_thinking.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

summarize_tool_routing.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

test_clean_tool_loop.py

fix(ci): make maintainer harness contract self-contained and portable

2026-09-22 11:31:45 +01:00

tool_followup_oracle.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

update_database.py

Remove duplicate update database body (#1584)

2026-06-03 08:57:03 +09:00

validate_runtime_wave1.sh

fix(runtime): isolate nested invocation ownership

2026-10-01 02:11:53 +01:00

verify_agent_turn_contract.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_audited_note_flows.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_background_delivery_isolation.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_background_research_cards.mjs

fix(css): repoint the two stylesheet links the split left behind

2026-09-30 17:14:52 +02:00

verify_background_research_chat.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_calendar_confirmation_links.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_clean_v3_email_read.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_clean_v3_private_browser.mjs

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

verify_clean_v3_search_quality.mjs

Schedule broad research before synthesis and clarify briefing layout

2026-09-17 22:46:33 +00:00

verify_clean_v3_stateful.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_clean_v3_vl_workflow.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_clean_v3_vl.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_clean_v3_write.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_cookbook_read_followups.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_document_suggestion_followup.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_email_search_read_followup.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_entity_link_navigation.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_frontend_runtime.py

refactor(notes): decompose Notes into feature-owned modules (#6713)

2026-10-15 09:29:41 +01:00

verify_interleaved_tool_followups.mjs

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

verify_minimized_document_context.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_mobile_active_editor_followups.mjs

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

verify_multi_note_delete_followup.mjs

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

verify_native_media_followups.mjs

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

verify_native_workspace_followups.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_notes_browser_runtime.py

perf(tests): bound Notes server descendant cleanup

2026-10-29 17:35:52 +00:00

verify_read_tool_followups.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_record_read_recovery.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_regular_model_tools.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_research_chat_launch.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_search_chats_followup.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_second_document_read_followup.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_second_item_followups.mjs

Consolidate Odysseus agent harness and tool contracts

2026-09-17 10:07:40 +00:00

verify_second_memory_delete_followup.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_second_skill_followup.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_streaming_entity_link.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_supplemental_read_drilldowns.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_terminal_error_visibility.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_ui_panel_followups.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00

verify_web_subtool_followups.mjs

Squash Odysseus development history

2026-09-11 06:04:19 +00:00