Backend / infrastructure:
- cortex/tools/_projects.py (new): shared project alias registry with ssh_host
for workstation projects (aether_api, aether_frontend, aether_container)
- cortex/tools/git.py: all git tools route to workstation via SSH when ssh_host set
- cortex/tools/aider.py: aider_run SSH-routes to workstation using bash -l -c
- cortex/routers/local_llm.py: POST /api/models/{id}/edit AJAX endpoint — save
model edits without page reload or tab reset; returns JSON {ok, label, model_name}
- cortex/llm_client.py: remove Gemini CLI and Claude CLI backends; clean up
fallback chain and process group tracking (continuation of Gemini CLI removal)
- cortex/routers/auth.py: strip Claude/Gemini CLI auth status checks (CLI removed)
- cortex/routers/chat.py: remove legacy claude/gemini backend fields
- cortex/config.py: clean up CLI-related settings
- cortex/main.py: remove CLI lifecycle hooks
UI:
- cortex/static/local_llm.html: model edit forms now save via fetch() + toast;
stay on Models tab; update row header label in place on success
- cortex/static/index.html: restructure input area to column layout — textarea
above, compact toolbar below (Chat/Tools/Attach + Send); fixes dead space at
M/L/XL sizes; context panel "Role" → "Model" section label
- cortex/static/style.css: column input-area layout; #input-toolbar; flex:1 →
width:100% on textarea (fixes scrollHeight in column flex context); compact
send/stop button padding
- cortex/static/app.js: add XL (720px) to height cycle; default M (240px)
Docs:
- cortex/static/HELP.md: S/M/L → S/M/L/XL; add Rebuild to distill table; fix
"Role selector" references (no such UI); fix "your active role" → Chat role;
fix ⚡ toggle description; Model Registry section cleanup
- documentation/ARCH__BACKENDS.md: reflect CLI removal, current backend state
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
aider_run multi-provider credentials (tools/aider.py):
- _resolve_credentials() — general credential resolver; replaces the previous
OpenRouter-only injection; resolution priority: Anthropic model hint → explicit
host_label → model prefix (openrouter/*, groq/*, deepseek/*, …) → OpenRouter
default → Anthropic API key → any keyed cloud host → local/generic host
- _host_flags() — generates --api-key slug=key for known cloud providers (OpenRouter,
OpenAI, Groq, Together, Fireworks, X.ai, DeepSeek, Mistral); generates
--openai-api-base + --openai-api-key for generic/local hosts (Open WebUI, Ollama);
appends /api suffix for openwebui host_type; auto-prefixes model with 'openai/'
for generic endpoints when model has no / prefix
- Anthropic API keys from providers.anthropic.credentials (not a host entry)
- host_label param added to aider_run and FunctionDeclaration — pick a configured
host by partial label match (e.g. 'OpenRouter', 'Local', 'scott-lt-i7-rtx')
- 16 unit tests for _resolve_credentials covering all resolution paths
main.py: move @app.get("/health") before app.include_router(ui.router) — the
/{username} catch-all in ui.router was swallowing the /health path
Test suite: 37 pre-existing failures → 182/182 passing
- test_tools.py: _task_list() missing priority arg (6 callsites); cron ID regex
c_\w+ → c_[\w-]+ (token_urlsafe includes '-', causing intermittent truncation)
- test_webhooks.py: rewritten for per-user channel config architecture —
patch routers.nextcloud_talk/google_chat.get_user_channels instead of removed
settings fields; corrected endpoints /webhook/nextcloud/scott and
/channels/google-chat/scott; non-empty cfg dicts so falsy-guard passes
- test_health.py: test_unknown_route_404 now uses 3-segment path (/{u}/{p}/x)
since single-segment paths hit the /{username} UI catch-all
- test_api_files.py: removed '../config.py' from not-in-allowed test (ASGI
normalizes it to /config.py which hits /{username} catch-all, not files router)
- test_security.py: same webhook patch target fix; per-user endpoint URLs
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Tool schema optimization (PLAN__Tool_Schema_Optimization.md Phases 1-3):
- model_registry.py: ROLE_DEFAULT_TOOLS — distill gets [], research/coder get
narrow tool lists by default; applied in get_role_config() when user hasn't
configured a custom list
- openai_orchestrator.py: keyword routing via narrow_tools_by_keywords() — scans
user message + last assistant turn; narrows active schemas to matched categories
only (e.g. "weather" → 3 web tools instead of 69); zero tools sent for pure chat
- openai_orchestrator.py: _get_cached_tools() — module-level schema cache keyed by
(role, sorted_tool_list, risk_params); eliminates redundant schema rebuilds
- openai_orchestrator.py: _TOOL_SCHEMA_OVERHEAD 3000 → 500 tokens (schemas now
excluded from the per-call fixed estimate since they're cached separately)
- tools/__init__.py: CATEGORY_TOOL_MAP + _KEYWORD_CATEGORY_MAP + classify_tool_categories()
+ narrow_tools_by_keywords() — the classifier logic lives here so both orchestrators
can share it
aider_run tool (cortex/tools/aider.py):
- Invokes Aider as a subprocess with --message --yes-always --no-pretty --no-stream
- Project aliases: cortex / aether_api / aether_frontend / aether_container
- Auto-injects OpenRouter API key from Cortex model registry (no ~/.env needed)
- background=True fires async + registers in agent_manager; notify=True sends push
notification on completion
- admin-only, confirm-required, TOOL_RISK=high
- .gitignore: added .aider.chat.history.md / .aider.input.history / .aider.llm.history
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
