Skip to content

History / Setup

Revisions

  • docs: strip migration trivia from product docs Remove the "Removed providers (v0.2.0+): Azure OpenAI, self-hosted Qwen, local Ollama …" callouts and the "legacy LinUCB bandit", "v1 + v2 services", "Legacy adapters auto-wrapped", and stale `--scorer v2` flag references. None of this belongs on a product page — it's implementation history that only matters to someone upgrading from v0.1.x, and that audience is already addressed in CHANGELOG.md. Touched: - README.md — drop the "Removed providers" blockquote. - Setup.md — same callout removed. - cortex/docs/setup.md — drop the "legacy env vars silently ignored" bullet from the LLM Options notes. - cortex/README.md — drop "(default)" + "The legacy LinUCB bandit remains as a non-default option" from Active Interventions and Learning Loop; drop "Legacy adapters auto-wrapped"; drop "v1 + v2 services"; modernise the Setup snippet to use the new Makefile shortcuts (`make setup` / `make dev`); refresh the Development section to mirror the four CI gates; replace the stale `--scorer v2 --prompts v2` and bandit_trainer commands with their current equivalents; update the tests/ tree to the real 124-file / 1,334-function count and surface the eval/ subdirectory.

    @StevenWang-CY StevenWang-CY committed May 19, 2026
  • audit F38+F39: strip dead LLM provider config + rewrite docs to match reality Closes audit F38 (dead env vars in shipped templates) and F39 (doc drift). Cortex moved to the Anthropic SDK in v0.2.0; the providers it supports today are ``bedrock``, ``vertex``, and ``direct``. The shipped templates and user-facing docs still advertised Azure OpenAI, self-hosted Qwen, and local Ollama — every one of those env vars (``CORTEX_LLM__MODE``, ``CORTEX_LLM__AZURE__*``, ``CORTEX_LLM__REMOTE__*``, ``CORTEX_LLM__LOCAL__*``, ``CORTEX_LLM__MODEL_NAME``) is silently dropped by ``LLMConfig.extra= "ignore"`` and the legacy-fallback validator maps stale values to the rule-based fallback. The user ends up entering credentials for a provider that no longer exists, then wonders why the daemon never talks to the LLM. Changes: - ``cortex/.env.example`` — rewrote the LLM block. It now lists ``CORTEX_LLM__PROVIDER``, the three transports, the BYOK Keychain service / account, and explicit logical model IDs. The dead env names are documented in a single trailing comment so a user grepping for ``CORTEX_LLM__MODE`` lands at the deprecation note instead of an example to copy. - ``README.md`` — the tech-stack row, the prereqs row, the configuration step, the "what to expect" paragraph, and the troubleshooting subsection all rewritten to name only the real providers, the ``CORTEX_LLM__PROVIDER`` selector, and the BYOK Keychain step. Added a "removed providers" footnote so users searching old docs find context. - ``Setup.md`` — same surgery. Option A/B/C now describe Bedrock, Vertex, and direct Anthropic API. Verification line fixed (``get_config().llm.mode`` no longer exists; replaced with ``llm.provider``). - ``Architecture.md`` — L4 ASCII diagram line says ``Anthropic SDK over AWS Bedrock / GCP Vertex / direct Anthropic API`` instead of the dead ``Azure/Ollama/remote/rule`` quartet. Test: ``cortex/tests/unit/test_seed_config_dead_envs.py`` — 7 cases. The whole-token regression guard (``CORTEX_LLM__MODE`` matches but ``CORTEX_LLM__MODEL_DEFAULT`` does not) scans ``seed_config.py`` and ``.env.example`` for any dead env name or model value outside a comment block. Positive checks confirm ``.env.example`` names a real provider and the user-facing docs (``README``, ``Setup``, ``Architecture``) all mention Bedrock + Vertex + Anthropic plus at least one of ``CORTEX_LLM__PROVIDER`` / ``ANTHROPIC_PROVIDER``. Outcomes: - On this branch: ``pytest cortex/tests/unit/test_seed_config_dead_envs.py`` → 7 passed. - On audit baseline (commit 36cc15f): the test module collects fine (it has no external deps); 5 of the 7 cases fail — ``test_env_example_has_no_dead_env_names`` (the file has ``CORTEX_LLM__MODE``, ``CORTEX_LLM__AZURE__*``, ``CORTEX_LLM__REMOTE__*``, ``CORTEX_LLM__LOCAL__*``, ``CORTEX_LLM__MODEL_NAME``), ``test_env_example_has_no_dead_values`` (``qwen3-8b``, ``gpt-5-mini``, ``llama3.1:8b``), ``test_env_example_lists_real_providers`` (no ``CORTEX_LLM__PROVIDER``), ``test_docs_name_the_three_real_providers`` (README + Setup + Architecture missing Bedrock/Vertex/Anthropic markers), ``test_docs_mention_the_provider_selector_env_var`` (no doc mentions the provider selector). The two ``test_seed_config_has_no_dead_*`` cases pass on baseline because ``seed_config.py`` already used the correct provider config in the audit baseline.

    @StevenWang-CY StevenWang-CY committed May 18, 2026
  • docs: update all documentation to reflect DMG installer as primary setup method

    @StevenWang-CY StevenWang-CY committed Apr 4, 2026
  • Add full wiki: setup, architecture, how it works, API, troubleshooting, privacy

    @StevenWang-CY StevenWang-CY committed Mar 24, 2026