ci: register codex eval workflows on main - #13

PR #13 landed the pre-hook version of the two manual-codex-judge*.yml
files on main as a workflow-registration commit. The feat branch
already carries the post-hook version (callbacks + PYTHONPATH). Take
the feat version wholesale — main's variant has nothing that isn't
also in feat.

Signed-off-by: Tanzim Saqib <[email protected]>

GitHub Actions registers workflow_dispatch workflows from the default
branch only. Merging the two manual-opencode-judge*.yml files to main
makes them visible in the Actions tab so they can be dispatched
against the opencode-evals branch (which carries the opencode driver,
conftest changes, and test scenarios) without having to merge that
branch first. Same pattern as the codex (#13) and copilot
registration PRs.

Both workflows are workflow_dispatch only — no push/PR triggers, so
this merge cannot kick anything off on its own. They depend on
skills-evals files that don't exist on main; running them against
main would fail at the pytest step. They are only meaningful when
dispatched with ref=opencode-evals.

Signed-off-by: Tanzim Saqib <[email protected]>

Roll forward the two manual-codex-judge*.yml files on main to match
what feat/codex-eval-backend currently carries. Workflow_dispatch
parses the YAML from main, so the iterative fixes on the feat branch
weren't visible to the Actions tab until this lands.

Cumulative changes since the initial registration in #13:
- Install LiteLLM proxy via `uv tool install` (was pip+setup-python).
- Drop a `cp .../litellm_proxy_hooks.py /tmp/litellm/` step so LiteLLM
  can resolve the hook module (it looks relative to the config file's
  directory, not PYTHONPATH).
- Register the hook via `litellm_settings.callbacks` so non-function
  tools (codex's namespace / MCP groupings) are stripped before
  forwarding to DeepSeek.
- Set `reasoning_effort: none` on both deepseek-v4-* models so
  thinking mode is disabled and codex doesn't have to round-trip
  `reasoning_content` (which it doesn't know about).
- Move `setup-uv` above the litellm step so `uv tool` is available
  for the proxy install; remove the obsolete `setup-python` step.

Workflows remain `workflow_dispatch:` only and depend on skills-evals
code (driver, hook, tests, conftest changes) that lives only on
feat/codex-eval-backend. Dispatch them with ref=feat/codex-eval-backend
until #11 merges.

Signed-off-by: Tanzim Saqib <[email protected]>

* ci: register kilo eval workflows on main

GitHub Actions registers `workflow_dispatch` triggers from the default
branch only. Until `manual-kilo-judge.yml` exists on `main`, it won't
show up in the Actions tab and `gh workflow run` will refuse it — even
when targeting the feature branch that holds the implementation. This
is the small focused PR described in
`docs/internal/adding-agent-eval-backend.md` §6, same shape as PR #12
(copilot) and PR #13 (codex).

The file is copied verbatim from `feat/kilo-eval-backend` (PR #16). No
code changes, no test changes, no doc changes.

Safe to merge now:

- `workflow_dispatch:` only — no push / pull_request / schedule
  triggers, so merging this PR cannot run anything on its own.
- The job depends on skills-evals files (`kilo_driver.py`,
  `test_kilo_*.py`, the `X_X_AGENT_UNDER_TEST`-aware conftest) that
  don't exist on `main` yet. Dispatching against `main` would fail at
  the pytest step; the workflow is only meaningful when dispatched
  with `ref=feat/kilo-eval-backend`.
- No new secrets. `DEEPSEEK_API_KEY` is already configured for the
  other manual-*-judge workflows.

After merge: open Actions, pick "manual / kilo code <- llm judge", set
**Use workflow from: feat/kilo-eval-backend**, and dispatch.

Signed-off-by: Tanzim Saqib <[email protected]>

* ci: add user-scope variant to the kilo registration

Mirrors the project-scope manual-kilo-judge.yml with
X_X_INSTALL_SCOPE=user added so `x-x init` lands skills under
~/.kilo/skills/ instead of <workspace>/.kilo/skills/. Matches the
existing claude/codex/copilot patterns where every backend ships
both scope variants.

Same merge-safety story as the project-scope file: workflow_dispatch
only, depends on skills-evals files from feat/kilo-eval-backend (#16)
that aren't on main yet, no new secrets.

Signed-off-by: Tanzim Saqib <[email protected]>

---------

Signed-off-by: Tanzim Saqib <[email protected]>

* ci: sync codex eval workflows on main with latest fixes

Roll forward the two manual-codex-judge*.yml files on main to match
what feat/codex-eval-backend currently carries. Workflow_dispatch
parses the YAML from main, so the iterative fixes on the feat branch
weren't visible to the Actions tab until this lands.

Cumulative changes since the initial registration in #13:
- Install LiteLLM proxy via `uv tool install` (was pip+setup-python).
- Drop a `cp .../litellm_proxy_hooks.py /tmp/litellm/` step so LiteLLM
  can resolve the hook module (it looks relative to the config file's
  directory, not PYTHONPATH).
- Register the hook via `litellm_settings.callbacks` so non-function
  tools (codex's namespace / MCP groupings) are stripped before
  forwarding to DeepSeek.
- Set `reasoning_effort: none` on both deepseek-v4-* models so
  thinking mode is disabled and codex doesn't have to round-trip
  `reasoning_content` (which it doesn't know about).
- Move `setup-uv` above the litellm step so `uv tool` is available
  for the proxy install; remove the obsolete `setup-python` step.

Workflows remain `workflow_dispatch:` only and depend on skills-evals
code (driver, hook, tests, conftest changes) that lives only on
feat/codex-eval-backend. Dispatch them with ref=feat/codex-eval-backend
until #11 merges.

Signed-off-by: Tanzim Saqib <[email protected]>

* fix: disable deepseek thinking via extra_body, not reasoning_effort

Same fix as on the feat branch — reasoning_effort=none was ignored
(DeepSeek's schema only accepts "high" or "max"). The actual
disable is `thinking: { type: "disabled" }` passed via extra_body
so LiteLLM merges it into the upstream request body.

Signed-off-by: Tanzim Saqib <[email protected]>

---------

Signed-off-by: Tanzim Saqib <[email protected]>