Skip to content

feat: configurable model + effort for agent commands#33

Merged
fazxes merged 1 commit intomainfrom
feat/configurable-model-effort
Apr 5, 2026
Merged

feat: configurable model + effort for agent commands#33
fazxes merged 1 commit intomainfrom
feat/configurable-model-effort

Conversation

@fazxes
Copy link
Copy Markdown
Member

@fazxes fazxes commented Apr 5, 2026

Summary

  • Make claude_model, claude_effort, codex_model, codex_thinking configurable via .nightshift.json keys and environment variables (NIGHTSHIFT_CLAUDE_MODEL, NIGHTSHIFT_CODEX_MODEL, NIGHTSHIFT_CODEX_THINKING)
  • Thread NightshiftConfig through all three command builders (command_for_agent, plan_command_for_agent, _build_subagent_command) and every caller in the chain
  • Update Codex CLI flags from old approval_policy pattern to --dangerously-bypass-approvals-and-sandbox
  • Config priority: config file > env var > DEFAULT_CONFIG (matches lib-agent.sh)

Files Changed (17)

Test plan

  • make check passes (mypy, ruff, 536 tests, dry-run, ASCII check)
  • New tests cover: custom model in codex/claude commands, env var overrides, config file overrides, old approval_policy flags removed

Make claude_model, claude_effort, codex_model, and codex_thinking
configurable via .nightshift.json and environment variables. Thread
NightshiftConfig through command_for_agent, plan_command_for_agent,
_build_subagent_command, and all their callers. Update Codex CLI flags
from old approval_policy pattern to --dangerously-bypass-approvals-and-sandbox.

Config priority: config file > env var > DEFAULT_CONFIG.
Env vars: NIGHTSHIFT_CLAUDE_MODEL, NIGHTSHIFT_CODEX_MODEL, NIGHTSHIFT_CODEX_THINKING.

Closes #35. 536 tests passing.
@fazxes fazxes merged commit bd23cc4 into main Apr 5, 2026
2 checks passed
@fazxes fazxes deleted the feat/configurable-model-effort branch April 5, 2026 04:36
fazxes added a commit that referenced this pull request Apr 5, 2026
Require agents to quote a specific learning from docs/learnings/INDEX.md
in status reports and handoffs, creating an auditable trail that learnings
are being read and applied, not just written.

Changes:
- evolve.md: add "Learnings applied" to Step 1 status report, Step 6b
  handoff requirements, and Step 12 session report
- PRE-PUSH-CHECKLIST.md: add learnings verification in Part 3
- handoffs/README.md: add "Learnings Applied" section to template
- New tasks #65 (E2E test runner, loop2) and #66 (auto-release, self-maintaining)
fazxes added a commit that referenced this pull request Apr 5, 2026
docs: learnings verification in status reports (task #33)
fazxes added a commit that referenced this pull request Apr 5, 2026
)

Agent-facing contributor guide covering quality gates, branch/PR conventions,
registration checklist, and resident daemon handling of external PRs.
Also archives completed tasks #31, #33, #61.
fazxes added a commit that referenced this pull request Apr 5, 2026
)

Agent-facing contributor guide covering quality gates, branch/PR conventions,
registration checklist, and resident daemon handling of external PRs.
Also archives completed tasks #31, #33, #61.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant