feat: configurable model + effort for agent commands#33
Merged
Conversation
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
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
fazxes
added a commit
that referenced
this pull request
Apr 5, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
claude_model,claude_effort,codex_model,codex_thinkingconfigurable via.nightshift.jsonkeys and environment variables (NIGHTSHIFT_CLAUDE_MODEL,NIGHTSHIFT_CODEX_MODEL,NIGHTSHIFT_CODEX_THINKING)NightshiftConfigthrough all three command builders (command_for_agent,plan_command_for_agent,_build_subagent_command) and every caller in the chainapproval_policypattern to--dangerously-bypass-approvals-and-sandboxlib-agent.sh)Files Changed (17)
nightshift/types.py,constants.py,config.py-- new config fields + env var overridesnightshift/cycle.py,planner.py,subagent.py-- updated command buildersnightshift/cli.py,feature.py,integrator.py,profiler.py-- callers pass configtests/test_nightshift.py-- 8 new tests (536 total).nightshift.json.example, docs (handoff Address quality issues from PR #13 review #20, changelog, task feat: cost tracking and budget ceiling for daemon sessions #35, learning)Test plan
make checkpasses (mypy, ruff, 536 tests, dry-run, ASCII check)