You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 88dcfe9
Browse filesBrowse the repository at this point in the historyBrowse files
Copy file name to clipboardExpand all lines: AGENTS.md
+5Lines changed: 5 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -103,6 +103,7 @@ An empty database is a bad test. Seed your worktree's `.t3` with a copy of real
103
103
- Use `vp run typecheck`, not `npx tsc`; it caches per package. Both run tsc-rs (`typescript` is the `@tsc-rs/typescript` drop-in).
104
104
- Run `node -e` snippets from `apps/server` or the owning package. `effect` does not resolve from the repo root.
105
105
- Test meaningful logic or observable behavior. Do not render components to static markup to assert props or attributes, or add tests that merely assert callback wiring or mirror the implementation.
106
+
-[Testing](docs/internals/testing.md) carries these same test rules, plus review guidance, for review bots. Change both together.
106
107
-**Do not run repo-wide checks.** No `vp check`, no `vp run -r test`, no `vp run -r typecheck` unless I ask. CI owns the full suite.
107
108
- Backend behavior changes ship with focused tests for that behavior.
108
109
- Proof for a bug fix depends on the bug. Logic, data, state, and protocol bugs get a failing test first (the fewest that fail on `main` for that reason, in the module's existing test file), then the fix. Purely visual bugs (spacing, colour, alignment, a layout shift) get before/after captures as their proof and no test: do not add UI tests for nitpicks, and do not ask for one in review when a capture already shows it. A server-only fix with no visible surface ships the test plus a short runtime transcript.
@@ -136,6 +137,10 @@ An empty database is a bad test. Seed your worktree's `.t3` with a copy of real
136
137
137
138
For authorized mobile verification, a missing or outdated native client is an install step, not a blocker. Run `vp run mobile:install <ios|android> [device-id]` on the device host before starting Metro; it targets the only booted simulator or connected Android device when the id is omitted. It installs the dev client for this checkout's native fingerprint from the shared cache in seconds and builds only when no machine has built it yet, so prefer it over `expo run:*`, `xcodebuild`, or `gradlew`, which rebuild from scratch. Its stdout is one JSON line; build output goes to the log it names. See `test-t3-mobile` for the full workflow.
138
139
140
+
## Evals
141
+
142
+
`evals/` checks how real models behave with T3 Code's model-facing text: agent instructions, MCP tool descriptions and schemas, and generated titles. Before you change that text, read [evals/README.md](evals/README.md) and run the evals it names. When you fix a model behavior bug, add a case that fails before the fix.
143
+
139
144
## Pull requests
140
145
141
146
- Never make a PR unless the developer explicitly asks you to do so.
`${reason}\n\nFalling back to the Windows backend so T3 Code can open. Re-enable the WSL backend from Settings > Connections once the WSL distro is fixed.`,
135
+
`${reason}\n\nFalling back to the Windows backend so T3 Code can open. Re-enable the WSL backend from Settings > Sharing & access once the WSL distro is fixed.`,
136
136
);
137
137
// Clear wslOnly too so enabling WSL cannot restore a failed mode.
138
138
// Keep the in-memory fallback if persistence fails.
0 commit comments