pj b8431c3e13 test(runner): both policies must dispatch the same authored action ...

Compares the recorded driver calls across 13 authored shapes. The builtin path
had a parity guard and the authored path had none, which is why it drifted on
almost every verb.

Claude-Session: https://claude.ai/code/session_01A5KmftdEJ49A9z5mF5ESrX

2026-08-12 23:51:01 +05:30

..

testdata

UX refactor (#52)

2026-06-02 09:52:53 +05:30

authored_action_parity_test.go

test(runner): both policies must dispatch the same authored action

2026-08-12 23:51:01 +05:30

golden_test.go

UX refactor (#52)

2026-06-02 09:52:53 +05:30

llm_source_test.go

test(runner): the echo guard admits a repeated description

2026-08-12 23:32:24 +05:30

llm_source.go

feat(runner): thread the label source to the model picker

2026-08-12 23:19:24 +05:30

runner_test.go

fix(runner): report every action that was chosen and never dispatched

2026-08-12 23:32:24 +05:30

runner.go

fix(runner): report every action that was chosen and never dispatched

2026-08-12 23:32:24 +05:30

source.go

feat(runner): thread the label source to the model picker

2026-08-12 23:19:24 +05:30

web_extractor_trace_test.go

fix ltl semantics and unify action enumeration (#71)

2026-08-12 18:06:04 +05:30