feat(directives): harvest 6 process anti-pattern directives from AGENTS.md + workflow.md

2026-07-02 22:09:05 -04:00
parent c8094ec225
commit 77ee0c68fd
6 changed files with 113 additions and 0 deletions
@@ -0,0 +1,16 @@
+# deduction_loop_limit — v1
+
+**Why this iteration:** Lifted verbatim from `AGENTS.md` §"Process Anti-Patterns" #1 (lines 119-125). This is the baseline encoding — the symptom-rule-pair style currently in production.
+Future variants will test alternative encodings (rule-only, tabular) against this baseline.
+
+**Source:** `AGENTS.md:119-125`
+
+---
+
+### 1. The Deduction Loop (kill it)
+
+**Symptom:** Run test → fail → read log → form hypothesis → run again → fail differently → add diag → run again → fail again → loop. You end up running the same test 4+ times in one session, each run reading partial log output.
+
+**Rule:** You are allowed to run a failing test at most **2 times** in a single investigation. After the 2nd failure, STOP running the test. Read the relevant source code (`get_file_slice` or `py_get_skeleton`), predict the failure mode from the code, and instrument ALL the relevant state in one pass before the next run. If the test still fails after 1 instrumented run, report to the user — do not loop.
+
+**Worst case captured upfront.** Before running the test, ask: "what is the worst-case information I will need if this fails?" Add the diag for that, then run. The diag lines themselves are wasteful in production — see "No Diagnostic Noise in Production" below.