bchanot/claude
1
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(prune-memory): RED-7 fictional example IDs + RED-8 accepted limit

Browse Source 
RED-7 (example-priming): the STEP-2 worked example named live IDs (LRN-014 +
LRN-016) and modeled merging them — but they are complementary (header-ids vs
checkbox-CSS), a merge the skill's own rule forbids. Live IDs in an example prime
the skill to act on those exact entries on real data. Fictionalized the whole
STEP-2 example to 9xx IDs (cannot match a live registry); the merge example now
models a same-concept merge. Closed by a DETERMINISTIC test (run-deterministic.sh
RED-7: the example must carry only 9xx ids) per LRN-046, not a flaky behavioral
fixture. The test caught its own ugrep false-green first (a leading-dash pattern
parsed as an option) — fixed via /usr/bin/grep, the same dodge the skill's verify
already uses at line 189.

RED-8 (added-negation inversion): re-reviewed, consciously accepted as a documented
limit in BACKLOG — remote (compression subtracts tokens), and an FP-safe increase
check is non-trivial (needs the HEAD entry-id set to exclude legit new/merged 0->N);
a noisy guard is worse than the honest limit on a destructive skill (LRN-047).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01C6bUdvHnajCNzgVQefZowj
This commit is contained in:
Bastien Chanot
2026-06-29 19:25:42 +02:00
co-authored by Claude Opus 4.8
parent ce4391a62f
commit 5821ce2017
3 changed files with 44 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/prune-memory/tests/run-deterministic.sh
+16 -1
View File
@@ -1,5 +1,5 @@
#!/usr/bin/env bash
# Deterministic RED suite for /prune-memory — RED-1, RED-2, RED-5, RED-6.
# Deterministic RED suite for /prune-memory — RED-1, RED-2, RED-5, RED-6, RED-7.
# Each MUST be red on the current (v1) skill. Pure mechanical oracles,
# no LLM. Faithful: RED-2/RED-6 execute the REAL bash blocks extracted
# from SKILL.md (no copy that could drift).
@@ -83,6 +83,21 @@ else
green 6 "verify does not false-orphan the title-less heading"
fi
# ---- RED-7: STEP 2 plan example must use FICTIONAL ids, never live registry ids
# Live ids in the worked example PRIME the skill to act on those exact entries on
# real data (observed 2026-06-25: it merged the example's LRN-014 + LRN-016 on the
# live learnings.md, though they are complementary, not overlapping). Fictional ids
# (9xx) cannot match a real registry. Reads SKILL.md only — sandbox-safe.
# /usr/bin/grep (not the system grep, which may be ugrep — a leading-dash pattern
# like `-9..` is then misparsed as an option, erroring to an empty + FALSE GREEN).
ex7="$(awk '/^PRUNE PLAN/{f=1} f{print} /^Approve per category/{f=0; exit}' "$SKILL")"
bad7="$(printf '%s\n' "$ex7" | /usr/bin/grep -oE '(BDR|LRN|BLK|EVAL)-[0-9]+' | /usr/bin/grep -vE '9[0-9][0-9]$' | sort -u | tr '\n' ' ')"
if [ -n "${bad7// /}" ]; then
red 7 "STEP 2 example uses LIVE-range ids (prime real-data ops): ${bad7% }"
else
green 7 "STEP 2 example uses only fictional (9xx) ids"
fi
echo "----"
if [ "$fail" -eq 0 ]; then
echo "SUITE: all GREEN"