GameCult/Eureka
Watch
9
0
Fork
You've already forked Eureka
 0
Code Issues Pull requests 3 Projects Releases Packages Wiki Activity Actions

test-tools: admit R9 Unavailable names the tool kind; R8 budget and unchecked-member cases; restore two literal CRs in the context-pack fixtures

Browse source 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
Eureka 2026-10-23 19:41:06 +02:00
commit da193e3e02
1 changed files with 11 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

20
tools/test-tools.sh
View file

@ -235,8 +235,7 @@ g() { git -C "$R" -c user.name=t -c user.email=t@t -c core.autocrlf=false "$@" >
seqf() { local i; for i in $(seq 1 "$2"); do echo "$1$i"; done; }
g init -q
seqf a 40 >"$R/a.txt"; seqf b 40 >"$R/b.txt"; seqf c 10 >"$R/c.txt"; seqf d 20 >"$R/d.txt"
seqf e 10 >"$R/e.txt"; seqf f 20 >"$R/f.txt"; seqf g 300 >"$R/big.txt"; seqf h 5 | sed 's/$/
/' >"$R/h.txt"; seqf m 40 >"$R/m.txt"
seqf e 10 >"$R/e.txt"; seqf f 20 >"$R/f.txt"; seqf g 300 >"$R/big.txt"; seqf h 5 | sed 's/$/ /' >"$R/h.txt"; seqf m 40 >"$R/m.txt"
g add -A; g commit -q -m base; BASE=$(git -C "$R" rev-parse HEAD)
{ sed -n 1,5p "$R/a.txt"; printf 'ins1\nins2\nins3\n'; sed -n '6,$p' "$R/a.txt"; } >"$R/a.new"; mv "$R/a.new" "$R/a.txt"
sed -e '2,3d' -e 's/^b10$/b10-EDITED/' "$R/b.txt" >"$R/b.new"; mv "$R/b.new" "$R/b.txt"
@ -277,8 +276,7 @@ cin "hunk ending just before the range shifts it" "[23] b.txt:4-5 MOVED(-2) ->
cin "NEW file present in the worktree gets a window" "== [24] n.txt:1-2"
cin "NEW window shows the file" " 2 n2"
cin "CRLF window text" " 2 h2"
{ tr -d '
' <"$T/cp.out" | cmp -s - "$T/cp.out"; } && echo "ok context-pack CRLF is stripped from windows" || { echo "FAIL context-pack CR in output"; fail=1; }
{ tr -d ' ' <"$T/cp.out" | cmp -s - "$T/cp.out"; } && echo "ok context-pack CRLF is stripped from windows" || { echo "FAIL context-pack CR in output"; fail=1; }
cin "window numbers are worktree lines" " 6 b8"
cin "window shows the edit" "b10-EDITED"
cin "GONE window is labelled AT BASE" "== [7] c.txt:2-3 AT BASE"
@ -903,6 +901,7 @@ check("R4 the first agent's retry still passes", silent(r) and calls == [])
# R2 nothing to check: zero calls, empty stdout
for label, hh, kw in [("a batch with no ruling or question", hook([doc("finding", "f", "x"), doc("cut_report", "c", "y")]), {}),
("an empty batch", hook([]), {}),
("a ruling with an empty title", hook([doc("ruling", "x", "")]), {}),
("a ruling with no title", hook([{"kind": "ruling", "value": {"campaign": "t", "label": "x"}}]), {}),
("a tool other than admit", hook([mine], tool_name="mcp__eureka-state__view"), {}),
("malformed stdin", None, {"stdin": b"not json"}),
@ -957,9 +956,12 @@ r, calls, ms = run(hook(five))
check("R8 five rulings make three queries, the first three titles, and the reason counts two unchecked",
len(calls) == 3 and sorted(c["semantic"]["text"] for c in calls) == ["Title 0", "Title 1", "Title 2"]
and reason(r).split("\n")[-1] == "2 rulings or questions over RECALL_ADMIT_MAX were not checked.", (calls, reason(r)[-120:]))
r, calls, ms = run(hook(five), RECALL_ADMIT_MAX="1", RECALL_BUDGET="900")
check("R8 RECALL_ADMIT_MAX=1 checks one, counts four, and the whole reason fits RECALL_BUDGET",
len(calls) == 1 and reason(r).endswith("4 rulings or questions over RECALL_ADMIT_MAX were not checked.") and len(reason(r)) <= 900, len(reason(r)))
r, calls, ms = run(hook(five), RECALL_ADMIT_MAX="1", RECALL_BUDGET="560")
check("R8 RECALL_ADMIT_MAX=1 checks one, counts four, and the whole reason, trimmed to fit, stays within RECALL_BUDGET",
len(calls) == 1 and reason(r).endswith("4 rulings or questions over RECALL_ADMIT_MAX were not checked.") and len(reason(r)) <= 560
and len(reason(r).split("\n")) == 3, len(reason(r)))
r, calls, ms = run(hook(five), items=[item("r3", "An unchecked batch member")] + NB)
check("R8 a ruling in the batch that was not checked is still never listed as a neighbour", held(r) and "t:ruling:r3" not in reason(r), reason(r)[:300])
r, calls, ms = run(hook(five[:3]))
check("R8 three rulings are all checked and nothing is counted unchecked", len(calls) == 3 and "RECALL_ADMIT_MAX" not in reason(r).split("\n")[-1])
@ -976,7 +978,7 @@ def failcase(label, kind, expect_calls, setup=None, env=None, **kw):
check("R9 %s: a note naming %s, no decision, nothing recorded" % (label, kind), ok, (r.stdout[:200], r.stderr[:100], len(calls)))
check("R9 %s: no byte of the input appears" % label, CANARY.encode() not in r.stdout + r.stderr)
return hh
failcase("Unavailable", "transport", 1, env={"FAKE_MODE": "unavailable"})
failcase("Unavailable", "tool", 1, env={"FAKE_MODE": "unavailable"})
failcase("an unparsable answer", "answer", 1, env={"FAKE_MODE": "garbage"})
failcase("a binding that dies", "transport", 1, env={"FAKE_MODE": "die"})
failcase("no binding", "binding", 0, env={"HOME": T + "/nohome", "USERPROFILE": T + "/nohome"})
@ -989,7 +991,7 @@ try:
failcase("an unwritable store (the deny is not printed before the record)", "store", 1, setup=dangling)
except OSError:
check("R9 an unwritable store (symlinks unavailable here)", True)
hh = failcase("Unavailable", "transport", 1, env={"FAKE_MODE": "unavailable"})
hh = failcase("Unavailable", "tool", 1, env={"FAKE_MODE": "unavailable"})
r, calls, ms = run(hh)
check("R9 after a failed check the same batch is still held on its first real check", held(r))