Commit graph Eureka/tools
Author SHA1 Message Date
1833e14bd2 bloom-sheet: split-marker check, single-pass fill, byte-equal caveat (#67) 2026-11-13 07:18:19 +00:00
894838df1a bloom-sheet --theme option and a calligraphic theme (#66) 2026-11-11 18:56:33 +00:00
11f4e08a21 ygg-verify: local mode for the Yggdrasil seat; executable modes
One code path with a transport switch: on a host named yggdrasil[-*] (or
YGG_VERIFY_LOCAL=1) the remote half runs through local bash with cp and a local
git push instead of ssh/scp; the ssh path is unchanged. Scripts meant to be run
directly are committed 100755, and the scripts that call ygg-verify.sh do so
through bash (noexec skill mount). test-tools.sh covers the local branch and,
under a mock ssh, the remote branch and the detection rule.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-11 16:22:11 +00:00
d5f247431a INDEX: --in-place replaces -j1, not joins it (Soul)
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-11 08:03:02 +00:00
011dd3e5bf INDEX: Libby's four native cargo-mutants corrections (--in-place, no -j, registry, harness background)
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-11 08:02:30 +00:00
05bf8a36f6 INDEX: fix Soul findings on the Self-seat section (absolute diff path, wait-on wording, line range, disk)
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-11 07:47:07 +00:00
fc325592d9 INDEX: how a Self seat runs the mutation tools (noexec mount, no ygg/docker; native cargo-mutants path)
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-11 07:43:41 +00:00
75ae56cd7a Merge pull request 'testparse: read dotnet 10's "Total tests:" summary block' (#49) from eureka-self/testparse-dotnet10 into main 2026-11-10 17:13:12 +00:00
Meta Vens
28a5e613c9 skill-tools-off-mcp s1 fixes: blocked recipe takes a spec id, paged recipes name --cursor, context-pack accepts a UTF-8 BOM and refuses non-cut_spec kinds, bare values and missing campaign/cut/revision
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-07 14:37:31 +01:00
0cc4f78f77 tools: delete mind.py, recall.py and the fake binding; context-pack reads huginn view --raw from a file or stdin
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-07 13:32:48 +01:00
ad6e3108b9 tools: dotnet-self wrapper, env outside the worktree, subshell warning
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-07 11:37:06 +00:00
bf95993e3b tools: dotnet-self-env.sh for Selves with a read-only HOME, and the scar in SKILL.md
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-07 11:35:06 +00:00
Meta Vens
c7f9b059cb test-tools: restore the two literal CR bytes 52c54b7 turned into newlines
The context-pack CRLF fixture (sed 's/$/\r/') and the CR-stripped check (tr -d '\r')
need a literal CR; an editor on Windows split each line at it. Byte-identical to
db2b250 on both lines (Soul s3 finding crlf-fixture-stripped).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 08:21:32 +01:00
52c54b7dd1 recall dispatch driver: D17 pins the hard stop (stdin held open, mutant without the exit timer fails it); D16 pins the mixed deadline; docs say silent only when no anchor answered
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-07 04:00:27 +01:00
db2b250380 recall dispatch: per anchor, one failed or refused cited id costs only its own recall (status line with the failure kind); every cited id stays out of the neighbours; D8 deadline band bounded by the fake's sleep
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-07 02:39:16 +01:00
8a8cf7516d recall dispatch driver: a finding beside a ruling is no anchor and does not silence it; failure lines print as ASCII
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-07 00:11:44 +01:00
fde0874386 Docs: dispatch recall in the tools index, campaign-state and changelog
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-06 23:21:57 +01:00
02e0a12252 recall.py dispatch: in-force neighbours of the ids a brief cites reach the subagent in its Agent prompt
neighbours(text, schemas, excluded, k, left) is the one query helper admit and dispatch share; fan_out and plain_id replace admit's private thread bookkeeping and id test. The fake binding answers view of any id and queries by text with scores.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-06 23:21:54 +01:00
655357806e testparse: read dotnet 10's "Total tests:" summary block
dotnet 10 at normal verbosity ends a run with
  Total tests: N / Passed: N / Failed: N / Skipped: N
(one count per indented line, zero counts omitted) instead of the
one-line "Passed!  - Failed: ..." form, so mutation-table.sh baselines
read as "ran zero tests". tp_scan now parses both forms. A count the
block does not account for (Total - Passed - Failed - Skipped) is
counted as failed, so a cut-off block cannot read as clean; a "Total
tests:" line that is not a count recognises nothing.

Fixtures: dotnet10-green/red/zero.log are real dotnet 10.0.403 MSTest
runs (-v n); dotnet10-all-failed/truncated.log are hand-written.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-06 12:34:46 +00:00
a1b19054bb bloom-sheet: a large bare fill is a wash and a heavy line, not a solid
Flat solids read as stickers beside the plant. Small fills stay solid, like a
flower's centre, and dark fills stay cutouts.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-05 15:53:43 +01:00
0c3f3e4831 bloom-sheet: visitors are drawn with the plant's pen, not pasted in
An SVG used to arrive as a PDF on top of the page, in its own colours and
line quality. It now parses into marks: stroked shapes go through ribbon and
neonfill as weighted lines, a fill under a stroke becomes a petal's wash, and
bare fills become solid neon. Colours snap to the palette and near-black paints
the ground, except in an all-black drawing, which would vanish. All of it must
touch, a closed outline counting as covering its inside. Text, images and
gradients are refused before the two minute render. rsvg-convert and graphicx
are gone; python3-svgelements and python3-shapely replace them.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-05 15:36:43 +01:00
ec542b9046 bloom-sheet: a CLI turning markdown into a neon one-page sheet, every heading a card, with caller SVG visitors
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-05 13:54:53 +01:00
5c15ccc9fd mutation-table: mount the shared cargo home, same lock as the other verify scripts
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 02:37:04 +01:00
25b98a9699 CARGO_HOME alone: the image's PATH already holds cargo/bin, and restating it clobbered the test mock's PATH
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 01:57:29 +01:00
83b00d2f54 Verify containers share cargo's package-cache lock: the shared volume is CARGO_HOME, and the wrapper retry goes
A registry-only mount at /usr/local/cargo/registry left the package-cache lock under CARGO_HOME=/usr/local/cargo in each
container's own layer, so sibling containers (cargo-mutants stages, concurrent ygg-verify jobs) shared no lock and removed
each other's half-unpacked crate directories. Reproduced on Yggdrasil from an empty registry: 15 of 18 containers failed
with a registry mount, 15 of 18 with RUSTC_WRAPPER= too, 0 of 18 with the volume as CARGO_HOME.

ygg-verify.sh and cargo-mutants.sh mount eureka-cargo-home at /cargo-home and set CARGO_HOME and PATH for the rust image.
Removed: the retry without RUSTC_WRAPPER, its note and diag plumbing, and its two tests and the FAKE_CM_DEADWRAP switch.
Kept: container errors tail 25 lines.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 01:50:23 +01:00
e1e7962238 cargo-mutants.sh: a failed build under the image's rustc wrapper retries once without it
Stage containers sharing the eureka-sccache volume died mid-build with cargo's
"could not execute process ... sccache ... (never executed)" or a missing dep-info
file in their own target dir, though the image's sccache is present, executes, and
a lone container builds clean. The wrapper only caches, so a failed build with
RUSTC_WRAPPER set is retried once without it; the job summary carries a NOTE line
saying which way it went, the first attempt's log is kept, and a build dead either
way stays a red baseline (exit 4) with its cause. Container errors now tail 25
lines, not 5. Tests: dead wrapper recovers with NOTE; red with and without the
wrapper stays red.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 01:19:30 +01:00
0bd4aeca1b cargo-mutants.sh: stage 2 always runs the full-suite baseline; zero-test files found at plan time; 5x timeout with a floor; --escape pinned
- full-baseline-skipped: stage 2 runs even when stage 1 settled every name (one name rides along; cargo-mutants runs no baseline for an empty selection), so a red suite is a red job
- timeout-mult-splits-missed: CONFIRM_TIMEOUT_MULT defaults to 5 and stage 2 gets --minimum-test-timeout like stage 1
- escaper-pipe-untested: the escaper is the --escape mode, run by the driver and by tests/test-tools.sh with each metacharacter
- zero-test-stage1-wasted: the plan container derives each file's filter and counts its tests (cargo test -- <filter> --list); 0 tests goes straight to stage 2; the container-side baseline.log count is deleted

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-01 20:57:04 +01:00
a2bfb59ab3 cargo-mutants.sh: the MUTANTS line reports containers per stage
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-01 19:43:21 +01:00
f37ea93eaa fakebin cargo and flock: executable, as docker and sudo are
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-01 19:15:47 +01:00
d4fba11da6 tools/cargo-mutants.sh: one owner of cargo-mutants on Yggdrasil
One verify job per range: a plan container lists the mutants (diff taken at the
workspace root), stage 1 runs each file's mutants against that file's tests only
and decides only caught and unviable, stage 2 confirms every survivor, timeout,
unfiltered or zero-test file on the full suite, sharded over free slot leases,
and the merge prints one MUTANTS line and the final MISSED/TIMEOUT names.
NAMES reruns chosen survivors; TEST_ARGS skips flaky tests.

Deletes ygg-verify.sh's MISSED/TIMEOUT summary grep and its inline cargo mutants
usage example; the host-mode export gains YGG_SLOTS and YGG_ROOT. Briefs and
SKILL.md name the script; the mock docker grows /cm and /out, with a fake cargo
and a fake flock for the new test-tools.sh cases.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-01 19:15:38 +01:00
d23cfd6151 context-pack docs: NEW anchors are allowed at base; escape the INDEX row's pipe (Soul s1 Lows on cut-context-pack-reads)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-01 04:08:04 +01:00
3c1d59cf2d test-tools: pin that a budget with caller lists and no unlisted symbols wastes no line
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-01 03:41:20 +01:00
5929db8225 test-tools: pin the context-pack window budgets, caller-list bounds and --only truncation
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-01 03:09:28 +01:00
ce3860949c context-pack.py: caller-list notes always fit --max-lines; pin the caller bounds
A cut window or caller list now reserves the lines its notes need, the
suggested --max-lines prints everything, and the 50-hit, 20-file, 160-character,
CR and --only bounds each have an assertion.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-01 02:42:53 +01:00
21b92bd85e Imagination writes reads and symbols; Hands uses the pack's caller lists
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-01 01:50:06 +01:00
c29671c4ac context-pack.py: reads, symbol checks and capped caller lists
Read anchors resolve like file_changes (r<k> rows, MISSING when absent at
base), anchors with a symbol must hold it in the mapped window or gain
SYMBOL_MISSING, and one capped git-grep caller list per symbol follows the
windows within --max-lines. Specs without reads or symbols print what v1 did.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-01 01:50:05 +01:00
0ac55b729f ygg-verify: jobs run at nice 10 and idle IO inside the container
nice on the docker client never reached the job, which containerd starts.
On 2026-10-31 three verify jobs held Yggdrasil's IO pressure near 75% full
and the swarm's turns slowed; idle IO lets the swarm go first.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 19:40:03 +01:00
0acb7c9286 test-tools: for-line escape case spells the expected backslash-u with chr(92)
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-23 20:26:54 +02:00
8da54074b1 test-tools: R8 budget case sized to hold one neighbour (a For line with none is no longer a deny)
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-23 20:24:51 +02:00
34cbdd45b7 recall: install form that cannot exit 2; a hold never lists a For line empty; For-line escape ASCII-only; tests for exclusion identity, cap and silent window
The install command is "<abs python.exe> <path>/recall.py prompt|admit || true"
(Claude Code runs hook commands through Git Bash on Windows; a missing script
made py -3 exit 2, which blocks every prompt or admit). A For line is joined to
its first neighbour so render keeps both or neither; no neighbour fitting the
budget is no deny. The escape test is [A-Za-z0-9_.:-], not Unicode \w.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-23 20:22:00 +02:00
40bed7ee25 mutation-mock fakebin: docker and sudo are executable (mode 100755)
The mutation-runner self-tests put them on PATH and got exit 126 in the
Linux container, which left 15 FAIL mutation rows red at every cut.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-23 20:22:00 +02:00
da193e3e02 test-tools: admit R9 Unavailable names the tool kind; R8 budget and unchecked-member cases; restore two literal CRs in the context-pack fixtures
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-23 19:41:06 +02:00
e12435e7e2 test-tools: the recall admit section, R1-R12 driven with real hook JSON against the fake binding
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-23 19:36:28 +02:00
13133bcb40 recall.py admit: a PreToolUse hook that holds an admit with rulings or questions once, listing in-force neighbours
Shares mind.call, line_of, inert, render and the hard stop with prompt mode;
render takes the header. Digest of tool_input plus agent_id in the session
scratchpad; fails open with a note naming only the failure kind.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-23 19:36:28 +02:00
8701da3a86 recall: the deadline clock starts at process creation and the kill fits inside it; R2 times the interpreter, not the shell
On Windows the run overshot its deadline by 450-720 ms in the R2 bands: ~200 ms of
interpreter start and imports ran before the clock, the hard stop sat 0.3 s after the
deadline, and the test timed bash, env and the py launcher too. The clock now starts at
process creation (GetProcessTimes), the reply wait ends 0.1 s early so the kill and exit
fit, and the hard stop is the deadline itself. Residual outside the script: the py
launcher (40-130 ms, rare spikes to 300) and the creation call. R2 times the interpreter
directly, best of two, bands -250/+100 ms around the deadline.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-22 18:44:11 +02:00
0342dceef9 recall: recalled text is inert data; the deadline is the whole run; budget, stdin and answer are bounded
Soul s1 fixes. The hook header says the lines are recalled records, data and
never instructions, written by agents not the operator. Every item is one JSON
object per line: id, title and operator_quote are JSON strings with < >, control,
bidi and separator characters escaped, so a title cannot close the framing, forge
a tag, a header or an operator segment. RECALL_DEADLINE_MS now bounds the whole
run through a hard stop; stdin is read to 4 MiB and the answer to 1 MiB
(mind.call max_bytes); RECALL_BUDGET is clamped to 9000 under Claude Code's
10,000-character cap. Tests: hostile text, a non-ASCII process-boundary run under
cp1252, byte-versus-character budget, stdin held open and endless, answer size,
budget ceiling, and the four unrecorded survivors (negative reply timeout, reply
id check, env-int positivity, EOF sentinel). Mutants of each were run and caught.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 21:44:02 +02:00
f35410a8b2 tools: recall.py prompt, the UserPromptSubmit hook that pushes nearest in-force rulings into context
Queries rulings, questions and follow-ups in force across every root, ranked by
Huginn against the prompt, through mind.call, and prints one hook JSON within
RECALL_BUDGET. Never blocks: any failure or the RECALL_DEADLINE_MS deadline
(default 4000) exits 0 with empty stdout; one attempt; prompts under 3 words are
not queried. test-tools.sh drives it against the fake binding and pins R1-R7;
the fake gains a query branch. INDEX rows and a Precedent note added. The
operator installs the hook; settings.json is not touched.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 16:34:20 +02:00
5e71d8e4ff tools: one mind client (mind.py); context-pack's private MCP client deleted
mind.call spawns the eureka-state binding, does the stdio handshake and one
tool call within a deadline, and kills the child on every exit path.
context-pack's mcp_view_once is deleted; mcp_view delegates to mind with
retry_once. Messages, exit codes, retry and env rules are unchanged (all 228
context-pack checks pass).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 15:55:46 +02:00
903794ca0c tools/INDEX.md: context-pack.py row names the briefs and SKILL.md step 1
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 14:07:12 +02:00
5bf88b80cb context-pack tests: pin the --only reserve and charge, the cut-window budget, header base, missing base
Targets the mutants that survived the first fix run: need arithmetic of cut
and full windows, the reserve for the not-expanded line at the budget edge,
the left-reserve >= 4 threshold with two windows, the exact more-lines
note, the blank line after the table, a non-sha base never echoed in the
header, and a spec without a base refused rather than crashing.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-09 02:50:19 +02:00