Commit graph Eureka/references
Author SHA1 Message Date
Meta Vens
17ce907ff0 Eureka: Soul checks git history before recommending a mechanism
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-29 16:36:16 +02:00
Meta Vens
dc26be5fc8 Eureka: a general library is judged by consumer expectation, not our call counts
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-29 16:11:35 +02:00
Meta Vens
19487f0f2e Hands brief: file-tool paths stay inside the named worktree
A Hands pass on Aetheria Cut 12.3 edited and built the main checkout by
using absolute Read/Edit paths, while its shell sat in the worktree.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-25 18:38:54 +02:00
Meta Vens
4855e60599 Treat split authority as a defect on sight, in Hands and Soul briefs
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-25 16:24:01 +02:00
Meta Vens
bd8dc2e4ed Rename the Mind Steward faculty to Life
Operator ruling, 2026-09-25: Epiphany and Aquarium call this organ Life
(role id `reorientation`), and it is "a much better fit as the actual
load-bearing organ". The eureka-site landing page already says Life.

SKILL.md (frontmatter description, faculty table, dispatch lines, step 6,
model allocation), README.md and briefs.md now say Life. The role itself is
unchanged. SKILL.md defers to global doctrine for the agent type, which the
operator owns and which still says mind-steward. Dated records keep the old
name: changelog entries as written, a note on the 2026-09-15 Epiphany
comparison, and "then called Mind Stewards" in the CultCache postmortem.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-25 14:59:59 +02:00
Meta Vens
7e2f66a2c4 Make Self size each cut against Hands' context budget
Operator direction, 2026-09-25: moderate inference spend mainly by making
cuts smaller, so each Hands agent carries less context. Sonnet degrades at
about 0.5M tokens.

SKILL.md step 3 now owns cut sizing: Self estimates the brief, the source
Hands must read, one verification and one fix round, and the item count,
treats 0.5M as the danger line, splits when the estimate passes about half
of it, and checks the reported token total afterwards. The Self-owned
clauses ("Self sizes a cut", one fix batch per file) moved out of the Hands
brief template into step 3; the Imagination template's split clause names
the budget. Section 5 no longer frames the 2026-09-23 spend as misplaced:
the operator counts it as legitimate work, the regret being the model.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-25 14:58:51 +02:00
Meta Vens
82afae1afc Record quota sizing, per-file fix batches, and greens that ran nothing
From the StreamPixels transport campaign, 2026-09-23 to 2026-09-24:
- SKILL.md section 5: quota is spent through scope. One Soul gate per cut,
  fix batches only for critical-path findings, and narrow passes for
  small deltas.
- briefs.md: one fix batch per file (800k and 550k runs); require a
  non-zero test count for each named file; a failure called
  "pre-existing" still needs a one-line cause.
- changelog: the evidence, with StreamPixels commit refs.

Staged by path. The unrelated uncommitted Ghostlight hunks in briefs.md
and changelog.md are left in the working tree.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-24 16:09:38 +02:00
Meta Vens
76fc62986b Record two more lessons from the Ghostlight play agent pass
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-23 11:54:35 +02:00
Meta Vens
301df32107 Name a tool's absolute path in every brief, and probe a redundancy before deleting
A brief said "use ygg-verify.sh" where earlier ones gave the full path. The
agent could not find it, verified the whole batch on the operator's
workstation instead, and said so plainly rather than claiming the bar was met.
A name is a guess; a path is an instruction. The brief must also say what to
do when a named tool is missing: stop and report, never substitute, because a
substitution can silently relocate work onto a host the load budget forbids.

Second scar. A redundancy ruling of Self's was wrong for the second time in
one campaign, and this one shipped: a guard was deleted on the premise that
aliases are unique per descriptor, which the source contradicts, and a legal
document shape then faulted on every hop path. Both Self and Hands reasoned
from the same unchecked property. Build the input that would need the guard
and watch the other authority handle it, or the argument is just the claim
restated.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-23 07:39:10 +02:00
Meta Vens
181e819131 Name the inference, not the line
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-23 06:45:25 +02:00
Meta Vens
75efac6d56 Confirm a survivor list at -j1 before ruling on it
The same commit mutated three times at -j4 gave three different survivor sets,
while every -j1 run reproduced the same one. Likely the shared cargo target
directory under concurrent builds, which is this file's existing scar wearing
a new hat.

A score survives concurrency roughly intact, because a genuinely killed mutant
stays killed. A survivor list does not, and survivors are what drive rulings.
Stryker's concurrency flag is in the same position, so figures taken at four
in earlier campaigns are provisional; the rulings they informed rest on the
hand-confirmed mutations beside them.

Second entry: three fixtures in two days passed by coincidence rather than by
rule. Values whose bit pattern happened to match the assertion, hashes that
happened to sort the right way, a file wrapped in a directory so a different
path ran. Breaking the rule and watching the test fail is what separates these
from coverage, and it is already in the brief.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-23 05:21:44 +02:00
Meta Vens
93a2d54dc3 A fixture chosen for convenience is worse than a gap
Three Soul passes over one file and a selection batch found the same thing
three ways. Every artifact-digest test wrapped its file in a directory so a
different code path ran, while production passes a bare file immediately
before launch. A row-tiebreak test passed with the rule reverted and swapped,
because of which real hash happened to sort first. An xattr test pinned
presence while the privilege lives in the value.

None of these looked like gaps. They looked like coverage, which is why they
survived. Write the fixture at the shape production uses, and derive keys from
ids discovered at runtime rather than hoping their order cooperates.

Second scar, same campaign: a counter was an honour system, so it became a
port, and the port is an honour system one level up. Soul restored the bug
around it with the suite green. Where a rule says all access goes through one
place, the enforcement belongs in the build, not in a habit. If the fix is
another thing to remember, it is the same defect one level up.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-23 04:55:34 +02:00
Meta Vens
ae0149c034 Pin a cost with a count, and check a tool before ruling it be configured
Three scars from one Idunn batch.

A test pinned a cost regression with a ratio whose clamp always fired, so it
was really a fixed 200 ms threshold, on a host that now runs three jobs at
once. Clean code had already measured 198.9 ms. The reported 33x separation
was an artifact of one pair straddling the clamp; the real figure was 1.63x.
Count the calls instead, and treat a reported ratio as a claim to check rather
than a result to accept.

Two fixtures in the same batch would have lied, and mutating caught both. A
setuid fixture chowned after chmod, which silently clears the bit. An
observe_frozen test tampered where a different check also fires, so it stayed
green with the check it pinned deleted. A third term could not be pinned
honestly at all, and Hands deleted the fixture rather than keep one that
implied otherwise.

Last, Self ruled a mount carry nosuid without checking that Docker offers it.
It does not, and the stronger mitigation was already in place. A ruling naming
a flag is a factual claim about a tool.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 23:40:35 +02:00
Meta Vens
8f0d29b932 Surviving deletion alone is not surviving deletion together
Soul reported four containment checks where one sufficed, each surviving
deletion on its own, and Self ruled three deleted. With all three gone a
symlink whose whole target is ".." at the root escapes containment. The method
was sound; the conclusion did not follow from it. A redundancy finding has to
be probed at the combination that will actually be deleted.

A Hands hand-trace caught it, because the brief says a deletion judged unsafe
comes back with evidence rather than being quietly kept. That rule stays, and
it applies to deletions Self ordered.

Second scar, same batch: Soul's HTTPS rig had evaporated by the time Hands
was told to commit it. Probes stay throwaway, but once Self rules one becomes
a committed test it is no longer scratch, and the handover has to happen while
it still exists.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 22:33:01 +02:00
Meta Vens
a565ae1c0c A dynamic dependency resolved by name is unproven until its identity is checked
A QUIC test suite passed every scenario on Windows against an unrelated
msquic.dll picked up from PATH, a tenth the size of the pinned build. The
same missing copy failed loudly on Linux. Windows' search order makes silent
substitution the default failure mode.

Two rules follow. A verification step that loads a pinned native library
reports what it actually loaded, by size or hash, rather than only that the
run passed. And a defect found on one platform gets checked on the other
before it is closed, because both earlier fixes for this lived inside
if(NOT WIN32) and nobody looked.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 21:45:13 +02:00
Meta Vens
fb2f2d722f Self creates the worktree before dispatch, and names it in the brief
Two Hands were dispatched into one working tree. The second switched the
branch out from under the first's running build, then found an uncommitted
edit it had not made and stopped rather than forcing the checkout. Nothing was
lost because of that refusal, not because of anything Self did.

The rule was already written and Self ignored it, so the fix is not a louder
warning to Hands. A brief that names a repo path without naming a worktree is
a defect in the brief.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 21:35:04 +02:00
Meta Vens
8b9d31e293 Maps go on main, and a refused instruction that was real
Two scars from one Hands report. The map it read was five days old because
Self commits maps to whatever branch it is standing on; SKILL.md now says
main, and says every brief names the map's branch.

The same agent refused a mid-task instruction from Self that it could not
distinguish from an injection. The instruction was genuine. The fix is not to
make the agent more trusting: scope expansion should arrive as a new dispatch,
not appended after a tool result.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 21:15:48 +02:00
Meta Vens
0bca98a64e Stop restating the stopgap's caps in prose; name the script as their owner
A Mind Steward pass falsified SKILL.md's claim that the stopgap runs at most
two jobs at once. The operator raised it to three this morning and the script
carries that; SKILL.md did not. An agent steering by SKILL.md would have
under-parallelized verification and quietly contradicted an operator ruling.

The changelog's entry for the same day is worse: it records caps of 6 CPUs and
16 GiB, which match neither the script nor SKILL.md. I cannot tell whether
that was ever live. The correction says so rather than inventing a history.

Both surfaces now name ygg-verify.sh as the owner of its own numbers. Prose
that restates a running tool's configuration goes stale in silence, which is
how three surfaces disagreed inside one day.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 21:02:01 +02:00
Meta Vens
2e0ea97e27 A test's inputs come from the production path
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 19:56:52 +02:00
Meta Vens
d1756ddb54 Changelog: the splash sign flip was an undefended mutant, not a shipped bug
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 18:36:45 +02:00
Meta Vens
e7cb45f554 Record the harness retirement in the changelog
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 18:36:38 +02:00
Meta Vens
37c80e4a06 Retire the hand-written mutation harness, with no fallback
Operator ruling 2026-09-22: better nothing than a harness that punishes
refactoring. Behavioural tests plus the ecosystem's mutation tools on a cut's
diff; Soul's hand mutants stay one-off probes. The stopgap image carries
cargo-mutants instead of pwsh and is tagged by its Dockerfile's hash.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 18:36:19 +02:00
Meta Vens
fd01545fb7 Hand mutations target the rule at the layer it protects
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 18:33:03 +02:00
Meta Vens
a0813f1110 Mutation testing moves to the ecosystem's tools; anchors become the fallback
Hands and Soul measure suites with Stryker.NET, cargo-mutants, StrykerJS or
mutmut scoped to the cut's diff, and triage every survivor by name. The
hand-written anchor harness is demoted to code no tool reaches. Evidence in
the changelog: Aetheria's 23 harnesses stranded on refactors and one anchor
silently re-targeted; a Stryker spike killed everything they defended and
found the splash-handedness bug they missed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 16:42:58 +02:00
Meta Vens
dbe952933b Move verification to Yggdrasil: a stopgap runner until Idunn verify lands
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 14:57:45 +02:00
Meta Vens
1912d435d3 Log the H14 fix batch: F1 refusal gate, F2 uniqueness, case-sensitivity
Records the three defects Soul's H14 pass found and this pass fixed:
the startup-repair marker check for H1's kept sidecar, the unique
overwritten-copy naming, and the case-sensitive content/hash/no-op
comparisons. Points at the fixing commits.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-09-22 12:16:26 +02:00
Meta Vens
5d2bd3e93c Fix H1: stop silently discarding an edit made while a mutation run is in flight
Restore-Targets never checked what a target's bytes actually were before
restoring over them, so a build step or stray edit landing mid-run or
between entries was overwritten without a trace (Soul's finding on the
Huginn memory-organ Cut 10 fourth fix batch, 2026-09-22; that same batch
had lost a Hands edit this way). Restore-Targets and the entry loop's
pre-write step now hash the target first: a match against the M0 original
or this entry's own mutant restores as before, anything else is saved to
<target>.eureka-mutation-overwritten, warned about loudly, and fails the
run with a non-zero exit and no further entries.

Demonstrated in the scratchpad with a throwaway repo whose test command
appends a line to the target mid-run: pre-fix the run went green and the
target came back pristine; post-fix it failed loudly and kept the
appended line. Recorded in references/changelog.md.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-09-22 07:32:57 +02:00
Meta Vens
8648fcaec8 Kill by the PID you started, never by image name
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 07:04:59 +02:00
Meta Vens
11ef23ec9c Say when to stop probing a rule and move the observation
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 05:11:24 +02:00
Meta Vens
a84669739b Say that recording a ruling is not specifying it, and qualify hand-back
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 03:18:20 +02:00
Meta Vens
20ca736e29 Forbid amend and force-push on shared branches
A Ghostlight Hands agent amended and force-pushed a kernel commit while
Self pushed map commits to the same branch. The briefs and the scars
list now forbid it.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 03:17:10 +02:00
Meta Vens
3d06231041 Give a second checkout its own build output
Two worktrees sharing one cargo target get one artifact hash, and a plain
cargo test in the older checkout ran the other's mutant binary. Found by
Soul on the Huginn Cut 10 second fix batch.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 02:38:07 +02:00
Meta Vens
065001c827 Ask what the test proves, not whether it passes
One line took three passes to pin. The suite proved the wait was not one
constant, then a scenario proved it was not any constant, and a clamp walked
through both. Capping a wait so shutdown gets noticed is the most ordinary way
that line will ever be broken, and it is a function of the argument rather
than a replacement for it.

So when a rule says a value is derived from an input, one mutant has to be a
function of that input, and the probe values have to sit where such a function
would show. Constants are only ever the first case.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-17 02:36:04 +02:00
Meta Vens
36da53be57 Falsify the gap, and stop observing downstream of the rule
Twice in one day a rule was honestly recorded as impossible to pin, and twice
the claim was wrong: one fell to a probe built from the crate's own public
surface, the other to a client opening a closed port in fifteen lines. An
unreachability claim is a hypothesis and gets falsified like any promise, so
it is written as not yet reached and the next pass opens by reaching it.

The same pass found why a rule kept being pinned by constants. The scenario
held its callers after the wait whose duration was the rule, so every mutant
of it landed behind the observation, and a hard-coded two seconds walked
through the whole matrix on both targets.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-17 01:18:25 +02:00
Meta Vens
865115f1dd Stop a suite from claiming coverage it does not have
Two ways a green sweep lied on the same afternoon. A bridge's whole mutation
history lived in scratchpads that no longer exist, so the rules it defended
were defended by nothing anyone could rerun; a probe that is the only killer
now gets committed by the next Hands pass. And a loosening that could not fail
was quietly swapped for an easier target, leaving an instance check that
survived comparing only lengths and only first bytes, because no fixture pair
had ever shared a length. An unfalsifiable loosening is a finding about the
fixtures, and the fixture is what gets fixed.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-16 23:42:39 +02:00
Meta Vens
e83420df99 Settle identity, lifecycle and authority before mapping any cut
Re-cutting came from questions answerable on day one and asked on day three,
not from maps that lacked detail. A model table now precedes every cut map,
one row per persistent kind, and no cut is mapped while a cell is empty. The
operator's forks are gathered once rather than discovered across five cuts.

In the other direction, the per-file anchors are required only where the code
exists and they say what not to touch. Transcribing the body of code nobody
has written yet is a map at full scale, and the only spec complete enough
there is the code. Cutting faster means less prose per cut, not more code.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-16 22:57:22 +02:00
Meta Vens
89a1182961 Require loosening mutations from Hands, and shape the reports
Most later Soul passes found rules the suite could not see rather than
defects, because Hands proved each rule with a revert and Soul with a
loosening. Hands now does both. Reports carry findings, promises and
numbers and nothing else, and a second pass on a cut is scoped to the fix
batch. Operator-approved after a cost review of one day's campaigns.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-16 20:22:10 +02:00
Meta Vens
6bbf6bd206 Tell agents how to wait; loop random-draw tests; probe the why
Three lessons from Ghostlight L1.

1. Three agents ended their turns while their own detached cargo job was
   still running, even though the briefs already said to wait for long jobs.
   The stall stopped only once the briefs named the mechanism: block inside
   a tool call.
2. A test built on a random draw passed by luck, failing 3 of 40 looped runs.
3. An operator's question about why a mechanism works exposed a defect
   that had been present all along.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-16 20:08:28 +02:00
Meta Vens
0a01979330 Name the model on every dispatch
"Default" inherits the root session's model, so once the root moved to
Fable every Hands and steward ran on Fable against the skill's own
allocation. The operator noticed before Self did. Self names the tier on
every dispatch from now on.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-16 16:54:04 +02:00
Meta Vens
450d7c35ba Say how to wait: a foreground poll loop, not a detached job and a yield
Three passes in one day ended their turn on "waiting" with the rule already
in their brief. The rule named the outcome and not the mechanism, and an
agent that has started a detached job reads "wait" as "stop and be woken".
Both briefs now name the loop.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-16 15:27:49 +02:00
Meta Vens
9aa3f156b0 Tell Soul to wait for long jobs before reporting
Two consecutive Soul passes on Cut 6b ended their turn while a mutation run
or a build was still going, delivering no findings until Self resumed them.
The Hands brief has carried this rule since the Ghostlight run; the Soul
brief now carries it too.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-16 14:35:00 +02:00
Meta Vens
12d1b9c0f8 Require a no-op control and byte-exact I/O in every mutation suite
A Soul pass ran a mutation that changed nothing and it killed a test. The
harness's text round-trip had collapsed a non-ASCII literal, so the
corruption alone failed the test and every mutation through that path would
have reported a kill. A working suite and a broken one look the same from
the verdicts; only a control tells them apart.

The audit that followed found every committed suite lossless and the
corrupting script inline and gone, which is the standing "no artifact on
disk" finding applied to Soul. So the rule binds Soul's harness as well as
Hands', and the Hands and Soul briefs both carry it.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-16 13:40:28 +02:00
Meta Vens
e1fd2a1d66 Record the substrate you needed, and treat absence as the hardest claim
Both rules come from the Ghostlight L0 run, which hit the missing typed-state
primitive six ways and nearly lost the requirement each time, because every
workaround worked. Doctrine already says not to wait on a service that does not
exist; nothing said to leave evidence while working around it. Now it does.

The second is a verification defect, not a state one. A Mind Steward reported a
stale phrase gone because a line break had split it from its grep. Prose
reflows, so an exact search over it has the same limits as any other text
scanner, and a check that cannot see its target closes the question instead of
answering it.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-16 12:33:45 +02:00
Meta Vens
82074a7ab5 Fold the Ghostlight L0 lessons into the briefs and the fork rule
The Soul template now attacks constructibility at sealed boundaries (a
derive is a public constructor, and on stable rustc a compile_fail test does
not pin its error code). It also asks for forgeries shaped like real values
and treats text scanners as tripwires with stated limits.

The Hands template now says to wait for long jobs instead of reporting a
to-do list, to restore mutations without git checkout, to measure warnings
from forced rebuilds, and to prefer semantic tools for semantic properties.

The fork rule now weighs proportion: a fork guarding only against the
project's own code gets a default and a recorded follow-up.

Evidence: Ghostlight's library extraction postmortem, recorded in the
changelog.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-16 12:26:08 +02:00
Meta Vens
96c98d5ceb Correct the anchor scar: no committed verdict was unearned
Soul checked the committed history. The script already threw on a missing
anchor, the affected mutation existed only in the working copy, and every
committed verdict was real. The rule stands, and gains the uniqueness check,
but the incident was narrower than first recorded.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-16 02:19:11 +02:00
Meta Vens
58cfc29b9e Add subtraction rules: deleted tests and unapplied mutations
Two rules from the Eureka campaign's own cuts. A deletion can take a live
rule's only test with it, so a cut that deletes must list every rule that lost
its test and either delete the rule or pin it in the same cut. And a mutation
whose anchor never matched is not a passing mutation: a multi-line anchor
matched nothing on a CRLF tree, reporting a verdict it had not earned.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-16 02:05:16 +02:00
Meta Vens
6ca78825f1 Record the ownership lesson: escalating guards mean a missing owner
The operator stopped a design in which a repo owned the pipeline store. Three
Soul passes had gone into a per-clone lease, git-directory resolution and
committed attribute checks, and the resolution still landed a store in an
unnamed directory. An instance owns its mind instead, and a service owns the
state.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-16 00:31:44 +02:00
Meta Vens
0109bf656c Make the session the operator channel, with swappable notification
Operator ruling: Eureka has no Persona. Self is the operator surface, and a
blocking question may be pushed through whatever notification MCP the user
configures, so Eureka owns no transport. Answering over a chat channel is a
later campaign.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-15 22:41:34 +02:00
Meta Vens
dcf4bd5091 Baseline shared build caches by path list, not counts
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-15 21:35:07 +02:00
Meta Vens
0d426e934d Tighten the Hands brief: defined mutations, base-commit proofs, started scripts
The rules come from the first Eureka pipeline-state cuts. Soul could not rerun
mutations that were only named. A digest captured from new code proved nothing
about the old code. A detached mutation script died silently on a parse error.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-15 21:16:11 +02:00