Commit Graph
3250 Commits
Author SHA1 Message Date
jschoubben 7c6cf18532 Design 47 H1: a held destroy-level ask says its level; an offer with no channel named says so
The router held the bus module's destroy-level asks with the bare words
"no channel can carry it now", so the asker could not tell why. holdWhy
now names the destroy level and that no channel carries a destroy answer
yet. The bus module's tool says "offered, channel not yet named" for an
open record with no tickets, never "offered on :".

Builds: design 47 H H-A-237 (3), H-A-239 (2)
2026-11-21 11:26:19 +01:00
jschoubben a8f2316d08 Design 47 H1: the keeper's warrant asks at approve level; the tool says the router's standing
The bus module's drop and rebuild asks were at the destroy level, which no
channel carries yet, so the router held every one unshown until it expired
while the tool answered "the operator is asked". The ask is now at the
approve level for the caller's expires_minutes (5 to 1430, default 60,
refused outside), the keeper accepts an approve-level choice for these two
acts and bounds a request by its ask's own expiry, and the tool makes one
read of the router's record after the publish and says offered, held or
refused as it finds it; the request read shows that standing too.

Builds: design 47 H H-A-237 (1) (2), H-A-239 (1) (2)
2026-11-21 11:17:58 +01:00
jschoubben e1974b770e Design 47 H1, proof 1 (second run): one line in feh
Design lines: H §5 step 7. The first run's pipeline failed on the validate ask before the assigner fix.
2026-11-21 11:07:41 +01:00
jschoubben 74488f3e66 Design 47 H1: the seat git answers a listing's missing directory not-found (H-A-232)
A directory of a trees listing's files the commit does not hold was
thrown as a plain error and answered with the kind failed, so the
indexer took it for a forge that failed, never ran its one-directory
fallback (issue 1585), and published nothing of the repository.
commitTrees throws DirectoryNotInTree for it, and the seat's failure
answers it with the kind not-found, the error naming the directory.

Builds: design 47 H H-A-232 (2), H-A-234; issue 1585
2026-11-21 02:59:05 +01:00
jschoubben 08ec25e367 Design 47 H1: a kept old-section entry keeps only the objects the keeper made; a kept state stays in the cap sum
Review round 1. keepOld took the old plan's objects whole, so a state's `<state>-objects` store
the grants part made beside a bucket the keeper made alone would have been compared, grown and,
on a recreate, deleted by the keeper: it now keeps only the old plan's objects the made record
already holds. CapSum skipped every kept entry as counted in the old sections' caps, which count
objects, logs and streams but never a state: it now skips only a kept objects, log or stream
entry, so a kept state's bucket stays in the sum.

At the delivery the plan digest changes once for every module with old sections (most modules,
since state counts): each plans again once, quietly, as its entries are compared with what the
bus holds and nothing is created or said where they agree.

Builds: design 47 H H-A-229, H-A-230, H-A-231; G §547
2026-11-21 02:32:01 +01:00
jschoubben ec305f08e6 Design 47 H1: the bus module counts every manifest's old-section entries as asked for (H-A-229)
The keeper read only a manifest's new-form asks, so the entries it had made for the artifact
registry and the forge, now declared in their old sections, stood as orphans with live data: a
rebuild refused, a drop offered. The keeper now reads every manifest's old sections (state,
objects, logs, streams) by the SDK's naming per section, as the grants part composes them. An
entry it made under one of those bus names is no orphan, is compared and grown to the declared
cap and rebuilt on request; it creates none of them and says no created for one, and counts a
kept one's cap once, in the old sections' sum.

Builds: design 47 H H-A-229, H-A-230, H-A-231
2026-11-21 02:26:20 +01:00
jschoubben ae9bb17e0f feh: name H1's proof 1 in the wallpaper file, the single-module change its pipeline delivers
A one-line comment in ~/.fehbg (the files archive) moves feh's fingerprint and
is readable on every machine that holds feh once it is delivered, with no hand act.

Design 47 H §5 runbook step 7: "Prove it. One single-module change (a comment in
a module with lint, unit and composition steps only), merged to main through a
merge call (merge-pull, design 47 H §734), followed from take-in.taken through
pipeline-ended to the node-engine's running and the gate's ended record, with no
hand act".
G §370: "The version reaches every artifact's build": the delivered files
archive carries the version the pipeline gave it.

Builds: design 47 H §5 step 7, G §370
2026-11-21 01:39:08 +01:00
jschoubben e1d2af8d6e mesh-build-go: build a same-repository requirement from the tree at any version (H item 6)
A requirement of the checked repository at a real version was fetched from the Go seat while the
indexer's fingerprint takes the tree, so the build and its key disagreed; and "same repository" was
read from the owner name novox/ written into the code. The fetch now takes every requirement of its
own repository from the fetched tree before anything is downloaded, at whatever version go.mod
names, keeps those directories in the narrowed tree, and judges "same repository" by the fetch's
repository as the ask names it.

Builds: design 47 H S31, S3, L8 (H-pins-spec-and-gaps section 8 item 6); H-A-204, H-A-202, H-A-198
2026-11-20 23:22:53 +01:00
jschoubben b889075e21 H-A-202: the narrowed tree keeps the repository's packages a required package requires, transitively
A package artifact's go.mod may require a package of its repository that
requires another of it at the zero version; the narrowing kept only the
first level, so the build of the second found no module of that path. The
entry's paths keep the manifest's form; the Go build module reads each kept
package's go.mod in turn, each directory once, and keeps what it requires.

Builds: design 47 H H-A-202, H-A-198
2026-11-20 22:28:28 +01:00
jschoubben 3fd2e58072 H-A-192: the Go build module refuses a requirement with no pin of its own
Given no pin, the module took the version of another package of the same
repository, or the latest, and built against versions never published. A
requirement of another repository is now taken at the pin the ask names for
its own path, else the build fails naming the path; a same-repository
requirement is still built from the fetched tree.

Builds: design 47 H H-A-192, H-A-198, G §370
2026-11-20 22:20:12 +01:00
jschoubben dc507ec9ff H-A-186, H-A-188: declare diskreadings as a package artifact; the gate accepts asks at 0.3
disk-load's Go package diskreadings is imported by mesh-grants, whose build
waits for a publish no release made: an imported mesh package is a declared
artifact of its module, so every release publishes it. The gate imports the
assigner's asks, published in the assigner's series 0.3, so it names that
series in its packages.

Builds: design 47 H H-A-186, H-A-188, H-A-198, G §370
2026-11-20 22:13:25 +01:00
jschoubben 7de86ff471 Design 47 H1: proof 2, a two-module change along a dependency edge delivered by its pipeline (H §5 step 7) 2026-11-20 18:55:28 +01:00
jschoubben 2cd3f20cb2 Design 47 H1: proof 1, a single-module change delivered by its pipeline (H §5 step 7) 2026-11-20 16:59:41 +01:00
mesh-tools e01c21f19e Merge pull request 'distribution: versions on the artifact seat answers the blob a reference names (A-430a, design 51)' (#717) from fix/47-H1-engine-archive-digest into main 2026-11-20 15:21:37 +00:00
jschoubben b68de8f186 distribution: test versions' digest per seat; say why a version has none
Review round 1: versionsAnswer's choice of digest per seat had no test.
TestTheVerbsSpeakTheSeatsContract now holds it, with a store whose blob
and manifest digests differ. OCI.Blob refuses a manifest that keeps no
single blob, naming its layers, and versions says that in the journal:
the contract's answer has no field for why.

Notes for H2: OCI.Held (oci.go) compares the tag's manifest digest with
a bundle's or an archive's blob digest, the same kind as this fault;
versions answers kind "" since the tool reads a kind its input does not
take.

Builds: design 47 G A-430a (G-22-lead-answers-2), design 51 *One contract*
2026-11-20 16:20:00 +01:00
jschoubben 6f4e85c656 distribution: versions on the artifact seat answers the blob a reference names
The node-engine resolves a want's version to an archive's digest through
oci-artifact-registry's verb versions and fetches /blobs/<digest> by it.
The holder answered the tag's manifest digest, so shanks asked
claude-code/files' manifest as a blob and got 404 (claude-code 0.1.17).
On the artifact seat versions now answers the manifest's one blob, the
digest the reference and the event published carry; the image seat
keeps the manifest digest.

Builds: design 47 G A-430a (G-22-lead-answers-2), design 51 *One contract* (the seats' events carry the digest), the seat's contract Artifact and Listed.artifact
2026-11-20 16:12:27 +01:00
jschoubben f4cd0e89fd mesh-build-node-narrowed-packages: narrow a step's workspace as H-A-136 and H-A-137 say
Review round 1. The node build module runs the seat generator's check at its unit level
(steprun.OutOfStep), so its narrowed workspace keeps what H-A-136 and H-A-137 name: every
generated-from directory of the module, and for a root module the seats/ directory and the
paths of every artifact naming generated-from. Narrowed bare, a step of one mesh-contracts
package named the generated files left out as out of step. The fetch and the steps verb now
narrow the same way, and the steps verb reads its narrowed tree as the levels do.

narrowTree and generatedFromDirs are copied from mesh-build-go without its Go part, not moved
into mesh-delivery-sdk's steprun: the move is a change to two more repositories and a group
delivery for some sixty lines, in a fix that unblocks the build steps now; the copy says so.
packageDir and narrowedAway share one path helper.

Builds: design 47 H H-A-136, H-A-137 (hq design/47-H1-answers-59), ADR 0499 clause 4
2026-11-20 16:10:08 +01:00
jschoubben 0b834bbca7 mesh-build-node-narrowed-packages: a package narrowed out of a step's workspace is no module of it
A step of one TypeScript package of a module with several (mesh-contracts' root:
ts-meshbroker beside ts-meshrecovery, pipeline main.3 of 2026-11-20) fetches a workspace
narrowed to that package's path. The fetch and the lint and test levels read every package
artifact of the manifest, and one whose path the narrowing left out fell back to the
module's directory, which holds no lock: every TypeScript step of mesh-contracts ended
"could not run: the package in . has no package-lock.json". Such a package is now left
out of the fetch's install and of the levels' targets; an unnarrowed tree is read as before.

Builds: design 47 H H-A-136 (a step's workspace holds the artifact's paths; nothing else is fetched), ADR 0499 clause 4
2026-11-20 16:01:19 +01:00
jschoubben 51a83ed3a8 mesh-vault, claude-code: consume binding.changed.<consumer>, so binding moves are heard
The licence manager says each binding change as binding.changed.<consumer>
(mesh.mod.claude-licence-manager.event.binding.changed.<consumer>), but both
manifests consumed claude-licence-manager.binding.changed, which the grants part
composes into the exact filter mesh.mod.claude-licence-manager.event.binding.changed:
the bus consumer never handed either module one change, and the vault kept only its
first view (2026-11-20: g14 refused a switched licence's token until the first view
was asked again by hand). The consumed pattern now names the further part, `*`.

Builds: design 47 G A-134; design 39 bus-and-switch §17, §19, §22
2026-11-20 15:09:45 +01:00
mesh-tools eb4e964fbf Merge pull request 'claude-code: a login not handed gives way to a newer lease of its own account (H-A-140)' (#714) from fix/licence-file-the-cli-accepts into main 2026-11-20 13:49:50 +00:00
jschoubben 121125aa50 claude-code: the latest login wins over a login not handed to the manager
A login not handed is kept only against a lease that does not succeed it; a lease
of the same account that succeeds it replaces it, said as login superseded. A login
to another account is kept until the manager adopts it.

Builds: ADR 0206, ADR 0209, design 39 §6, H-A-138 (hq design/47-H1-answers-59 175ed320), H-A-139 (hq design/47-H1-answers-59 e359911e), H-A-140 (hq design/47-H1-answers-59 b75d1386)
2026-11-20 14:47:49 +01:00
mesh-tools 947a68d274 Merge pull request 'claude-code: a login is succeeded by its own refresh, not only by a newer lineage (H-A-139)' (#713) from fix/licence-file-the-cli-accepts into main 2026-11-20 13:27:19 +00:00
jschoubben 0934292f47 claude-code: a login is succeeded by its own refresh, not only by a newer lineage
The manager's refresh keeps the licence's refresh-token expiry, so a grant of the
same lineage with a later access expiry replaces the login; a grant with no
mark, an older lineage or no later access expiry is the older lease and is kept.

Builds: ADR 0206, ADR 0209, design 39 §3 §6, design 14, H-A-138 (hq design/47-H1-answers-59 175ed320), H-A-139 (hq design/47-H1-answers-59 e359911e)
2026-11-20 14:25:47 +01:00
mesh-tools 1b706ca0b1 Merge pull request 'claude-code: the node side never writes a lease over a login the manager was not handed, and only a newer lineage over a handed one' (#712) from fix/licence-file-the-cli-accepts into main 2026-11-20 13:24:15 +00:00
jschoubben a8a0cfeb8f claude-code: a login handed is replaced only by a grant of a newer lineage
One reason, login kept, on both paths, with a journal line; the not-handed
return skips the binding's generation on purpose.

Builds: ADR 0206, ADR 0209, design 39 §3 §6, design 14, H-A-138 (hq design/47-H1-answers-59 175ed320)
2026-11-20 14:21:47 +01:00
jschoubben a7459c6e4f claude-code: never write a lease over a login the manager was not handed
A login made on a node (while the tool runner was stopped, or before the
manager asked claude_code_grant for it) was overwritten by the next apply
of the binding's older grant: Apply took any refresh token in the file as
one already handed, and forced the write. The person's login was lost and
the session asked for a login again.

The node side now keeps the fingerprint of the login claude_code_grant last
sealed (state login-handed, never the token). Apply leaves a file whose
login is not that one untouched (applied false, reason login-not-adopted);
its report makes it the manager's candidate, and the successor the manager
hands back replaces it, as before without a refresh token.

Builds: ADR 0206, ADR 0209; design 39 §6 (the latest login wins, a login
moves its node); design 14 (a node never holds a refresh token).
2026-11-20 14:02:37 +01:00
mesh-tools 677c149022 Merge pull request 'The claude-code module renders no shell guard; the wait-list hooks stay (the operator, 2026-11-20)' (#711) from fix/claude-code-no-shell-guard into main 2026-11-20 12:56:56 +00:00
jschoubben 1ae83499ba claude-code: drop the machines data only the guard read
With the guard gone nothing reads the machines' names, domains and
addresses: remove Machine, the name lookup and the ten-minute timer that
resolved them again, so the tools' table is read only when a followed
state changes. Also remove the now unused cut helper.
2026-11-20 13:15:52 +01:00
jschoubben f57ae96e55 claude-code: remove the guard on the agent's shell
The operator asked for the shell guard to go (2026-11-20): the plugin no
longer carries a PreToolUse hook or guard.json, the binary no longer has
a guard verb, and the claude_code_guard tool, its record and the
refusal-ranked order of the instead-of table are gone. The SessionStart
and Stop hooks of the wait list stay, run by the same binary at the same
path, which is also the home-fs helper's. The rendered rule against ssh
to a mesh machine stays as the session's own and no longer claims a
guard enforces it; claude-agent no longer passes the guard's override.
2026-11-20 13:06:55 +01:00
jschoubben 30f274bcb0 mesh-build-go: a narrowed root module keeps its seats/ and every generated package
A module at the repository's root naming generated-from "." (mesh-contracts)
kept nothing of it: the narrowing kept "." alone, which prunes everything,
so the seat generator's check of go-meshconfig still found every file out
of step. Such a module now keeps the seats/ directory the generator reads
and the paths of every artifact naming generated-from; nothing else of the
root.

Builds: design 47 H H-A-137
2026-11-20 13:03:05 +01:00
jschoubben c52907a346 mesh-build-go: a narrowed workspace keeps generated-from and same-repository zero-version packages
The first pipeline of the clean state (main.3) failed every build of a
mesh-delivery-contracts client: the fetch narrowed the tree to the
artifact's paths (ADR 0499 clause 4), which removed
modules/mesh-delivery-sdk, so its requirement at the zero version found
"no module of that path in the fetched tree". The same narrowing left the
seat generator's out-of-step check without its seat definitions.

The narrowed workspace now also holds every generated-from directory an
artifact of the module names and the directory of every package of the
same repository the artifact's go.mod requires at the zero version, found
by the repository's manifests; the root's manifest and lock files are not
kept when narrowing from the root. The fetch's own Go modules stay those
under the artifact's paths (A-447a), not the added directories.

Builds: design 47 H H-A-136; design 47 G-22 A-447a

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 12:41:16 +01:00
jschoubben 6ecadf294e GATE-R2: the retired checker no longer reads the gate's state source
Builds: design 47 H §764

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 06:35:44 +01:00
jschoubben ae8b0c65bc NATS-R2: nats_consumer_remove judges durables by every accepted module
The refusal read the keeper's state asked, which holds only a module that
asks for kept data, so a running module keeping no bus data would lose its
live durables. It now reads the keeper's state plans, one key per module of
a watched branch's newest revision; the keeper no longer deletes a plan key
when a module's asked key goes, so plans stays that accepted set.

Builds: design 47 H H-A-126, H-A-127, H-A-128; design 47 G §538

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 06:35:44 +01:00
jschoubben 1568877f35 nats-tools: a durable beginning <node>_<module>_ is the module's too
Builds: design 47 H H-A-128

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 06:22:51 +01:00
jschoubben 04eda6130d mesh-cli: nox checks goes; the seat mesh-delivery no longer serves checks
Builds: design 47 H §764 (the checker and its verbs retire)

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 06:20:40 +01:00
jschoubben 959e8d6d30 nats-tools: nats_consumer_remove judges a consumer by its name and records the hand act
An accepted module's durable (<node>_<module>) is refused on any stream; any
other durable is an orphan and goes, why its warrant, recorded through
mesh-hand-acts. It no longer refuses every consumer of a kept-data stream.

Builds: design 47 H H-A-126, H-A-127

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 06:20:30 +01:00
jschoubben 01543d9121 gate: gate_record_end takes an all form for the clean state
Every open record ends after one hand act naming how many; the answer says
what it ended, counted.

Builds: design 47 H H-A-121 (2), §765 (the gate's open records go at the clean state)

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 06:12:40 +01:00
jschoubben 8c8b4367f1 mesh-mail-reader: its callers list goes; every verb answers every caller
Every account may call every verb; what protects the mail is what the verbs
answer (ADR 0459 §2), not who may call them.

Builds: design 47 H §764 (every callers list, §752); H-A-122

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 06:10:56 +01:00
jschoubben c775aab29a gitea, mesh-issues: no timer said for main's rules; the checker is no owner
Review round 1, notes: keep-main-rules acts at the token's mint alone since the
ten-minute step went (H-A-100), and the issue tracker's owners named the
checker's path, which a search for the checker must not find (§764).

Builds: design 47 H §764 (the forge module's ten-minute timer; the checker whole); H-A-100

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 06:06:57 +01:00
jschoubben df79ab8769 mesh-knowledge: the overview's delivery block and the progress verb's groups lines go
Review round 1, Must 3: the groups and group-ended are retired; the overview
showed the deliveries, another module's state, which the status view owns.
The overview keeps two sources (the tracker, the asks), consumes no merge,
transition or pipeline's end, and the progress verb asks no groups.

Builds: design 47 H §764 (the gate's verb groups; the runner's group-ended); H-A-28; H-A-125

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 06:04:16 +01:00
jschoubben 5b06dd7e43 messenger: the operator channel's holder keeps no held-back asks and serves no ask-again
Review round 1, Must 5: the seat lost held-back and ask-again (mesh-contracts
9db2e1d); the holder still offered held-back asks of before, refused choices
on them, listed them in asks and served ask-again.

Builds: design 47 H §764 (The operator channel's limit); H-A-57

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 05:57:16 +01:00
jschoubben c99ad77633 mesh-cli: nox try and nox groups go with the checker and the groups
Review round 1, Must 4: both called verbs no part serves.

Builds: design 47 H §764 (the checker whole; the gate's verb groups)

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 05:54:54 +01:00
jschoubben 401289afac mesh-conditions: the hold reads a want's fingerprint alone
Review round 1, Must 2: the want's composed digest left mesh-sdk's motion.Want
(H-A-78); the hold read it and no longer built.

Builds: design 47 H H-A-78 (1)

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 05:52:52 +01:00
jschoubben a6a6135f74 gate: drop the require of the checker's seat contract, which is gone
Review round 1, Must 1: commit 11a22fdf removed the checker's seat package;
the require left the gate unbuildable against the H1 heads.

Builds: design 47 H §764 (the checker whole goes); H-A-57

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 05:52:00 +01:00
jschoubben c91ab3acfa build modules: the checker seat's invoke, its client and its fixtures go; a run's input is asked of the seat mesh-wants
The kinds check and recheck stay in H1 (H-A-117).

Builds: design 47 H §764 (the checker (H1)); lead answers H-A-57, H-A-117

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 04:59:05 +01:00
jschoubben ba0330c205 mesh-cli: nox head take calls gate_head_take; indexer_take_in is gone
Builds: design 47 H §742, lead answer H-A-105

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 04:14:18 +01:00
jschoubben 15458aeb61 FORGE-6: the seat git's whole test runs the forge module's bundle on a real bus
A Go integration test builds the TypeScript bundle and plays its tool
runner over stdin and stdout against a bus of its own and a fixture
forge: a call stopped after two of three merges says one merge-called at
the start; a failed required step refuses its head; two pull requests in
two repositories merge and say one merge-called; a forge refusing the
second merge says what landed and raises merge-partial, cleared by a
later call.

Builds: design 47 H §774 (forge module: tests 111, 114, 115), §734, §735, §736, §766, §767; H-A-61, H-A-87 (1)

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 03:58:00 +01:00
jschoubben 815be6bdce FORGE-6: the forge module's merge-check machinery and its polls go
announceHead with its mesh/merge-gate pending, the weighing of trunk and
sibling moves (passPulls, trunksMoved, siblingMoves, GateWriter) and their
files on disk, the pass's pull-passing half with its 60 s retry, and the
10-minute keep-main-rules step go. A pull request's new head is said as
pull.updated from the forge's event alone; the seat's status writes
through the client; pollRepos, pollMerged and readAllAtStart stay.

Builds: design 47 H §764 (the forge module: the merge-check machinery, its poll and timer), §762; H-A-28, H-A-100

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 03:54:09 +01:00
jschoubben f85f639afe FORGE-1: failed-steps reads the body's fingerprint; a step-ended without it writes step-unread
The forge module keeps a step's failure at the step-ended body's
fingerprint alone, consumes step-ended on its <module>.<branch>.<commit>
subject, and writes step-unread (scope module, keyed <run>.<module>.<step>,
warning, resolver operator) for a step-ended without its fingerprint,
cleared by the step's later step-ended with it.

Builds: design 47 H §735 (failed-steps from step-ended); G §585; H-A-18, H-A-47 (FORGE-1 builds step-unread), H-A-93

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 03:49:12 +01:00
jschoubben 0400d7bbe7 FORGE-5: forge_calls reads the merge calls; forge_call_say_again says one again
forge_calls answers the kept calls newest first with each member's base,
head and state; forge_call_say_again, with call and why, says a call's
merge-called again once the hand-act log took it.

Builds: design 47 H §766 (its tools); H-A-18

Claude-Session: https://claude.ai/code/session_01JG73KHUnBze48rdua8u2sy
2026-11-20 03:47:41 +01:00