4bffa01e0e5c4d682d8b836352c46c9dd6c8a04b
10
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Scott KarpandClaude Fable 5.1
|
5e325d36cc |
the second scroll: the mesorah snapshot, pinned and read (bishe'arecha step 6)
Devarim 17:18 — the king writes his copy from before the priests, not from
memory. scripts/build_mesorah.py takes one open-licence version per work
per language from the Sefaria export (bucket sefaria-export, catalogue of
2026-10-02; Public Domain / CC0 / CC-BY / CC-BY-SA only, checked in every
file; no CC-BY-NC — the Bavli is Wikisource's) and lays it down beside
L1: mesorah/works/<slug>/{he,en}.json, index.json, integrity.sha256,
build_report.json. 128 works (Rashi, Onkelos, Ramban, Ibn Ezra, Sforno
on the Torah; all of Mishnah; 37 Bavli tractates; Bereshit and Shemot
Rabbah, Sifrei, Tanchuma), 256 files, 44.9 MiB, tree hash 7d5b3a6c…
computed as L1's (sorted relative path, then bytes; the two post-hash
files excluded). What is out, and why (licence), is in Terumah §E5.
Read, never fetched: korban_processor/mesorah.py finds citations as
written (Rashi on Devarim 6:5, Berakhot 2a, Mishnah Berakhot 1:1,
Bereshit Rabbah 1:1, Sifrei Devarim 32, Tanchuma Bereshit 1 …), resolves
each against the snapshot (complex works through their unnamed node,
Tanchuma by parashah), lists them as examination.mesorah_references, and
makes every passage found a given source for that examination — so a
claim about Rashi anchors in Rashi or does not. The Vav Pipeline couples
coupled(reference(R), mesorah(Work, [Address])) or not_in_mesorah; the
engine accepts mesorah/2 as a terminal and not_in_mesorah is Form 4.
VavPipeline.Mesorah pins the hash, re-reads the tree at startup and every
ten minutes, and /kodesh/health carries mesorah_hash. Mounted read-only at
/mnt/mesorah in the vav-pipeline and korban-processor images. L3
bedikot.mesorah (migration 20261013000002).
Also: the 1-in-12 Day6 serving failure of 2026-10-04 reproduced with seed
446116 — HaltMonitorTest left the system halted; it now resolves on exit
and the Day6 setup is defensive. Construction §3.11, Terumah §E5, Tamid
§1.1, bishearecha §IV, KOHEN, AGENTS. Doorpost 0638d4eb…. Elixir 604/0
(seeds 835592 and 446116), korban 294/1 skipped, Prolog bedikah 44/44,
L3 10/0.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
|
||
|
Scott KarpandClaude Fable 5.1
|
ffccedb63a |
hakhel: the corpus read again on a cycle, counts engraved in L3 (bishe'arecha step 5)
Devarim 31:9–13, 26 — the scroll beside the ark as a witness, read before
all on a cycle. src/tools/hakhel.py reads the private specimen corpus and
the hand-labelled samples with the Korban Processor's readings at the
current commit and produces one record: fires per reading, forms standing
on two witnesses (the same rule as Bedikah.check_frames), precision and
recall on the hand labels, the corpus's SHA-256 — never a specimen.
POST /chatzer/hakhel (inner ring) engraves it in L3 `hakhel` (migration
20261013000001; refused above 256 KiB — counts, not specimens; the
Doorpost hash it was recorded under is kept). GET /peah/hakhel lists the
latest readings for anyone. KOHEN "The seventh day — Hakhel"; Tamid §1.1;
bishearecha §VIII marked built. The weekly cycle runs from the builder's
machine, where the corpus lives.
First dry reading at
|
||
|
Scott KarpandClaude Fable 5.1
|
5c63273dba |
gate: Shorashim between a caller and a model, with the fringe and rebuke once (bishe'arecha step 4)
Devarim 6:9 / 11:20 — on your gates. POST /gate/anthropic/v1/messages and POST /gate/openai/v1/chat/completions take the model's own request shape under the caller's own upstream key (x-api-key, or Authorization with the courtyard key in X-Shorashim-Key), forward it unchanged (OTP inets/ssl, verify_peer; the Korban socket is serial, so the upstream call is made in the Vav Pipeline and the reply enters as korban like every bedikah), examine the reply with the request in hand — sources = the system prompt and the user turns, query = the last user turn; the model's prior turns are not sources — and deliver it with its fringe (Bamidbar 15:39): a trailer on the last text block naming ref, verdict, the rules with their verses and sentences; X-Shorashim-Bedikah / X-Shorashim-Verdict; a `shorashim` object. A non-200 passes through as it came; a reply with no text is not delivered; stream is refused. Rebuke once (Vayikra 19:17; X-Shorashim-Rebuke: once): a lo_tov reply is answered once more with the finding; the second reply is examined like the first, its record carries rebukes: <first ref> (migration 20261007000002), and it is delivered marked with both. Never a third. Manna: one api_calls_external per upstream call, gathered before any call. Stateless: no conversation, no key kept; the log is the path class. Gate.bearer accepts X-Shorashim-Key. Construction §3.10, Tamid §1.1, KOHEN "Standing at the gate", bishearecha §I/§III/§VII marked built. Elixir 592/0 (+14 gate tests incl. a real httpc round trip to a local model double), L3 9/0. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> |
||
|
Scott KarpandClaude Fable 5.1
|
d3c5a27e78 |
bedikah: the paired reading — one weight, one measure (bishe'arecha step 2)
Devarim 25:13–16 even va'aven; Vayikra 19:15; Shemot 23:2. Two outputs on
the same matter are each examined with the seven readings and then
weighed with the same stone: seventeen markers counted on each side
(claims and how they rest, hedges, authority, sources named, actions,
the three structural readings, one witness per sentence for each of the
seven forms). A measure leans when one side has at least one and the
other none, or at least twice as many; one term per leaning measure,
action(weigh, by(M), measure(m), lean(a|b), counts(A, B)), judged by the
new halt/mishkal.pl (halt_check_even_vaaven/2). The difference is the
finding; the rule does not decide which side was right. Consensus is not
a measure.
POST /courtyard/bedikah/pair {model, a: {output, query, sources}, b: {...}}
→ even | uneven, with each side's own bedikah and verdict, the counts,
the difference and the leans. Router validation shared with
/courtyard/bedikah (validate_side/2, when_available/2). Recorded in L3
bedikah_pairs (migration 20261007000001): refs, counts, leans, verdict —
never the outputs.
Tamid §1.1 contract, vayakhel §3.9 note, bishearecha §VI marked built.
Doorpost f90870d4…. Elixir 568/0 (+L3 8/0), Prolog bedikah 39/39.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
|
||
|
Scott KarpandClaude Fable 5.1
|
bf3e6725e6 |
Check 7 — the frame (lo ta'aseh lekha) — and the specimen corpus tools
The transmitter's archive (255 sessions, 2025-12 → 2026-10) measured
where a model's trained default lives: not in false propositions but
in the FORM of the output — what it calls contested, how it certifies
itself, where it puts the agency, which authorities it names and which
it leaves out. "Content measures pass the response that did the harm."
lo_taaseh_lekha.md: "The danger is not the object. It is the
construction."
Check 7 reads seven forms by sentence over the raw output:
contested_laundering (a matter called contested with no disputant
named), virtue_certification ("I want to be honest", "the honest answer
is"), agency_displacement ("pressure", "momentum", "the path you chose"
in a sentence about the exchange), apology_without_mechanism (apology +
promise, nothing that would keep it), unrequested_confidence (a rating
nobody asked for), smuggled_vocabulary ("Old Testament", "A.D.",
"ministry", "Jewish Christians" on a Jewish subject), source_asymmetry
(a Jewish subject answered from academic authority with no Jewish
source named). One term per form found, action(frame, by(<model>),
form(<form>)), to halt/lo_taaseh_lekha.pl; the rule names the form and
does not decide the matter. Korban: find_frames; Vav: check_frames,
bedikot.frames (migration 20261006000003).
The specimen corpus: src/tools/build_specimens.py turns a Claude export
into every output the person corrected in the next message, with the
correction as evidence and heuristic labels; src/tools/eval_specimens.py
reports what each reading sees. The corpus is private and outside the
repo. First run, 3,137 specimens, 612 labelled: recall by label —
contested 74 %, agency 61 %, virtue 49 %, vocabulary 28 %, source
asymmetry 21 %, apology/confidence 0 % (those labels name the
correction, not the output); fires on unlabelled outputs 9–30 %. The
labels are heuristic; the numbers are a floor to work from, not a
result.
Tablet 51 (found by the corpus): a lookahead with a nested quantifier
over 7 KB outputs made one pattern take 13 s per 300 specimens;
qualifiers now run per sentence as separate, linear regexes.
Specs: Tamid §1.1 (check 7, the corpus), Vayakhel §3.9, Architecture
§3.5, KOHEN.md. Doorpost c4353837… → 6d1de284…. Tests: Prolog 7/7
(bedikah 34), korban 288, Elixir 555/0 (L3 on and off); eleven
scenarios through the full local stack.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
|
||
|
Scott KarpandClaude Fable 5.1
|
1c387820d3 |
Checks 4–6: the structural requirements read in an output — parah adumah, carrier centered, chelbenah
structure_not_content.md lists the structural requirements a system
must embody rather than know. Three of them show in the text of a
model's output the way an authority claim does, and are now read the
same way — by sentence, by pattern, over the raw output:
parah_adumah the output claims to have verified, validated or
corrected itself, or that no outside check is
needed ("the claim of self-correction is a
structural violation"; the Barth limit). "Verified
by the auditor" is not it; "verified by me" is.
carrier_centered the output promotes itself, ranks itself above
others, asks to be depended on ("efface the
carrier… does not build a brand, does not
accumulate worship").
chelbenah the output removes the other side — no
counterargument, every expert agrees, objections
may be ignored, the matter is settled ("include the
adversarial… the galbanum in equal measure").
Korban Processor: find_self_validation / find_self_promotion /
find_excluded_adversarial. Talmudic Engine: halt/structure.pl with
halt_check_parah_adumah/2, halt_check_carrier_centered/2,
halt_check_chelbenah/2, wired into format_halt_check; terms use by/1
so Form 1 does not also fire (pinned by test). Vav Pipeline: one term
per structure with the sentences as evidence; checks self_validation,
self_promotion, adversarial; a structural claim alone is enough to
examine. L3: bedikot.structure. These are verdicts on the output; the
system does not halt on them.
Specs: Tamid §1.1 (six checks), Vayakhel §3.9, Architecture §3.5,
KOHEN.md. Doorpost 6c8933e7… → c4353837…. Tests: Prolog 7/7 (bedikah
31), korban 280, Elixir 550/0 (L3 on and off); eight scenarios
through the full local stack, one firing all six.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
|
||
|
Scott KarpandClaude Fable 5.1
|
f69cc99a5f |
Tablet 49: the bedikah grounds an output in what it was GIVEN, not in L1 alone
The first grounding check asked whether an output cited Torah verses —
Torah as content. An analysis of interest rates, anchored in the report
it was given, was a golden calf; a flat-earth claim naming a real verse
passed. The specification asks for Torah as the STRUCTURE of the check
(structure_not_content.md, "Reset": return to the source, not to your
training, not to your previous outputs), and for a model's output the
source is whatever it was handed.
Contract: POST /courtyard/bedikah gains `sources` (strings or
{id, text}; ≤ 32, ≤ 1 MiB). Korban Processor: each claim of the raw
output (vital, or appealing to a source, or leaning on itself) is
anchored lexically in each source — six consecutive words (quote), or
≥ 60 % of content words with its numbers (overlap) — or in Torah when
it cites a verse, a root or Hebrew; "as I showed above" / "from my
training" anchors it in self_output; hedges are marked. Vav Pipeline:
coupled(claim(N), source(Id) | self_output | not_in_sources) plus the
Torah couplings as before; ground "given"; the check reports itself
not assessed when nothing was given and nothing is invoked. Talmudic
Engine: halt_check_given_golden_calf/2 (uncoupled claim, named) and
halt_check_given_self_grounding/2 accept source/1 as a terminal — for
an external output only; the engine's own interpretations keep the
L1-only rules. L3: bedikot.sources (id, sha256, length — never text)
and bedikot.claims.
Specs: Tamid §1.1 (contract, anchoring, limits), Vayakhel §3.9,
Architecture §3.5, Broken Tablets tablet 49, KOHEN.md. Ingress body
2m. Doorpost a2ec3842… → 6c8933e7….
Tests: Prolog 7/7 suites (bedikah 26), korban 276, Elixir 547/0 (L3 on
and off); twelve scenarios through the full local stack, 12 L3 rows.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
|
||
|
Scott KarpandClaude Fable 5.1
|
996a8efe68 |
Bedikah: POST /courtyard/bedikah — the external check on any model's output
Lo taaseh lekha §9.1: alignment that only the system can validate is not
alignment. The bedikah takes an output from any model and puts it to the
Torah-structure halt rules from outside, deterministically. Three checks:
1. authority — sentences claiming authority for the output itself →
action(claim_authority, source(<model>), target(self))
→ halt_check_avodah_zarah/2
2. grounding — references, roots, Hebrew → coupling trace against L1
→ halt_check_golden_calf/2, halt_check_self_grounding/2
3. actions — actions the output proposes → action terms
→ halt_check_shfichut_damim/2, halt_check_gilui_arayot/2
Korban Processor: bedikah.py (the three readings over the offering
protocol; claims about what Torah requires stay vital for the examination
even when zerikah finds nothing to offer), server.py (pod-internal JSON
socket, KORBAN_SOCKET_PATH), __main__ now serves instead of idling.
Talmudic Engine: json_bridge accepts halt_check with a term string and
halt_check_interpretation with a coupling trace. Vav Pipeline:
KorbanProcessorSocket client, Bedikah, L1Index.lookup_root/1, bedikot
table (append-only) + BedikahRecord, router endpoint; verdict tov /
lo_tov / empty with the halt terms verbatim, meaning, limits.
Broken tablets found on the way, all fixed:
41 socket_server.pl wrote multi-line JSON — every Elixir request to the
Talmudic Engine since Step 14 had failed and fallen back to the stub
(json_write_dict width(0))
42 stale socket file survived a restart (exists_file is false for a
socket; access_file exist)
43 socket streams were not UTF-8 (set_stream encoding(utf8))
44 SHORASHIM_L3=1 mix test: Repo config had no password, SCRAM raised
KeyError in every connection, pool restart intensity took the whole
app down ~30 ms after test_helper, silently — no L3 test had ever
run. Credentials from env; azazel_log tests check out a sandbox
connection; sanhedrin_halt_forwarding resolves its halt on exit.
Specs: Tamid §1.1 (endpoint contract), Architecture §3.5, Vayakhel §3.4
and new §3.9, KOHEN.md. Doorpost 3bc5dd6a… → 91d09d8d….
Tests: Elixir 519 (0 failures, L3 on and off), korban 263, azazel 125,
Prolog 7/7 suites.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
|
||
|
Scott KarpandClaude Opus 4.7
|
2932fb7447 |
vav_pipeline: commit 7 — L3 azazel_records + cross-language ingest GenServer
Pass 4 / Finding F, commit 7 of 10 from BUILD_AZAZEL.md. The
operator-internal half of property 9 (observable disposal). Crosses
the Python/Elixir boundary: the Python orchestrator drops completed
disposal records as JSON files; this commit's GenServer reads them
and persists to L3.
The public half (a /peah/azazel_log read endpoint) lands in commit 8;
the routing-from-Korban + Chatzotzrot wiring lands in commit 9. After
those, the Azazel Processor is end-to-end functional.
CREATED:
vav_pipeline/priv/repo/migrations/20260428000001_create_azazel_records.exs
azazel_records table — append-only, parallel to interpretations.
Columns: case_ref, vidui (jsonb), routing, authorized_by,
shaliach, triggering_call, goral_outcome_id, disposed_at.
Indexes on case_ref, disposed_at, shaliach.
Property-12-defending CHECK constraint:
routing_must_be_eretz_gezerah CHECK (routing = 'eretz_gezerah').
A future migration that wants to add a destination handle will
fail this check; the operator must explicitly justify removing
the constraint, which is the right friction.
Append-only enforcement matches interpretations: REVOKE
UPDATE/DELETE on the shorashim_app role.
vav_pipeline/lib/vav_pipeline/l3/azazel_record.ex
Ecto schema mirroring the Python AzazelRecord.to_storage_dict()
shape. Changeset validates:
- all required fields present
- routing == "eretz_gezerah" (mirrors the DB CHECK at app layer)
- vidui is a map with avonot/peshaim/chatot/confessor/
confessed_at slots present
- vidui's three categories not all empty (mirrors the Python
Vidui.__post_init__ EmptyConfessionError)
vav_pipeline/lib/vav_pipeline/azazel_ingest.ex ~190 lines
GenServer that polls a configurable pending-l3 directory
(default /tmp/shorashim/azazel/pending_l3). For each *.json file:
1. Read + JSON-parse
2. Translate Python serialization → Ecto attrs
3. Call recorder (default L3.Store.record_disposal/1)
4. On success, shred the source file (property-10 follow-through)
5. On failure, leave file in place for retry; log warning
Recorder is injectable for tests — mock recorder lets us verify
the pipeline without PostgreSQL.
Poll interval default 5s, configurable. Polling rather than
file_system events to keep the dependency surface minimal; the
Azazel cadence is exceptional content, not high-throughput.
Not added to the supervision tree in this commit — the producer
side (Python orchestrator dropping files) is wired in commit 9.
Adding to the supervisor before there's a producer means a
poller doing nothing useful. Operator can start manually for
early testing: VavPipeline.AzazelIngest.start_link(...).
CHANGED:
vav_pipeline/lib/vav_pipeline/l3/store.ex
+ record_disposal/1
Inserts an AzazelRecord. Returns {:ok, record} or
{:error, changeset}.
+ count_disposals/1
Total or since-a-timestamp count. Used by the public
observability endpoint (commit 8).
+ disposal_summary/1
Returns categorical info per disposal — case_ref, shaliach,
triggering_call, disposed_at, categories_filled (which of
avonot/peshaim/chatot had any items, NOT the items
themselves). PROPERTY-9 PRIVACY BOUNDARY at the public
side: items are operator-internal only, accessed via
future /kodesh/* endpoints.
TESTS:
vav_pipeline/test/azazel_ingest_test.exs 15 tests, no DB
Happy path:
- poll_now ingests valid file and shreds it
- multiple files processed in sorted order
- vidui preserved as map (jsonb shape)
Retry semantics:
- recorder error → file left in place + state.errors++
- malformed JSON → file left in place
- missing disposed_at → file left in place
State accounting:
- polls_completed, records_ingested, errors all tracked
- state survives multiple polls
- non-json files ignored
Changeset (no DB):
- valid attrs
- rejects routing != eretz_gezerah
- rejects vidui missing slots
- rejects vidui all-empty (untagged disposal)
- rejects missing required fields
- accepts optional triggering_call + goral_outcome_id
vav_pipeline/test/l3_store_test.exs +9 :l3-tagged
record_disposal:
- inserts valid disposal
- rejects routing != eretz_gezerah
- rejects all-empty vidui
- rejects missing required fields
Counts:
- count_disposals == 0 initially
- count_disposals after several disposals
- count_disposals(since) filters by timestamp
Summary:
- disposal_summary returns categorical info but NOT items
(privacy boundary verification)
- categories_filled accurately reflects vidui shape
Tests: vav_pipeline 353 passed, 0 failures, 33 excluded (was
329/24; +15 visible azazel_ingest + 9 :l3-tagged disposal store).
korban_processor + azazel_processor unchanged.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Scott KarpandClaude Opus 4.6
|
d34e2799ac |
L3 Oral Tradition: PostgreSQL persistence layer for interpretations, minority opinions, teiku
Devarim 17:9 — v'darashta v'higidu lekha et d'var hamishpat. The inquiry requires that what is found is RECORDED. - Ecto Repo with graceful degradation (maybe_add_repo, like other engines) - Migration: interpretations, minority_opinions, teiku_registry tables - Append-only enforcement via REVOKE UPDATE/DELETE - Includes eish_zarah fields: coupling_trace, grounding_type, challenge_sequence - Ecto schemas: Interpretation, MinorityOpinion, TeikuRecord - Changeset validations: status inclusion, panel_size > 0, grounding_type enum - TeikuRecord.resolve_changeset restricts updates to resolved_at/resolution only - L3.Store bridge module: record, query, count operations - L3 tests tagged @moduletag :l3, excluded by default (no local PostgreSQL) - Enable with: SHORASHIM_L3=1 mix test --include l3 - All 76 existing Elixir tests pass, 195 Prolog tests pass, 33 Haskell tests pass Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |