Skip to content

Revisions batch: on-ramp + model currency + D13 scope row (spec), six guide rules, first full live-AC run (6/6 after the thread-identity fix) - #25

Open
Carr1005 wants to merge 10 commits into
mainfrom
guide-revisions-batch
Open

Revisions batch: on-ramp + model currency + D13 scope row (spec), six guide rules, first full live-AC run (6/6 after the thread-identity fix)#25
Carr1005 wants to merge 10 commits into
mainfrom
guide-revisions-batch

Conversation

@Carr1005

@Carr1005 Carr1005 commented Sep 9, 2026

Copy link
Copy Markdown
Collaborator

The revisions batch from the tester-feedback triage (#24) plus the promoted #18 findings — spec edits and their guide generalizations, validated Option-B style (surgical edits + clean-room Opus regens; no adoption, no rebuild). Also includes the lab's first full keyed live-AC run, which caught and fixed a real design gap.

Spec (3 commits)

  • 2835655on-ramp + currency: the opening blockquote gains the orientation lead ("what you're building" as a user-visible scene) and the fastest-path/completion sentence (offline suite green = the recommended baseline is complete; keys unlock only live tests/live use); inline heavy-setup notes on D11 Oracle and D12 Tavily; D4 Options name providers, never "current" model names ("expect the build agent to recommend current ones at the gate"); CTX-D gains the request-parameter-compatibility perishable (the temperature-rejection class); fixtures/llm-stubs.pyllm_stubs.py.
  • 809dea8D13 summary-memory-scope row (owner decision, first contradicted-category row): thread-scoped default (the app path) vs the Lesson-5 notebook's unscoped global pool — both course-demonstrated; stakes test passes because the choice changes what a read returns. Side edits: contradicted-group paragraph, R18 defers to D13, §5 coverage note, CTX-C11 cross-ref.
  • R11 harness-known-identity sentence — added mid-batch after the live AC21 run caught the gap (below), per the spec's own living-document rule.

Guide (1 commit, 0cd5ff2)

Six course-agnostic rules: G1 orientation-block template + reader test; G2 heavy options state setup weight inline at choice time; G3 model currency is the generation-vs-gate timing split, CTX-D parameter-constraint category; G4 identifier formats are Pass-A parameters, alphabet included; G5 fixture module filenames must be importable identifiers; G6 the contradicted route's worked storage-scoping example. Reference-style §14 lines.

Validation

  • 3/3 clean-room Opus regens: all six new V-properties present in every regen (B full-scored 30/30 PRESENT, 0 PARTIAL with quoted evidence + orchestrator spot-audits; A and C grep-verified). G4 closed the id-alphabet cross-model gap 3/3 (was 0/3); G6 held the scope row 3/3; regen-B is the first exact-canon 13/13 Ledger in any pass. Carried residual expressed as documented (A +1 row, C −1) — logged, not fix-rounded.
  • Stage-1 gate probe (Opus): cold-start build agent still stops at the gate with the new blockquote; relayed the completion criterion correctly.
  • Matrix: docs/research/guide-revisions-batch-matrix.md (decision log incl. F8 parked and Recording: Claude Code transcript compaction can erase the /prepare-build announcement bookend #19 excluded by owner).

Live-AC run (run-09, owner-supplied key) — the headline

First keyed run: AC4, AC9, AC19, AC22, AC24 passed live. AC21 — the course's cross-session continuity demo — failed deterministically: the assembled context never tells the model its thread id, so it called summarize_and_store with a guessed "current_thread" and the tool honestly consolidated nothing. The oracle worked exactly as designed: the spec gained the missing constraint (R11: harness-known identities are injected, never model-supplied), the run-09 build was conformed (~20 lines), offline suite re-green 21/21, and AC21 passed on rerun — live suite 6/6. The course-agnostic guide rule ("harness-known identities are injected, never model-guessed") is recorded in the matrix as the next pass's first candidate, per fix-and-test-travel-together.

Issue routing

🤖 Generated with Claude Code

Carr1005 and others added 10 commits September 9, 2026 12:20
…ency updates, importable fixture filename

Owner-approved texts from the #24 batch: blockquote gains 'what you're
building' + fastest-path/completion sentences (R16/R18 density feedback;
keyless finish blessed); D11/D12 course-default entries carry inline setup
weight; D4 Options name providers not current model names, with gate-time
recommendation deferred to the build agent; CTX-D gains the perishable
request-parameter-behavior category (temperature rejection); §2 key wording
acknowledges compatible endpoints; fixtures/llm-stubs.py -> llm_stubs.py.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…o canon)

First contradicted-category row: thread-scoped default (the app path) vs the
Lesson-5 notebook's unscoped global pool, both course-demonstrated; stakes
test passes because the choice changes what a summary read returns. Side
edits: contradicted-group paragraph updated; R18 defers to D13 (no deciding
twice); §5 coverage note and CTX-C11 cross-reference D13; provenance note
records the batch.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…nline heavy-option weights, model-currency timing, id alphabets, importable fixture filenames, scoping-contradiction example

G1 blockquote anatomy: orientation lead (goal-row default as a user-visible
interaction, never a component inventory) + fastest-path/completion sentence.
G2 §5.5 Options: heavy options state setup weight inline at choice time.
G3 §6.0 + CTX-D anatomy: model currency is the canonical generation-vs-gate
timing split; request-parameter-compatibility perishables.
G4 Pass A: identifier formats are working parameters, alphabet included.
G5 §5 anatomy: fixture module filenames must be importable identifiers.
G6 §5.5 contradicted route: worked storage-scoping example that passes the
stakes test (stabilizes the D13-class subject).
§14: reference-style audit lines for G1/G2/G3/G5; G4 rides the existing
Pass-A coverage line.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…1-V6 properties

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…1 residual class recurrence

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
… (augmentation fold)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…marization (R11)

AC21's live run caught the gap deterministically: the model, never told its
thread id, called summarize_and_store with a guessed 'current_thread' and the
tool honestly consolidated nothing. The constraint is now stated; AC21 is its
end-to-end test. Living-document rule applied; guide-level generalization
(harness-known identities are injected, never model-guessed) queued as a
pass finding.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…ct PASS; AC21 finding + live-run record

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant