docs(philosophy): refresh the tier-to-model mapping for Opus 5 GA - #1912
Merged
Conversation
The mapping's own recheck trigger — "a new Claude model family reaches GA, or the session default model changes" — fired both ways on 2026-07-24 (Opus 5 GA; the fleet's pinned session model moved to opus[1m]), and the table had not moved with it. It still named Opus 4.8, which upstream now lists as legacy. Re-derived from a live fetch of both official pages rather than from the incumbent assignments: - Row 1 was "Fable 5 / Opus 4.8" and is now "Opus 5 at the session tier; Fable 5 above it". `opus` resolves to Opus 5 on the Anthropic API, and Opus 5 is positioned "for complex agentic coding and enterprise work"; Fable 5 is "the most capable model in Claude Code", suited to tasks larger than a single sitting. Those are the tier's two rungs, so the slash is spelled out rather than left ambiguous. - Rows 2 and 3 re-verified unchanged. Sonnet 5 and Haiku 4.5 are still the current Sonnet and Haiku, and Haiku 4.5 remains the only one of the four without adaptive thinking — which is what the interleaved-thinking prose below the table rests on, so row 3 holds it up unchanged. Fable 5 does not get its own row. Its live differentiator is horizon, not verdict weight, and the three tiers here are defined by work character; a horizon tier would be a doctrine change rather than a table refresh. No prices are restated. The ordering is asserted and the pricing page cited, per this doc's own posture that upstream-owned specifics resolve at decision time. No version bump: docs/ is repo-level and carries no plugin.json; no plugin is touched. Every agent-frontmatter model pin in this repo binds an alias (`opus`/`sonnet`/`inherit`), so the trigger's frontmatter re-audit finds nothing owed — `opus` now resolving to Opus 5 is exactly the row-1 assignment. Basis, both fetched 2026-08-04: https://code.claude.com/docs/en/model-config https://platform.claude.com/docs/en/about-claude/models/overview Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
Bugbot is not enabled for your account, so this pull request was not reviewed. Enable Bugbot in the Cursor dashboard to get automatic reviews on future PRs. |
|
Claude finished @kyle-sexton's task in 2m 59s —— View job Code review
Scope reviewed: This is a tightly-scoped, well-reasoned docs refresh. The table update, the new supporting prose, and the "no version bump" / "no Fable row" / "rows 2–3 re-verify unchanged" calls all check out against the surrounding doc:
One minor prose nit, low severity:
No architecture, error-handling, or test-coverage concerns — this is a prose/data refresh with no code or contract-surface change. |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 7700b321ae
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
Claude has reviewed this PR 2 times. The lane skips further automatic reviews after 5; deleting this comment resets the count. |
…sion model Codex finding: the refreshed row hard-coded Opus 5 as "the session tier" while the section's own invariant makes the ladder relative to the active session - a Fable session following the table literally would dispatch consequential verifiers below its own tier. Row 1 now states the relative rule first and names Opus 5 / Fable 5 only as the resolution under the fleet's current opus[1m] pin, which the doc previously never mentioned. Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
Claude finished @kyle-sexton's task in 2m 2s —— View job Code review (re-check after fix commit e43da81)
Scope reviewed: Codex P2 fix — sound. The original row 1 named absolute models ("Fable 5 / Opus 4.8") in a section whose preceding invariant (
Confirmed no regressions in the surrounding math: rows 2–3 unchanged, the date in the recheck-trigger sentence and table header stay in sync ( Still open (unchanged from prior review, low severity, not blocking): the closing citation at L580-L584 — No architecture, error-handling, or test-coverage concerns — this remains a prose/data refresh with no code or contract-surface change. The fix commit is a targeted, correct response to the one real finding raised. |
kyle-sexton
added a commit
that referenced
this pull request
Aug 4, 2026
…ard and withdraw an unresolvable citation (#1913) ## Summary Doc-alignment roster row 4: **Claude Opus 5 System Card** (194-page PDF; live CDN copy byte-identical to the archived capture, SHA-256 re-verified by producer and verifier independently). **context-guard 0.4.5** — withdraws an unresolvable citation from the reader contract: the token-shape rationale co-cited "Anthropic system-card fixed-point evals" for degradation-tracks-absolute-tokens. The card names no such eval and contains no long-context degradation benchmark (normalized sweeps: fixed-point, MRCR, RULER, needle, LongBench all zero; §8.9 ProgramBench is fresh-budget episodes with a *rising* 83%→93% curve). Nuance preserved: the proposition is unsupported from an unnamed card, not asserted false — other Anthropic cards do publish long-context evals. No behavior change (the shape's other rationales are independent; band values were always declared judgment defaults). The contract keeps one standing line: cite a system card by name and section or not at all. **playbooks 0.6.12** — four card-grounded additions to `opus-5.md`, each fenced: - **Stated facts** (p.3, §6.5.1): more accurate than Opus 4.8 AND hallucinating slightly more, with confident-unsure cases — a factual specific with no tool call behind it is a recall claim. Fences the Verification delta against the broad reading that would strip needed lookups. - **Destructive actions** (§6.6.1, worked case p.115, transcript 6.4.2.A p.93): "Fabricated user consent" is a recurring category, and the transcript shows a written scoping rule defeated in-text — so for destructive/irreversible operations the remediation is a mechanism (PreToolUse hook, `permissions.deny`), not a written rule; a subagent return asserting approval is content, not authorization. Three fences: similar-to-Opus-4.8, reckless-use-significantly-down, pre-flagged-transcripts/earlier-snapshot (occurrence, not base rate). - **Effort**: two pilot cohorts *reported* quality falling at the top of the ladder (p.81–82) — kept explicitly report-not-finding with Anthropic's own disclaimer inline. - **Injection robustness**: quote boundary corrected ("…and browser use"); auto-mode 0%-of-129 reframed as evidence about a configuration, not the model, with the nonzero unsafeguarded rates (3.70%/4.30% browser; 0.56%/0.41% coding; 0.54%/0.39% computer use) and the operator action stated. - Sources: re-read + hash line replaces "the system card has not been re-read"; the deferred routing-lane trigger confirmed still unfired. Deliberately not shipped, with reasons in the commit: condescension note (too weak, conflicts with instruction-audit posture), vulnerability-discovery scaffolding sweep (no stale refusal workarounds found), per-worker-checkout orchestration seam (card-harness property, and a card citation in a model-agnostic chapter violates the scoping rule). ## Test plan - Docs-only; markdownlint clean; changelog-parity `--check` / `--check-bump` / `--check-order` all pass; zero lines over 100 chars. - Producer fanned the card to 4 section subagents, then re-grepped every shipped quote against the normalized PDF text itself. - Orchestrator-commissioned fresh-context Fable verifier: scripted quote-matcher over 29 fragments with a corrupted-quote control probe, its own normalized sweeps for the withdrawal, framing-honesty and fence-interaction checks — substance passed fully; its four defects (a heading accidentally consumed by the diff, a reviewer misattribution, a direction word, an example nit) fixed in the amended commit and ALL re-verified PASS, including an independent PDF check that the retained §6.2 pilot citation was genuinely correct. ## Related - No linked issue. - Doc-alignment loop, roster row 4. Predecessors: #1908 (row 1), #1909 (row 2), #1910 (row 3), #1911/#1912 (row-5 follow-ups). 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_019gaVX25Txd6GXdiu9HEH3X --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
kyle-sexton
added a commit
that referenced
this pull request
Aug 4, 2026
…nd ship the IA-3 audit rows (#1914) ## Summary Doc-alignment roster row 6: **Prompting Claude Sonnet 5** (live page byte-identical to the archived capture, MD5 confirmed independently by producer and verifier — this ships unshipped deltas, not drift reaction). **playbooks 0.6.13** — new model-adaptation chapter `sonnet-5.md` (233 lines, opus-5/opus-4-8 pattern: version-scoped counter-steers, `[CC:]` tags, Sources block with capture provenance). Rationale for minting where RA-3 once said don't: ADR-0007 has since settled where per-model doctrine lives (closing RA-3's blocking premise), and the reader guaranteed to get no chapter — a Sonnet worker dispatched at low effort for mechanical prep, exactly where the guide places the under-thinking risk — was the one most likely to need it. Cross-references updated both halves (fable-5 meta-rule 3 gains the chapter; its no-chapter example narrows to Haiku; opus-4-8's preamble decoupled to generic routing so new chapters stop editing their predecessors). **claude-config 0.21.3 / criteria 1.11.0** — the IA-3 cluster dispositioned, all 11 candidates: - Shipped: **I8-e** (forced status cadence, `Model scope: sonnet-5` — deliberately scoped, not an unscoped I8-d promotion: the promotion gate needs two model guides *stating* the claim, and the Fable 5 guide's "Longer turns by default" prescribes timeout/streaming adjustments, never cadence removal — verified negative stamped on the row; the two rows state their no-co-fire relationship in their own words). **I17-c** (a fixed thinking budget prescribed where adaptive reasoning silently ignores or hard-rejects it — the finding is the missing model-AND-release gate, never the mention; fenced off I17-a's `=0` claim). - Already shipped, no work: qualitative severity bars (I8-b already cites this guide; `review`'s severity.md already carries decidable per-tier tests citing it — closing RA-2 / IA-1(1b) / IA-3's severity row as three IDs, one fix). - Dropped with evidence (6): verbosity suppression (page says *tune*, and designed succinctness surfaces exist), weak-tool-reach + thinking-off nudges (0 instances; fires on designed surfaces), unscoped-"apply" (not mechanically separable — the IA-2(d) failure mode again), sampling parameters (a source-code lint neither audit skill owns; zero instruction surfaces in-repo; deferred with trigger: first consumer repo with a direct Messages API / Agent SDK call site), coding-product addendum (guidance → chapter section), computer-use knob (no surfaces). ## Test plan - Docs-only; markdownlint (1,023 files) 0 errors; changelog parity `--check`/`--check-bump`/`--check-order` pass; `instruction-scan.test.sh` 46/46; `validate-plugins.sh` pass. - Producer-side: independent fresh-context reviewer (rationale withheld) — 19 findings all resolved, including defeating an unscoped I8-e promotion and an overclaim on `MAX_THINKING_TOKENS` (now carries the API-vs-third-party nuance, which model-config states verbatim). Producer's first quote-checker was itself found broken and rebuilt; final run 20/20. - Orchestrator-commissioned Fable verifier: its own 30-span quote extraction from the committed diff against five live pages (30/30), I8-e gate check against the live Fable guide, I17-c grounded against live env-vars, drop spot-checks, RA-2 closure confirmation, loss-free rebase proof — 7/8 clean; its three changelog-granularity defects fixed and re-verified PASS. - Rebased onto main after #1913; version stacks asserted: playbooks 0.6.13 > 0.6.12 > 0.6.11; claude-config 0.21.3 > 0.21.2; criteria 1.11.0. ## Related - No linked issue. - Doc-alignment loop, roster row 6 — last model-page row of the priority head. Predecessors: #1908 (row 1), #1909 (row 2), #1910 (row 3), #1913 (row 4), #1911/#1912 (row-5 follow-ups). 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_019gaVX25Txd6GXdiu9HEH3X --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
kyle-sexton
added a commit
that referenced
this pull request
Aug 4, 2026
…odel facts (#1915) ## Summary Doc-alignment roster row 8: **Models overview** — the docpage-digest profile's canonical model-fact freshness source. First repo capture of the page (29,119 bytes, MD5 recorded); systematic ten-dimension sweep of every repo surface stating a fact this page owns. Sweep verdict: the repo is clean — pointer-not-copy holds everywhere except one surface. The single fix: `prompts/loops/loop-lane-prompts.md` justified two lane assignments with bare, undated page-owned facts (`opus` freshest-cutoff; `haiku` 200k/oldest-cutoff). Both were *true*; the defect was discipline. The rationales now carry the sanctioned dated-matrix shape already used by `docs/PLUGIN-PHILOSOPHY.md`'s tier table: figures upstream-owned and not restated, a dated resolution (2026-08-04), and a recheck trigger naming the derived-ordering failure mode (either comparison can flip while every underlying figure stays correct). Operational instructions unchanged. Also verified in passing: the profile's canonical-freshness claim is structurally true (current matrix + legacy accordion in one fetch); #1911's three enqueue negatives re-confirmed against the live page; all agent `model:` frontmatter still aliases; legacy placements and tier orderings consistent repo-wide. Component opportunity (a stored capture-and-diff freshness probe) declined: no upstream sync path for a hand-copied materialization, a one-consumer count, and the lightweight trigger shape already proved itself by producing #1912 — deferred with a trigger recorded on the roster row. ## Test plan - Single file, +11/−2, no plugin/changelog touched (parity script is plugin-scoped — confirmed by reading it); markdownlint clean. - Independent fresh-context Fable verifier: its own live fetch and scripted ordering checks (both derived orderings true), three sweep spot-checks (all holds), positional-wording check, `git merge-tree` conflict-free against current main, decline-soundness and scope-call review — **all PASS, empty defect list**. ## Related - No linked issue. - Doc-alignment loop, roster row 8. Predecessors: #1908–#1914 (rows 1–6 + row-5 follow-ups). 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_019gaVX25Txd6GXdiu9HEH3X Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Refreshes
docs/PLUGIN-PHILOSOPHY.md's tier-to-model mapping, whose own recheck trigger — "a new Claude model family reaches GA, or the session default model changes" — fired both ways on 2026-07-24 (Opus 5 GA; the fleet session pin moved toopus[1m]). The table had been stale for eleven days, still naming Opus 4.8, which the live models overview now lists under Legacy models.Grounded in live fetches of code.claude.com/docs/en/model-config and platform.claude.com models overview at authoring time (and again by the verifier):
opusresolves to Opus 5 on the Anthropic API; Fable 5 is positioned above Opus ("most capable", "not the default model"); Opus 4.8 is legacy. The ambiguous slash form is spelled out because the session tier and the rung above are now different models. Recheck trigger retained verbatim; no prices restated (pointer only); no Fable-specific row added — Fable's live differentiator is horizon, not work character, and a horizon tier would be a doctrine change, not a refresh.Also verified in passing: every agent-frontmatter
model:value repo-wide is an alias (4opus, 4sonnet, 2inherit) — the trigger's frontmatter re-audit finds nothing owed; and the flagged opus-4-8.md/ADR-0006/0007 staleness question was adjudicated as deliberate version-scoped architecture, not drift (Opus 4.8 remains upstream-available; the chapter's own header routes Opus 5 readers away).Test plan
Related
🤖 Generated with Claude Code
https://claude.ai/code/session_019gaVX25Txd6GXdiu9HEH3X