feat(skl,cml): --context-window auto model→window probe (v5.12 B8b) [skip-docs]
Completes the deferred B8 half. `--context-window auto` now probes the configured model and calibrates SKL/CML budgets to its real window instead of always falling back to the conservative advisory anchor. - lib/context-window.mjs: pure modelToContextWindow() maps known 1M-tier model IDs (Fable 5, Opus 4.8/4.7/4.6, Sonnet 4.6 — verified June 2026 — plus the explicit [1m] tier tag, dated/provider-prefixed IDs, and the opus/sonnet/fable aliases) to the 1M window; unknown/unconfirmed -> null (caller keeps the conservative anchor). resolveContextWindow() auto branch now probes opts.model: recognized -> auto-probed (not advisory); unknown or unpinned -> auto-unresolved (advisory, pre-B8b behavior). - lib/active-model.mjs (new): resolveActiveModel() reads the model the way Claude Code resolves it — shell ANTHROPIC_MODEL override, then settings cascade local > project > user. Injectable env, hermetic under test HOME. - scan-orchestrator: resolves the active model only when the flag is `auto` and threads it into resolveContextWindow; posture inherits via runAllScanners. Default (no flag) and explicit --context-window <n> paths ignore the model and stay byte-stable; frozen v5.0.0 + SC-5 snapshots untouched. TDD: 17 new tests (context-window mapping/probe + active-model cascade). Suite 1296 green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
ad1eceb76a
commit
cf75249b5e
5 changed files with 308 additions and 8 deletions
51
scanners/lib/active-model.mjs
Normal file
51
scanners/lib/active-model.mjs
Normal file
|
|
@ -0,0 +1,51 @@
|
|||
/**
|
||||
* Active-model resolution for the `--context-window auto` probe (B8b).
|
||||
*
|
||||
* Reads the configured model the way Claude Code itself resolves it, so the
|
||||
* window probe (context-window.mjs `modelToContextWindow`) sees the real model:
|
||||
* 1. the shell `ANTHROPIC_MODEL` override (applies to the launched session);
|
||||
* 2. otherwise the settings cascade `model` field — user `~/.claude`, then
|
||||
* project `.claude`, then project-local `.claude` (local > project > user).
|
||||
*
|
||||
* Reads the cascade files directly (like isBundledSkillsDisabled) rather than via
|
||||
* config-discovery classification, and takes an injectable `env` so it is
|
||||
* deterministic and hermetic under the test HOME. Returns null when no model is
|
||||
* pinned anywhere — the honest signal that `auto` must fall back to advisory.
|
||||
*
|
||||
* Zero external dependencies (repo invariant).
|
||||
*/
|
||||
|
||||
import { join } from 'node:path';
|
||||
import { readTextFile } from './file-discovery.mjs';
|
||||
import { parseJson } from './yaml-parser.mjs';
|
||||
|
||||
/**
|
||||
* @param {string|null|undefined} projectPath - project root, to also read project + local settings
|
||||
* @param {{ env?: Record<string,string|undefined> }} [opts]
|
||||
* @returns {Promise<string|null>} the resolved model id/alias, or null if unset
|
||||
*/
|
||||
export async function resolveActiveModel(projectPath, { env = process.env } = {}) {
|
||||
// 1. Shell ANTHROPIC_MODEL overrides settings (CC: applies to the session).
|
||||
const envModel = typeof env?.ANTHROPIC_MODEL === 'string' ? env.ANTHROPIC_MODEL.trim() : '';
|
||||
if (envModel) return envModel;
|
||||
|
||||
// 2. Settings cascade: user -> project -> project-local, later wins.
|
||||
const home = (env && (env.HOME || env.USERPROFILE)) || '';
|
||||
const candidates = [];
|
||||
if (home) candidates.push(join(home, '.claude', 'settings.json'));
|
||||
if (projectPath) {
|
||||
candidates.push(join(projectPath, '.claude', 'settings.json'));
|
||||
candidates.push(join(projectPath, '.claude', 'settings.local.json'));
|
||||
}
|
||||
|
||||
let model = null;
|
||||
for (const p of candidates) {
|
||||
const content = await readTextFile(p);
|
||||
if (!content) continue;
|
||||
const parsed = parseJson(content);
|
||||
if (parsed && typeof parsed.model === 'string' && parsed.model.trim()) {
|
||||
model = parsed.model.trim();
|
||||
}
|
||||
}
|
||||
return model;
|
||||
}
|
||||
|
|
@ -27,13 +27,58 @@ export const LARGE_CONTEXT_SCALE = LARGE_CONTEXT_WINDOW / CONTEXT_WINDOW_ANCHOR;
|
|||
// Dependency-free thousands separator (repo invariant: zero external deps).
|
||||
export const withCommas = (n) => String(n).replace(/\B(?=(\d{3})+(?!\d))/g, ',');
|
||||
|
||||
// Model families whose context window is the large (1M) tier. Verified June 2026
|
||||
// (platform.claude.com models overview): Fable 5, Opus 4.8/4.7/4.6 and Sonnet 4.6
|
||||
// all run a 1M context window. Matched by substring so dated IDs
|
||||
// (claude-opus-4-8-20260528) and provider-prefixed IDs
|
||||
// (us.anthropic.claude-opus-4-8) resolve too. Models we cannot confirm (e.g.
|
||||
// Haiku, older 200k-era IDs) are deliberately left out: the caller then keeps the
|
||||
// conservative anchor rather than guess a relaxed budget.
|
||||
export const LARGE_CONTEXT_MODEL_IDS = [
|
||||
'claude-fable-5',
|
||||
'claude-opus-4-8',
|
||||
'claude-opus-4-7',
|
||||
'claude-opus-4-6',
|
||||
'claude-sonnet-4-6',
|
||||
];
|
||||
|
||||
// Short aliases Claude Code accepts in the `model` setting / ANTHROPIC_MODEL that
|
||||
// currently resolve to a 1M-tier model (`opusplan` plans on an Opus-tier model).
|
||||
export const LARGE_CONTEXT_MODEL_ALIASES = new Set(['opus', 'sonnet', 'fable', 'opusplan']);
|
||||
|
||||
/**
|
||||
* Map a configured model id/alias to its context window, or null when we cannot
|
||||
* confirm it. Pure: no IO. Used by the `--context-window auto` probe (B8b) so
|
||||
* known 1M-tier models calibrate budgets instead of falling back to the
|
||||
* conservative advisory anchor.
|
||||
*
|
||||
* @param {string} modelId - e.g. "claude-opus-4-8[1m]", "claude-sonnet-4-6", "opus"
|
||||
* @returns {number|null} the context window, or null if unrecognized
|
||||
*/
|
||||
export function modelToContextWindow(modelId) {
|
||||
if (typeof modelId !== 'string') return null;
|
||||
const id = modelId.trim().toLowerCase();
|
||||
if (!id) return null;
|
||||
// Explicit tier tag wins — the running session model surfaces as e.g.
|
||||
// "claude-opus-4-8[1m]". This is the strongest, most future-proof signal.
|
||||
if (id.includes('[1m]')) return LARGE_CONTEXT_WINDOW;
|
||||
// Known 1M-tier families (substring → tolerant of date/provider-prefix variants).
|
||||
for (const fam of LARGE_CONTEXT_MODEL_IDS) {
|
||||
if (id.includes(fam)) return LARGE_CONTEXT_WINDOW;
|
||||
}
|
||||
// Short aliases.
|
||||
if (LARGE_CONTEXT_MODEL_ALIASES.has(id)) return LARGE_CONTEXT_WINDOW;
|
||||
// Unknown: cannot confirm the window — keep the conservative anchor (null).
|
||||
return null;
|
||||
}
|
||||
|
||||
/**
|
||||
* @typedef {object} ResolvedContextWindow
|
||||
* @property {number} window - the context window budgets calibrate against
|
||||
* @property {boolean} advisory - true when the window is unknown: keep the anchor
|
||||
* but downgrade budget findings to info instead of
|
||||
* firing them as a breach
|
||||
* @property {'default'|'explicit'|'auto-unresolved'} source
|
||||
* @property {'default'|'explicit'|'auto-probed'|'auto-unresolved'} source
|
||||
*/
|
||||
|
||||
/**
|
||||
|
|
@ -41,19 +86,29 @@ export const withCommas = (n) => String(n).replace(/\B(?=(\d{3})+(?!\d))/g, ',')
|
|||
*
|
||||
* Design (B8): the DEFAULT (no flag) is byte-identical to the pre-B8 behavior —
|
||||
* the conservative 200k anchor at full severity. Only an explicit value changes
|
||||
* calibration. `auto` asks the tool to figure out the window; until model→window
|
||||
* probing ships (B8b) it cannot, so it keeps the conservative anchor but marks the
|
||||
* result advisory so SKL/CML downgrade their budget findings to info rather than
|
||||
* "crying wolf" with a breach on a window we cannot confirm.
|
||||
* calibration. `auto` asks the tool to figure out the window.
|
||||
*
|
||||
* B8b: `auto` now probes the configured model (`opts.model`, resolved from the
|
||||
* settings cascade / ANTHROPIC_MODEL by the orchestrator). A recognized 1M-tier
|
||||
* model calibrates to its window (source `auto-probed`, not advisory). When the
|
||||
* model is unknown or unpinned, it keeps the conservative anchor but marks the
|
||||
* result advisory (source `auto-unresolved`) so SKL/CML downgrade their budget
|
||||
* findings to info rather than "crying wolf" on a window we cannot confirm.
|
||||
*
|
||||
* @param {string|number|null|undefined} arg
|
||||
* @param {{ model?: string|null }} [opts] - probe input for `auto` (ignored on the
|
||||
* default/explicit paths, which stay byte-stable).
|
||||
* @returns {ResolvedContextWindow}
|
||||
*/
|
||||
export function resolveContextWindow(arg) {
|
||||
export function resolveContextWindow(arg, opts = {}) {
|
||||
if (arg == null) {
|
||||
return { window: CONTEXT_WINDOW_ANCHOR, advisory: false, source: 'default' };
|
||||
}
|
||||
if (String(arg).trim().toLowerCase() === 'auto') {
|
||||
const probed = modelToContextWindow(opts.model);
|
||||
if (probed) {
|
||||
return { window: probed, advisory: false, source: 'auto-probed' };
|
||||
}
|
||||
return { window: CONTEXT_WINDOW_ANCHOR, advisory: true, source: 'auto-unresolved' };
|
||||
}
|
||||
const n = typeof arg === 'number' ? arg : parseInt(String(arg).trim(), 10);
|
||||
|
|
|
|||
|
|
@ -15,6 +15,7 @@ import { discoverConfigFiles, discoverConfigFilesMulti, discoverFullMachinePaths
|
|||
import { loadSuppressions, applySuppressions, formatSuppressionSummary } from './lib/suppression.mjs';
|
||||
import { humanizeEnvelope } from './lib/humanizer.mjs';
|
||||
import { resolveContextWindow } from './lib/context-window.mjs';
|
||||
import { resolveActiveModel } from './lib/active-model.mjs';
|
||||
|
||||
// Scanner registry — import order determines execution order
|
||||
import { scan as scanClaudeMd } from './claude-md-linter.mjs';
|
||||
|
|
@ -98,7 +99,13 @@ export async function runAllScanners(targetPath, opts = {}) {
|
|||
// B8 — resolve the context window once and thread it to budget-aware scanners
|
||||
// (SKL, CML). Undefined opts.contextWindow → conservative 200k anchor, which is
|
||||
// byte-identical to the pre-B8 default; other scanners ignore the third arg.
|
||||
const contextWindow = resolveContextWindow(opts.contextWindow);
|
||||
// B8b — `--context-window auto` probes the configured model (settings cascade /
|
||||
// ANTHROPIC_MODEL) so a 1M-tier host self-calibrates; unknown/unpinned → advisory.
|
||||
let probedModel = null;
|
||||
if (String(opts.contextWindow ?? '').trim().toLowerCase() === 'auto') {
|
||||
probedModel = await resolveActiveModel(resolvedPath, { env: process.env });
|
||||
}
|
||||
const contextWindow = resolveContextWindow(opts.contextWindow, { model: probedModel });
|
||||
|
||||
// Shared file discovery — scanners reuse this
|
||||
let discovery;
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue