vrr/codeburn
2
0
Fork 0
mirror of https://github.com/AgentSeal/codeburn.git synced 2026-08-25 08:22:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

merge: rebase #1056 onto main with Codex v12 / daily v24

Browse source 
Main already spent Codex results v11 and daily v23 on #1075, and
result caches are now version-suffixed. Keep both parse-version
tokens (codex-pricing-v1 + activity-price-v1) so a take-ours merge
cannot drop the pricing invalidation. Do not Extra High again.
This commit is contained in:
Aditya Vikram Singh 2026-08-22 02:35:51 +05:30
commit 33d344abc3
60 changed files with 1881 additions and 358 deletions
Download patch file Download diff file Expand all files Collapse all files

29
scripts/upgrade-path/compare.mjs
View file

@ -22,11 +22,26 @@
// which is the part the corpus can honestly establish.
// dsh did not exist in the published CLI. Reported; required to be absent
// in the baseline and present after the upgrade.
// codex PRICING changed by design in #1075: reasoning tokens are billed
// inside output rather than on top of it, and cache writes are carved out
// of the input bucket. Nothing about what was PARSED moved, so codex keeps
// the full exact treatment for the call count and every token field; the
// cost tolerance is instead replaced with REPRICE_TOLERANCE — the
// upgraded cost must be strictly lower than the baseline and within 25%
// of it, since #1075 only ever removes a double-count and never raises
// cost — and the delta is reported instead. Drop it from this list once a
// published CLI carries the fix.
const EXACT = ['claude', 'codex', 'gemini', 'kiro', 'cursor']
const CHANGED_BY_DESIGN = ['grok']
const COST_CHANGED_BY_DESIGN = ['codex']
const NEW_IN_THIS_RELEASE = ['dsh']
const COST_TOLERANCE = 0.005 // 0.5% relative
// #1075 only ever LOWERS codex cost (double-counted reasoning removed, cache
// writes carved out of the input bucket) and by a bounded amount on any real
// corpus; a rise, or a drop past this bound, means something beyond the known
// repricing changed.
const REPRICE_TOLERANCE = 0.25 // 25% relative
import { readFileSync } from 'node:fs'
import { join } from 'node:path'
@ -95,13 +110,25 @@ for (const name of providers) {
if (b.calls !== u.calls) diffs.push(`calls ${b.calls} != ${u.calls}`)
for (const f of TOKEN_FIELDS) if (b[f] !== u[f]) diffs.push(`${f} ${b[f]} != ${u[f]}`)
const costDrift = relDiff(b.cost, u.cost)
if (costDrift > COST_TOLERANCE) diffs.push(`cost ${fmt(b.cost)} != ${fmt(u.cost)} (${(costDrift * 100).toFixed(3)}% > ${(COST_TOLERANCE * 100).toFixed(1)}%)`)
let repriced = false
if (COST_CHANGED_BY_DESIGN.includes(name)) {
if (u.cost > b.cost) diffs.push(`cost ${fmt(b.cost)} -> ${fmt(u.cost)} rose; #1075 should only lower codex cost`)
else if (costDrift > REPRICE_TOLERANCE) diffs.push(`cost ${fmt(b.cost)} -> ${fmt(u.cost)} (${(costDrift * 100).toFixed(3)}% > ${(REPRICE_TOLERANCE * 100).toFixed(0)}% expected bound for #1075)`)
else {
repriced = true
notes.push(`${name}: cost ${fmt(b.cost)} -> ${fmt(u.cost)} (${(costDrift * 100).toFixed(3)}%) — repricing expected (#1075); tokens and calls still asserted exactly`)
}
} else if (costDrift > COST_TOLERANCE) {
diffs.push(`cost ${fmt(b.cost)} != ${fmt(u.cost)} (${(costDrift * 100).toFixed(3)}% > ${(COST_TOLERANCE * 100).toFixed(1)}%)`)
}
if (!EXACT.includes(name)) {
notes.push(`${name}: no expectation declared in compare.mjs; ${diffs.length ? diffs.join(', ') : 'identical'}`)
verdict = diffs.length ? 'differs (unclassified)' : 'identical'
} else if (diffs.length) {
failures.push(`${name}: ${diffs.join(', ')}`)
verdict = 'DIFFERS'
} else if (repriced) {
verdict = `repriced (cost ${(costDrift * 100).toFixed(3)}% drift)`
} else {
verdict = costDrift === 0 ? 'identical' : `identical (cost ${(costDrift * 100).toFixed(3)}% drift)`
}

2
scripts/upgrade-path/run.mjs
View file

@ -33,7 +33,7 @@ const WORK = process.env['UPGRADE_PATH_WORK'] || join(tmpdir(), 'codeburn upgrad
const OLD_SESSION_CACHE = 'session-cache.v7.json'
const OLD_DAILY_CACHE = 'daily-cache.v17.json'
const NEW_SESSION_CACHE_DIR = 'session-cache.v9'
const NEW_DAILY_CACHE = 'daily-cache.v22.json'
const NEW_DAILY_CACHE = 'daily-cache.v24.json'
const HOME = join(WORK, 'user home')
const PAYLOADS = join(WORK, 'payloads')