John Smith ac6df68d3a fix(math): enforce physical token fit invariant, eliminate virtual pool hallucinations, and unify cache scaling ...

- Enforce token-first fit invariant in WorkflowCalculator: require caps.basis >= requiredTokens and poolDrain.overageCost === 0 to qualify as fits
- Re-anchor Google Antigravity Ultra 20x Gemini Flash to empirical 3.0B tokens/mo (down from 18.7B virtual dollar division) and Claude Sonnet to 180M tokens/mo matching DevForth ~00/7d telemetry
- Cap Ollama Cloud Team tier at 4,500M tokens/mo (10-stream physical socket bandwidth ceiling) and Kimi Code Vivace K2.7 Code at 1,200M tokens/mo
- Unclamp negative savings in WorkflowCalculator to transparently show when plans cost more than direct API
- Integrate rate-limit lockout wage exposure into Breakeven Verdict headline to penalize severe lockout risks
- Add parsePlanCacheAssumption and symmetric cache-rate scaling to computeApplesToApples
- Fix internal credit burn rate in calculatePoolDrain when models have dedicated perModelTokenBudgets
- Add unit tests verifying 115 passing tests across 8 suites

2026-09-20 22:15:27 -04:00

..

_schema.json

Add perModelTokenBudgets engine: types, schema, validator, resolver, computeApplesToApples; Z.ai official per-model table, Kiro multipliers, CommandCode credit pools

2026-09-19 18:28:46 -04:00

aider.json

feat(plans): update coding plans per live web crawl audit and quota validation

2026-09-19 13:42:52 -04:00

alibaba-cloud.json

fix(pricing): model-aware subscription capacity resolution and cache rate calibration

2026-09-19 21:28:46 -04:00

amazon-q.json

docs: add OSINT usage statistics dossier and update telemetry for obfuscated providers

2026-09-19 22:01:51 -04:00

anthropic-api.json

feat(plans): update coding plans per live web crawl audit and quota validation

2026-09-19 13:42:52 -04:00

augment-code.json

feat(pricing): adversarial math remediations for credit pools, string limits, partitioned drains, and single-seat caps

2026-09-19 22:10:49 -04:00

byteplus.json

fix(pricing): model-aware subscription capacity resolution and cache rate calibration

2026-09-19 21:28:46 -04:00

claude-code.json

fix(pricing): standardize 21K requests, single-seat clamping, Max 20x ceiling, and frontier pool drain (ADV-06..09)

2026-09-20 21:58:46 -04:00

commandcode.json

feat(plans): recalibrate CommandCode tiers (Go, GOAT, Pro, Max) with official usage limits and per-model allowances

2026-09-19 21:45:07 -04:00

cursor.json

fix(pricing): model-aware subscription capacity resolution and cache rate calibration

2026-09-19 21:28:46 -04:00

deepseek-api.json

feat(plans): update coding plans per live web crawl audit and quota validation

2026-09-19 13:42:52 -04:00

fireworks-ai.json

feat(plans): update coding plans per live web crawl audit and quota validation

2026-09-19 13:42:52 -04:00

github-copilot.json

fix(pricing): model-aware subscription capacity resolution and cache rate calibration

2026-09-19 21:28:46 -04:00

google-ai-studio.json

feat(plans): update coding plans per live web crawl audit and quota validation

2026-09-19 13:42:52 -04:00

google-antigravity.json

fix(math): enforce physical token fit invariant, eliminate virtual pool hallucinations, and unify cache scaling

2026-09-20 22:15:27 -04:00

groq-api.json

feat(plans): update coding plans per live web crawl audit and quota validation

2026-09-19 13:42:52 -04:00

kilo-code.json

feat(plans): update coding plans per live web crawl audit and quota validation

2026-09-19 13:42:52 -04:00

kimi-code.json

fix(math): enforce physical token fit invariant, eliminate virtual pool hallucinations, and unify cache scaling

2026-09-20 22:15:27 -04:00

kiro.json

Add perModelTokenBudgets engine: types, schema, validator, resolver, computeApplesToApples; Z.ai official per-model table, Kiro multipliers, CommandCode credit pools

2026-09-19 18:28:46 -04:00

lovable.json

feat(plans): update coding plans per live web crawl audit and quota validation

2026-09-19 13:42:52 -04:00

meta-model-api.json

fix(pricing,docs): per-model subscription quota scaling and LaTeX math syntax

2026-09-19 21:09:46 -04:00

meta-muse-code.json

fix(pricing): model-aware subscription capacity resolution and cache rate calibration

2026-09-19 21:28:46 -04:00

minimax.json

fix(pricing,docs): per-model subscription quota scaling and LaTeX math syntax

2026-09-19 21:09:46 -04:00

mistral-api.json

feat(plans): update coding plans per live web crawl audit and quota validation

2026-09-19 13:42:52 -04:00

ollama-cloud.json

fix(math): enforce physical token fit invariant, eliminate virtual pool hallucinations, and unify cache scaling

2026-09-20 22:15:27 -04:00

openai-api.json

feat(plans): update coding plans per live web crawl audit and quota validation

2026-09-19 13:42:52 -04:00

openai-codex.json

fix(pricing): model-aware subscription capacity resolution and cache rate calibration

2026-09-19 21:28:46 -04:00

opencode.json

feat(plans): recalibrate OpenCode Go with 28-model usage limits, allowances, and 5h/7d caps

2026-09-19 21:49:04 -04:00

openrouter.json

feat(plans): update coding plans per live web crawl audit and quota validation

2026-09-19 13:42:52 -04:00

replit.json

feat(pricing): adversarial math remediations for credit pools, string limits, partitioned drains, and single-seat caps

2026-09-19 22:10:49 -04:00

tabnine.json

feat(plans): update coding plans per live web crawl audit and quota validation

2026-09-19 13:42:52 -04:00

together-ai.json

feat(plans): update coding plans per live web crawl audit and quota validation

2026-09-19 13:42:52 -04:00

windsurf.json

docs: add OSINT usage statistics dossier and update telemetry for obfuscated providers

2026-09-19 22:01:51 -04:00

xiaomi-mimo.json

feat(plans): add Xiaomi MiMo Token Plan as 34th curated plan with credit-based per-model token budgets

2026-09-19 22:34:09 -04:00

z-ai.json

docs: update agent files, documentation, and tracking sources for usage-limits export and plan audits

2026-09-19 21:57:30 -04:00