Pick any line to see why it is the way it is: the commit, the pull request and issue it came from, and what the agent was thinking.
| Integrations: your own model provider, alerts that open issues, tickets agents read | 1 | { |
| 2 | "$schema": "../../node_modules/wrangler/config-schema.json", | |
| 3 | "name": "g1t-models", | |
| 4 | "account_id": "1e6f2cffa3f445920836e8ebe446bb58", | |
| 5 | "compatibility_date": "2026-09-26", | |
| 6 | "main": "./src/index.ts", | |
| 7 | "workers_dev": false, | |
| Merge the AI Gateway: Anthropic's Messages API on a workspace's tokens | 8 | // Sandboxes reach models only through here, with a token for their run; |
| 9 | // a workspace's own code reaches the AI Gateway here with one of its | |
| AI Gateway: OpenAI's format, open models, and your own providers | 10 | // access tokens, at /anthropic or /openai/v1. |
| Integrations: your own model provider, alerts that open issues, tickets agents read | 11 | "routes": [{ "pattern": "models.g1t.sh", "custom_domain": true }], |
| Mission control shows model usage, yours and the workspace's: tokens, cost, active days, cache share, each day, and the mix | 12 | "services": [ |
| 13 | { "binding": "INTEGRATIONS", "service": "g1t-integrations" }, | |
| 14 | // Where each run's tokens are counted, for usage views. | |
| Merge the AI Gateway: Anthropic's Messages API on a workspace's tokens | 15 | { "binding": "BILLING", "service": "g1t-billing" }, |
| 16 | // Who an AI Gateway request's access token belongs to, and its scopes. | |
| 17 | { "binding": "IDENTITY", "service": "g1t-identity" } | |
| Mission control shows model usage, yours and the workspace's: tokens, cost, active days, cache share, each day, and the mix | 18 | ], |
| Merge platform pause and the hourly usage watcher: staff can pause compute, schedules, indexing or renders for everyone, the watcher emails on a breach and is never blind quietly, and the models proxy holds each run to its cap (billing 0051, integrations 0006) | 19 | // Each run's model spend, one object per model session, so its cost cap |
| 20 | // holds across every isolate its requests reach (src/run-spend.ts). | |
| 21 | "durable_objects": { | |
| 22 | "bindings": [{ "name": "RUN_SPEND", "class_name": "RunSpend" }] | |
| 23 | }, | |
| 24 | "migrations": [{ "tag": "v1", "new_sqlite_classes": ["RunSpend"] }], | |
| Integrations: your own model provider, alerts that open issues, tickets agents read | 25 | "vars": { |
| 26 | // g1t's own route, for runs g1t pays for: a Cloudflare AI Gateway, | |
| 27 | // which holds g1t's key. | |
| 28 | "AI_GATEWAY_ID": "g1t", | |
| 29 | "CLOUDFLARE_ACCOUNT_ID": "1e6f2cffa3f445920836e8ebe446bb58" | |
| 30 | }, | |
| Merge branch 'main' into actions-toolkit-oidc-artifacts | 31 | // Once a day, after billing's daily run: every provider's model list, |
| 32 | // recorded with billing's catalogue (src/discover.ts). sudo's "Check | |
| 33 | // for new models" does the same through the `Discovery` entrypoint. | |
| 34 | "triggers": { "crons": ["29 5 * * *"] }, | |
| Integrations: your own model provider, alerts that open issues, tickets agents read | 35 | // Secrets: AI_GATEWAY_TOKEN; ANTHROPIC_API_KEY only if the gateway does |
| AI Gateway: OpenAI's format, open models, and your own providers | 36 | // not hold g1t's key; WORKERS_AI_TOKEN, a Cloudflare API token with |
| 37 | // Workers AI Read on this account, for the AI Gateway's open models | |
| 38 | // (without it AI_GATEWAY_TOKEN is tried, and needs that permission too). | |
| Merge branch 'worktree-agent-a8752162fea25f63f' into spend-guardrails | 39 | // Logs of a tenth of requests: every model call is one. |
| 40 | "observability": { "enabled": true, "head_sampling_rate": 0.1 } | |
| Integrations: your own model provider, alerts that open issues, tickets agents read | 41 | } |
This file's history is long; its oldest lines are credited to the oldest commit read.