vrr/opencode
2
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-09 23:08:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

fix(provider): improve prompt caching

Browse source
This commit is contained in:
Aiden Cline 2026-07-08 19:22:45 -05:00
parent 0abbcddac2
commit 439a5a5281
19 changed files with 861 additions and 62 deletions
Download patch file Download diff file Expand all files Collapse all files

47
bun.lock
View file

@ -293,14 +293,14 @@
"@ai-sdk/amazon-bedrock": "4.0.112",
"@ai-sdk/anthropic": "3.0.82",
"@ai-sdk/azure": "3.0.49",
"@ai-sdk/cerebras": "2.0.41",
"@ai-sdk/cerebras": "2.0.60",
"@ai-sdk/cohere": "3.0.27",
"@ai-sdk/deepinfra": "2.0.41",
"@ai-sdk/gateway": "3.0.104",
"@ai-sdk/google": "3.0.73",
"@ai-sdk/google-vertex": "4.0.128",
"@ai-sdk/groq": "3.0.31",
"@ai-sdk/mistral": "3.0.27",
"@ai-sdk/mistral": "3.0.34",
"@ai-sdk/openai": "3.0.53",
"@ai-sdk/openai-compatible": "2.0.41",
"@ai-sdk/perplexity": "3.0.26",
@ -575,7 +575,7 @@
"@ai-sdk/google": "3.0.73",
"@ai-sdk/google-vertex": "4.0.128",
"@ai-sdk/groq": "3.0.31",
"@ai-sdk/mistral": "3.0.27",
"@ai-sdk/mistral": "3.0.34",
"@ai-sdk/openai": "3.0.53",
"@ai-sdk/openai-compatible": "2.0.41",
"@ai-sdk/perplexity": "3.0.26",
@ -1063,19 +1063,24 @@
"tree-sitter-bash",
],
"patchedDependencies": {
"ai-gateway-provider@3.1.2": "patches/ai-gateway-provider@3.1.2.patch",
"@ai-sdk/openai-compatible@2.0.37": "patches/@ai-sdk%2Fopenai-compatible@2.0.37.patch",
"@pierre/trees@1.0.0-beta.4": "patches/@pierre%2Ftrees@1.0.0-beta.4.patch",
"@ai-sdk/xai@3.0.102": "patches/@ai-sdk%2Fxai@3.0.102.patch",
"@modelcontextprotocol/sdk@1.29.0": "patches/@modelcontextprotocol%2Fsdk@1.29.0.patch",
"gcp-metadata@8.1.2": "patches/gcp-metadata@8.1.2.patch",
"@ai-sdk/cohere@3.0.27": "patches/@ai-sdk%2Fcohere@3.0.27.patch",
"@standard-community/standard-openapi@0.2.9": "patches/@standard-community%2Fstandard-openapi@0.2.9.patch",
"effect@4.0.0-beta.83": "patches/effect@4.0.0-beta.83.patch",
"@npmcli/agent@4.0.2": "patches/@npmcli%2Fagent@4.0.2.patch",
"@silvia-odwyer/photon-node@0.3.4": "patches/@silvia-odwyer%2Fphoton-node@0.3.4.patch",
"@tanstack/solid-virtual@3.13.28": "patches/@tanstack%2Fsolid-virtual@3.13.28.patch",
"solid-js@1.9.10": "patches/solid-js@1.9.10.patch",
"@ai-sdk/groq@3.0.31": "patches/@ai-sdk%2Fgroq@3.0.31.patch",
"@ai-sdk/google@3.0.73": "patches/@ai-sdk%2Fgoogle@3.0.73.patch",
"@tanstack/virtual-core@3.17.0": "patches/@tanstack%2Fvirtual-core@3.17.0.patch",
"pacote@21.5.0": "patches/pacote@21.5.0.patch",
"@ai-sdk/mistral@3.0.34": "patches/@ai-sdk%2Fmistral@3.0.34.patch",
},
"overrides": {
"@opentui/core": "catalog:",
@ -1173,7 +1178,7 @@
"@ai-sdk/azure": ["@ai-sdk/azure@3.0.49", "", { "dependencies": { "@ai-sdk/openai": "3.0.48", "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-wskgAL+OmrHG7by/iWIxEBQCEdc1mDudha/UZav46i0auzdFfsDB/k2rXZaC4/3nWSgMZkxr0W3ncyouEGX/eg=="],
"@ai-sdk/cerebras": ["@ai-sdk/cerebras@2.0.41", "", { "dependencies": { "@ai-sdk/openai-compatible": "2.0.37", "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-kDMEpjaRdRXIUi1EH8WHwLRahyDTYv9SAJnP6VCCeq8X+tVqZbMLCqqxSG5dRknrI65ucjvzQt+FiDKTAa7AHg=="],
"@ai-sdk/cerebras": ["@ai-sdk/cerebras@2.0.60", "", { "dependencies": { "@ai-sdk/openai-compatible": "2.0.54", "@ai-sdk/provider": "3.0.12", "@ai-sdk/provider-utils": "4.0.33" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-Rnok3cThg6awBwaDSyiZpgRpbV7pqxGYrA89LODCo5cuEHeP2h0AM0lLHP7zIkclAdXfOm4wldKi/S2T/DGCOw=="],
"@ai-sdk/cohere": ["@ai-sdk/cohere@3.0.27", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-OqcCq2PiFY1dbK/0Ck45KuvE8jfdxRuuAE9Y5w46dAk6U+9vPOeg1CDcmR+ncqmrYrhRl3nmyDttyDahyjCzAw=="],
@ -1195,7 +1200,7 @@
"@ai-sdk/groq": ["@ai-sdk/groq@3.0.31", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-XbbugpnFmXGu2TlXiq8KUJskP6/VVbuFcnFIGDzDIB/Chg6XHsNnqrTF80Zxkh0Pd3+NvbM+2Uqrtsndk6bDAg=="],
"@ai-sdk/mistral": ["@ai-sdk/mistral@3.0.27", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-ZXe7nZQgliDdjz5ufH5RKpHWxbN72AzmzzKGbF/z+0K9GN5tUCnftrQRvTRFHA5jAzTapcm2BEevmGLVbMkW+A=="],
"@ai-sdk/mistral": ["@ai-sdk/mistral@3.0.34", "", { "dependencies": { "@ai-sdk/provider": "3.0.10", "@ai-sdk/provider-utils": "4.0.26" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-HpK28sWGdIfg1vTSScJNtzVdvNRfA4mfCmPmPR+j/MGJ0oAuEJMqxWkL96ZnGPdhZt5KdW09aKovdIe+q2zQ7A=="],
"@ai-sdk/openai": ["@ai-sdk/openai@3.0.48", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-ALmj/53EXpcRqMbGpPJPP4UOSWw0q4VGpnDo7YctvsynjkrKDmoneDG/1a7VQnSPYHnJp6tTRMf5ZdxZ5whulg=="],
@ -5641,7 +5646,11 @@
"@ai-sdk/azure/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
"@ai-sdk/cerebras/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
"@ai-sdk/cerebras/@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.54", "", { "dependencies": { "@ai-sdk/provider": "3.0.12", "@ai-sdk/provider-utils": "4.0.33" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-OyXt0zK8y2/ZIyWlbxTv2r1M7AK227S+Gl4BYOEF42q0wz1n5m4fwR8L4Fy/MQ4Ho6xje47MPsFcRdIqIyP6Rw=="],
"@ai-sdk/cerebras/@ai-sdk/provider": ["@ai-sdk/provider@3.0.12", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-sj9DWTJ2Ze0WR9qsiOPqoqzNx3OxL6iMxHImbhvoe9qOspekbzxNDMiJ4TIGfYHYh9w4OmBjz3prvqhzTi96+Q=="],
"@ai-sdk/cerebras/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.33", "", { "dependencies": { "@ai-sdk/provider": "3.0.12", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.8" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-nJ0bAfegMAIJtrzMJtbzer1cS3nb7c7DsyU1S4nrPm7ZU0Mn6SBBZv5IGZZGTbpWTJwqKTSPeZJTXalbAxt1BA=="],
"@ai-sdk/cohere/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
@ -5679,7 +5688,9 @@
"@ai-sdk/groq/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
"@ai-sdk/mistral/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
"@ai-sdk/mistral/@ai-sdk/provider": ["@ai-sdk/provider@3.0.10", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-Q3BZ27qfpYqnCYGvE3vt+Qi6LGOF9R5Nmzn+9JoM1lCRsD9mYaIhfJLkSunN48nfGXJ6n+XNV0J/XVpqGQl7Dw=="],
"@ai-sdk/mistral/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.26", "", { "dependencies": { "@ai-sdk/provider": "3.0.10", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.8" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-CsKNLKsOpvPujRlIYvoz+Ybw+kGn7J4/fIZa/58+R7iWLLfwn6ifE2G6Yq8K9XvH/I/3bzaDAJ3NhRwEMsLBKQ=="],
"@ai-sdk/openai/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
@ -6145,6 +6156,10 @@
"ai-gateway-provider/@ai-sdk/anthropic": ["@ai-sdk/anthropic@3.0.78", "", { "dependencies": { "@ai-sdk/provider": "3.0.10", "@ai-sdk/provider-utils": "4.0.27" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-0OY12G20cUt6iU6htpEA1491Oz++NVxZxlmWGX4B7rSbeZ5pnDmOu6YtW9BKzdZlNx5Gn23i6WMxyZFoMKNcgA=="],
"ai-gateway-provider/@ai-sdk/cerebras": ["@ai-sdk/cerebras@2.0.41", "", { "dependencies": { "@ai-sdk/openai-compatible": "2.0.37", "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-kDMEpjaRdRXIUi1EH8WHwLRahyDTYv9SAJnP6VCCeq8X+tVqZbMLCqqxSG5dRknrI65ucjvzQt+FiDKTAa7AHg=="],
"ai-gateway-provider/@ai-sdk/mistral": ["@ai-sdk/mistral@3.0.27", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-ZXe7nZQgliDdjz5ufH5RKpHWxbN72AzmzzKGbF/z+0K9GN5tUCnftrQRvTRFHA5jAzTapcm2BEevmGLVbMkW+A=="],
"ai-gateway-provider/@ai-sdk/openai": ["@ai-sdk/openai@3.0.53", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.23" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-Wld+Rbc05KaUn08uBt06eEuwcgalcIFtIl32Yp+GxuZXUQwOb6YeAuq+C6da4ch6BurFoqEaLemJVwjBb7x+PQ=="],
"ai-gateway-provider/@ai-sdk/xai": ["@ai-sdk/xai@3.0.82", "", { "dependencies": { "@ai-sdk/openai-compatible": "2.0.41", "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.23" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-A0VFMufnVf4wODcT3SPQUUzvYXiIO1VhFuXj9r6z/vP4rlo+QRDPw3WSTchcz93ROQWSfBE3I6Szqz342OHi5w=="],
@ -6369,8 +6384,6 @@
"nypm/tinyexec": ["tinyexec@1.2.4", "", {}, "sha512-SHf/r48b7vOrjve9PxJo3MN5v5yuyjHvdUcrQffT3WXMUfnGmHDVbC4k3sHJaJTgZCwpUplIaAo5ANtMyp3YHg=="],
"opencode/@ai-sdk/cerebras": ["@ai-sdk/cerebras@2.0.60", "", { "dependencies": { "@ai-sdk/openai-compatible": "2.0.54", "@ai-sdk/provider": "3.0.12", "@ai-sdk/provider-utils": "4.0.33" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-Rnok3cThg6awBwaDSyiZpgRpbV7pqxGYrA89LODCo5cuEHeP2h0AM0lLHP7zIkclAdXfOm4wldKi/S2T/DGCOw=="],
"opencode/@ai-sdk/openai": ["@ai-sdk/openai@3.0.53", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.23" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-Wld+Rbc05KaUn08uBt06eEuwcgalcIFtIl32Yp+GxuZXUQwOb6YeAuq+C6da4ch6BurFoqEaLemJVwjBb7x+PQ=="],
"opencode/@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.41", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.23" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-kNAGINk71AlOXx10Dq/PXw4t/9XjdK8uxfpVElRwtSFMdeSiLVt58p9TPx4/FJD+hxZuVhvxYj9r42osxWq79g=="],
@ -6947,6 +6960,10 @@
"ai-gateway-provider/@ai-sdk/anthropic/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.27", "", { "dependencies": { "@ai-sdk/provider": "3.0.10", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.8" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-ubkAJ+xODouwtmN1tYlvTPphH1hPOBfZaEQe8U7skGvFAnIRs9PPpsq57bC2+Ky/MB4yzhd6YOsxTAx9sGpazw=="],
"ai-gateway-provider/@ai-sdk/cerebras/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
"ai-gateway-provider/@ai-sdk/mistral/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
"ai-gateway-provider/@ai-sdk/xai/@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.41", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.23" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-kNAGINk71AlOXx10Dq/PXw4t/9XjdK8uxfpVElRwtSFMdeSiLVt58p9TPx4/FJD+hxZuVhvxYj9r42osxWq79g=="],
"ajv-keywords/ajv/json-schema-traverse": ["json-schema-traverse@0.4.1", "", {}, "sha512-xbbCH5dCYU5T8LcEhhuh7HJ88HXuW3qsI3Y0zOZFKfZEHcpWiHU/Jxzk629Brsab/mMiHQti9wMP+845RPe3Vg=="],
@ -7093,12 +7110,6 @@
"opencode-gitlab-auth/open/wsl-utils": ["wsl-utils@0.1.0", "", { "dependencies": { "is-wsl": "^3.1.0" } }, "sha512-h3Fbisa2nKGPxCpm89Hk33lBLsnaGBvctQopaBSOW/uIs6FTe1ATyAnKFJrzVs9vpGdsTe73WF3V4lIsk4Gacw=="],
"opencode/@ai-sdk/cerebras/@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.54", "", { "dependencies": { "@ai-sdk/provider": "3.0.12", "@ai-sdk/provider-utils": "4.0.33" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-OyXt0zK8y2/ZIyWlbxTv2r1M7AK227S+Gl4BYOEF42q0wz1n5m4fwR8L4Fy/MQ4Ho6xje47MPsFcRdIqIyP6Rw=="],
"opencode/@ai-sdk/cerebras/@ai-sdk/provider": ["@ai-sdk/provider@3.0.12", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-sj9DWTJ2Ze0WR9qsiOPqoqzNx3OxL6iMxHImbhvoe9qOspekbzxNDMiJ4TIGfYHYh9w4OmBjz3prvqhzTi96+Q=="],
"opencode/@ai-sdk/cerebras/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.33", "", { "dependencies": { "@ai-sdk/provider": "3.0.12", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.8" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-nJ0bAfegMAIJtrzMJtbzer1cS3nb7c7DsyU1S4nrPm7ZU0Mn6SBBZv5IGZZGTbpWTJwqKTSPeZJTXalbAxt1BA=="],
"p-locate/p-limit/yocto-queue": ["yocto-queue@0.1.0", "", {}, "sha512-rVksvsnNCdJ/ohGc6xgPwyN8eheCxsiLM8mxuE/t/mOVqJewPuO1miLpTHQiRgTKCLexL4MeAFVagts7HmNZ2Q=="],
"pkg-dir/find-up/locate-path": ["locate-path@5.0.0", "", { "dependencies": { "p-locate": "^4.1.0" } }, "sha512-t7hw9pI+WvuwNJXwk5zVHpyhIqzg2qTlklJOf0mVxGSbe3Fp2VieZcduNYjaLDoy6p9uGpQEGWG87WpMKlNq8g=="],
@ -7363,6 +7374,10 @@
"ai-gateway-provider/@ai-sdk/anthropic/@ai-sdk/provider-utils/@standard-schema/spec": ["@standard-schema/spec@1.1.0", "", {}, "sha512-l2aFy5jALhniG5HgqrD6jXLi/rUWrKvqN/qJx6yoJsgKhblVd+iqqU4RCXavm/jPityDo5TCvKMnpjKnOriy0w=="],
"ai-gateway-provider/@ai-sdk/cerebras/@ai-sdk/provider-utils/@standard-schema/spec": ["@standard-schema/spec@1.1.0", "", {}, "sha512-l2aFy5jALhniG5HgqrD6jXLi/rUWrKvqN/qJx6yoJsgKhblVd+iqqU4RCXavm/jPityDo5TCvKMnpjKnOriy0w=="],
"ai-gateway-provider/@ai-sdk/mistral/@ai-sdk/provider-utils/@standard-schema/spec": ["@standard-schema/spec@1.1.0", "", {}, "sha512-l2aFy5jALhniG5HgqrD6jXLi/rUWrKvqN/qJx6yoJsgKhblVd+iqqU4RCXavm/jPityDo5TCvKMnpjKnOriy0w=="],
"ansi-align/string-width/strip-ansi/ansi-regex": ["ansi-regex@5.0.1", "", {}, "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ=="],
"app-builder-lib/@electron/get/fs-extra/universalify": ["universalify@0.1.2", "", {}, "sha512-rBJeI5CXAlmy1pV+617WB9J63U6XcazHHF2f2dbJix4XzpUF0RS3Zbj0FGIOCAva5P/d/GBOYaACQ1w+0azUkg=="],
@ -7431,8 +7446,6 @@
"js-beautify/glob/path-scurry/lru-cache": ["lru-cache@10.4.3", "", {}, "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ=="],
"opencode/@ai-sdk/cerebras/@ai-sdk/provider-utils/@standard-schema/spec": ["@standard-schema/spec@1.1.0", "", {}, "sha512-l2aFy5jALhniG5HgqrD6jXLi/rUWrKvqN/qJx6yoJsgKhblVd+iqqU4RCXavm/jPityDo5TCvKMnpjKnOriy0w=="],
"pkg-dir/find-up/locate-path/p-locate": ["p-locate@4.1.0", "", { "dependencies": { "p-limit": "^2.2.0" } }, "sha512-R79ZZ/0wAxKGu3oYMlz8jy/kbhsNrS7SKZ7PxEHBgJ5+F2mtFW2fK2cOtBh1cHYkQsbzFV7I+EoRKe6Yt0oK7A=="],
"pkg-up/find-up/locate-path/p-locate": ["p-locate@3.0.0", "", { "dependencies": { "p-limit": "^2.0.0" } }, "sha512-x+12w/To+4GFfgJhBEpiDcLozRJGegY+Ei7/z0tSLkMmxGZNybVMSfWj9aJn8Z5Fc7dBUNJOOVgPv2H7IwulSQ=="],

7
package.json
View file

@ -155,6 +155,11 @@
"@pierre/trees@1.0.0-beta.4": "patches/@pierre%2Ftrees@1.0.0-beta.4.patch",
"@modelcontextprotocol/sdk@1.29.0": "patches/@modelcontextprotocol%2Fsdk@1.29.0.patch",
"@tanstack/virtual-core@3.17.0": "patches/@tanstack%2Fvirtual-core@3.17.0.patch",
"effect@4.0.0-beta.83": "patches/effect@4.0.0-beta.83.patch"
"effect@4.0.0-beta.83": "patches/effect@4.0.0-beta.83.patch",
"@ai-sdk/mistral@3.0.34": "patches/@ai-sdk%2Fmistral@3.0.34.patch",
"ai-gateway-provider@3.1.2": "patches/ai-gateway-provider@3.1.2.patch",
"@ai-sdk/cohere@3.0.27": "patches/@ai-sdk%2Fcohere@3.0.27.patch",
"@ai-sdk/groq@3.0.31": "patches/@ai-sdk%2Fgroq@3.0.31.patch",
"@ai-sdk/openai-compatible@2.0.37": "patches/@ai-sdk%2Fopenai-compatible@2.0.37.patch"
}
}

4
packages/core/package.json
View file

@ -65,14 +65,14 @@
"@ai-sdk/amazon-bedrock": "4.0.112",
"@ai-sdk/anthropic": "3.0.82",
"@ai-sdk/azure": "3.0.49",
"@ai-sdk/cerebras": "2.0.41",
"@ai-sdk/cerebras": "2.0.60",
"@ai-sdk/cohere": "3.0.27",
"@ai-sdk/deepinfra": "2.0.41",
"@ai-sdk/gateway": "3.0.104",
"@ai-sdk/google": "3.0.73",
"@ai-sdk/google-vertex": "4.0.128",
"@ai-sdk/groq": "3.0.31",
"@ai-sdk/mistral": "3.0.27",
"@ai-sdk/mistral": "3.0.34",
"@ai-sdk/openai": "3.0.53",
"@ai-sdk/openai-compatible": "2.0.41",
"@ai-sdk/perplexity": "3.0.26",

91
packages/core/test/provider-cache-key.test.ts Normal file
View file

@ -0,0 +1,91 @@
import { createCerebras } from "@ai-sdk/cerebras"
import { createDeepInfra } from "@ai-sdk/deepinfra"
import { createMistral } from "@ai-sdk/mistral"
import { createOpenAI } from "@ai-sdk/openai"
import { describe, expect, test } from "bun:test"
test("Mistral sends promptCacheKey as prompt_cache_key", async () => {
let body: Record<string, unknown> | undefined
const mockFetch = Object.assign(
async (_input: Parameters<typeof fetch>[0], init?: RequestInit) => {
body = JSON.parse(String(init?.body))
return Response.json({
id: "response-1",
created: 0,
model: "mistral-large-latest",
object: "chat.completion",
choices: [{ index: 0, message: { role: "assistant", content: "Hello" }, finish_reason: "stop" }],
usage: { prompt_tokens: 1, completion_tokens: 1, total_tokens: 2 },
})
},
{ preconnect: fetch.preconnect },
)
const model = createMistral({ apiKey: "test", fetch: mockFetch })("mistral-large-latest")
await model.doGenerate({
prompt: [{ role: "user", content: [{ type: "text", text: "Hello" }] }],
providerOptions: { mistral: { promptCacheKey: "session-123" } },
})
expect(body?.prompt_cache_key).toBe("session-123")
})
test("OpenAI Responses sends promptCacheKey as prompt_cache_key", async () => {
let body: Record<string, unknown> | undefined
const mockFetch = Object.assign(
async (_input: Parameters<typeof fetch>[0], init?: RequestInit) => {
body = JSON.parse(String(init?.body))
return Response.json({
id: "response-1",
created_at: 0,
model: "gpt-5",
object: "response",
output: [],
usage: { input_tokens: 1, output_tokens: 0 },
status: "completed",
})
},
{ preconnect: fetch.preconnect },
)
const model = createOpenAI({ apiKey: "test", fetch: mockFetch }).responses("gpt-5")
await model.doGenerate({
prompt: [{ role: "user", content: [{ type: "text", text: "Hello" }] }],
providerOptions: { openai: { promptCacheKey: "session-123" } },
})
expect(body?.prompt_cache_key).toBe("session-123")
})
describe("OpenAI-compatible provider cache keys", () => {
for (const provider of [
{ name: "Cerebras", create: createCerebras, namespace: "cerebras" },
{ name: "DeepInfra", create: createDeepInfra, namespace: "deepinfra" },
]) {
test(`${provider.name} passes prompt_cache_key through`, async () => {
let body: Record<string, unknown> | undefined
const mockFetch = Object.assign(
async (_input: Parameters<typeof fetch>[0], init?: RequestInit) => {
body = JSON.parse(String(init?.body))
return Response.json({
id: "response-1",
created: 0,
model: "test-model",
object: "chat.completion",
choices: [{ index: 0, message: { role: "assistant", content: "Hello" }, finish_reason: "stop" }],
usage: { prompt_tokens: 1, completion_tokens: 1, total_tokens: 2 },
})
},
{ preconnect: fetch.preconnect },
)
const model = provider.create({ apiKey: "test", fetch: mockFetch })("test-model")
await model.doGenerate({
prompt: [{ role: "user", content: [{ type: "text", text: "Hello" }] }],
providerOptions: { [provider.namespace]: { prompt_cache_key: "session-123" } },
})
expect(body?.prompt_cache_key).toBe("session-123")
})
}
})

69
packages/core/test/provider-cache-usage.test.ts Normal file
View file

@ -0,0 +1,69 @@
import { createCohere } from "@ai-sdk/cohere"
import { createGroq } from "@ai-sdk/groq"
import { createTogetherAI } from "@ai-sdk/togetherai"
import { describe, expect, test } from "bun:test"
const prompt = [{ role: "user" as const, content: [{ type: "text" as const, text: "Hello" }] }]
describe("provider cache usage", () => {
test("Cohere reports cached input tokens", async () => {
const model = createCohere({
apiKey: "test",
fetch: mockFetch({
generation_id: "response-1",
message: { role: "assistant", content: [{ type: "text", text: "Hello" }] },
finish_reason: "COMPLETE",
usage: {
billed_units: { input_tokens: 500, output_tokens: 1 },
tokens: { input_tokens: 500, output_tokens: 1, cached_tokens: 400 },
},
}),
})("command-r")
const result = await model.doGenerate({ prompt })
expect(result.usage.inputTokens).toEqual({ total: 500, noCache: 100, cacheRead: 400, cacheWrite: undefined })
})
test("Groq reports cached input tokens", async () => {
const model = createGroq({
apiKey: "test",
fetch: mockFetch({
id: "response-1",
created: 0,
model: "openai/gpt-oss-20b",
object: "chat.completion",
choices: [{ index: 0, message: { role: "assistant", content: "Hello" }, finish_reason: "stop" }],
usage: {
prompt_tokens: 500,
completion_tokens: 1,
total_tokens: 501,
prompt_tokens_details: { cached_tokens: 400 },
},
}),
})("openai/gpt-oss-20b")
const result = await model.doGenerate({ prompt })
expect(result.usage.inputTokens).toEqual({ total: 500, noCache: 100, cacheRead: 400, cacheWrite: undefined })
})
test("Together AI reports flat cached input tokens", async () => {
const model = createTogetherAI({
apiKey: "test",
fetch: mockFetch({
id: "response-1",
created: 0,
model: "moonshotai/Kimi-K2.6",
object: "chat.completion",
choices: [{ index: 0, message: { role: "assistant", content: "Hello" }, finish_reason: "stop" }],
usage: { prompt_tokens: 500, completion_tokens: 1, total_tokens: 501, cached_tokens: 400 },
}),
})("moonshotai/Kimi-K2.6")
const result = await model.doGenerate({ prompt })
expect(result.usage.inputTokens).toEqual({ total: 500, noCache: 100, cacheRead: 400, cacheWrite: undefined })
})
})
function mockFetch(response: unknown) {
return Object.assign(async () => Response.json(response), { preconnect: fetch.preconnect })
}

14
packages/llm/src/protocols/bedrock-converse.ts
View file

@ -436,21 +436,19 @@ const mapFinishReason = (reason: string): FinishReason => {
return "unknown"
}
// AWS Bedrock Converse reports `inputTokens` (inclusive total) with
// `cacheReadInputTokens` and `cacheWriteInputTokens` as subsets. Pass
// the total through and derive the non-cached breakdown. Bedrock does
// not break reasoning out of `outputTokens` for any current model.
// AWS reports inputTokens separately from cache reads and writes.
// Bedrock does not break reasoning out of outputTokens for current models.
const mapUsage = (usage: BedrockUsageSchema | undefined): Usage | undefined => {
if (!usage) return undefined
const cacheTotal = (usage.cacheReadInputTokens ?? 0) + (usage.cacheWriteInputTokens ?? 0)
const nonCached = ProviderShared.subtractTokens(usage.inputTokens, cacheTotal)
const inputTokens = usage.inputTokens === undefined ? undefined : usage.inputTokens + cacheTotal
return new Usage({
inputTokens: usage.inputTokens,
inputTokens,
outputTokens: usage.outputTokens,
nonCachedInputTokens: nonCached,
nonCachedInputTokens: usage.inputTokens,
cacheReadInputTokens: usage.cacheReadInputTokens,
cacheWriteInputTokens: usage.cacheWriteInputTokens,
totalTokens: ProviderShared.totalTokens(usage.inputTokens, usage.outputTokens, usage.totalTokens),
totalTokens: ProviderShared.totalTokens(inputTokens, usage.outputTokens, usage.totalTokens),
providerMetadata: { bedrock: usage },
})
}

33
packages/llm/test/provider/bedrock-converse.test.ts
View file

@ -269,6 +269,39 @@ describe("Bedrock Converse route", () => {
}),
)
it.effect("adds cache reads and writes to Bedrock input usage", () =>
Effect.gen(function* () {
const body = eventStreamBody(
["messageStart", { role: "assistant" }],
["contentBlockDelta", { contentBlockIndex: 0, delta: { text: "Hello" } }],
["contentBlockStop", { contentBlockIndex: 0 }],
["messageStop", { stopReason: "end_turn" }],
[
"metadata",
{
usage: {
inputTokens: 5,
outputTokens: 2,
totalTokens: 12,
cacheReadInputTokens: 3,
cacheWriteInputTokens: 2,
},
},
],
)
const response = yield* LLMClient.generate(baseRequest).pipe(Effect.provide(fixedBytes(body)))
expect(response.usage).toMatchObject({
inputTokens: 10,
nonCachedInputTokens: 5,
cacheReadInputTokens: 3,
cacheWriteInputTokens: 2,
outputTokens: 2,
totalTokens: 12,
})
}),
)
it.effect("assembles streamed tool call input", () =>
Effect.gen(function* () {
const body = eventStreamBody(

2
packages/opencode/package.json
View file

@ -66,7 +66,7 @@
"@ai-sdk/google": "3.0.73",
"@ai-sdk/google-vertex": "4.0.128",
"@ai-sdk/groq": "3.0.31",
"@ai-sdk/mistral": "3.0.27",
"@ai-sdk/mistral": "3.0.34",
"@ai-sdk/openai": "3.0.53",
"@ai-sdk/openai-compatible": "2.0.41",
"@ai-sdk/perplexity": "3.0.26",

94
packages/opencode/src/provider/transform.ts
View file

@ -46,6 +46,28 @@ function sdkKey(npm: string): string | undefined {
return "vertex"
case "@ai-sdk/google":
return "google"
case "@ai-sdk/alibaba":
return "alibaba"
case "@ai-sdk/cerebras":
return "cerebras"
case "@ai-sdk/cohere":
return "cohere"
case "@ai-sdk/deepinfra":
return "deepinfra"
case "@ai-sdk/groq":
return "groq"
case "@ai-sdk/mistral":
return "mistral"
case "@ai-sdk/perplexity":
return "perplexity"
case "@ai-sdk/togetherai":
return "togetherai"
case "@ai-sdk/vercel":
return "vercel"
case "@ai-sdk/xai":
return "xai"
case "venice-ai-sdk-provider":
return "venice"
case "@ai-sdk/gateway":
return "gateway"
case "@openrouter/ai-sdk-provider":
@ -430,6 +452,9 @@ function mapProviderOptions(
export function message(msgs: ModelMessage[], model: Provider.Model, options: Record<string, unknown>) {
msgs = unsupportedParts(msgs, model)
msgs = normalizeMessages(msgs, model, options)
const usesAnthropicAutomaticCaching =
options.cacheControl !== undefined &&
(model.api.npm === "@ai-sdk/anthropic" || model.api.npm === "@ai-sdk/google-vertex/anthropic")
if (
(model.providerID === "anthropic" ||
model.providerID === "google-vertex-anthropic" ||
@ -439,7 +464,8 @@ export function message(msgs: ModelMessage[], model: Provider.Model, options: Re
model.id.includes("claude") ||
model.api.npm === "@ai-sdk/anthropic" ||
model.api.npm === "@ai-sdk/alibaba") &&
model.api.npm !== "@ai-sdk/gateway"
model.api.npm !== "@ai-sdk/gateway" &&
!usesAnthropicAutomaticCaching
) {
msgs = applyCaching(msgs, model)
}
@ -1077,7 +1103,7 @@ export function options(input: {
sessionID: string
providerOptions?: Record<string, any>
}): Record<string, any> {
const result: Record<string, any> = {}
const result: Record<string, any> = cachingOptions(input)
if (
input.model.api.npm === "@ai-sdk/google-vertex/anthropic" ||
@ -1098,7 +1124,6 @@ export function options(input: {
if (input.model.api.npm === "@ai-sdk/azure") {
result["store"] = false
result["promptCacheKey"] = input.sessionID
}
if (input.model.api.npm === "@openrouter/ai-sdk-provider" || input.model.api.npm === "@llmgateway/ai-sdk-provider") {
@ -1127,13 +1152,6 @@ export function options(input: {
}
}
if (
input.providerOptions?.setCacheKey !== false &&
(input.model.providerID === "openai" || input.model.api.npm === "@ai-sdk/xai" || input.providerOptions?.setCacheKey)
) {
result["promptCacheKey"] = input.sessionID
}
if (input.model.api.npm === "@ai-sdk/google" || input.model.api.npm === "@ai-sdk/google-vertex") {
if (input.model.capabilities.reasoning) {
result["thinkingConfig"] = {
@ -1209,37 +1227,55 @@ export function options(input: {
result["textVerbosity"] = "low"
}
if (input.model.providerID.startsWith("opencode")) {
if (input.model.providerID.startsWith("opencode") && input.providerOptions?.setCacheKey !== false) {
result["promptCacheKey"] = input.sessionID
result["include"] = INCLUDE_ENCRYPTED_REASONING
result["reasoningSummary"] = "auto"
}
}
if (input.model.providerID === "venice") {
result["promptCacheKey"] = input.sessionID
}
if (input.model.providerID === "openrouter") {
result["prompt_cache_key"] = input.sessionID
}
if (input.model.api.npm === "@ai-sdk/gateway") {
result["gateway"] = {
caching: "auto",
}
}
return result
}
export function smallOptions(model: Provider.Model) {
function cachingOptions(input: {
model: Provider.Model
sessionID: string
providerOptions?: Record<string, any>
}): Record<string, any> {
if (input.providerOptions?.setCacheKey === false) {
if (input.model.api.npm === "@ai-sdk/gateway") return { gateway: { caching: "auto" } }
return {}
}
if (input.model.api.npm === "@ai-sdk/deepinfra" || input.model.api.npm === "@ai-sdk/cerebras") {
return { prompt_cache_key: input.sessionID }
}
if (
input.model.api.npm === "@ai-sdk/openai" ||
(input.model.providerID === "openai" && input.model.api.npm !== "@ai-sdk/openai-compatible") ||
input.model.api.npm === "@ai-sdk/azure" ||
input.model.api.npm === "@ai-sdk/xai" ||
input.model.api.npm === "@ai-sdk/mistral" ||
input.model.api.npm === "venice-ai-sdk-provider" ||
input.providerOptions?.setCacheKey === true
) {
return { promptCacheKey: input.sessionID }
}
if (input.model.api.npm === "@ai-sdk/gateway") return { gateway: { caching: "auto" } }
return {}
}
export function smallOptions(model: Provider.Model, sessionID?: string, providerOptions?: Record<string, any>) {
const small = Object.values(model.variants ?? {})[0] ?? {}
const caching = sessionID ? cachingOptions({ model, sessionID, providerOptions }) : {}
if (
model.providerID === "openai" ||
model.api.npm === "@ai-sdk/openai" ||
model.api.npm === "@ai-sdk/github-copilot"
) {
const base = { store: false }
const base = { ...caching, store: false }
return mergeDeep(base, small)
}
if (model.providerID === "openrouter" || model.providerID === "llmgateway") {
@ -1249,11 +1285,11 @@ export function smallOptions(model: Provider.Model) {
}
if (model.providerID === "venice") {
if (Object.keys(small).length > 0) return small
return { veniceParameters: { disableThinking: true } }
if (Object.keys(small).length > 0) return mergeDeep(caching, small)
return mergeDeep(caching, { veniceParameters: { disableThinking: true } })
}
return small
return mergeDeep(caching, small)
}
// Maps model ID prefix to provider slug used in providerOptions.

2
packages/opencode/src/session/llm/request.ts
View file

@ -82,7 +82,7 @@ export const prepare = Effect.fn("LLMRequestPrep.prepare")(function* (input: Pre
? input.model.variants[input.user.model.variant]
: {}
const base = input.small
? ProviderTransform.smallOptions(input.model)
? ProviderTransform.smallOptions(input.model, input.sessionID, input.provider.options)
: ProviderTransform.options({
model: input.model,
sessionID: input.sessionID,

3
packages/opencode/src/session/session.ts
View file

@ -387,6 +387,7 @@ export const getUsage = (input: { model: Provider.Model; usage: Usage; metadata?
? input.model.cost.experimentalOver200K
: input.model.cost)
const totalNanoAiu = input.metadata?.["copilot"]?.["totalNanoAiu"]
const cacheReadCost = input.model.api.npm === "@ai-sdk/cerebras" ? costInfo?.input : costInfo?.cache?.read
return {
cost:
typeof totalNanoAiu === "number" && Number.isFinite(totalNanoAiu) && totalNanoAiu >= 0
@ -395,7 +396,7 @@ export const getUsage = (input: { model: Provider.Model; usage: Usage; metadata?
new Decimal(0)
.add(new Decimal(tokens.input).mul(costInfo?.input ?? 0).div(1_000_000))
.add(new Decimal(tokens.output).mul(costInfo?.output ?? 0).div(1_000_000))
.add(new Decimal(tokens.cache.read).mul(costInfo?.cache?.read ?? 0).div(1_000_000))
.add(new Decimal(tokens.cache.read).mul(cacheReadCost ?? 0).div(1_000_000))
.add(new Decimal(tokens.cache.write).mul(costInfo?.cache?.write ?? 0).div(1_000_000))
// TODO: update models.dev to have better pricing model, for now:
// charge reasoning tokens at the same rate as output tokens

19
packages/opencode/test/provider/cf-ai-gateway-e2e.test.ts
View file

@ -16,7 +16,7 @@ import type * as Provider from "@/provider/provider"
import { ProviderV2 } from "@opencode-ai/core/provider"
import { ModelV2 } from "@opencode-ai/core/model"
type Captured = { url: string; outerBody: unknown }
type Captured = { url: string; headers: Headers; outerBody: unknown }
type ProviderOptions = Record<string, Record<string, JSONValue>>
const realFetch = globalThis.fetch
@ -32,7 +32,7 @@ beforeEach(() => {
const url = typeof input === "string" ? input : input instanceof URL ? input.toString() : input.url
if (url.startsWith("https://gateway.ai.cloudflare.com/")) {
const bodyText = typeof init?.body === "string" ? init.body : ""
captured = { url, outerBody: bodyText ? JSON.parse(bodyText) : null }
captured = { url, headers: new Headers(init?.headers), outerBody: bodyText ? JSON.parse(bodyText) : null }
return new Response(
JSON.stringify({
id: "chatcmpl-test",
@ -129,4 +129,19 @@ describe("cf-ai-gateway end-to-end (regression: #24432)", () => {
})
expect(upstream?.reasoning_effort).toBeUndefined()
})
test("uses current Cloudflare cache headers", async () => {
const aigateway = createAiGateway({
accountId: "test",
gateway: "test",
apiKey: "test",
options: { cacheTtl: 300, skipCache: true },
})
await generateText({ model: aigateway(createUnified()("openai/gpt-5.4")), prompt: "hi" })
expect(captured?.headers.get("cf-aig-cache-ttl")).toBe("300")
expect(captured?.headers.get("cf-aig-skip-cache")).toBe("true")
expect(captured?.headers.get("cf-cache-ttl")).toBeNull()
expect(captured?.headers.get("cf-skip-cache")).toBeNull()
})
})

107
packages/opencode/test/provider/transform.test.ts
View file

@ -87,6 +87,32 @@ describe("ProviderTransform.options - setCacheKey", () => {
expect(result.promptCacheKey).toBe(sessionID)
})
test("should set promptCacheKey for the OpenAI SDK regardless of provider ID", () => {
const result = ProviderTransform.options({
model: {
...mockModel,
providerID: "custom-openai",
api: { id: "gpt-5", url: "https://example.com", npm: "@ai-sdk/openai" },
},
sessionID,
providerOptions: {},
})
expect(result.promptCacheKey).toBe(sessionID)
})
test("should not set promptCacheKey for the OpenAI-compatible SDK by provider name", () => {
const result = ProviderTransform.options({
model: {
...mockModel,
providerID: "openai",
api: { id: "gpt-5", url: "https://example.com", npm: "@ai-sdk/openai-compatible" },
},
sessionID,
providerOptions: {},
})
expect(result.promptCacheKey).toBeUndefined()
})
test("should not set promptCacheKey for openai when explicitly disabled", () => {
const openaiModel = {
...mockModel,
@ -171,6 +197,55 @@ describe("ProviderTransform.options - setCacheKey", () => {
providerOptions: {},
})
expect(result.store).toBe(false)
expect(result.promptCacheKey).toBe(sessionID)
})
test("should disable the Azure cache key without disabling store=false", () => {
const result = ProviderTransform.options({
model: {
...mockModel,
providerID: "azure",
api: { id: "gpt-5", url: "https://azure.com", npm: "@ai-sdk/azure" },
},
sessionID,
providerOptions: { setCacheKey: false },
})
expect(result.store).toBe(false)
expect(result.promptCacheKey).toBeUndefined()
})
for (const npm of ["@ai-sdk/deepinfra", "@ai-sdk/cerebras"]) {
test(`should set the snake-case cache key for ${npm}`, () => {
const result = ProviderTransform.options({
model: { ...mockModel, providerID: "custom", api: { ...mockModel.api, npm } },
sessionID,
providerOptions: {},
})
expect(result.prompt_cache_key).toBe(sessionID)
expect(result.promptCacheKey).toBeUndefined()
})
}
test("should set promptCacheKey for the Mistral SDK", () => {
const result = ProviderTransform.options({
model: { ...mockModel, providerID: "custom", api: { ...mockModel.api, npm: "@ai-sdk/mistral" } },
sessionID,
providerOptions: {},
})
expect(result.promptCacheKey).toBe(sessionID)
})
test("should not send an undocumented OpenRouter prompt_cache_key", () => {
const result = ProviderTransform.options({
model: {
...mockModel,
providerID: "openrouter",
api: { ...mockModel.api, npm: "@openrouter/ai-sdk-provider" },
},
sessionID,
providerOptions: {},
})
expect(result.prompt_cache_key).toBeUndefined()
})
})
@ -663,6 +738,17 @@ describe("ProviderTransform.providerOptions", () => {
})
})
test("uses canonical sdk key for custom xAI models", () => {
const model = createModel({
providerID: "my-xai",
api: { id: "grok-4", url: "https://api.x.ai", npm: "@ai-sdk/xai" },
})
expect(ProviderTransform.providerOptions(model, { promptCacheKey: "session" })).toEqual({
xai: { promptCacheKey: "session" },
})
})
test("forces reasoning for custom OpenAI package models with explicit effort", () => {
const model = createModel({
providerID: "meta",
@ -2924,6 +3010,20 @@ describe("ProviderTransform.message - cache control on gateway", () => {
})
})
test("does not add explicit breakpoints when Anthropic automatic caching is enabled", () => {
const model = createModel({
providerID: "anthropic",
api: { id: "claude-sonnet-4", url: "https://api.anthropic.com", npm: "@ai-sdk/anthropic" },
})
const msgs = [
{ role: "system", content: "You are a helpful assistant" },
{ role: "user", content: "Hello" },
] as any[]
const result = ProviderTransform.message(msgs, model, { cacheControl: { type: "ephemeral" } }) as any[]
expect(result.every((message) => message.providerOptions === undefined)).toBe(true)
})
test("google-vertex-anthropic applies cache control", () => {
const model = createModel({
providerID: "google-vertex-anthropic",
@ -4686,6 +4786,13 @@ describe("ProviderTransform.smallOptions - gpt-5 chat/search", () => {
expect(ProviderTransform.smallOptions(createModel(testCase.id))).toEqual(testCase.options)
})
}
test("includes the OpenAI cache key in small requests", () => {
expect(ProviderTransform.smallOptions(createModel("gpt-5-chat-latest"), "session-123")).toEqual({
store: false,
promptCacheKey: "session-123",
})
})
})
test("ProviderTransform.smallOptions preserves the weakest OpenRouter reasoning effort", () => {

19
packages/opencode/test/session/compaction.test.ts
View file

@ -1564,6 +1564,25 @@ describe("SessionNs.getUsage", () => {
expect(result.tokens.cache.read).toBe(200)
})
test("charges Cerebras cache reads at the normal input rate", () => {
const result = SessionNs.getUsage({
model: createModel({
context: 100_000,
output: 32_000,
npm: "@ai-sdk/cerebras",
cost: { input: 10, output: 0, cache: { read: 0, write: 0 } },
}),
usage: usage({
inputTokens: 1_000_000,
outputTokens: 0,
totalTokens: 1_000_000,
cacheReadInputTokens: 200_000,
}),
})
expect(result.cost).toBe(10)
})
test("handles anthropic cache write metadata", () => {
const model = createModel({ context: 100_000, output: 32_000 })
const result = SessionNs.getUsage({

126
patches/@ai-sdk%2Fcohere@3.0.27.patch Normal file
View file

@ -0,0 +1,126 @@
diff --git a/dist/index.js b/dist/index.js
index ce8d4ae802f5909937840b856866c2d735800212..d448e921d51cb0a4f752cdad09080b21d4d8e8a9 100644
--- a/dist/index.js
+++ b/dist/index.js
@@ -139,11 +139,12 @@ function convertCohereUsage(tokens) {
}
const inputTokens = tokens.input_tokens;
const outputTokens = tokens.output_tokens;
+ const cacheReadTokens = tokens.cached_tokens ?? 0;
return {
inputTokens: {
total: inputTokens,
- noCache: inputTokens,
- cacheRead: void 0,
+ noCache: Math.max(0, inputTokens - cacheReadTokens),
+ cacheRead: cacheReadTokens || void 0,
cacheWrite: void 0
},
outputTokens: {
@@ -672,7 +673,8 @@ var cohereChatResponseSchema = import_v43.z.object({
}),
tokens: import_v43.z.object({
input_tokens: import_v43.z.number(),
- output_tokens: import_v43.z.number()
+ output_tokens: import_v43.z.number(),
+ cached_tokens: import_v43.z.number().optional()
})
})
});
@@ -732,7 +734,8 @@ var cohereChatChunkSchema = import_v43.z.discriminatedUnion("type", [
usage: import_v43.z.object({
tokens: import_v43.z.object({
input_tokens: import_v43.z.number(),
- output_tokens: import_v43.z.number()
+ output_tokens: import_v43.z.number(),
+ cached_tokens: import_v43.z.number().optional()
})
})
})
diff --git a/dist/index.mjs b/dist/index.mjs
index 44f26c27511f9089cdcc9456590dee100b070b0a..d3f585b58208430404135060af5774a7ecfa65d0 100644
--- a/dist/index.mjs
+++ b/dist/index.mjs
@@ -126,11 +126,12 @@ function convertCohereUsage(tokens) {
}
const inputTokens = tokens.input_tokens;
const outputTokens = tokens.output_tokens;
+ const cacheReadTokens = tokens.cached_tokens ?? 0;
return {
inputTokens: {
total: inputTokens,
- noCache: inputTokens,
- cacheRead: void 0,
+ noCache: Math.max(0, inputTokens - cacheReadTokens),
+ cacheRead: cacheReadTokens || void 0,
cacheWrite: void 0
},
outputTokens: {
@@ -661,7 +662,8 @@ var cohereChatResponseSchema = z3.object({
}),
tokens: z3.object({
input_tokens: z3.number(),
- output_tokens: z3.number()
+ output_tokens: z3.number(),
+ cached_tokens: z3.number().optional()
})
})
});
@@ -721,7 +723,8 @@ var cohereChatChunkSchema = z3.discriminatedUnion("type", [
usage: z3.object({
tokens: z3.object({
input_tokens: z3.number(),
- output_tokens: z3.number()
+ output_tokens: z3.number(),
+ cached_tokens: z3.number().optional()
})
})
})
diff --git a/src/cohere-chat-language-model.ts b/src/cohere-chat-language-model.ts
index e4971ccf255ffff77c38fd35caccf84a032ad150..93fea74a08c0f9bcc6c63689fbc9e72669cdeba1 100644
--- a/src/cohere-chat-language-model.ts
+++ b/src/cohere-chat-language-model.ts
@@ -495,6 +495,7 @@ const cohereChatResponseSchema = z.object({
tokens: z.object({
input_tokens: z.number(),
output_tokens: z.number(),
+ cached_tokens: z.number().optional(),
}),
}),
});
@@ -558,6 +559,7 @@ const cohereChatChunkSchema = z.discriminatedUnion('type', [
tokens: z.object({
input_tokens: z.number(),
output_tokens: z.number(),
+ cached_tokens: z.number().optional(),
}),
}),
}),
diff --git a/src/convert-cohere-usage.ts b/src/convert-cohere-usage.ts
index 0f83a63ab85ab2c2ae136edd509e1f738553041f..3913f8d221c8980916769a9890b56030f69a6070 100644
--- a/src/convert-cohere-usage.ts
+++ b/src/convert-cohere-usage.ts
@@ -3,6 +3,7 @@ import { LanguageModelV3Usage } from '@ai-sdk/provider';
export type CohereUsageTokens = {
input_tokens: number;
output_tokens: number;
+ cached_tokens?: number;
};
export function convertCohereUsage(
@@ -27,12 +28,13 @@ export function convertCohereUsage(
const inputTokens = tokens.input_tokens;
const outputTokens = tokens.output_tokens;
+ const cacheReadTokens = tokens.cached_tokens ?? 0;
return {
inputTokens: {
total: inputTokens,
- noCache: inputTokens,
- cacheRead: undefined,
+ noCache: Math.max(0, inputTokens - cacheReadTokens),
+ cacheRead: cacheReadTokens || undefined,
cacheWrite: undefined,
},
outputTokens: {

67
patches/@ai-sdk%2Fgroq@3.0.31.patch Normal file
View file

@ -0,0 +1,67 @@
diff --git a/dist/index.js b/dist/index.js
index 45a104f2e0775761858eac2a82ced64bceba1f5e..36861246fa3aea50f82a233aec8c8edaef0ff6e3 100644
--- a/dist/index.js
+++ b/dist/index.js
@@ -57,13 +57,14 @@ function convertGroqUsage(usage) {
}
const promptTokens = (_a = usage.prompt_tokens) != null ? _a : 0;
const completionTokens = (_b = usage.completion_tokens) != null ? _b : 0;
- const reasoningTokens = (_d = (_c = usage.completion_tokens_details) == null ? void 0 : _c.reasoning_tokens) != null ? _d : void 0;
+ const cacheReadTokens = (_d = (_c = usage.prompt_tokens_details) == null ? void 0 : _c.cached_tokens) != null ? _d : 0;
+ const reasoningTokens = usage.completion_tokens_details?.reasoning_tokens ?? void 0;
const textTokens = reasoningTokens != null ? completionTokens - reasoningTokens : completionTokens;
return {
inputTokens: {
total: promptTokens,
- noCache: promptTokens,
- cacheRead: void 0,
+ noCache: Math.max(0, promptTokens - cacheReadTokens),
+ cacheRead: cacheReadTokens || void 0,
cacheWrite: void 0
},
outputTokens: {
diff --git a/dist/index.mjs b/dist/index.mjs
index c644c32235d8fa88c51c0fc6958feb1da4877c96..6aa35dd173cd67dbdd2f6f3a5fe2d901cbaafae8 100644
--- a/dist/index.mjs
+++ b/dist/index.mjs
@@ -44,13 +44,14 @@ function convertGroqUsage(usage) {
}
const promptTokens = (_a = usage.prompt_tokens) != null ? _a : 0;
const completionTokens = (_b = usage.completion_tokens) != null ? _b : 0;
- const reasoningTokens = (_d = (_c = usage.completion_tokens_details) == null ? void 0 : _c.reasoning_tokens) != null ? _d : void 0;
+ const cacheReadTokens = (_d = (_c = usage.prompt_tokens_details) == null ? void 0 : _c.cached_tokens) != null ? _d : 0;
+ const reasoningTokens = usage.completion_tokens_details?.reasoning_tokens ?? void 0;
const textTokens = reasoningTokens != null ? completionTokens - reasoningTokens : completionTokens;
return {
inputTokens: {
total: promptTokens,
- noCache: promptTokens,
- cacheRead: void 0,
+ noCache: Math.max(0, promptTokens - cacheReadTokens),
+ cacheRead: cacheReadTokens || void 0,
cacheWrite: void 0
},
outputTokens: {
diff --git a/src/convert-groq-usage.ts b/src/convert-groq-usage.ts
index a16809223b068bc1d682ef9156ccc82ce89ace5c..732b14508609106bd5946ba9f9323c7863ee2da5 100644
--- a/src/convert-groq-usage.ts
+++ b/src/convert-groq-usage.ts
@@ -40,6 +40,7 @@ export function convertGroqUsage(
const promptTokens = usage.prompt_tokens ?? 0;
const completionTokens = usage.completion_tokens ?? 0;
+ const cacheReadTokens = usage.prompt_tokens_details?.cached_tokens ?? 0;
const reasoningTokens =
usage.completion_tokens_details?.reasoning_tokens ?? undefined;
const textTokens =
@@ -50,8 +51,8 @@ export function convertGroqUsage(
return {
inputTokens: {
total: promptTokens,
- noCache: promptTokens,
- cacheRead: undefined,
+ noCache: Math.max(0, promptTokens - cacheReadTokens),
+ cacheRead: cacheReadTokens || undefined,
cacheWrite: undefined,
},
outputTokens: {

84
patches/@ai-sdk%2Fmistral@3.0.34.patch Normal file
View file

@ -0,0 +1,84 @@
diff --git a/dist/index.d.ts b/dist/index.d.ts
index 1ca9113bed2728a616db773a8e08d8d6957447d7..15408ec429dc210b5fa43589d81b69c93bf27b2d 100644
--- a/dist/index.d.ts
+++ b/dist/index.d.ts
@@ -14,6 +14,7 @@ declare const mistralLanguageModelOptions: z.ZodObject<{
none: "none";
high: "high";
}>>;
+ promptCacheKey: z.ZodOptional<z.ZodString>;
}, z.core.$strip>;
type MistralLanguageModelOptions = z.infer<typeof mistralLanguageModelOptions>;
diff --git a/dist/index.js b/dist/index.js
index 45735e524aaff54ea058c99c729c5ffd3c507058..6aca5f6f13da0054ede31c1f1a692e4eaed37d34 100644
--- a/dist/index.js
+++ b/dist/index.js
@@ -268,7 +268,8 @@ var mistralLanguageModelOptions = import_v4.z.object({
* - `'high'`: Enable reasoning
* - `'none'`: Disable reasoning
*/
- reasoningEffort: import_v4.z.enum(["high", "none"]).optional()
+ reasoningEffort: import_v4.z.enum(["high", "none"]).optional(),
+ promptCacheKey: import_v4.z.string().optional()
});
// src/mistral-error.ts
@@ -413,6 +414,7 @@ var MistralChatLanguageModel = class {
top_p: topP,
random_seed: seed,
reasoning_effort: options.reasoningEffort,
+ prompt_cache_key: options.promptCacheKey,
// response format:
response_format: (responseFormat == null ? void 0 : responseFormat.type) === "json" ? structuredOutputs && (responseFormat == null ? void 0 : responseFormat.schema) != null ? {
type: "json_schema",
diff --git a/dist/index.mjs b/dist/index.mjs
index 4c22df1cd78a1ba81309c8a86ceecefef4ba4aea..30cd3b1f503860109b7fa2107cd1eb17b70c96be 100644
--- a/dist/index.mjs
+++ b/dist/index.mjs
@@ -256,7 +256,8 @@ var mistralLanguageModelOptions = z.object({
* - `'high'`: Enable reasoning
* - `'none'`: Disable reasoning
*/
- reasoningEffort: z.enum(["high", "none"]).optional()
+ reasoningEffort: z.enum(["high", "none"]).optional(),
+ promptCacheKey: z.string().optional()
});
// src/mistral-error.ts
@@ -403,6 +404,7 @@ var MistralChatLanguageModel = class {
top_p: topP,
random_seed: seed,
reasoning_effort: options.reasoningEffort,
+ prompt_cache_key: options.promptCacheKey,
// response format:
response_format: (responseFormat == null ? void 0 : responseFormat.type) === "json" ? structuredOutputs && (responseFormat == null ? void 0 : responseFormat.schema) != null ? {
type: "json_schema",
diff --git a/src/mistral-chat-language-model.ts b/src/mistral-chat-language-model.ts
index 480c472d534bedbe8897979673453bd1c29a70b7..e46496da94f7d4af9822897202ca6baae67dae3a 100644
--- a/src/mistral-chat-language-model.ts
+++ b/src/mistral-chat-language-model.ts
@@ -129,6 +129,7 @@ export class MistralChatLanguageModel implements LanguageModelV3 {
top_p: topP,
random_seed: seed,
reasoning_effort: options.reasoningEffort,
+ prompt_cache_key: options.promptCacheKey,
// response format:
response_format:
diff --git a/src/mistral-chat-options.ts b/src/mistral-chat-options.ts
index 80fff45fba2c378fa06962f071946bcd2b882a0b..b4fdfa51f3bf11a4220e010c8aca92482cb0c3db 100644
--- a/src/mistral-chat-options.ts
+++ b/src/mistral-chat-options.ts
@@ -62,6 +62,11 @@ export const mistralLanguageModelOptions = z.object({
* - `'none'`: Disable reasoning
*/
reasoningEffort: z.enum(['high', 'none']).optional(),
+
+ /**
+ * A stable identifier used to route requests with shared prompt prefixes.
+ */
+ promptCacheKey: z.string().optional(),
});
export type MistralLanguageModelOptions = z.infer<

101
patches/@ai-sdk%2Fopenai-compatible@2.0.37.patch Normal file
View file

@ -0,0 +1,101 @@
diff --git a/dist/index.js b/dist/index.js
index d73573b013e61903991cad2074187a3ade8921ab..ca7923e551f8f0cb4c27e0afd5f6cb3bc3b6c1c4 100644
--- a/dist/index.js
+++ b/dist/index.js
@@ -73,7 +73,7 @@ function convertOpenAICompatibleChatUsage(usage) {
}
const promptTokens = (_a = usage.prompt_tokens) != null ? _a : 0;
const completionTokens = (_b = usage.completion_tokens) != null ? _b : 0;
- const cacheReadTokens = (_d = (_c = usage.prompt_tokens_details) == null ? void 0 : _c.cached_tokens) != null ? _d : 0;
+ const cacheReadTokens = usage.prompt_tokens_details?.cached_tokens ?? usage.cached_tokens ?? 0;
const reasoningTokens = (_f = (_e = usage.completion_tokens_details) == null ? void 0 : _e.reasoning_tokens) != null ? _f : 0;
return {
inputTokens: {
@@ -894,6 +894,7 @@ var openaiCompatibleTokenUsageSchema = import_v43.z.looseObject({
prompt_tokens: import_v43.z.number().nullish(),
completion_tokens: import_v43.z.number().nullish(),
total_tokens: import_v43.z.number().nullish(),
+ cached_tokens: import_v43.z.number().nullish(),
prompt_tokens_details: import_v43.z.object({
cached_tokens: import_v43.z.number().nullish()
}).nullish(),
diff --git a/dist/index.mjs b/dist/index.mjs
index 237c9e209da9da2d4d557eb309e1adc2157c1426..fb45541149086633e27f02c89b742208222bb185 100644
--- a/dist/index.mjs
+++ b/dist/index.mjs
@@ -53,7 +53,7 @@ function convertOpenAICompatibleChatUsage(usage) {
}
const promptTokens = (_a = usage.prompt_tokens) != null ? _a : 0;
const completionTokens = (_b = usage.completion_tokens) != null ? _b : 0;
- const cacheReadTokens = (_d = (_c = usage.prompt_tokens_details) == null ? void 0 : _c.cached_tokens) != null ? _d : 0;
+ const cacheReadTokens = usage.prompt_tokens_details?.cached_tokens ?? usage.cached_tokens ?? 0;
const reasoningTokens = (_f = (_e = usage.completion_tokens_details) == null ? void 0 : _e.reasoning_tokens) != null ? _f : 0;
return {
inputTokens: {
@@ -881,6 +881,7 @@ var openaiCompatibleTokenUsageSchema = z3.looseObject({
prompt_tokens: z3.number().nullish(),
completion_tokens: z3.number().nullish(),
total_tokens: z3.number().nullish(),
+ cached_tokens: z3.number().nullish(),
prompt_tokens_details: z3.object({
cached_tokens: z3.number().nullish()
}).nullish(),
diff --git a/dist/internal/index.js b/dist/internal/index.js
index 0858632db778d30b303fbc9d5d46a29582d6e5b5..bb414ac25b77cb1a492cf6ad64f24decae38dd31 100644
--- a/dist/internal/index.js
+++ b/dist/internal/index.js
@@ -249,7 +249,7 @@ function convertOpenAICompatibleChatUsage(usage) {
}
const promptTokens = (_a = usage.prompt_tokens) != null ? _a : 0;
const completionTokens = (_b = usage.completion_tokens) != null ? _b : 0;
- const cacheReadTokens = (_d = (_c = usage.prompt_tokens_details) == null ? void 0 : _c.cached_tokens) != null ? _d : 0;
+ const cacheReadTokens = usage.prompt_tokens_details?.cached_tokens ?? usage.cached_tokens ?? 0;
const reasoningTokens = (_f = (_e = usage.completion_tokens_details) == null ? void 0 : _e.reasoning_tokens) != null ? _f : 0;
return {
inputTokens: {
diff --git a/dist/internal/index.mjs b/dist/internal/index.mjs
index 116b2deee86bf07cf981a64c000c7a4f3e42b52e..de08e6248318a0e48866ba41e9788485d56dd5cb 100644
--- a/dist/internal/index.mjs
+++ b/dist/internal/index.mjs
@@ -224,7 +224,7 @@ function convertOpenAICompatibleChatUsage(usage) {
}
const promptTokens = (_a = usage.prompt_tokens) != null ? _a : 0;
const completionTokens = (_b = usage.completion_tokens) != null ? _b : 0;
- const cacheReadTokens = (_d = (_c = usage.prompt_tokens_details) == null ? void 0 : _c.cached_tokens) != null ? _d : 0;
+ const cacheReadTokens = usage.prompt_tokens_details?.cached_tokens ?? usage.cached_tokens ?? 0;
const reasoningTokens = (_f = (_e = usage.completion_tokens_details) == null ? void 0 : _e.reasoning_tokens) != null ? _f : 0;
return {
inputTokens: {
diff --git a/src/chat/convert-openai-compatible-chat-usage.ts b/src/chat/convert-openai-compatible-chat-usage.ts
index 7982309cd99afbf7eb84a733c37446ac3cb9b626..454f14fe45af3f7475ba0371173c3342f242ccd9 100644
--- a/src/chat/convert-openai-compatible-chat-usage.ts
+++ b/src/chat/convert-openai-compatible-chat-usage.ts
@@ -5,6 +5,7 @@ export function convertOpenAICompatibleChatUsage(
| {
prompt_tokens?: number | null;
completion_tokens?: number | null;
+ cached_tokens?: number | null;
prompt_tokens_details?: {
cached_tokens?: number | null;
} | null;
@@ -34,7 +35,7 @@ export function convertOpenAICompatibleChatUsage(
const promptTokens = usage.prompt_tokens ?? 0;
const completionTokens = usage.completion_tokens ?? 0;
- const cacheReadTokens = usage.prompt_tokens_details?.cached_tokens ?? 0;
+ const cacheReadTokens = usage.prompt_tokens_details?.cached_tokens ?? usage.cached_tokens ?? 0;
const reasoningTokens =
usage.completion_tokens_details?.reasoning_tokens ?? 0;
diff --git a/src/chat/openai-compatible-chat-language-model.ts b/src/chat/openai-compatible-chat-language-model.ts
index 9a803cb1173e1454facb73ae430ede0ea0a3d2de..fd2c8e78ad850e11492b6be51922a382664739bf 100644
--- a/src/chat/openai-compatible-chat-language-model.ts
+++ b/src/chat/openai-compatible-chat-language-model.ts
@@ -723,6 +723,7 @@ const openaiCompatibleTokenUsageSchema = z
prompt_tokens: z.number().nullish(),
completion_tokens: z.number().nullish(),
total_tokens: z.number().nullish(),
+ cached_tokens: z.number().nullish(),
prompt_tokens_details: z
.object({
cached_tokens: z.number().nullish(),

34
patches/ai-gateway-provider@3.1.2.patch Normal file
View file

@ -0,0 +1,34 @@
diff --git a/dist/index.js b/dist/index.js
index 6fb7ae621cf5fe350ec9295af8f3d3507d265df3..ee16ee3af60f461fe2b074eb9cab44ea586c97ee 100644
--- a/dist/index.js
+++ b/dist/index.js
@@ -283,10 +283,10 @@ function createAiGateway(options) {
function parseAiGatewayOptions(options) {
const headers = new Headers();
if (options.skipCache === true) {
- headers.set("cf-skip-cache", "true");
+ headers.set("cf-aig-skip-cache", "true");
}
if (options.cacheTtl) {
- headers.set("cf-cache-ttl", options.cacheTtl.toString());
+ headers.set("cf-aig-cache-ttl", options.cacheTtl.toString());
}
if (options.metadata) {
headers.set("cf-aig-metadata", JSON.stringify(options.metadata));
diff --git a/dist/index.mjs b/dist/index.mjs
index 1c00a815117b5854073eb9c01cafa5bc273a367e..11acdaa65021952eb52622ebd3d9b87633e5f8e5 100644
--- a/dist/index.mjs
+++ b/dist/index.mjs
@@ -254,10 +254,10 @@ function createAiGateway(options) {
function parseAiGatewayOptions(options) {
const headers = new Headers();
if (options.skipCache === true) {
- headers.set("cf-skip-cache", "true");
+ headers.set("cf-aig-skip-cache", "true");
}
if (options.cacheTtl) {
- headers.set("cf-cache-ttl", options.cacheTtl.toString());
+ headers.set("cf-aig-cache-ttl", options.cacheTtl.toString());
}
if (options.metadata) {
headers.set("cf-aig-metadata", JSON.stringify(options.metadata));