npm - @daniel156161/prism - Versions diffs - 0.2.98 → 0.2.101 - Mend

@daniel156161/prism 0.2.98 → 0.2.101

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (1188) hide show

package/node_modules/@earendil-works/pi-ai/dist/api/azure-openai-responses.js.map CHANGED Viewed

	@@ -1 +1 @@
1	- {"version":3,"file":"azure-openai-responses.js","sourceRoot":"","sources":["../../src/api/azure-openai-responses.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,WAAW,EAAE,MAAM,QAAQ,CAAC;AAErC,OAAO,EAAE,kBAAkB,EAAE,MAAM,cAAc,CAAC;AAUlD,OAAO,EAAE,mBAAmB,EAAE,sBAAsB,EAAE,MAAM,wBAAwB,CAAC;AACrF,OAAO,EAAE,2BAA2B,EAAE,MAAM,0BAA0B,CAAC;AACvE,OAAO,EAAE,eAAe,EAAE,MAAM,qBAAqB,CAAC;AACtD,OAAO,EAAE,mBAAmB,EAAE,MAAM,0BAA0B,CAAC;AAC/D,OAAO,EAAE,oBAAoB,EAAE,MAAM,4BAA4B,CAAC;AAClE,OAAO,EAAE,gCAAgC,EAAE,MAAM,2BAA2B,CAAC;AAC7E,OAAO,EAAE,yBAAyB,EAAE,MAAM,0BAA0B,CAAC;AACrE,OAAO,EAAE,wBAAwB,EAAE,qBAAqB,EAAE,sBAAsB,EAAE,MAAM,8BAA8B,CAAC;AACvH,OAAO,EAAE,gBAAgB,EAAE,MAAM,qBAAqB,CAAC;AAEvD,MAAM,yBAAyB,GAAG,IAAI,CAAC;AACvC,MAAM,yBAAyB,GAAG,IAAI,GAAG,CAAC,CAAC,QAAQ,EAAE,cAAc,EAAE,UAAU,EAAE,wBAAwB,CAAC,CAAC,CAAC;AAC5G,wGAAwG;AACxG,MAAM,kCAAkC,GAAG,EAAE,CAAC;AAE9C,SAAS,sBAAsB,CAAC,KAAyB,EAAuB;IAC/E,MAAM,GAAG,GAAG,IAAI,GAAG,EAAkB,CAAC;IACtC,IAAI,CAAC,KAAK;QAAE,OAAO,GAAG,CAAC;IACvB,KAAK,MAAM,KAAK,IAAI,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC;QACtC,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,EAAE,CAAC;QAC7B,IAAI,CAAC,OAAO;YAAE,SAAS;QACvB,MAAM,CAAC,OAAO,EAAE,cAAc,CAAC,GAAG,OAAO,CAAC,KAAK,CAAC,GAAG,EAAE,CAAC,CAAC,CAAC;QACxD,IAAI,CAAC,OAAO,IAAI,CAAC,cAAc;YAAE,SAAS;QAC1C,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,EAAE,EAAE,cAAc,CAAC,IAAI,EAAE,CAAC,CAAC;IAChD,CAAC;IACD,OAAO,GAAG,CAAC;AAAA,CACX;AAED,SAAS,qBAAqB,CAAC,KAAsC,EAAE,OAAqC,EAAU;IACrH,IAAI,OAAO,EAAE,mBAAmB,EAAE,CAAC;QAClC,OAAO,OAAO,CAAC,mBAAmB,CAAC;IACpC,CAAC;IACD,MAAM,gBAAgB,GAAG,sBAAsB,CAC9C,mBAAmB,CAAC,kCAAkC,EAAE,OAAO,EAAE,GAAG,CAAC,CACrE,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;IAChB,OAAO,gBAAgB,IAAI,KAAK,CAAC,EAAE,CAAC;AAAA,CACpC;AAED,SAAS,sBAAsB,CAAC,KAAc,EAAU;IACvD,OAAO,mBAAmB,CAAC,sBAAsB,CAAC,KAAK,CAAC,EAAE,wBAAwB,CAAC,CAAC;AAAA,CACpF;AAYD;;GAEG;AACH,MAAM,CAAC,MAAM,MAAM,GAA0E,CAC5F,KAAsC,EACtC,OAAgB,EAChB,OAAqC,EACP,EAAE,CAAC;IACjC,MAAM,MAAM,GAAG,IAAI,2BAA2B,EAAE,CAAC;IAEjD,yBAAyB;IACzB,CAAC,KAAK,IAAI,EAAE,CAAC;QACZ,MAAM,cAAc,GAAG,qBAAqB,CAAC,KAAK,EAAE,OAAO,CAAC,CAAC;QAE7D,MAAM,MAAM,GAAqB;YAChC,IAAI,EAAE,WAAW;YACjB,OAAO,EAAE,EAAE;YACX,GAAG,EAAE,wBAA+B;YACpC,QAAQ,EAAE,KAAK,CAAC,QAAQ;YACxB,KAAK,EAAE,KAAK,CAAC,EAAE;YACf,KAAK,EAAE;gBACN,KAAK,EAAE,CAAC;gBACR,MAAM,EAAE,CAAC;gBACT,SAAS,EAAE,CAAC;gBACZ,UAAU,EAAE,CAAC;gBACb,WAAW,EAAE,CAAC;gBACd,IAAI,EAAE,EAAE,KAAK,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE;aACpE;YACD,UAAU,EAAE,SAAS;YACrB,SAAS,EAAE,IAAI,CAAC,GAAG,EAAE;SACrB,CAAC;QAEF,IAAI,CAAC;YACJ,6BAA6B;YAC7B,MAAM,MAAM,GAAG,OAAO,EAAE,MAAM,CAAC;YAC/B,IAAI,CAAC,MAAM,EAAE,CAAC;gBACb,MAAM,IAAI,KAAK,CAAC,4BAA4B,KAAK,CAAC,QAAQ,EAAE,CAAC,CAAC;YAC/D,CAAC;YACD,MAAM,MAAM,GAAG,YAAY,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC;YACpD,MAAM,0BAA0B,GAAG,gCAAgC,CAClE,OAAO,CAAC,KAAK,EACb,KAAK,CAAC,MAAM,EAAE,0BAA0B,IAAI,KAAK,CACjD,CAAC;YACF,IAAI,MAAM,GAAG,WAAW,CAAC,KAAK,EAAE,OAAO,EAAE,OAAO,EAAE,cAAc,EAAE,0BAA0B,CAAC,CAAC;YAC9F,MAAM,UAAU,GAAG,MAAM,OAAO,EAAE,SAAS,EAAE,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC;YAC7D,IAAI,UAAU,KAAK,SAAS,EAAE,CAAC;gBAC9B,MAAM,GAAG,UAA2C,CAAC;YACtD,CAAC;YACD,MAAM,cAAc,GAAG;gBACtB,GAAG,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;gBACtD,GAAG,CAAC,OAAO,EAAE,SAAS,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,OAAO,EAAE,OAAO,CAAC,SAAS,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;gBAC3E,UAAU,EAAE,CAAC;aACb,CAAC;YACF,MAAM,EAAE,IAAI,EAAE,YAAY,EAAE,QAAQ,EAAE,GAAG,MAAM,oBAAoB,CAClE,GAAG,EAAE,CAAC,MAAM,CAAC,SAAS,CAAC,MAAM,CAAC,MAAM,EAAE,cAAc,CAAC,CAAC,YAAY,EAAE,EACpE;gBACC,UAAU,EAAE,OAAO,EAAE,UAAU;gBAC/B,eAAe,EAAE,OAAO,EAAE,eAAe;gBACzC,MAAM,EAAE,OAAO,EAAE,MAAM;aACvB,CACD,CAAC;YACF,MAAM,OAAO,EAAE,UAAU,EAAE,CAAC,EAAE,MAAM,EAAE,QAAQ,CAAC,MAAM,EAAE,OAAO,EAAE,eAAe,CAAC,QAAQ,CAAC,OAAO,CAAC,EAAE,EAAE,KAAK,CAAC,CAAC;YAC5G,MAAM,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,CAAC;YAEhD,MAAM,sBAAsB,CAAC,YAAY,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,EAAE,0BAA0B,EAAE,CAAC,CAAC;YAElG,IAAI,OAAO,EAAE,MAAM,EAAE,OAAO,EAAE,CAAC;gBAC9B,MAAM,IAAI,KAAK,CAAC,qBAAqB,CAAC,CAAC;YACxC,CAAC;YAED,IAAI,MAAM,CAAC,UAAU,KAAK,SAAS,EAAE,CAAC;gBACrC,MAAM,IAAI,KAAK,CAAC,2DAA2D,CAAC,CAAC;YAC9E,CAAC;YACD,IAAI,MAAM,CAAC,UAAU,KAAK,SAAS,IAAI,MAAM,CAAC,UAAU,KAAK,OAAO,EAAE,CAAC;gBACtE,MAAM,IAAI,KAAK,CAAC,MAAM,CAAC,YAAY,IAAI,2BAA2B,CAAC,CAAC;YACrE,CAAC;YAED,MAAM,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,CAAC,UAAU,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,CAAC;YAC1E,MAAM,CAAC,GAAG,EAAE,CAAC;QACd,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,KAAK,MAAM,KAAK,IAAI,MAAM,CAAC,OAAO,EAAE,CAAC;gBACpC,OAAQ,KAA4B,CAAC,KAAK,CAAC;gBAC3C,8EAA8E;gBAC9E,OAAQ,KAAkC,CAAC,WAAW,CAAC;gBACvD,OAAQ,KAAmC,CAAC,WAAW,CAAC;YACzD,CAAC;YACD,MAAM,CAAC,UAAU,GAAG,OAAO,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC;YACnE,MAAM,CAAC,YAAY,GAAG,sBAAsB,CAAC,KAAK,CAAC,CAAC;YACpD,MAAM,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,EAAE,MAAM,CAAC,UAAU,EAAE,KAAK,EAAE,MAAM,EAAE,CAAC,CAAC;YACzE,MAAM,CAAC,GAAG,EAAE,CAAC;QACd,CAAC;IAAA,CACD,CAAC,EAAE,CAAC;IAEL,OAAO,MAAM,CAAC;AAAA,CACd,CAAC;AAEF,MAAM,CAAC,MAAM,YAAY,GAAkE,CAC1F,KAAsC,EACtC,OAAgB,EAChB,OAA6B,EACC,EAAE,CAAC;IACjC,MAAM,MAAM,GAAG,OAAO,EAAE,MAAM,CAAC;IAC/B,IAAI,CAAC,MAAM,EAAE,CAAC;QACb,MAAM,IAAI,KAAK,CAAC,4BAA4B,KAAK,CAAC,QAAQ,EAAE,CAAC,CAAC;IAC/D,CAAC;IAED,MAAM,IAAI,GAAG,gBAAgB,CAAC,KAAK,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,CAAC,CAAC;IAC/D,MAAM,gBAAgB,GAAG,OAAO,EAAE,SAAS,CAAC,CAAC,CAAC,kBAAkB,CAAC,KAAK,EAAE,OAAO,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;IACvG,MAAM,eAAe,GAAG,gBAAgB,KAAK,KAAK,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,gBAAgB,CAAC;IAElF,OAAO,MAAM,CAAC,KAAK,EAAE,OAAO,EAAE;QAC7B,GAAG,IAAI;QACP,eAAe;KACuB,CAAC,CAAC;AAAA,CACzC,CAAC;AAEF,SAAS,qBAAqB,CAAC,OAAe,EAAU;IACvD,MAAM,OAAO,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC,OAAO,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;IACnD,IAAI,GAAQ,CAAC;IACb,IAAI,CAAC;QACJ,GAAG,GAAG,IAAI,GAAG,CAAC,OAAO,CAAC,CAAC;IACxB,CAAC;IAAC,MAAM,CAAC;QACR,MAAM,IAAI,KAAK,CAAC,kCAAkC,OAAO,EAAE,CAAC,CAAC;IAC9D,CAAC;IAED,MAAM,WAAW,GAChB,GAAG,CAAC,QAAQ,CAAC,QAAQ,CAAC,mBAAmB,CAAC;QAC1C,GAAG,CAAC,QAAQ,CAAC,QAAQ,CAAC,8BAA8B,CAAC;QACrD,GAAG,CAAC,QAAQ,CAAC,QAAQ,CAAC,eAAe,CAAC,CAAC;IACxC,MAAM,cAAc,GAAG,GAAG,CAAC,QAAQ,CAAC,OAAO,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;IAExD,yEAAyE;IACzE,qEAAqE;IACrE,IACC,WAAW;QACX,CAAC,cAAc,KAAK,EAAE;YACrB,cAAc,KAAK,GAAG;YACtB,cAAc,KAAK,SAAS;YAC5B,cAAc,KAAK,sBAAsB,CAAC,EAC1C,CAAC;QACF,GAAG,CAAC,QAAQ,GAAG,YAAY,CAAC;QAC5B,GAAG,CAAC,MAAM,GAAG,EAAE,CAAC;IACjB,CAAC;IAED,OAAO,GAAG,CAAC,QAAQ,EAAE,CAAC,OAAO,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;AAAA,CAC1C;AAED,SAAS,mBAAmB,CAAC,YAAoB,EAAU;IAC1D,OAAO,WAAW,YAAY,6BAA6B,CAAC;AAAA,CAC5D;AAED,SAAS,kBAAkB,CAC1B,KAAsC,EACtC,OAAqC,EACK;IAC1C,MAAM,UAAU,GACf,OAAO,EAAE,eAAe;QACxB,mBAAmB,CAAC,0BAA0B,EAAE,OAAO,EAAE,GAAG,CAAC;QAC7D,yBAAyB,CAAC;IAE3B,MAAM,OAAO,GACZ,OAAO,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,mBAAmB,CAAC,uBAAuB,EAAE,OAAO,EAAE,GAAG,CAAC,EAAE,IAAI,EAAE,IAAI,SAAS,CAAC;IAClH,MAAM,YAAY,GAAG,OAAO,EAAE,iBAAiB,IAAI,mBAAmB,CAAC,4BAA4B,EAAE,OAAO,EAAE,GAAG,CAAC,CAAC;IAEnH,IAAI,eAAe,GAAG,OAAO,CAAC;IAE9B,IAAI,CAAC,eAAe,IAAI,YAAY,EAAE,CAAC;QACtC,eAAe,GAAG,mBAAmB,CAAC,YAAY,CAAC,CAAC;IACrD,CAAC;IAED,IAAI,CAAC,eAAe,IAAI,KAAK,CAAC,OAAO,EAAE,CAAC;QACvC,eAAe,GAAG,KAAK,CAAC,OAAO,CAAC;IACjC,CAAC;IAED,IAAI,CAAC,eAAe,EAAE,CAAC;QACtB,MAAM,IAAI,KAAK,CACd,wJAAwJ,CACxJ,CAAC;IACH,CAAC;IAED,OAAO;QACN,OAAO,EAAE,qBAAqB,CAAC,eAAe,CAAC;QAC/C,UAAU;KACV,CAAC;AAAA,CACF;AAED,SAAS,YAAY,CAAC,KAAsC,EAAE,MAAc,EAAE,OAAqC,EAAE;IACpH,MAAM,OAAO,GAAG,EAAE,GAAG,KAAK,CAAC,OAAO,EAAE,CAAC;IAErC,IAAI,OAAO,EAAE,OAAO,EAAE,CAAC;QACtB,MAAM,CAAC,MAAM,CAAC,OAAO,EAAE,OAAO,CAAC,OAAO,CAAC,CAAC;IACzC,CAAC;IAED,MAAM,EAAE,OAAO,EAAE,UAAU,EAAE,GAAG,kBAAkB,CAAC,KAAK,EAAE,OAAO,CAAC,CAAC;IAEnE,OAAO,IAAI,WAAW,CAAC;QACtB,MAAM;QACN,UAAU;QACV,uBAAuB,EAAE,IAAI;QAC7B,KAAK,EAAE,OAAO,EAAE,KAAK;QACrB,cAAc,EAAE,OAAO;QACvB,OAAO,EAAE,OAAO;KAChB,CAAC,CAAC;AAAA,CACH;AAED,SAAS,WAAW,CACnB,KAAsC,EACtC,OAAgB,EAChB,OAAgD,EAChD,cAAsB,EACtB,0BAA0B,GAAgC,gCAAgC,CACzF,OAAO,CAAC,KAAK,EACb,KAAK,CAAC,MAAM,EAAE,0BAA0B,IAAI,KAAK,CACjD,EACA;IACD,MAAM,QAAQ,GAAG,wBAAwB,CAAC,KAAK,EAAE,OAAO,EAAE,yBAAyB,EAAE;QACpF,0BAA0B;KAC1B,CAAC,CAAC;IAEH,MAAM,MAAM,GAAkC;QAC7C,KAAK,EAAE,cAAc;QACrB,KAAK,EAAE,QAAQ;QACf,MAAM,EAAE,IAAI;QACZ,gBAAgB,EAAE,yBAAyB,CAAC,OAAO,EAAE,SAAS,CAAC;QAC/D,KAAK,EAAE,KAAK;KACZ,CAAC;IAEF,IAAI,OAAO,EAAE,SAAS,EAAE,CAAC;QACxB,MAAM,CAAC,iBAAiB,GAAG,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,SAAS,EAAE,kCAAkC,CAAC,CAAC;IAC5F,CAAC;IAED,IAAI,OAAO,EAAE,WAAW,KAAK,SAAS,EAAE,CAAC;QACxC,MAAM,CAAC,WAAW,GAAG,OAAO,EAAE,WAAW,CAAC;IAC3C,CAAC;IAED,IAAI,OAAO,CAAC,KAAK,IAAI,OAAO,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC/C,MAAM,CAAC,KAAK,GAAG,qBAAqB,CAAC,OAAO,CAAC,KAAK,EAAE;YACnD,kBAAkB,EAAE,KAAK,CAAC,MAAM,EAAE,kBAAkB,IAAI,IAAI;YAC5D,0BAA0B,EAAE,KAAK,CAAC,MAAM,EAAE,0BAA0B,IAAI,KAAK;SAC7E,CAAC,CAAC;IACJ,CAAC;IAED,IAAI,KAAK,CAAC,SAAS,EAAE,CAAC;QACrB,IAAI,OAAO,EAAE,eAAe,IAAI,OAAO,EAAE,gBAAgB,EAAE,CAAC;YAC3D,MAAM,MAAM,GAAG,OAAO,EAAE,eAAe;gBACtC,CAAC,CAAC,CAAC,KAAK,CAAC,gBAAgB,EAAE,CAAC,OAAO,CAAC,eAAe,CAAC,IAAI,OAAO,CAAC,eAAe,CAAC;gBAChF,CAAC,CAAC,QAAQ,CAAC;YACZ,MAAM,CAAC,SAAS,GAAG;gBAClB,MAAM,EAAE,MAAwD;gBAChE,OAAO,EAAE,OAAO,EAAE,gBAAgB,IAAI,MAAM;aAC5C,CAAC;YACF,MAAM,CAAC,OAAO,GAAG,CAAC,6BAA6B,CAAC,CAAC;QAClD,CAAC;aAAM,IAAI,KAAK,CAAC,gBAAgB,EAAE,GAAG,KAAK,IAAI,EAAE,CAAC;YACjD,MAAM,CAAC,SAAS,GAAG;gBAClB,MAAM,EAAE,CAAC,KAAK,CAAC,gBAAgB,EAAE,GAAG,IAAI,MAAM,CAAmD;aACjG,CAAC;QACH,CAAC;IACF,CAAC;IAED,yDAAyD;IACzD,IAAI,OAAO,EAAE,cAAc,EAAE,CAAC;QAC7B,MAAM,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,cAAc,CAAC,CAAC;IAC/C,CAAC;IAED,OAAO,MAAM,CAAC;AAAA,CACd","sourcesContent":["import { AzureOpenAI } from \"openai\";\nimport type { ResponseCreateParamsStreaming } from \"openai/resources/responses/responses.js\";\nimport { clampThinkingLevel } from \"../models.ts\";\nimport type {\n\tApi,\n\tAssistantMessage,\n\tContext,\n\tModel,\n\tSimpleStreamOptions,\n\tStreamFunction,\n\tStreamOptions,\n} from \"../types.ts\";\nimport { formatProviderError, normalizeProviderError } from \"../utils/error-body.ts\";\nimport { AssistantMessageEventStream } from \"../utils/event-stream.ts\";\nimport { headersToRecord } from \"../utils/headers.ts\";\nimport { getProviderEnvValue } from \"../utils/provider-env.ts\";\nimport { retryProviderRequest } from \"../utils/provider-retry.ts\";\nimport { createGrammarToolInputProperties } from \"./constrained-sampling.ts\";\nimport { clampOpenAIPromptCacheKey } from \"./openai-prompt-cache.ts\";\nimport { convertResponsesMessages, convertResponsesTools, processResponsesStream } from \"./openai-responses-shared.ts\";\nimport { buildBaseOptions } from \"./simple-options.ts\";\n\nconst DEFAULT_AZURE_API_VERSION = \"v1\";\nconst AZURE_TOOL_CALL_PROVIDERS = new Set([\"openai\", \"openai-codex\", \"opencode\", \"azure-openai-responses\"]);\n// OpenAI Responses rejects max_output_tokens below 16: https://github.com/earendil-works/pi/issues/6265\nconst OPENAI_RESPONSES_MIN_OUTPUT_TOKENS = 16;\n\nfunction parseDeploymentNameMap(value: string \| undefined): Map<string, string> {\n\tconst map = new Map<string, string>();\n\tif (!value) return map;\n\tfor (const entry of value.split(\",\")) {\n\t\tconst trimmed = entry.trim();\n\t\tif (!trimmed) continue;\n\t\tconst [modelId, deploymentName] = trimmed.split(\"=\", 2);\n\t\tif (!modelId \|\| !deploymentName) continue;\n\t\tmap.set(modelId.trim(), deploymentName.trim());\n\t}\n\treturn map;\n}\n\nfunction resolveDeploymentName(model: Model<\"azure-openai-responses\">, options?: AzureOpenAIResponsesOptions): string {\n\tif (options?.azureDeploymentName) {\n\t\treturn options.azureDeploymentName;\n\t}\n\tconst mappedDeployment = parseDeploymentNameMap(\n\t\tgetProviderEnvValue(\"AZURE_OPENAI_DEPLOYMENT_NAME_MAP\", options?.env),\n\t).get(model.id);\n\treturn mappedDeployment \|\| model.id;\n}\n\nfunction formatAzureOpenAIError(error: unknown): string {\n\treturn formatProviderError(normalizeProviderError(error), \"Azure OpenAI API error\");\n}\n\n// Azure OpenAI Responses-specific options\nexport interface AzureOpenAIResponsesOptions extends StreamOptions {\n\treasoningEffort?: \"minimal\" \| \"low\" \| \"medium\" \| \"high\" \| \"xhigh\" \| \"max\";\n\treasoningSummary?: \"auto\" \| \"detailed\" \| \"concise\" \| null;\n\tazureApiVersion?: string;\n\tazureResourceName?: string;\n\tazureBaseUrl?: string;\n\tazureDeploymentName?: string;\n}\n\n/*\n Generate function for Azure OpenAI Responses API\n */\nexport const stream: StreamFunction<\"azure-openai-responses\", AzureOpenAIResponsesOptions> = (\n\tmodel: Model<\"azure-openai-responses\">,\n\tcontext: Context,\n\toptions?: AzureOpenAIResponsesOptions,\n): AssistantMessageEventStream => {\n\tconst stream = new AssistantMessageEventStream();\n\n\t// Start async processing\n\t(async () => {\n\t\tconst deploymentName = resolveDeploymentName(model, options);\n\n\t\tconst output: AssistantMessage = {\n\t\t\trole: \"assistant\",\n\t\t\tcontent: [],\n\t\t\tapi: \"azure-openai-responses\" as Api,\n\t\t\tprovider: model.provider,\n\t\t\tmodel: model.id,\n\t\t\tusage: {\n\t\t\t\tinput: 0,\n\t\t\t\toutput: 0,\n\t\t\t\tcacheRead: 0,\n\t\t\t\tcacheWrite: 0,\n\t\t\t\ttotalTokens: 0,\n\t\t\t\tcost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },\n\t\t\t},\n\t\t\tstopReason: \"pending\",\n\t\t\ttimestamp: Date.now(),\n\t\t};\n\n\t\ttry {\n\t\t\t// Create Azure OpenAI client\n\t\t\tconst apiKey = options?.apiKey;\n\t\t\tif (!apiKey) {\n\t\t\t\tthrow new Error(`No API key for provider: ${model.provider}`);\n\t\t\t}\n\t\t\tconst client = createClient(model, apiKey, options);\n\t\t\tconst grammarToolInputProperties = createGrammarToolInputProperties(\n\t\t\t\tcontext.tools,\n\t\t\t\tmodel.compat?.supportsOpenAIGrammarTools ?? false,\n\t\t\t);\n\t\t\tlet params = buildParams(model, context, options, deploymentName, grammarToolInputProperties);\n\t\t\tconst nextParams = await options?.onPayload?.(params, model);\n\t\t\tif (nextParams !== undefined) {\n\t\t\t\tparams = nextParams as ResponseCreateParamsStreaming;\n\t\t\t}\n\t\t\tconst requestOptions = {\n\t\t\t\t...(options?.signal ? { signal: options.signal } : {}),\n\t\t\t\t...(options?.timeoutMs !== undefined ? { timeout: options.timeoutMs } : {}),\n\t\t\t\tmaxRetries: 0,\n\t\t\t};\n\t\t\tconst { data: openaiStream, response } = await retryProviderRequest(\n\t\t\t\t() => client.responses.create(params, requestOptions).withResponse(),\n\t\t\t\t{\n\t\t\t\t\tmaxRetries: options?.maxRetries,\n\t\t\t\t\tmaxRetryDelayMs: options?.maxRetryDelayMs,\n\t\t\t\t\tsignal: options?.signal,\n\t\t\t\t},\n\t\t\t);\n\t\t\tawait options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);\n\t\t\tstream.push({ type: \"start\", partial: output });\n\n\t\t\tawait processResponsesStream(openaiStream, output, stream, model, { grammarToolInputProperties });\n\n\t\t\tif (options?.signal?.aborted) {\n\t\t\t\tthrow new Error(\"Request was aborted\");\n\t\t\t}\n\n\t\t\tif (output.stopReason === \"pending\") {\n\t\t\t\tthrow new Error(\"Azure OpenAI Responses stream ended without a stop reason\");\n\t\t\t}\n\t\t\tif (output.stopReason === \"aborted\" \|\| output.stopReason === \"error\") {\n\t\t\t\tthrow new Error(output.errorMessage \|\| \"An unknown error occurred\");\n\t\t\t}\n\n\t\t\tstream.push({ type: \"done\", reason: output.stopReason, message: output });\n\t\t\tstream.end();\n\t\t} catch (error) {\n\t\t\tfor (const block of output.content) {\n\t\t\t\tdelete (block as { index?: number }).index;\n\t\t\t\t// Streaming scratch buffers are only used during parsing; never persist them.\n\t\t\t\tdelete (block as { partialJson?: string }).partialJson;\n\t\t\t\tdelete (block as { customInput?: unknown }).customInput;\n\t\t\t}\n\t\t\toutput.stopReason = options?.signal?.aborted ? \"aborted\" : \"error\";\n\t\t\toutput.errorMessage = formatAzureOpenAIError(error);\n\t\t\tstream.push({ type: \"error\", reason: output.stopReason, error: output });\n\t\t\tstream.end();\n\t\t}\n\t})();\n\n\treturn stream;\n};\n\nexport const streamSimple: StreamFunction<\"azure-openai-responses\", SimpleStreamOptions> = (\n\tmodel: Model<\"azure-openai-responses\">,\n\tcontext: Context,\n\toptions?: SimpleStreamOptions,\n): AssistantMessageEventStream => {\n\tconst apiKey = options?.apiKey;\n\tif (!apiKey) {\n\t\tthrow new Error(`No API key for provider: ${model.provider}`);\n\t}\n\n\tconst base = buildBaseOptions(model, context, options, apiKey);\n\tconst clampedReasoning = options?.reasoning ? clampThinkingLevel(model, options.reasoning) : undefined;\n\tconst reasoningEffort = clampedReasoning === \"off\" ? undefined : clampedReasoning;\n\n\treturn stream(model, context, {\n\t\t...base,\n\t\treasoningEffort,\n\t} satisfies AzureOpenAIResponsesOptions);\n};\n\nfunction normalizeAzureBaseUrl(baseUrl: string): string {\n\tconst trimmed = baseUrl.trim().replace(/\\/+$/, \"\");\n\tlet url: URL;\n\ttry {\n\t\turl = new URL(trimmed);\n\t} catch {\n\t\tthrow new Error(`Invalid Azure OpenAI base URL: ${baseUrl}`);\n\t}\n\n\tconst isAzureHost =\n\t\turl.hostname.endsWith(\".openai.azure.com\") \|\|\n\t\turl.hostname.endsWith(\".cognitiveservices.azure.com\") \|\|\n\t\turl.hostname.endsWith(\".ai.azure.com\");\n\tconst normalizedPath = url.pathname.replace(/\\/+$/, \"\");\n\n\t// Ensure Azure hosts have /openai/v1 as base path so the AzureOpenAI SDK\n\t// can append /deployments/<model>/... and ?api-version=v1 correctly.\n\tif (\n\t\tisAzureHost &&\n\t\t(normalizedPath === \"\" \|\|\n\t\t\tnormalizedPath === \"/\" \|\|\n\t\t\tnormalizedPath === \"/openai\" \|\|\n\t\t\tnormalizedPath === \"/openai/v1/responses\")\n\t) {\n\t\turl.pathname = \"/openai/v1\";\n\t\turl.search = \"\";\n\t}\n\n\treturn url.toString().replace(/\\/+$/, \"\");\n}\n\nfunction buildDefaultBaseUrl(resourceName: string): string {\n\treturn `https://${resourceName}.openai.azure.com/openai/v1`;\n}\n\nfunction resolveAzureConfig(\n\tmodel: Model<\"azure-openai-responses\">,\n\toptions?: AzureOpenAIResponsesOptions,\n): { baseUrl: string; apiVersion: string } {\n\tconst apiVersion =\n\t\toptions?.azureApiVersion \|\|\n\t\tgetProviderEnvValue(\"AZURE_OPENAI_API_VERSION\", options?.env) \|\|\n\t\tDEFAULT_AZURE_API_VERSION;\n\n\tconst baseUrl =\n\t\toptions?.azureBaseUrl?.trim() \|\| getProviderEnvValue(\"AZURE_OPENAI_BASE_URL\", options?.env)?.trim() \|\| undefined;\n\tconst resourceName = options?.azureResourceName \|\| getProviderEnvValue(\"AZURE_OPENAI_RESOURCE_NAME\", options?.env);\n\n\tlet resolvedBaseUrl = baseUrl;\n\n\tif (!resolvedBaseUrl && resourceName) {\n\t\tresolvedBaseUrl = buildDefaultBaseUrl(resourceName);\n\t}\n\n\tif (!resolvedBaseUrl && model.baseUrl) {\n\t\tresolvedBaseUrl = model.baseUrl;\n\t}\n\n\tif (!resolvedBaseUrl) {\n\t\tthrow new Error(\n\t\t\t\"Azure OpenAI base URL is required. Set AZURE_OPENAI_BASE_URL or AZURE_OPENAI_RESOURCE_NAME, or pass azureBaseUrl, azureResourceName, or model.baseUrl.\",\n\t\t);\n\t}\n\n\treturn {\n\t\tbaseUrl: normalizeAzureBaseUrl(resolvedBaseUrl),\n\t\tapiVersion,\n\t};\n}\n\nfunction createClient(model: Model<\"azure-openai-responses\">, apiKey: string, options?: AzureOpenAIResponsesOptions) {\n\tconst headers = { ...model.headers };\n\n\tif (options?.headers) {\n\t\tObject.assign(headers, options.headers);\n\t}\n\n\tconst { baseUrl, apiVersion } = resolveAzureConfig(model, options);\n\n\treturn new AzureOpenAI({\n\t\tapiKey,\n\t\tapiVersion,\n\t\tdangerouslyAllowBrowser: true,\n\t\tfetch: options?.fetch,\n\t\tdefaultHeaders: headers,\n\t\tbaseURL: baseUrl,\n\t});\n}\n\nfunction buildParams(\n\tmodel: Model<\"azure-openai-responses\">,\n\tcontext: Context,\n\toptions: AzureOpenAIResponsesOptions \| undefined,\n\tdeploymentName: string,\n\tgrammarToolInputProperties: ReadonlyMap<string, string> = createGrammarToolInputProperties(\n\t\tcontext.tools,\n\t\tmodel.compat?.supportsOpenAIGrammarTools ?? false,\n\t),\n) {\n\tconst messages = convertResponsesMessages(model, context, AZURE_TOOL_CALL_PROVIDERS, {\n\t\tgrammarToolInputProperties,\n\t});\n\n\tconst params: ResponseCreateParamsStreaming = {\n\t\tmodel: deploymentName,\n\t\tinput: messages,\n\t\tstream: true,\n\t\tprompt_cache_key: clampOpenAIPromptCacheKey(options?.sessionId),\n\t\tstore: false,\n\t};\n\n\tif (options?.maxTokens) {\n\t\tparams.max_output_tokens = Math.max(options.maxTokens, OPENAI_RESPONSES_MIN_OUTPUT_TOKENS);\n\t}\n\n\tif (options?.temperature !== undefined) {\n\t\tparams.temperature = options?.temperature;\n\t}\n\n\tif (context.tools && context.tools.length > 0) {\n\t\tparams.tools = convertResponsesTools(context.tools, {\n\t\t\tsupportsStrictMode: model.compat?.supportsStrictMode ?? true,\n\t\t\tsupportsOpenAIGrammarTools: model.compat?.supportsOpenAIGrammarTools ?? false,\n\t\t});\n\t}\n\n\tif (model.reasoning) {\n\t\tif (options?.reasoningEffort \|\| options?.reasoningSummary) {\n\t\t\tconst effort = options?.reasoningEffort\n\t\t\t\t? (model.thinkingLevelMap?.[options.reasoningEffort] ?? options.reasoningEffort)\n\t\t\t\t: \"medium\";\n\t\t\tparams.reasoning = {\n\t\t\t\teffort: effort as NonNullable<typeof params.reasoning>[\"effort\"],\n\t\t\t\tsummary: options?.reasoningSummary \|\| \"auto\",\n\t\t\t};\n\t\t\tparams.include = [\"reasoning.encrypted_content\"];\n\t\t} else if (model.thinkingLevelMap?.off !== null) {\n\t\t\tparams.reasoning = {\n\t\t\t\teffort: (model.thinkingLevelMap?.off ?? \"none\") as NonNullable<typeof params.reasoning>[\"effort\"],\n\t\t\t};\n\t\t}\n\t}\n\n\t// Last so custom keys override the named request fields.\n\tif (options?.samplingParams) {\n\t\tObject.assign(params, options.samplingParams);\n\t}\n\n\treturn params;\n}\n"]}
1	+ {"version":3,"file":"azure-openai-responses.js","sourceRoot":"","sources":["../../src/api/azure-openai-responses.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,WAAW,EAAE,MAAM,QAAQ,CAAC;AAErC,OAAO,EAAE,kBAAkB,EAAE,MAAM,cAAc,CAAC;AAUlD,OAAO,EAAE,mBAAmB,EAAE,sBAAsB,EAAE,MAAM,wBAAwB,CAAC;AACrF,OAAO,EAAE,2BAA2B,EAAE,MAAM,0BAA0B,CAAC;AACvE,OAAO,EAAE,eAAe,EAAE,MAAM,qBAAqB,CAAC;AACtD,OAAO,EAAE,cAAc,EAAE,MAAM,2BAA2B,CAAC;AAC3D,OAAO,EAAE,mBAAmB,EAAE,MAAM,0BAA0B,CAAC;AAC/D,OAAO,EAAE,oBAAoB,EAAE,MAAM,4BAA4B,CAAC;AAClE,OAAO,EAAE,gCAAgC,EAAE,MAAM,2BAA2B,CAAC;AAC7E,OAAO,EAAE,yBAAyB,EAAE,MAAM,0BAA0B,CAAC;AACrE,OAAO,EAAE,wBAAwB,EAAE,qBAAqB,EAAE,sBAAsB,EAAE,MAAM,8BAA8B,CAAC;AACvH,OAAO,EAAE,gBAAgB,EAAE,MAAM,qBAAqB,CAAC;AAEvD,MAAM,yBAAyB,GAAG,IAAI,CAAC;AACvC,MAAM,yBAAyB,GAAG,IAAI,GAAG,CAAC,CAAC,QAAQ,EAAE,cAAc,EAAE,UAAU,EAAE,wBAAwB,CAAC,CAAC,CAAC;AAC5G,wGAAwG;AACxG,MAAM,kCAAkC,GAAG,EAAE,CAAC;AAE9C,SAAS,sBAAsB,CAAC,KAAyB,EAAuB;IAC/E,MAAM,GAAG,GAAG,IAAI,GAAG,EAAkB,CAAC;IACtC,IAAI,CAAC,KAAK;QAAE,OAAO,GAAG,CAAC;IACvB,KAAK,MAAM,KAAK,IAAI,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC;QACtC,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,EAAE,CAAC;QAC7B,IAAI,CAAC,OAAO;YAAE,SAAS;QACvB,MAAM,CAAC,OAAO,EAAE,cAAc,CAAC,GAAG,OAAO,CAAC,KAAK,CAAC,GAAG,EAAE,CAAC,CAAC,CAAC;QACxD,IAAI,CAAC,OAAO,IAAI,CAAC,cAAc;YAAE,SAAS;QAC1C,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,EAAE,EAAE,cAAc,CAAC,IAAI,EAAE,CAAC,CAAC;IAChD,CAAC;IACD,OAAO,GAAG,CAAC;AAAA,CACX;AAED,SAAS,qBAAqB,CAAC,KAAsC,EAAE,OAAqC,EAAU;IACrH,IAAI,OAAO,EAAE,mBAAmB,EAAE,CAAC;QAClC,OAAO,OAAO,CAAC,mBAAmB,CAAC;IACpC,CAAC;IACD,MAAM,gBAAgB,GAAG,sBAAsB,CAC9C,mBAAmB,CAAC,kCAAkC,EAAE,OAAO,EAAE,GAAG,CAAC,CACrE,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;IAChB,OAAO,gBAAgB,IAAI,KAAK,CAAC,EAAE,CAAC;AAAA,CACpC;AAED,SAAS,sBAAsB,CAAC,KAAc,EAAU;IACvD,OAAO,mBAAmB,CAAC,sBAAsB,CAAC,KAAK,CAAC,EAAE,wBAAwB,CAAC,CAAC;AAAA,CACpF;AAaD;;GAEG;AACH,MAAM,CAAC,MAAM,MAAM,GAA0E,CAC5F,KAAsC,EACtC,OAAgB,EAChB,OAAqC,EACP,EAAE,CAAC;IACjC,MAAM,MAAM,GAAG,IAAI,2BAA2B,EAAE,CAAC;IAEjD,yBAAyB;IACzB,CAAC,KAAK,IAAI,EAAE,CAAC;QACZ,MAAM,cAAc,GAAG,qBAAqB,CAAC,KAAK,EAAE,OAAO,CAAC,CAAC;QAE7D,MAAM,MAAM,GAAqB;YAChC,IAAI,EAAE,WAAW;YACjB,OAAO,EAAE,EAAE;YACX,GAAG,EAAE,wBAA+B;YACpC,QAAQ,EAAE,KAAK,CAAC,QAAQ;YACxB,KAAK,EAAE,KAAK,CAAC,EAAE;YACf,KAAK,EAAE;gBACN,KAAK,EAAE,CAAC;gBACR,MAAM,EAAE,CAAC;gBACT,SAAS,EAAE,CAAC;gBACZ,UAAU,EAAE,CAAC;gBACb,WAAW,EAAE,CAAC;gBACd,IAAI,EAAE,EAAE,KAAK,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE;aACpE;YACD,UAAU,EAAE,SAAS;YACrB,SAAS,EAAE,IAAI,CAAC,GAAG,EAAE;SACrB,CAAC;QAEF,IAAI,CAAC;YACJ,6BAA6B;YAC7B,MAAM,MAAM,GAAG,OAAO,EAAE,MAAM,CAAC;YAC/B,IAAI,CAAC,MAAM,EAAE,CAAC;gBACb,MAAM,IAAI,KAAK,CAAC,4BAA4B,KAAK,CAAC,QAAQ,EAAE,CAAC,CAAC;YAC/D,CAAC;YACD,MAAM,MAAM,GAAG,YAAY,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC;YACpD,MAAM,0BAA0B,GAAG,gCAAgC,CAClE,OAAO,CAAC,KAAK,EACb,KAAK,CAAC,MAAM,EAAE,0BAA0B,IAAI,KAAK,CACjD,CAAC;YACF,IAAI,MAAM,GAAG,WAAW,CAAC,KAAK,EAAE,OAAO,EAAE,OAAO,EAAE,cAAc,EAAE,0BAA0B,CAAC,CAAC;YAC9F,MAAM,UAAU,GAAG,MAAM,OAAO,EAAE,SAAS,EAAE,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC;YAC7D,IAAI,UAAU,KAAK,SAAS,EAAE,CAAC;gBAC9B,MAAM,GAAG,UAA2C,CAAC;YACtD,CAAC;YACD,MAAM,cAAc,GAAG;gBACtB,GAAG,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;gBACtD,GAAG,CAAC,OAAO,EAAE,SAAS,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,OAAO,EAAE,OAAO,CAAC,SAAS,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;gBAC3E,UAAU,EAAE,CAAC;aACb,CAAC;YACF,MAAM,EAAE,IAAI,EAAE,YAAY,EAAE,QAAQ,EAAE,GAAG,MAAM,oBAAoB,CAClE,GAAG,EAAE,CAAC,MAAM,CAAC,SAAS,CAAC,MAAM,CAAC,MAAM,EAAE,cAAc,CAAC,CAAC,YAAY,EAAE,EACpE;gBACC,UAAU,EAAE,OAAO,EAAE,UAAU;gBAC/B,eAAe,EAAE,OAAO,EAAE,eAAe;gBACzC,MAAM,EAAE,OAAO,EAAE,MAAM;aACvB,CACD,CAAC;YACF,MAAM,OAAO,EAAE,UAAU,EAAE,CAAC,EAAE,MAAM,EAAE,QAAQ,CAAC,MAAM,EAAE,OAAO,EAAE,eAAe,CAAC,QAAQ,CAAC,OAAO,CAAC,EAAE,EAAE,KAAK,CAAC,CAAC;YAC5G,MAAM,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,CAAC;YAEhD,MAAM,sBAAsB,CAAC,YAAY,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,EAAE,0BAA0B,EAAE,CAAC,CAAC;YAElG,IAAI,OAAO,EAAE,MAAM,EAAE,OAAO,EAAE,CAAC;gBAC9B,MAAM,IAAI,KAAK,CAAC,qBAAqB,CAAC,CAAC;YACxC,CAAC;YAED,IAAI,MAAM,CAAC,UAAU,KAAK,SAAS,EAAE,CAAC;gBACrC,MAAM,IAAI,KAAK,CAAC,2DAA2D,CAAC,CAAC;YAC9E,CAAC;YACD,IAAI,MAAM,CAAC,UAAU,KAAK,SAAS,IAAI,MAAM,CAAC,UAAU,KAAK,OAAO,EAAE,CAAC;gBACtE,MAAM,IAAI,KAAK,CAAC,MAAM,CAAC,YAAY,IAAI,2BAA2B,CAAC,CAAC;YACrE,CAAC;YAED,MAAM,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,CAAC,UAAU,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,CAAC;YAC1E,MAAM,CAAC,GAAG,EAAE,CAAC;QACd,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,KAAK,MAAM,KAAK,IAAI,MAAM,CAAC,OAAO,EAAE,CAAC;gBACpC,OAAQ,KAA4B,CAAC,KAAK,CAAC;gBAC3C,8EAA8E;gBAC9E,OAAQ,KAAkC,CAAC,WAAW,CAAC;gBACvD,OAAQ,KAAmC,CAAC,WAAW,CAAC;YACzD,CAAC;YACD,MAAM,CAAC,UAAU,GAAG,OAAO,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC;YACnE,MAAM,CAAC,YAAY,GAAG,sBAAsB,CAAC,KAAK,CAAC,CAAC;YACpD,MAAM,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,EAAE,MAAM,CAAC,UAAU,EAAE,KAAK,EAAE,MAAM,EAAE,CAAC,CAAC;YACzE,MAAM,CAAC,GAAG,EAAE,CAAC;QACd,CAAC;IAAA,CACD,CAAC,EAAE,CAAC;IAEL,OAAO,MAAM,CAAC;AAAA,CACd,CAAC;AAEF,MAAM,CAAC,MAAM,YAAY,GAAkE,CAC1F,KAAsC,EACtC,OAAgB,EAChB,OAA6B,EACC,EAAE,CAAC;IACjC,MAAM,MAAM,GAAG,OAAO,EAAE,MAAM,CAAC;IAC/B,IAAI,CAAC,MAAM,EAAE,CAAC;QACb,MAAM,IAAI,KAAK,CAAC,4BAA4B,KAAK,CAAC,QAAQ,EAAE,CAAC,CAAC;IAC/D,CAAC;IAED,MAAM,IAAI,GAAG;QACZ,GAAG,gBAAgB,CAAC,KAAK,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,CAAC;QACpD,UAAU,EAAE,OAAO,EAAE,UAAU;KACO,CAAC;IACxC,MAAM,gBAAgB,GAAG,OAAO,EAAE,SAAS,CAAC,CAAC,CAAC,kBAAkB,CAAC,KAAK,EAAE,OAAO,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;IACvG,MAAM,eAAe,GAAG,gBAAgB,KAAK,KAAK,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,gBAAgB,CAAC;IAElF,OAAO,MAAM,CAAC,KAAK,EAAE,OAAO,EAAE;QAC7B,GAAG,IAAI;QACP,eAAe;KACuB,CAAC,CAAC;AAAA,CACzC,CAAC;AAEF,SAAS,qBAAqB,CAAC,OAAe,EAAU;IACvD,MAAM,OAAO,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC,OAAO,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;IACnD,IAAI,GAAQ,CAAC;IACb,IAAI,CAAC;QACJ,GAAG,GAAG,IAAI,GAAG,CAAC,OAAO,CAAC,CAAC;IACxB,CAAC;IAAC,MAAM,CAAC;QACR,MAAM,IAAI,KAAK,CAAC,kCAAkC,OAAO,EAAE,CAAC,CAAC;IAC9D,CAAC;IAED,MAAM,WAAW,GAChB,GAAG,CAAC,QAAQ,CAAC,QAAQ,CAAC,mBAAmB,CAAC;QAC1C,GAAG,CAAC,QAAQ,CAAC,QAAQ,CAAC,8BAA8B,CAAC;QACrD,GAAG,CAAC,QAAQ,CAAC,QAAQ,CAAC,eAAe,CAAC,CAAC;IACxC,MAAM,cAAc,GAAG,GAAG,CAAC,QAAQ,CAAC,OAAO,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;IAExD,yEAAyE;IACzE,qEAAqE;IACrE,IACC,WAAW;QACX,CAAC,cAAc,KAAK,EAAE;YACrB,cAAc,KAAK,GAAG;YACtB,cAAc,KAAK,SAAS;YAC5B,cAAc,KAAK,sBAAsB,CAAC,EAC1C,CAAC;QACF,GAAG,CAAC,QAAQ,GAAG,YAAY,CAAC;QAC5B,GAAG,CAAC,MAAM,GAAG,EAAE,CAAC;IACjB,CAAC;IAED,OAAO,GAAG,CAAC,QAAQ,EAAE,CAAC,OAAO,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC;AAAA,CAC1C;AAED,SAAS,mBAAmB,CAAC,YAAoB,EAAU;IAC1D,OAAO,WAAW,YAAY,6BAA6B,CAAC;AAAA,CAC5D;AAED,SAAS,kBAAkB,CAC1B,KAAsC,EACtC,OAAqC,EACK;IAC1C,MAAM,UAAU,GACf,OAAO,EAAE,eAAe;QACxB,mBAAmB,CAAC,0BAA0B,EAAE,OAAO,EAAE,GAAG,CAAC;QAC7D,yBAAyB,CAAC;IAE3B,MAAM,OAAO,GACZ,OAAO,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,mBAAmB,CAAC,uBAAuB,EAAE,OAAO,EAAE,GAAG,CAAC,EAAE,IAAI,EAAE,IAAI,SAAS,CAAC;IAClH,MAAM,YAAY,GAAG,OAAO,EAAE,iBAAiB,IAAI,mBAAmB,CAAC,4BAA4B,EAAE,OAAO,EAAE,GAAG,CAAC,CAAC;IAEnH,IAAI,eAAe,GAAG,OAAO,CAAC;IAE9B,IAAI,CAAC,eAAe,IAAI,YAAY,EAAE,CAAC;QACtC,eAAe,GAAG,mBAAmB,CAAC,YAAY,CAAC,CAAC;IACrD,CAAC;IAED,IAAI,CAAC,eAAe,IAAI,KAAK,CAAC,OAAO,EAAE,CAAC;QACvC,eAAe,GAAG,KAAK,CAAC,OAAO,CAAC;IACjC,CAAC;IAED,IAAI,CAAC,eAAe,EAAE,CAAC;QACtB,MAAM,IAAI,KAAK,CACd,wJAAwJ,CACxJ,CAAC;IACH,CAAC;IAED,OAAO;QACN,OAAO,EAAE,qBAAqB,CAAC,eAAe,CAAC;QAC/C,UAAU;KACV,CAAC;AAAA,CACF;AAED,SAAS,YAAY,CAAC,KAAsC,EAAE,MAAc,EAAE,OAAqC,EAAE;IACpH,MAAM,OAAO,GAAG,EAAE,YAAY,EAAE,cAAc,EAAE,EAAE,GAAG,KAAK,CAAC,OAAO,EAAE,CAAC;IAErE,IAAI,OAAO,EAAE,OAAO,EAAE,CAAC;QACtB,MAAM,CAAC,MAAM,CAAC,OAAO,EAAE,OAAO,CAAC,OAAO,CAAC,CAAC;IACzC,CAAC;IAED,MAAM,EAAE,OAAO,EAAE,UAAU,EAAE,GAAG,kBAAkB,CAAC,KAAK,EAAE,OAAO,CAAC,CAAC;IAEnE,OAAO,IAAI,WAAW,CAAC;QACtB,MAAM;QACN,UAAU;QACV,uBAAuB,EAAE,IAAI;QAC7B,KAAK,EAAE,OAAO,EAAE,KAAK;QACrB,cAAc,EAAE,OAAO;QACvB,OAAO,EAAE,OAAO;KAChB,CAAC,CAAC;AAAA,CACH;AAED,SAAS,WAAW,CACnB,KAAsC,EACtC,OAAgB,EAChB,OAAgD,EAChD,cAAsB,EACtB,0BAA0B,GAAgC,gCAAgC,CACzF,OAAO,CAAC,KAAK,EACb,KAAK,CAAC,MAAM,EAAE,0BAA0B,IAAI,KAAK,CACjD,EACA;IACD,MAAM,QAAQ,GAAG,wBAAwB,CAAC,KAAK,EAAE,OAAO,EAAE,yBAAyB,EAAE;QACpF,0BAA0B;KAC1B,CAAC,CAAC;IAEH,MAAM,MAAM,GAAkC;QAC7C,KAAK,EAAE,cAAc;QACrB,KAAK,EAAE,QAAQ;QACf,MAAM,EAAE,IAAI;QACZ,gBAAgB,EAAE,yBAAyB,CAAC,OAAO,EAAE,SAAS,CAAC;QAC/D,KAAK,EAAE,KAAK;KACZ,CAAC;IAEF,IAAI,OAAO,EAAE,SAAS,EAAE,CAAC;QACxB,MAAM,CAAC,iBAAiB,GAAG,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,SAAS,EAAE,kCAAkC,CAAC,CAAC;IAC5F,CAAC;IAED,IAAI,OAAO,EAAE,WAAW,KAAK,SAAS,EAAE,CAAC;QACxC,MAAM,CAAC,WAAW,GAAG,OAAO,EAAE,WAAW,CAAC;IAC3C,CAAC;IAED,IAAI,OAAO,CAAC,KAAK,IAAI,OAAO,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC/C,MAAM,CAAC,KAAK,GAAG,qBAAqB,CAAC,OAAO,CAAC,KAAK,EAAE;YACnD,kBAAkB,EAAE,KAAK,CAAC,MAAM,EAAE,kBAAkB,IAAI,IAAI;YAC5D,0BAA0B,EAAE,KAAK,CAAC,MAAM,EAAE,0BAA0B,IAAI,KAAK;SAC7E,CAAC,CAAC;IACJ,CAAC;IACD,IAAI,OAAO,EAAE,UAAU,KAAK,SAAS,EAAE,CAAC;QACvC,MAAM,CAAC,WAAW,GAAG,OAAO,CAAC,UAAU,CAAC;IACzC,CAAC;IAED,IAAI,KAAK,CAAC,SAAS,EAAE,CAAC;QACrB,IAAI,OAAO,EAAE,eAAe,IAAI,OAAO,EAAE,gBAAgB,EAAE,CAAC;YAC3D,MAAM,MAAM,GAAG,OAAO,EAAE,eAAe;gBACtC,CAAC,CAAC,CAAC,KAAK,CAAC,gBAAgB,EAAE,CAAC,OAAO,CAAC,eAAe,CAAC,IAAI,OAAO,CAAC,eAAe,CAAC;gBAChF,CAAC,CAAC,QAAQ,CAAC;YACZ,MAAM,CAAC,SAAS,GAAG;gBAClB,MAAM,EAAE,MAAwD;gBAChE,OAAO,EAAE,OAAO,EAAE,gBAAgB,IAAI,MAAM;aAC5C,CAAC;YACF,MAAM,CAAC,OAAO,GAAG,CAAC,6BAA6B,CAAC,CAAC;QAClD,CAAC;aAAM,IAAI,KAAK,CAAC,gBAAgB,EAAE,GAAG,KAAK,IAAI,EAAE,CAAC;YACjD,MAAM,CAAC,SAAS,GAAG;gBAClB,MAAM,EAAE,CAAC,KAAK,CAAC,gBAAgB,EAAE,GAAG,IAAI,MAAM,CAAmD;aACjG,CAAC;QACH,CAAC;IACF,CAAC;IAED,yDAAyD;IACzD,IAAI,OAAO,EAAE,cAAc,EAAE,CAAC;QAC7B,MAAM,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,cAAc,CAAC,CAAC;IAC/C,CAAC;IAED,OAAO,MAAM,CAAC;AAAA,CACd","sourcesContent":["import { AzureOpenAI } from \"openai\";\nimport type { ResponseCreateParamsStreaming } from \"openai/resources/responses/responses.js\";\nimport { clampThinkingLevel } from \"../models.ts\";\nimport type {\n\tApi,\n\tAssistantMessage,\n\tContext,\n\tModel,\n\tSimpleStreamOptions,\n\tStreamFunction,\n\tStreamOptions,\n} from \"../types.ts\";\nimport { formatProviderError, normalizeProviderError } from \"../utils/error-body.ts\";\nimport { AssistantMessageEventStream } from \"../utils/event-stream.ts\";\nimport { headersToRecord } from \"../utils/headers.ts\";\nimport { getPiUserAgent } from \"../utils/pi-user-agent.ts\";\nimport { getProviderEnvValue } from \"../utils/provider-env.ts\";\nimport { retryProviderRequest } from \"../utils/provider-retry.ts\";\nimport { createGrammarToolInputProperties } from \"./constrained-sampling.ts\";\nimport { clampOpenAIPromptCacheKey } from \"./openai-prompt-cache.ts\";\nimport { convertResponsesMessages, convertResponsesTools, processResponsesStream } from \"./openai-responses-shared.ts\";\nimport { buildBaseOptions } from \"./simple-options.ts\";\n\nconst DEFAULT_AZURE_API_VERSION = \"v1\";\nconst AZURE_TOOL_CALL_PROVIDERS = new Set([\"openai\", \"openai-codex\", \"opencode\", \"azure-openai-responses\"]);\n// OpenAI Responses rejects max_output_tokens below 16: https://github.com/earendil-works/pi/issues/6265\nconst OPENAI_RESPONSES_MIN_OUTPUT_TOKENS = 16;\n\nfunction parseDeploymentNameMap(value: string \| undefined): Map<string, string> {\n\tconst map = new Map<string, string>();\n\tif (!value) return map;\n\tfor (const entry of value.split(\",\")) {\n\t\tconst trimmed = entry.trim();\n\t\tif (!trimmed) continue;\n\t\tconst [modelId, deploymentName] = trimmed.split(\"=\", 2);\n\t\tif (!modelId \|\| !deploymentName) continue;\n\t\tmap.set(modelId.trim(), deploymentName.trim());\n\t}\n\treturn map;\n}\n\nfunction resolveDeploymentName(model: Model<\"azure-openai-responses\">, options?: AzureOpenAIResponsesOptions): string {\n\tif (options?.azureDeploymentName) {\n\t\treturn options.azureDeploymentName;\n\t}\n\tconst mappedDeployment = parseDeploymentNameMap(\n\t\tgetProviderEnvValue(\"AZURE_OPENAI_DEPLOYMENT_NAME_MAP\", options?.env),\n\t).get(model.id);\n\treturn mappedDeployment \|\| model.id;\n}\n\nfunction formatAzureOpenAIError(error: unknown): string {\n\treturn formatProviderError(normalizeProviderError(error), \"Azure OpenAI API error\");\n}\n\n// Azure OpenAI Responses-specific options\nexport interface AzureOpenAIResponsesOptions extends StreamOptions {\n\treasoningEffort?: \"minimal\" \| \"low\" \| \"medium\" \| \"high\" \| \"xhigh\" \| \"max\";\n\ttoolChoice?: ResponseCreateParamsStreaming[\"tool_choice\"];\n\treasoningSummary?: \"auto\" \| \"detailed\" \| \"concise\" \| null;\n\tazureApiVersion?: string;\n\tazureResourceName?: string;\n\tazureBaseUrl?: string;\n\tazureDeploymentName?: string;\n}\n\n/*\n Generate function for Azure OpenAI Responses API\n */\nexport const stream: StreamFunction<\"azure-openai-responses\", AzureOpenAIResponsesOptions> = (\n\tmodel: Model<\"azure-openai-responses\">,\n\tcontext: Context,\n\toptions?: AzureOpenAIResponsesOptions,\n): AssistantMessageEventStream => {\n\tconst stream = new AssistantMessageEventStream();\n\n\t// Start async processing\n\t(async () => {\n\t\tconst deploymentName = resolveDeploymentName(model, options);\n\n\t\tconst output: AssistantMessage = {\n\t\t\trole: \"assistant\",\n\t\t\tcontent: [],\n\t\t\tapi: \"azure-openai-responses\" as Api,\n\t\t\tprovider: model.provider,\n\t\t\tmodel: model.id,\n\t\t\tusage: {\n\t\t\t\tinput: 0,\n\t\t\t\toutput: 0,\n\t\t\t\tcacheRead: 0,\n\t\t\t\tcacheWrite: 0,\n\t\t\t\ttotalTokens: 0,\n\t\t\t\tcost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },\n\t\t\t},\n\t\t\tstopReason: \"pending\",\n\t\t\ttimestamp: Date.now(),\n\t\t};\n\n\t\ttry {\n\t\t\t// Create Azure OpenAI client\n\t\t\tconst apiKey = options?.apiKey;\n\t\t\tif (!apiKey) {\n\t\t\t\tthrow new Error(`No API key for provider: ${model.provider}`);\n\t\t\t}\n\t\t\tconst client = createClient(model, apiKey, options);\n\t\t\tconst grammarToolInputProperties = createGrammarToolInputProperties(\n\t\t\t\tcontext.tools,\n\t\t\t\tmodel.compat?.supportsOpenAIGrammarTools ?? false,\n\t\t\t);\n\t\t\tlet params = buildParams(model, context, options, deploymentName, grammarToolInputProperties);\n\t\t\tconst nextParams = await options?.onPayload?.(params, model);\n\t\t\tif (nextParams !== undefined) {\n\t\t\t\tparams = nextParams as ResponseCreateParamsStreaming;\n\t\t\t}\n\t\t\tconst requestOptions = {\n\t\t\t\t...(options?.signal ? { signal: options.signal } : {}),\n\t\t\t\t...(options?.timeoutMs !== undefined ? { timeout: options.timeoutMs } : {}),\n\t\t\t\tmaxRetries: 0,\n\t\t\t};\n\t\t\tconst { data: openaiStream, response } = await retryProviderRequest(\n\t\t\t\t() => client.responses.create(params, requestOptions).withResponse(),\n\t\t\t\t{\n\t\t\t\t\tmaxRetries: options?.maxRetries,\n\t\t\t\t\tmaxRetryDelayMs: options?.maxRetryDelayMs,\n\t\t\t\t\tsignal: options?.signal,\n\t\t\t\t},\n\t\t\t);\n\t\t\tawait options?.onResponse?.({ status: response.status, headers: headersToRecord(response.headers) }, model);\n\t\t\tstream.push({ type: \"start\", partial: output });\n\n\t\t\tawait processResponsesStream(openaiStream, output, stream, model, { grammarToolInputProperties });\n\n\t\t\tif (options?.signal?.aborted) {\n\t\t\t\tthrow new Error(\"Request was aborted\");\n\t\t\t}\n\n\t\t\tif (output.stopReason === \"pending\") {\n\t\t\t\tthrow new Error(\"Azure OpenAI Responses stream ended without a stop reason\");\n\t\t\t}\n\t\t\tif (output.stopReason === \"aborted\" \|\| output.stopReason === \"error\") {\n\t\t\t\tthrow new Error(output.errorMessage \|\| \"An unknown error occurred\");\n\t\t\t}\n\n\t\t\tstream.push({ type: \"done\", reason: output.stopReason, message: output });\n\t\t\tstream.end();\n\t\t} catch (error) {\n\t\t\tfor (const block of output.content) {\n\t\t\t\tdelete (block as { index?: number }).index;\n\t\t\t\t// Streaming scratch buffers are only used during parsing; never persist them.\n\t\t\t\tdelete (block as { partialJson?: string }).partialJson;\n\t\t\t\tdelete (block as { customInput?: unknown }).customInput;\n\t\t\t}\n\t\t\toutput.stopReason = options?.signal?.aborted ? \"aborted\" : \"error\";\n\t\t\toutput.errorMessage = formatAzureOpenAIError(error);\n\t\t\tstream.push({ type: \"error\", reason: output.stopReason, error: output });\n\t\t\tstream.end();\n\t\t}\n\t})();\n\n\treturn stream;\n};\n\nexport const streamSimple: StreamFunction<\"azure-openai-responses\", SimpleStreamOptions> = (\n\tmodel: Model<\"azure-openai-responses\">,\n\tcontext: Context,\n\toptions?: SimpleStreamOptions,\n): AssistantMessageEventStream => {\n\tconst apiKey = options?.apiKey;\n\tif (!apiKey) {\n\t\tthrow new Error(`No API key for provider: ${model.provider}`);\n\t}\n\n\tconst base = {\n\t\t...buildBaseOptions(model, context, options, apiKey),\n\t\ttoolChoice: options?.toolChoice,\n\t} satisfies AzureOpenAIResponsesOptions;\n\tconst clampedReasoning = options?.reasoning ? clampThinkingLevel(model, options.reasoning) : undefined;\n\tconst reasoningEffort = clampedReasoning === \"off\" ? undefined : clampedReasoning;\n\n\treturn stream(model, context, {\n\t\t...base,\n\t\treasoningEffort,\n\t} satisfies AzureOpenAIResponsesOptions);\n};\n\nfunction normalizeAzureBaseUrl(baseUrl: string): string {\n\tconst trimmed = baseUrl.trim().replace(/\\/+$/, \"\");\n\tlet url: URL;\n\ttry {\n\t\turl = new URL(trimmed);\n\t} catch {\n\t\tthrow new Error(`Invalid Azure OpenAI base URL: ${baseUrl}`);\n\t}\n\n\tconst isAzureHost =\n\t\turl.hostname.endsWith(\".openai.azure.com\") \|\|\n\t\turl.hostname.endsWith(\".cognitiveservices.azure.com\") \|\|\n\t\turl.hostname.endsWith(\".ai.azure.com\");\n\tconst normalizedPath = url.pathname.replace(/\\/+$/, \"\");\n\n\t// Ensure Azure hosts have /openai/v1 as base path so the AzureOpenAI SDK\n\t// can append /deployments/<model>/... and ?api-version=v1 correctly.\n\tif (\n\t\tisAzureHost &&\n\t\t(normalizedPath === \"\" \|\|\n\t\t\tnormalizedPath === \"/\" \|\|\n\t\t\tnormalizedPath === \"/openai\" \|\|\n\t\t\tnormalizedPath === \"/openai/v1/responses\")\n\t) {\n\t\turl.pathname = \"/openai/v1\";\n\t\turl.search = \"\";\n\t}\n\n\treturn url.toString().replace(/\\/+$/, \"\");\n}\n\nfunction buildDefaultBaseUrl(resourceName: string): string {\n\treturn `https://${resourceName}.openai.azure.com/openai/v1`;\n}\n\nfunction resolveAzureConfig(\n\tmodel: Model<\"azure-openai-responses\">,\n\toptions?: AzureOpenAIResponsesOptions,\n): { baseUrl: string; apiVersion: string } {\n\tconst apiVersion =\n\t\toptions?.azureApiVersion \|\|\n\t\tgetProviderEnvValue(\"AZURE_OPENAI_API_VERSION\", options?.env) \|\|\n\t\tDEFAULT_AZURE_API_VERSION;\n\n\tconst baseUrl =\n\t\toptions?.azureBaseUrl?.trim() \|\| getProviderEnvValue(\"AZURE_OPENAI_BASE_URL\", options?.env)?.trim() \|\| undefined;\n\tconst resourceName = options?.azureResourceName \|\| getProviderEnvValue(\"AZURE_OPENAI_RESOURCE_NAME\", options?.env);\n\n\tlet resolvedBaseUrl = baseUrl;\n\n\tif (!resolvedBaseUrl && resourceName) {\n\t\tresolvedBaseUrl = buildDefaultBaseUrl(resourceName);\n\t}\n\n\tif (!resolvedBaseUrl && model.baseUrl) {\n\t\tresolvedBaseUrl = model.baseUrl;\n\t}\n\n\tif (!resolvedBaseUrl) {\n\t\tthrow new Error(\n\t\t\t\"Azure OpenAI base URL is required. Set AZURE_OPENAI_BASE_URL or AZURE_OPENAI_RESOURCE_NAME, or pass azureBaseUrl, azureResourceName, or model.baseUrl.\",\n\t\t);\n\t}\n\n\treturn {\n\t\tbaseUrl: normalizeAzureBaseUrl(resolvedBaseUrl),\n\t\tapiVersion,\n\t};\n}\n\nfunction createClient(model: Model<\"azure-openai-responses\">, apiKey: string, options?: AzureOpenAIResponsesOptions) {\n\tconst headers = { \"User-Agent\": getPiUserAgent(), ...model.headers };\n\n\tif (options?.headers) {\n\t\tObject.assign(headers, options.headers);\n\t}\n\n\tconst { baseUrl, apiVersion } = resolveAzureConfig(model, options);\n\n\treturn new AzureOpenAI({\n\t\tapiKey,\n\t\tapiVersion,\n\t\tdangerouslyAllowBrowser: true,\n\t\tfetch: options?.fetch,\n\t\tdefaultHeaders: headers,\n\t\tbaseURL: baseUrl,\n\t});\n}\n\nfunction buildParams(\n\tmodel: Model<\"azure-openai-responses\">,\n\tcontext: Context,\n\toptions: AzureOpenAIResponsesOptions \| undefined,\n\tdeploymentName: string,\n\tgrammarToolInputProperties: ReadonlyMap<string, string> = createGrammarToolInputProperties(\n\t\tcontext.tools,\n\t\tmodel.compat?.supportsOpenAIGrammarTools ?? false,\n\t),\n) {\n\tconst messages = convertResponsesMessages(model, context, AZURE_TOOL_CALL_PROVIDERS, {\n\t\tgrammarToolInputProperties,\n\t});\n\n\tconst params: ResponseCreateParamsStreaming = {\n\t\tmodel: deploymentName,\n\t\tinput: messages,\n\t\tstream: true,\n\t\tprompt_cache_key: clampOpenAIPromptCacheKey(options?.sessionId),\n\t\tstore: false,\n\t};\n\n\tif (options?.maxTokens) {\n\t\tparams.max_output_tokens = Math.max(options.maxTokens, OPENAI_RESPONSES_MIN_OUTPUT_TOKENS);\n\t}\n\n\tif (options?.temperature !== undefined) {\n\t\tparams.temperature = options?.temperature;\n\t}\n\n\tif (context.tools && context.tools.length > 0) {\n\t\tparams.tools = convertResponsesTools(context.tools, {\n\t\t\tsupportsStrictMode: model.compat?.supportsStrictMode ?? true,\n\t\t\tsupportsOpenAIGrammarTools: model.compat?.supportsOpenAIGrammarTools ?? false,\n\t\t});\n\t}\n\tif (options?.toolChoice !== undefined) {\n\t\tparams.tool_choice = options.toolChoice;\n\t}\n\n\tif (model.reasoning) {\n\t\tif (options?.reasoningEffort \|\| options?.reasoningSummary) {\n\t\t\tconst effort = options?.reasoningEffort\n\t\t\t\t? (model.thinkingLevelMap?.[options.reasoningEffort] ?? options.reasoningEffort)\n\t\t\t\t: \"medium\";\n\t\t\tparams.reasoning = {\n\t\t\t\teffort: effort as NonNullable<typeof params.reasoning>[\"effort\"],\n\t\t\t\tsummary: options?.reasoningSummary \|\| \"auto\",\n\t\t\t};\n\t\t\tparams.include = [\"reasoning.encrypted_content\"];\n\t\t} else if (model.thinkingLevelMap?.off !== null) {\n\t\t\tparams.reasoning = {\n\t\t\t\teffort: (model.thinkingLevelMap?.off ?? \"none\") as NonNullable<typeof params.reasoning>[\"effort\"],\n\t\t\t};\n\t\t}\n\t}\n\n\t// Last so custom keys override the named request fields.\n\tif (options?.samplingParams) {\n\t\tObject.assign(params, options.samplingParams);\n\t}\n\n\treturn params;\n}\n"]}

package/node_modules/@earendil-works/pi-ai/dist/api/bedrock-converse-stream.d.ts.map CHANGED Viewed

	@@ -1 +1 @@
1	- {"version":3,"file":"bedrock-converse-stream.d.ts","sourceRoot":"","sources":["../../src/api/bedrock-converse-stream.ts"],"names":[],"mappings":"AA6BA,OAAO,KAAK,EAQX,mBAAmB,EAEnB,cAAc,EACd,aAAa,EAEb,eAAe,EAEf,aAAa,EAIb,MAAM,aAAa,CAAC;AAkBrB,MAAM,MAAM,sBAAsB,GAAG,YAAY,GAAG,SAAS,CAAC;AAE9D,MAAM,WAAW,cAAe,SAAQ,aAAa;IACpD,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,UAAU,CAAC,EAAE,MAAM,GAAG,KAAK,GAAG,MAAM,GAAG;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAC;IAEtE,SAAS,CAAC,EAAE,aAAa,CAAC;IAE1B,eAAe,CAAC,EAAE,eAAe,CAAC;IAElC,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B;;;;;;;;;OASG;IACH,eAAe,CAAC,EAAE,sBAAsB,CAAC;IACzC;;;sGAGkG;IAClG,eAAe,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACzC;;;;yGAIqG;IACrG,WAAW,CAAC,EAAE,MAAM,CAAC;CACrB;AAMD,eAAO,MAAM,MAAM,EAAE,cAAc,CAAC,yBAAyB,EAAE,cAAc,CA6N5E,CAAC;AAqIF,eAAO,MAAM,YAAY,EAAE,cAAc,CAAC,yBAAyB,EAAE,mBAAmB,CA8CvF,CAAC","sourcesContent":["import type { Agent as HttpsAgent } from \"node:https\";\nimport {\n\tBedrockRuntimeClient,\n\ttype BedrockRuntimeClientConfig,\n\tBedrockRuntimeServiceException,\n\tStopReason as BedrockStopReason,\n\ttype Tool as BedrockTool,\n\tCachePointType,\n\tCacheTTL,\n\ttype ContentBlock,\n\ttype ContentBlockDeltaEvent,\n\ttype ContentBlockStartEvent,\n\ttype ContentBlockStopEvent,\n\tConversationRole,\n\tConverseStreamCommand,\n\ttype ConverseStreamMetadataEvent,\n\tImageFormat,\n\ttype Message,\n\ttype SystemContentBlock,\n\ttype ToolChoice,\n\ttype ToolConfiguration,\n\ttype ToolResultContentBlock,\n\tToolResultStatus,\n} from \"@aws-sdk/client-bedrock-runtime\";\nimport { NodeHttpHandler } from \"@smithy/node-http-handler\";\nimport type { BuildMiddleware, DocumentType, MetadataBearer } from \"@smithy/types\";\nimport { HttpProxyAgent } from \"http-proxy-agent\";\nimport { HttpsProxyAgent } from \"https-proxy-agent\";\nimport { calculateCost } from \"../models.ts\";\nimport type {\n\tApi,\n\tAssistantMessage,\n\tCacheRetention,\n\tContext,\n\tImageContent,\n\tModel,\n\tProviderEnv,\n\tSimpleStreamOptions,\n\tStopReason,\n\tStreamFunction,\n\tStreamOptions,\n\tTextContent,\n\tThinkingBudgets,\n\tThinkingContent,\n\tThinkingLevel,\n\tTool,\n\tToolCall,\n\tToolResultMessage,\n} from \"../types.ts\";\nimport { appendAssistantMessageDiagnostic } from \"../utils/diagnostics.ts\";\nimport { normalizeProviderError } from \"../utils/error-body.ts\";\nimport { AssistantMessageEventStream } from \"../utils/event-stream.ts\";\nimport { providerHeadersToRecord } from \"../utils/headers.ts\";\nimport { parseStreamingJson } from \"../utils/json-parse.ts\";\nimport { resolveHttpProxyUrlForTarget } from \"../utils/node-http-proxy.ts\";\nimport { getProviderEnvValue } from \"../utils/provider-env.ts\";\nimport { sanitizeSurrogates } from \"../utils/sanitize-unicode.ts\";\nimport { getJsonSchemaToolParameters, resolveJsonSchemaStrictSampling } from \"./constrained-sampling.ts\";\nimport {\n\tadjustMaxTokensForThinking,\n\tbuildBaseOptions,\n\tclampMaxTokensToContext,\n\tclampReasoning,\n} from \"./simple-options.ts\";\nimport { transformMessages } from \"./transform-messages.ts\";\n\nexport type BedrockThinkingDisplay = \"summarized\" \| \"omitted\";\n\nexport interface BedrockOptions extends StreamOptions {\n\tregion?: string;\n\tprofile?: string;\n\ttoolChoice?: \"auto\" \| \"any\" \| \"none\" \| { type: \"tool\"; name: string };\n\t/* See https://docs.aws.amazon.com/bedrock/latest/userguide/inference-reasoning.html for supported models. /\n\treasoning?: ThinkingLevel;\n\t/ Custom token budgets per thinking level. Overrides default budgets. /\n\tthinkingBudgets?: ThinkingBudgets;\n\t/ Only supported by Claude 4.x models, see https://docs.aws.amazon.com/bedrock/latest/userguide/claude-messages-extended-thinking.html#claude-messages-extended-thinking-tool-use-interleaved /\n\tinterleavedThinking?: boolean;\n\t/\n\t Controls how Claude's thinking content is returned in responses.\n\t * - \"summarized\": Thinking blocks contain summarized thinking text (default here).\n\t * - \"omitted\": Thinking content is redacted but the signature still travels back\n\t * for multi-turn continuity, reducing time-to-first-text-token.\n\t \n\t Note: Anthropic's API default for Claude Opus 4.8 and Mythos Preview is\n\t * \"omitted\". We default to \"summarized\" here to keep behavior consistent with\n\t * older Claude 4 models. Only applies to Claude models on Bedrock.\n\t /\n\tthinkingDisplay?: BedrockThinkingDisplay;\n\t/* Key-value pairs attached to the inference request for cost allocation tagging.\n\t * Keys: max 64 chars, no `aws:` prefix. Values: max 256 chars. Max 50 pairs.\n\t * Tags appear in AWS Cost Explorer split cost allocation data.\n\t * @see https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ConverseStream.html /\n\trequestMetadata?: Record<string, string>;\n\t/* Bearer token for Bedrock API key authentication.\n\t * When set, bypasses SigV4 signing and sends Authorization: Bearer <token> instead.\n\t * Requires `bedrock:CallWithBearerToken` IAM permission on the token's identity.\n\t * Set via AWS_BEARER_TOKEN_BEDROCK env var or pass directly.\n\t * @see https://docs.aws.amazon.com/service-authorization/latest/reference/list_amazonbedrock.html /\n\tbearerToken?: string;\n}\n\ntype Block = (TextContent \| ThinkingContent \| ToolCall) & { index?: number; partialJson?: string };\n\nconst EMPTY_TEXT_PLACEHOLDER = \"<empty>\";\n\nexport const stream: StreamFunction<\"bedrock-converse-stream\", BedrockOptions> = (\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcontext: Context,\n\toptions: BedrockOptions = {},\n): AssistantMessageEventStream => {\n\tconst stream = new AssistantMessageEventStream();\n\n\t(async () => {\n\t\tconst output: AssistantMessage = {\n\t\t\trole: \"assistant\",\n\t\t\tcontent: [],\n\t\t\tapi: \"bedrock-converse-stream\" as Api,\n\t\t\tprovider: model.provider,\n\t\t\tmodel: model.id,\n\t\t\tusage: {\n\t\t\t\tinput: 0,\n\t\t\t\toutput: 0,\n\t\t\t\tcacheRead: 0,\n\t\t\t\tcacheWrite: 0,\n\t\t\t\ttotalTokens: 0,\n\t\t\t\tcost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },\n\t\t\t},\n\t\t\tstopReason: \"pending\",\n\t\t\ttimestamp: Date.now(),\n\t\t};\n\n\t\tconst blocks = output.content as Block[];\n\n\t\t// A profile explicitly configured through pi's auth flow (the `profile`\n\t\t// option or scoped `AWS_PROFILE` on the stored credential's env) must win\n\t\t// over ambient AWS_ACCESS_KEY_ID/AWS_SECRET_ACCESS_KEY. The SDK default\n\t\t// chain already prefers a configured profile over env keys, but only when\n\t\t// `credentials` is not set on the client config. See #6957.\n\t\tconst optionsProfile = options.profile \|\| options.env?.AWS_PROFILE;\n\t\tconst config: BedrockRuntimeClientConfig = {\n\t\t\tprofile: optionsProfile \|\| getProviderEnvValue(\"AWS_PROFILE\", options.env),\n\t\t};\n\t\tconst configuredRegion = getConfiguredBedrockRegion(options);\n\t\tconst hasAmbientConfiguredProfile = Boolean(getProviderEnvValue(\"AWS_PROFILE\"));\n\t\tconst endpointRegion = getStandardBedrockEndpointRegion(model.baseUrl);\n\t\tconst useExplicitEndpoint = shouldUseExplicitBedrockEndpoint(\n\t\t\tmodel.baseUrl,\n\t\t\tconfiguredRegion,\n\t\t\thasAmbientConfiguredProfile,\n\t\t);\n\n\t\t// Only pin standard AWS Bedrock runtime endpoints when no region or ambient AWS_PROFILE is configured.\n\t\t// This preserves custom endpoints (VPC/proxy) from #3402 without forcing built-in\n\t\t// catalog defaults such as us-east-1 to override AWS_REGION/AWS_PROFILE.\n\t\tif (useExplicitEndpoint) {\n\t\t\tconfig.endpoint = model.baseUrl;\n\t\t}\n\n\t\t// Resolve bearer token for Bedrock API key auth.\n\t\tconst skipAuth = getProviderEnvValue(\"AWS_BEDROCK_SKIP_AUTH\", options.env) === \"1\";\n\t\tconst bearerToken =\n\t\t\toptions.bearerToken \|\|\n\t\t\toptions.apiKey \|\|\n\t\t\tgetProviderEnvValue(\"AWS_BEARER_TOKEN_BEDROCK\", options.env) \|\|\n\t\t\tundefined;\n\t\tconst useBearerToken = bearerToken !== undefined && !skipAuth;\n\n\t\t// in Node.js/Bun environment only\n\t\tif (typeof process !== \"undefined\" && (process.versions?.node \|\| process.versions?.bun)) {\n\t\t\t// Region resolution: ARN-embedded > explicit option > env vars > SDK default chain.\n\t\t\t// When the model ID is an inference profile ARN, extract the region from it.\n\t\t\t// This avoids conflicts with AWS_REGION set for other services.\n\t\t\tconst arnRegionMatch = model.id.match(/^arn:aws(?:-[a-z0-9-]+)?:bedrock:([a-z0-9-]+):/);\n\t\t\tif (arnRegionMatch) {\n\t\t\t\tconfig.region = arnRegionMatch[1];\n\t\t\t} else if (configuredRegion) {\n\t\t\t\tconfig.region = configuredRegion;\n\t\t\t} else if (endpointRegion && useExplicitEndpoint) {\n\t\t\t\tconfig.region = endpointRegion;\n\t\t\t} else if (!hasAmbientConfiguredProfile) {\n\t\t\t\tconfig.region = \"us-east-1\";\n\t\t\t}\n\n\t\t\t// Support proxies that don't need authentication\n\t\t\tif (skipAuth) {\n\t\t\t\tconfig.credentials = {\n\t\t\t\t\taccessKeyId: \"dummy-access-key\",\n\t\t\t\t\tsecretAccessKey: \"dummy-secret-key\",\n\t\t\t\t};\n\t\t\t}\n\n\t\t\tconst credentials = getConfiguredBedrockCredentials(options.env);\n\t\t\tif (!skipAuth && credentials && !optionsProfile) {\n\t\t\t\tconfig.credentials = credentials;\n\t\t\t}\n\n\t\t\tconst proxyUrl = resolveHttpProxyUrlForTarget(model.baseUrl, options.env);\n\t\t\tif (proxyUrl) {\n\t\t\t\t// Bedrock runtime uses NodeHttp2Handler by default since v3.798.0, which is based\n\t\t\t\t// on `http2` module and has no support for http agent.\n\t\t\t\t// Use NodeHttpHandler to support HTTP(S) proxy agents.\n\t\t\t\tconfig.requestHandler = new NodeHttpHandler({\n\t\t\t\t\thttpAgent: new HttpProxyAgent(proxyUrl),\n\t\t\t\t\thttpsAgent: new HttpsProxyAgent(proxyUrl) as unknown as HttpsAgent,\n\t\t\t\t});\n\t\t\t} else if (getProviderEnvValue(\"AWS_BEDROCK_FORCE_HTTP1\", options.env) === \"1\") {\n\t\t\t\t// Some custom endpoints require HTTP/1.1 instead of HTTP/2\n\t\t\t\tconfig.requestHandler = new NodeHttpHandler();\n\t\t\t}\n\t\t} else {\n\t\t\t// Non-Node environment (browser): fall back to us-east-1 since\n\t\t\t// there's no config file resolution available.\n\t\t\tconfig.region =\n\t\t\t\tconfiguredRegion \|\| (endpointRegion && useExplicitEndpoint ? endpointRegion : undefined) \|\| \"us-east-1\";\n\t\t}\n\n\t\tif (useBearerToken) {\n\t\t\tconfig.token = { token: bearerToken };\n\t\t\tconfig.authSchemePreference = [\"httpBearerAuth\"];\n\t\t}\n\n\t\t// Kept outside the try so the catch can still correlate a mid-stream failure:\n\t\t// exceptions delivered as stream events carry no HTTP metadata of their own.\n\t\tlet responseRequestId: string \| undefined;\n\n\t\ttry {\n\t\t\tconst supportsStrictMode = model.compat?.supportsStrictMode ?? false;\n\t\t\tconst client = new BedrockRuntimeClient(config);\n\t\t\tconst customHeaders = providerHeadersToRecord(options.headers);\n\t\t\tif (customHeaders) {\n\t\t\t\taddCustomHeadersMiddleware(client, customHeaders);\n\t\t\t}\n\t\t\tconst cacheRetention = resolveCacheRetention(options.cacheRetention, options.env);\n\t\t\tconst inferenceMaxTokens = options.maxTokens ?? (isAnthropicClaudeModel(model) ? model.maxTokens : undefined);\n\t\t\tlet commandInput = {\n\t\t\t\tmodelId: model.id,\n\t\t\t\tmessages: convertMessages(context, model, cacheRetention, options.env),\n\t\t\t\tsystem: buildSystemPrompt(context.systemPrompt, model, cacheRetention, options.env),\n\t\t\t\tinferenceConfig: {\n\t\t\t\t\t...(inferenceMaxTokens !== undefined && { maxTokens: inferenceMaxTokens }),\n\t\t\t\t\t...(options.temperature !== undefined && { temperature: options.temperature }),\n\t\t\t\t},\n\t\t\t\ttoolConfig: convertToolConfig(context.tools, options.toolChoice, supportsStrictMode),\n\t\t\t\tadditionalModelRequestFields: buildAdditionalModelRequestFields(model, options),\n\t\t\t\t...(options.requestMetadata !== undefined && { requestMetadata: options.requestMetadata }),\n\t\t\t};\n\t\t\tconst nextCommandInput = await options?.onPayload?.(commandInput, model);\n\t\t\tif (nextCommandInput !== undefined) {\n\t\t\t\tcommandInput = nextCommandInput as typeof commandInput;\n\t\t\t}\n\t\t\tconst command = new ConverseStreamCommand(commandInput);\n\n\t\t\tconst response = await client.send(command, { abortSignal: options.signal });\n\t\t\tresponseRequestId = normalizeDiagnosticValue(response.$metadata.requestId);\n\t\t\tif (response.$metadata.httpStatusCode !== undefined) {\n\t\t\t\tconst responseHeaders: Record<string, string> = {};\n\t\t\t\tif (response.$metadata.requestId) {\n\t\t\t\t\tresponseHeaders[\"x-amzn-requestid\"] = response.$metadata.requestId;\n\t\t\t\t}\n\t\t\t\tawait options?.onResponse?.({ status: response.$metadata.httpStatusCode, headers: responseHeaders }, model);\n\t\t\t}\n\n\t\t\tfor await (const item of response.stream!) {\n\t\t\t\tif (item.messageStart) {\n\t\t\t\t\tif (item.messageStart.role !== ConversationRole.ASSISTANT) {\n\t\t\t\t\t\tthrow new Error(\"Unexpected assistant message start but got user message start instead\");\n\t\t\t\t\t}\n\t\t\t\t\tstream.push({ type: \"start\", partial: output });\n\t\t\t\t} else if (item.contentBlockStart) {\n\t\t\t\t\thandleContentBlockStart(item.contentBlockStart, blocks, output, stream);\n\t\t\t\t} else if (item.contentBlockDelta) {\n\t\t\t\t\thandleContentBlockDelta(item.contentBlockDelta, blocks, output, stream);\n\t\t\t\t} else if (item.contentBlockStop) {\n\t\t\t\t\thandleContentBlockStop(item.contentBlockStop, blocks, output, stream);\n\t\t\t\t} else if (item.messageStop) {\n\t\t\t\t\toutput.rawStopReason = item.messageStop.stopReason;\n\t\t\t\t\tconst { stopReason, errorMessage } = mapStopReason(item.messageStop.stopReason);\n\t\t\t\t\toutput.stopReason = stopReason;\n\t\t\t\t\tif (errorMessage) {\n\t\t\t\t\t\toutput.errorMessage = errorMessage;\n\t\t\t\t\t}\n\t\t\t\t} else if (item.metadata) {\n\t\t\t\t\thandleMetadata(item.metadata, model, output);\n\t\t\t\t} else if (item.internalServerException) {\n\t\t\t\t\tthrow item.internalServerException;\n\t\t\t\t} else if (item.modelStreamErrorException) {\n\t\t\t\t\tthrow item.modelStreamErrorException;\n\t\t\t\t} else if (item.validationException) {\n\t\t\t\t\tthrow item.validationException;\n\t\t\t\t} else if (item.throttlingException) {\n\t\t\t\t\tthrow item.throttlingException;\n\t\t\t\t} else if (item.serviceUnavailableException) {\n\t\t\t\t\tthrow item.serviceUnavailableException;\n\t\t\t\t}\n\t\t\t}\n\n\t\t\tif (options.signal?.aborted) {\n\t\t\t\tthrow new Error(\"Request was aborted\");\n\t\t\t}\n\n\t\t\tif (output.stopReason === \"pending\") {\n\t\t\t\tthrow new Error(\"Bedrock stream ended without a stop reason\");\n\t\t\t}\n\t\t\tif (output.stopReason === \"error\" \|\| output.stopReason === \"aborted\") {\n\t\t\t\tthrow new Error(output.errorMessage \|\| \"An unknown error occurred\");\n\t\t\t}\n\n\t\t\tstream.push({ type: \"done\", reason: output.stopReason, message: output });\n\t\t\tstream.end();\n\t\t} catch (error) {\n\t\t\tfor (const block of output.content) {\n\t\t\t\tdelete (block as Block).index;\n\t\t\t\t// partialJson is only a streaming scratch buffer; never persist it.\n\t\t\t\tdelete (block as Block).partialJson;\n\t\t\t}\n\t\t\toutput.stopReason = options.signal?.aborted ? \"aborted\" : \"error\";\n\t\t\toutput.errorMessage = formatBedrockError(error);\n\t\t\tif (output.stopReason === \"error\") {\n\t\t\t\tappendBedrockFailureDiagnostic(output, error, responseRequestId);\n\t\t\t}\n\t\t\tstream.push({ type: \"error\", reason: output.stopReason, error: output });\n\t\t\tstream.end();\n\t\t}\n\t})();\n\n\treturn stream;\n};\n\n/\n Human-readable prefixes for Bedrock SDK exception names.\n * The downstream retry logic in agent-session matches patterns like\n * `server.?error` and `service.?unavailable`, so we preserve the legacy\n * prefix format rather than using the raw SDK exception name.\n /\nconst BEDROCK_ERROR_PREFIXES: Record<string, string> = {\n\tInternalServerException: \"Internal server error\",\n\tModelStreamErrorException: \"Model stream error\",\n\tValidationException: \"Validation error\",\n\tThrottlingException: \"Throttling error\",\n\tServiceUnavailableException: \"Service unavailable\",\n};\n\n/\n Some models reject the account/profile's configured Bedrock data retention mode\n * (e.g. \"data retention mode 'default' is not available for this model\"). Point\n * users at the AWS docs explaining how to configure a supported mode.\n /\nconst BEDROCK_DATA_RETENTION_DOCS_URL = \"https://docs.aws.amazon.com/bedrock/latest/userguide/data-retention.html\";\n\n/\n Format a Bedrock error with a human-readable prefix.\n * AWS SDK exceptions (both from `client.send()` and from stream event items)\n * extend BedrockRuntimeServiceException. We map the `.name` to a stable\n * human-readable prefix so downstream consumers (retry logic, context-overflow\n * detection) can distinguish error categories via simple string matching.\n /\nfunction formatBedrockError(error: unknown): string {\n\tconst norm = normalizeProviderError(error);\n\t// Surface the raw HTTP body (with status) when the SDK did not fold it into\n\t// the message; otherwise fall back to the message. This is what stops a\n\t// gateway 403 from collapsing to `Unknown: UnknownError`.\n\tconst core =\n\t\t!norm.messageCarriesBody && norm.status !== undefined && norm.body !== undefined\n\t\t\t? `${norm.status}: ${norm.body}`\n\t\t\t: norm.message;\n\tconst dataRetentionHint = /data retention mode/i.test(core)\n\t\t? ` See ${BEDROCK_DATA_RETENTION_DOCS_URL} for supported data retention modes.`\n\t\t: \"\";\n\tif (error instanceof BedrockRuntimeServiceException) {\n\t\tconst prefix = BEDROCK_ERROR_PREFIXES[error.name] ?? error.name;\n\t\treturn `${prefix}: ${core}${dataRetentionHint}`;\n\t}\n\treturn `${core}${dataRetentionHint}`;\n}\n\ntype SdkErrorMetadata = { $metadata?: { httpStatusCode?: unknown; requestId?: unknown } };\n\n/* Over-long header values are dropped rather than truncated: a truncated request id is not a request id. /\nconst MAX_BEDROCK_DIAGNOSTIC_VALUE_CHARS = 200;\n\nfunction normalizeDiagnosticValue(value: unknown): string \| undefined {\n\tif (typeof value !== \"string\") return undefined;\n\tconst trimmed = value.trim();\n\tif (trimmed.length === 0 \|\| trimmed.length > MAX_BEDROCK_DIAGNOSTIC_VALUE_CHARS) return undefined;\n\treturn trimmed;\n}\n\n/\n The SDK puts the modeled code on `error.name` for service exceptions and unmodeled stream errors alike, so\n * do not narrow to `BedrockRuntimeServiceException`. Modeled Bedrock errors all end in `Exception`, unlike\n * transport names such as `TimeoutError`.\n /\nfunction extractBedrockErrorCode(error: unknown): string \| undefined {\n\tif (!(error instanceof Error) \|\| !error.name.endsWith(\"Exception\")) return undefined;\n\treturn normalizeDiagnosticValue(error.name);\n}\n\n/\n Structured metadata alongside `errorMessage`, which stays byte-identical because `isRetryableAssistantError`\n * matches against it. Unknown fields are omitted, never guessed: a modeled mid-stream exception reaches us as\n * a bare object literal, leaving only `fallbackRequestId`. `details` only, as the throw is not always `Error`.\n /\nfunction appendBedrockFailureDiagnostic(\n\toutput: AssistantMessage,\n\terror: unknown,\n\tfallbackRequestId: string \| undefined,\n): void {\n\tconst metadata = (error as SdkErrorMetadata)?.$metadata;\n\tconst details: Record<string, unknown> = {};\n\n\tif (typeof metadata?.httpStatusCode === \"number\") details.status = metadata.httpStatusCode;\n\n\tconst errorCode = extractBedrockErrorCode(error);\n\tif (errorCode !== undefined) details.errorCode = errorCode;\n\n\tconst requestId = normalizeDiagnosticValue(metadata?.requestId) ?? fallbackRequestId;\n\tif (requestId !== undefined) details.requestId = requestId;\n\n\tif (Object.keys(details).length === 0) return;\n\n\tappendAssistantMessageDiagnostic(output, { type: \"bedrock_response_failure\", timestamp: Date.now(), details });\n}\n\n/\n Header keys that must never be overwritten by caller-supplied headers.\n * `host` and `x-amz-` participate in the SigV4 canonical request; `authorization`\n is owned by SigV4 or the bearer-token path (config.token + authSchemePreference).\n * Compared case-insensitively (caller key is lower-cased before lookup).\n /\nconst RESERVED_HEADER_EXACT = new Set([\"authorization\", \"host\"]);\n\nfunction isReservedHeader(key: string): boolean {\n\tconst lower = key.toLowerCase();\n\treturn lower.startsWith(\"x-amz-\") \|\| RESERVED_HEADER_EXACT.has(lower);\n}\n\n/\n Attach caller-supplied headers to the outgoing Bedrock request via a Smithy\n * `build`-step middleware. The `build` step runs after request serialisation but\n * before SigV4 signing, so injected headers are covered by the signature. Reserved\n * SigV4 / auth headers (`x-amz-`, `authorization`, `host`) are silently skipped;\n all other caller headers override any existing same-named header on the request.\n /\nfunction addCustomHeadersMiddleware(client: BedrockRuntimeClient, headers: Record<string, string>): void {\n\tconst middleware: BuildMiddleware<object, MetadataBearer> = (next) => async (args) => {\n\t\tconst request = args.request;\n\t\tif (request && typeof request === \"object\" && \"headers\" in request) {\n\t\t\tconst requestHeaders = (request as { headers: Record<string, string> }).headers;\n\t\t\tfor (const [key, value] of Object.entries(headers)) {\n\t\t\t\tif (!isReservedHeader(key)) {\n\t\t\t\t\trequestHeaders[key] = value;\n\t\t\t\t}\n\t\t\t}\n\t\t}\n\t\treturn next(args);\n\t};\n\tclient.middlewareStack.add(middleware, { step: \"build\", name: \"pi-ai-custom-headers\", priority: \"low\" });\n}\n\nexport const streamSimple: StreamFunction<\"bedrock-converse-stream\", SimpleStreamOptions> = (\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcontext: Context,\n\toptions?: SimpleStreamOptions,\n): AssistantMessageEventStream => {\n\tconst base = buildBaseOptions(model, context, options, undefined);\n\tif (!options?.reasoning) {\n\t\treturn stream(model, context, { ...base, reasoning: undefined } satisfies BedrockOptions);\n\t}\n\n\tif (isAnthropicClaudeModel(model)) {\n\t\tif (supportsAdaptiveThinking(model.id, model.name)) {\n\t\t\treturn stream(model, context, {\n\t\t\t\t...base,\n\t\t\t\treasoning: options.reasoning,\n\t\t\t\tthinkingBudgets: options.thinkingBudgets,\n\t\t\t} satisfies BedrockOptions);\n\t\t}\n\n\t\t// Undefined means the caller did not request an output cap; let the helper use the model cap.\n\t\t// Do not coerce to 0 here, or the thinking budget would become the entire maxTokens value.\n\t\tconst adjusted = adjustMaxTokensForThinking(\n\t\t\tbase.maxTokens,\n\t\t\tmodel.maxTokens,\n\t\t\toptions.reasoning,\n\t\t\toptions.thinkingBudgets,\n\t\t);\n\n\t\tconst maxTokens = clampMaxTokensToContext(model, context, adjusted.maxTokens);\n\n\t\treturn stream(model, context, {\n\t\t\t...base,\n\t\t\tmaxTokens,\n\t\t\treasoning: options.reasoning,\n\t\t\tthinkingBudgets: {\n\t\t\t\t...(options.thinkingBudgets \|\| {}),\n\t\t\t\t[clampReasoning(options.reasoning)!]: Math.min(adjusted.thinkingBudget, Math.max(0, maxTokens - 1024)),\n\t\t\t},\n\t\t} satisfies BedrockOptions);\n\t}\n\n\treturn stream(model, context, {\n\t\t...base,\n\t\treasoning: options.reasoning,\n\t\tthinkingBudgets: options.thinkingBudgets,\n\t} satisfies BedrockOptions);\n};\n\nfunction handleContentBlockStart(\n\tevent: ContentBlockStartEvent,\n\tblocks: Block[],\n\toutput: AssistantMessage,\n\tstream: AssistantMessageEventStream,\n): void {\n\tconst index = event.contentBlockIndex!;\n\tconst start = event.start;\n\n\tif (start?.toolUse) {\n\t\tconst block: Block = {\n\t\t\ttype: \"toolCall\",\n\t\t\tid: start.toolUse.toolUseId \|\| \"\",\n\t\t\tname: start.toolUse.name \|\| \"\",\n\t\t\targuments: {},\n\t\t\tpartialJson: \"\",\n\t\t\tindex,\n\t\t};\n\t\toutput.content.push(block);\n\t\tstream.push({ type: \"toolcall_start\", contentIndex: blocks.length - 1, partial: output });\n\t}\n}\n\nfunction handleContentBlockDelta(\n\tevent: ContentBlockDeltaEvent,\n\tblocks: Block[],\n\toutput: AssistantMessage,\n\tstream: AssistantMessageEventStream,\n): void {\n\tconst contentBlockIndex = event.contentBlockIndex!;\n\tconst delta = event.delta;\n\tlet index = blocks.findIndex((b) => b.index === contentBlockIndex);\n\tlet block = blocks[index];\n\n\tif (delta?.text !== undefined) {\n\t\t// If no text block exists yet, create one, as `handleContentBlockStart` is not sent for text blocks\n\t\tif (!block) {\n\t\t\tconst newBlock: Block = { type: \"text\", text: \"\", index: contentBlockIndex };\n\t\t\toutput.content.push(newBlock);\n\t\t\tindex = blocks.length - 1;\n\t\t\tblock = blocks[index];\n\t\t\tstream.push({ type: \"text_start\", contentIndex: index, partial: output });\n\t\t}\n\t\tif (block.type === \"text\") {\n\t\t\tblock.text += delta.text;\n\t\t\tstream.push({ type: \"text_delta\", contentIndex: index, delta: delta.text, partial: output });\n\t\t}\n\t} else if (delta?.toolUse && block?.type === \"toolCall\") {\n\t\tblock.partialJson = (block.partialJson \|\| \"\") + (delta.toolUse.input \|\| \"\");\n\t\tblock.arguments = parseStreamingJson(block.partialJson);\n\t\tstream.push({ type: \"toolcall_delta\", contentIndex: index, delta: delta.toolUse.input \|\| \"\", partial: output });\n\t} else if (delta?.reasoningContent) {\n\t\tlet thinkingBlock = block;\n\t\tlet thinkingIndex = index;\n\n\t\tif (!thinkingBlock) {\n\t\t\tconst newBlock: Block = { type: \"thinking\", thinking: \"\", thinkingSignature: \"\", index: contentBlockIndex };\n\t\t\toutput.content.push(newBlock);\n\t\t\tthinkingIndex = blocks.length - 1;\n\t\t\tthinkingBlock = blocks[thinkingIndex];\n\t\t\tstream.push({ type: \"thinking_start\", contentIndex: thinkingIndex, partial: output });\n\t\t}\n\n\t\tif (thinkingBlock?.type === \"thinking\") {\n\t\t\tif (delta.reasoningContent.text) {\n\t\t\t\tthinkingBlock.thinking += delta.reasoningContent.text;\n\t\t\t\tstream.push({\n\t\t\t\t\ttype: \"thinking_delta\",\n\t\t\t\t\tcontentIndex: thinkingIndex,\n\t\t\t\t\tdelta: delta.reasoningContent.text,\n\t\t\t\t\tpartial: output,\n\t\t\t\t});\n\t\t\t}\n\t\t\tif (delta.reasoningContent.signature) {\n\t\t\t\tthinkingBlock.thinkingSignature =\n\t\t\t\t\t(thinkingBlock.thinkingSignature \|\| \"\") + delta.reasoningContent.signature;\n\t\t\t}\n\t\t}\n\t}\n}\n\nfunction handleMetadata(\n\tevent: ConverseStreamMetadataEvent,\n\tmodel: Model<\"bedrock-converse-stream\">,\n\toutput: AssistantMessage,\n): void {\n\tif (event.usage) {\n\t\toutput.usage.input = event.usage.inputTokens \|\| 0;\n\t\toutput.usage.output = event.usage.outputTokens \|\| 0;\n\t\toutput.usage.cacheRead = event.usage.cacheReadInputTokens \|\| 0;\n\t\toutput.usage.cacheWrite = event.usage.cacheWriteInputTokens \|\| 0;\n\t\toutput.usage.totalTokens = event.usage.totalTokens \|\| output.usage.input + output.usage.output;\n\t\tcalculateCost(model, output.usage);\n\t}\n}\n\nfunction handleContentBlockStop(\n\tevent: ContentBlockStopEvent,\n\tblocks: Block[],\n\toutput: AssistantMessage,\n\tstream: AssistantMessageEventStream,\n): void {\n\tconst index = blocks.findIndex((b) => b.index === event.contentBlockIndex);\n\tconst block = blocks[index];\n\tif (!block) return;\n\tdelete (block as Block).index;\n\n\tswitch (block.type) {\n\t\tcase \"text\":\n\t\t\tstream.push({ type: \"text_end\", contentIndex: index, content: block.text, partial: output });\n\t\t\tbreak;\n\t\tcase \"thinking\":\n\t\t\tstream.push({ type: \"thinking_end\", contentIndex: index, content: block.thinking, partial: output });\n\t\t\tbreak;\n\t\tcase \"toolCall\":\n\t\t\tblock.arguments = parseStreamingJson(block.partialJson);\n\t\t\t// Finalize in-place and strip the scratch buffer so replay only\n\t\t\t// carries parsed arguments.\n\t\t\tdelete (block as Block).partialJson;\n\t\t\tstream.push({ type: \"toolcall_end\", contentIndex: index, toolCall: block, partial: output });\n\t\t\tbreak;\n\t}\n}\n\n/\n Check if the model supports adaptive thinking (Opus 4.6+, Sonnet 4.6).\n * Checks both model ID and model name to support application inference profiles\n * whose ARNs don't contain the model name.\n /\nfunction getModelMatchCandidates(modelId: string, modelName?: string): string[] {\n\tconst values = modelName ? [modelId, modelName] : [modelId];\n\treturn values.flatMap((value) => {\n\t\tconst lower = value.toLowerCase();\n\t\treturn [lower, lower.replace(/[\\s_.:]+/g, \"-\")];\n\t});\n}\n\nfunction supportsAdaptiveThinking(modelId: string, modelName?: string): boolean {\n\tconst candidates = getModelMatchCandidates(modelId, modelName);\n\treturn candidates.some(\n\t\t(s) =>\n\t\t\ts.includes(\"opus-4-6\") \|\|\n\t\t\ts.includes(\"opus-4-7\") \|\|\n\t\t\ts.includes(\"opus-4-8\") \|\|\n\t\t\ts.includes(\"opus-5\") \|\|\n\t\t\ts.includes(\"sonnet-4-6\") \|\|\n\t\t\ts.includes(\"sonnet-5\") \|\|\n\t\t\ts.includes(\"fable-5\"),\n\t);\n}\n\nfunction supportsNativeXhighEffort(model: Model<\"bedrock-converse-stream\">): boolean {\n\tconst candidates = getModelMatchCandidates(model.id, model.name);\n\treturn candidates.some(\n\t\t(s) =>\n\t\t\ts.includes(\"opus-4-7\") \|\|\n\t\t\ts.includes(\"opus-4-8\") \|\|\n\t\t\ts.includes(\"opus-5\") \|\|\n\t\t\ts.includes(\"sonnet-5\") \|\|\n\t\t\ts.includes(\"fable-5\"),\n\t);\n}\n\nfunction mapThinkingLevelToEffort(\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tlevel: SimpleStreamOptions[\"reasoning\"],\n): \"low\" \| \"medium\" \| \"high\" \| \"xhigh\" \| \"max\" {\n\tif (level === \"xhigh\" && supportsNativeXhighEffort(model)) return \"xhigh\";\n\n\tconst mapped = level ? model.thinkingLevelMap?.[level] : undefined;\n\tif (typeof mapped === \"string\") return mapped as \"low\" \| \"medium\" \| \"high\" \| \"xhigh\" \| \"max\";\n\n\tswitch (level) {\n\t\tcase \"minimal\":\n\t\tcase \"low\":\n\t\t\treturn \"low\";\n\t\tcase \"medium\":\n\t\t\treturn \"medium\";\n\t\tcase \"high\":\n\t\t\treturn \"high\";\n\t\tdefault:\n\t\t\treturn \"high\";\n\t}\n}\n\n/\n Resolve cache retention preference.\n * Defaults to \"short\" and uses PI_CACHE_RETENTION for backward compatibility.\n /\nfunction resolveCacheRetention(cacheRetention?: CacheRetention, env?: ProviderEnv): CacheRetention {\n\tif (cacheRetention) {\n\t\treturn cacheRetention;\n\t}\n\tif (getProviderEnvValue(\"PI_CACHE_RETENTION\", env) === \"long\") {\n\t\treturn \"long\";\n\t}\n\treturn \"short\";\n}\n\n/\n Check if the model is an Anthropic Claude model on Bedrock.\n * Checks both model ID and model name to support application inference profiles\n * whose ARNs don't contain the model name.\n /\nfunction isAnthropicClaudeModel(model: Model<\"bedrock-converse-stream\">): boolean {\n\tconst id = model.id.toLowerCase();\n\tconst name = model.name?.toLowerCase() ?? \"\";\n\treturn (\n\t\tid.includes(\"anthropic.claude\") \|\|\n\t\tid.includes(\"anthropic/claude\") \|\|\n\t\tname.includes(\"anthropic.claude\") \|\|\n\t\tname.includes(\"anthropic/claude\") \|\|\n\t\tname.includes(\"claude\")\n\t);\n}\n\n/\n Check if the model supports prompt caching.\n * Supported: Claude 3.5 Haiku, Claude 3.7 Sonnet, Claude 4.x models, Claude 5 models\n \n For base models and system-defined inference profiles the model ID / ARN\n * contains the model name, so we can decide locally.\n \n For application inference profiles (whose ARNs don't contain the model name),\n * also checks model.name which is user-controlled via models.json or registerProvider.\n * As a last resort, set AWS_BEDROCK_FORCE_CACHE=1 to enable cache points.\n * Amazon Nova models have automatic caching and don't need explicit cache points.\n /\nfunction supportsPromptCaching(model: Model<\"bedrock-converse-stream\">, env?: ProviderEnv): boolean {\n\tconst candidates = getModelMatchCandidates(model.id, model.name);\n\n\tconst hasClaudeRef = candidates.some((s) => s.includes(\"claude\"));\n\tif (!hasClaudeRef) {\n\t\t// Application inference profiles don't contain the model name in the ARN.\n\t\t// Allow users to force cache points via environment variable.\n\t\tif (getProviderEnvValue(\"AWS_BEDROCK_FORCE_CACHE\", env) === \"1\") return true;\n\t\treturn false;\n\t}\n\t// Claude 5 models (fable-5, opus-5, sonnet-5)\n\tif (candidates.some((s) => s.includes(\"fable-5\") \|\| s.includes(\"opus-5\") \|\| s.includes(\"sonnet-5\"))) return true;\n\t// Claude 4.x models (opus-4, sonnet-4, haiku-4)\n\tif (candidates.some((s) => s.includes(\"-4-\"))) return true;\n\t// Claude 3.7 Sonnet\n\tif (candidates.some((s) => s.includes(\"claude-3-7-sonnet\"))) return true;\n\t// Claude 3.5 Haiku\n\tif (candidates.some((s) => s.includes(\"claude-3-5-haiku\"))) return true;\n\treturn false;\n}\n\n/\n Check if the model supports thinking signatures in reasoningContent.\n * Only Anthropic Claude models support the signature field.\n * Other models (OpenAI, Qwen, Minimax, Moonshot, etc.) reject it with:\n * \"This model doesn't support the reasoningContent.reasoningText.signature field\"\n \n Checks both model ID and model name to support application inference profiles.\n */\nfunction supportsThinkingSignature(model: Model<\"bedrock-converse-stream\">): boolean {\n\treturn isAnthropicClaudeModel(model);\n}\n\nfunction buildSystemPrompt(\n\tsystemPrompt: string \| undefined,\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcacheRetention: CacheRetention,\n\tenv?: ProviderEnv,\n): SystemContentBlock[] \| undefined {\n\tif (!systemPrompt) return undefined;\n\n\tconst blocks: SystemContentBlock[] = [{ text: sanitizeSurrogates(systemPrompt) }];\n\n\t// Add cache point for supported Claude models when caching is enabled\n\tif (cacheRetention !== \"none\" && supportsPromptCaching(model, env)) {\n\t\tblocks.push({\n\t\t\tcachePoint: { type: CachePointType.DEFAULT, ...(cacheRetention === \"long\" ? { ttl: CacheTTL.ONE_HOUR } : {}) },\n\t\t});\n\t}\n\n\treturn blocks;\n}\n\nfunction normalizeToolCallId(id: string): string {\n\tconst sanitized = id.replace(/[^a-zA-Z0-9_-]/g, \"_\");\n\treturn sanitized.length > 64 ? sanitized.slice(0, 64) : sanitized;\n}\n\nfunction createNonBlankTextBlock(text: string): ContentBlock.TextMember \| undefined {\n\tconst sanitized = sanitizeSurrogates(text);\n\treturn sanitized.trim().length === 0 ? undefined : { text: sanitized };\n}\n\nfunction createRequiredTextBlock(text: string): ContentBlock.TextMember {\n\treturn createNonBlankTextBlock(text) ?? { text: EMPTY_TEXT_PLACEHOLDER };\n}\n\nfunction sanitizeBedrockDocument(value: DocumentType): DocumentType {\n\tif (Array.isArray(value)) {\n\t\treturn value.map(sanitizeBedrockDocument);\n\t}\n\tif (value !== null && typeof value === \"object\") {\n\t\treturn Object.fromEntries(\n\t\t\tObject.entries(value)\n\t\t\t\t.filter(([key]) => key.length > 0)\n\t\t\t\t.map(([key, nestedValue]) => [key, sanitizeBedrockDocument(nestedValue)]),\n\t\t);\n\t}\n\treturn value;\n}\n\nfunction convertToolResultContent(content: (TextContent \| ImageContent)[]): ToolResultContentBlock[] {\n\tconst result: ToolResultContentBlock[] = [];\n\tfor (const c of content) {\n\t\tif (c.type === \"image\") {\n\t\t\tresult.push({ image: createImageBlock(c.mimeType, c.data) });\n\t\t} else {\n\t\t\tconst textBlock = createNonBlankTextBlock(c.text);\n\t\t\tif (textBlock) result.push(textBlock);\n\t\t}\n\t}\n\tif (result.length === 0) result.push({ text: EMPTY_TEXT_PLACEHOLDER });\n\treturn result;\n}\n\nfunction convertMessages(\n\tcontext: Context,\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcacheRetention: CacheRetention,\n\tenv?: ProviderEnv,\n): Message[] {\n\tconst result: Message[] = [];\n\tconst transformedMessages = transformMessages(context.messages, model, normalizeToolCallId);\n\n\tfor (let i = 0; i < transformedMessages.length; i++) {\n\t\tconst m = transformedMessages[i];\n\n\t\tswitch (m.role) {\n\t\t\tcase \"user\": {\n\t\t\t\tconst content: ContentBlock[] = [];\n\t\t\t\tif (typeof m.content === \"string\") {\n\t\t\t\t\tcontent.push(createRequiredTextBlock(m.content));\n\t\t\t\t} else {\n\t\t\t\t\tfor (const c of m.content) {\n\t\t\t\t\t\tswitch (c.type) {\n\t\t\t\t\t\t\tcase \"text\": {\n\t\t\t\t\t\t\t\tconst textBlock = createNonBlankTextBlock(c.text);\n\t\t\t\t\t\t\t\tif (textBlock) content.push(textBlock);\n\t\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\tcase \"image\":\n\t\t\t\t\t\t\t\tcontent.push({ image: createImageBlock(c.mimeType, c.data) });\n\t\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\t\tdefault:\n\t\t\t\t\t\t\t\tcontinue;\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t\tif (content.length === 0) content.push({ text: EMPTY_TEXT_PLACEHOLDER });\n\t\t\t\t}\n\t\t\t\tresult.push({\n\t\t\t\t\trole: ConversationRole.USER,\n\t\t\t\t\tcontent,\n\t\t\t\t});\n\t\t\t\tbreak;\n\t\t\t}\n\t\t\tcase \"assistant\": {\n\t\t\t\t// Skip assistant messages with empty content (e.g., from aborted requests)\n\t\t\t\t// Bedrock rejects messages with empty content arrays\n\t\t\t\tif (m.content.length === 0) {\n\t\t\t\t\tcontinue;\n\t\t\t\t}\n\t\t\t\tconst contentBlocks: ContentBlock[] = [];\n\t\t\t\tfor (const c of m.content) {\n\t\t\t\t\tswitch (c.type) {\n\t\t\t\t\t\tcase \"text\": {\n\t\t\t\t\t\t\t// Skip empty text blocks\n\t\t\t\t\t\t\tconst textBlock = createNonBlankTextBlock(c.text);\n\t\t\t\t\t\t\tif (!textBlock) continue;\n\t\t\t\t\t\t\tcontentBlocks.push(textBlock);\n\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\t}\n\t\t\t\t\t\tcase \"toolCall\":\n\t\t\t\t\t\t\tcontentBlocks.push({\n\t\t\t\t\t\t\t\ttoolUse: { toolUseId: c.id, name: c.name, input: sanitizeBedrockDocument(c.arguments) },\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\tcase \"thinking\": {\n\t\t\t\t\t\t\t// Skip empty thinking blocks\n\t\t\t\t\t\t\tconst thinking = sanitizeSurrogates(c.thinking);\n\t\t\t\t\t\t\tif (thinking.trim().length === 0) continue;\n\t\t\t\t\t\t\t// Only Anthropic models support the signature field in reasoningText.\n\t\t\t\t\t\t\t// For other models, we omit the signature to avoid errors like:\n\t\t\t\t\t\t\t// \"This model doesn't support the reasoningContent.reasoningText.signature field\"\n\t\t\t\t\t\t\tif (supportsThinkingSignature(model)) {\n\t\t\t\t\t\t\t\t// Signatures arrive after thinking deltas. If a partial or externally\n\t\t\t\t\t\t\t\t// persisted message lacks a signature, Bedrock rejects the replayed\n\t\t\t\t\t\t\t\t// reasoning block. Fall back to plain text, matching Anthropic.\n\t\t\t\t\t\t\t\tif (!c.thinkingSignature \|\| c.thinkingSignature.trim().length === 0) {\n\t\t\t\t\t\t\t\t\tcontentBlocks.push({ text: thinking });\n\t\t\t\t\t\t\t\t} else {\n\t\t\t\t\t\t\t\t\tcontentBlocks.push({\n\t\t\t\t\t\t\t\t\t\treasoningContent: {\n\t\t\t\t\t\t\t\t\t\t\treasoningText: {\n\t\t\t\t\t\t\t\t\t\t\t\ttext: thinking,\n\t\t\t\t\t\t\t\t\t\t\t\tsignature: c.thinkingSignature,\n\t\t\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t\t\t\t});\n\t\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\t} else {\n\t\t\t\t\t\t\t\tcontentBlocks.push({\n\t\t\t\t\t\t\t\t\treasoningContent: {\n\t\t\t\t\t\t\t\t\t\treasoningText: { text: thinking },\n\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t\t\t});\n\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\t}\n\t\t\t\t\t\tdefault:\n\t\t\t\t\t\t\tcontinue;\n\t\t\t\t\t}\n\t\t\t\t}\n\t\t\t\t// Skip if all content blocks were filtered out\n\t\t\t\tif (contentBlocks.length === 0) {\n\t\t\t\t\tcontinue;\n\t\t\t\t}\n\t\t\t\tresult.push({\n\t\t\t\t\trole: ConversationRole.ASSISTANT,\n\t\t\t\t\tcontent: contentBlocks,\n\t\t\t\t});\n\t\t\t\tbreak;\n\t\t\t}\n\t\t\tcase \"toolResult\": {\n\t\t\t\t// Collect all consecutive toolResult messages into a single user message\n\t\t\t\t// Bedrock requires all tool results to be in one message\n\t\t\t\tconst toolResults: ContentBlock.ToolResultMember[] = [];\n\n\t\t\t\t// Add current tool result with all content blocks combined\n\t\t\t\ttoolResults.push({\n\t\t\t\t\ttoolResult: {\n\t\t\t\t\t\ttoolUseId: m.toolCallId,\n\t\t\t\t\t\tcontent: convertToolResultContent(m.content),\n\t\t\t\t\t\tstatus: m.isError ? ToolResultStatus.ERROR : ToolResultStatus.SUCCESS,\n\t\t\t\t\t},\n\t\t\t\t});\n\n\t\t\t\t// Look ahead for consecutive toolResult messages\n\t\t\t\tlet j = i + 1;\n\t\t\t\twhile (j < transformedMessages.length && transformedMessages[j].role === \"toolResult\") {\n\t\t\t\t\tconst nextMsg = transformedMessages[j] as ToolResultMessage;\n\t\t\t\t\ttoolResults.push({\n\t\t\t\t\t\ttoolResult: {\n\t\t\t\t\t\t\ttoolUseId: nextMsg.toolCallId,\n\t\t\t\t\t\t\tcontent: convertToolResultContent(nextMsg.content),\n\t\t\t\t\t\t\tstatus: nextMsg.isError ? ToolResultStatus.ERROR : ToolResultStatus.SUCCESS,\n\t\t\t\t\t\t},\n\t\t\t\t\t});\n\t\t\t\t\tj++;\n\t\t\t\t}\n\n\t\t\t\t// Skip the messages we've already processed\n\t\t\t\ti = j - 1;\n\n\t\t\t\tresult.push({\n\t\t\t\t\trole: ConversationRole.USER,\n\t\t\t\t\tcontent: toolResults,\n\t\t\t\t});\n\t\t\t\tbreak;\n\t\t\t}\n\t\t\tdefault:\n\t\t\t\tcontinue;\n\t\t}\n\t}\n\n\t// Add cache point to the last user message for supported Claude models when caching is enabled\n\tif (cacheRetention !== \"none\" && supportsPromptCaching(model, env) && result.length > 0) {\n\t\tconst lastMessage = result[result.length - 1];\n\t\tif (lastMessage.role === ConversationRole.USER && lastMessage.content) {\n\t\t\t(lastMessage.content as ContentBlock[]).push({\n\t\t\t\tcachePoint: {\n\t\t\t\t\ttype: CachePointType.DEFAULT,\n\t\t\t\t\t...(cacheRetention === \"long\" ? { ttl: CacheTTL.ONE_HOUR } : {}),\n\t\t\t\t},\n\t\t\t});\n\t\t}\n\t}\n\n\treturn result;\n}\n\nfunction convertToolConfig(\n\ttools: Tool[] \| undefined,\n\ttoolChoice: BedrockOptions[\"toolChoice\"],\n\tsupportsStrictMode: boolean,\n): ToolConfiguration \| undefined {\n\tif (!tools?.length) return undefined;\n\tif (toolChoice === \"none\") return undefined;\n\n\tconst bedrockTools: BedrockTool[] = tools.map((tool) => {\n\t\tconst strict = resolveJsonSchemaStrictSampling(tool, supportsStrictMode);\n\t\treturn {\n\t\t\ttoolSpec: {\n\t\t\t\tname: tool.name,\n\t\t\t\tdescription: tool.description,\n\t\t\t\tinputSchema: { json: getJsonSchemaToolParameters(tool, strict) as unknown as DocumentType },\n\t\t\t\t...(strict === true ? { strict: true } : {}),\n\t\t\t},\n\t\t};\n\t});\n\n\tlet bedrockToolChoice: ToolChoice \| undefined;\n\tswitch (toolChoice) {\n\t\tcase \"auto\":\n\t\t\tbedrockToolChoice = { auto: {} };\n\t\t\tbreak;\n\t\tcase \"any\":\n\t\t\tbedrockToolChoice = { any: {} };\n\t\t\tbreak;\n\t\tdefault:\n\t\t\tif (toolChoice?.type === \"tool\") {\n\t\t\t\tbedrockToolChoice = { tool: { name: toolChoice.name } };\n\t\t\t}\n\t}\n\n\treturn { tools: bedrockTools, toolChoice: bedrockToolChoice };\n}\n\nfunction mapStopReason(reason: string \| undefined): { stopReason: StopReason; errorMessage?: string } {\n\tswitch (reason) {\n\t\tcase BedrockStopReason.END_TURN:\n\t\tcase BedrockStopReason.STOP_SEQUENCE:\n\t\t\treturn { stopReason: \"stop\" };\n\t\tcase BedrockStopReason.MAX_TOKENS:\n\t\tcase BedrockStopReason.MODEL_CONTEXT_WINDOW_EXCEEDED:\n\t\t\treturn { stopReason: \"length\" };\n\t\tcase BedrockStopReason.TOOL_USE:\n\t\t\treturn { stopReason: \"toolUse\" };\n\t\tdefault:\n\t\t\treturn reason\n\t\t\t\t? { stopReason: \"error\", errorMessage: `Provider stopped with: ${reason}` }\n\t\t\t\t: { stopReason: \"error\" };\n\t}\n}\n\nfunction getConfiguredBedrockRegion(options: BedrockOptions): string \| undefined {\n\treturn (\n\t\toptions.region \|\|\n\t\tgetProviderEnvValue(\"AWS_REGION\", options.env) \|\|\n\t\tgetProviderEnvValue(\"AWS_DEFAULT_REGION\", options.env) \|\|\n\t\tundefined\n\t);\n}\n\nfunction getConfiguredBedrockCredentials(env?: ProviderEnv): BedrockRuntimeClientConfig[\"credentials\"] \| undefined {\n\tconst accessKeyId = getProviderEnvValue(\"AWS_ACCESS_KEY_ID\", env);\n\tconst secretAccessKey = getProviderEnvValue(\"AWS_SECRET_ACCESS_KEY\", env);\n\tif (!accessKeyId \|\| !secretAccessKey) {\n\t\treturn undefined;\n\t}\n\tconst sessionToken = getProviderEnvValue(\"AWS_SESSION_TOKEN\", env);\n\treturn {\n\t\taccessKeyId,\n\t\tsecretAccessKey,\n\t\t...(sessionToken ? { sessionToken } : {}),\n\t};\n}\n\nfunction getStandardBedrockEndpointRegion(baseUrl: string \| undefined): string \| undefined {\n\tif (!baseUrl) {\n\t\treturn undefined;\n\t}\n\n\ttry {\n\t\tconst { hostname } = new URL(baseUrl);\n\t\tconst match = hostname.toLowerCase().match(/^bedrock-runtime(?:-fips)?\\.([a-z0-9-]+)\\.amazonaws\\.com(?:\\.cn)?$/);\n\t\treturn match?.[1];\n\t} catch {\n\t\treturn undefined;\n\t}\n}\n\nfunction shouldUseExplicitBedrockEndpoint(\n\tbaseUrl: string,\n\tconfiguredRegion: string \| undefined,\n\thasAmbientConfiguredProfile: boolean,\n): boolean {\n\tconst endpointRegion = getStandardBedrockEndpointRegion(baseUrl);\n\tif (!endpointRegion) {\n\t\treturn true;\n\t}\n\n\treturn !configuredRegion && !hasAmbientConfiguredProfile;\n}\n\nfunction isGovCloudBedrockTarget(model: Model<\"bedrock-converse-stream\">, options: BedrockOptions): boolean {\n\tconst region = getConfiguredBedrockRegion(options);\n\tif (region?.toLowerCase().startsWith(\"us-gov-\")) {\n\t\treturn true;\n\t}\n\n\tconst modelId = model.id.toLowerCase();\n\treturn modelId.startsWith(\"us-gov.\") \|\| modelId.startsWith(\"arn:aws-us-gov:\");\n}\n\nfunction buildAdditionalModelRequestFields(\n\tmodel: Model<\"bedrock-converse-stream\">,\n\toptions: BedrockOptions,\n): Record<string, any> \| undefined {\n\tif (!options.reasoning \|\| !model.reasoning) {\n\t\treturn undefined;\n\t}\n\n\tif (isAnthropicClaudeModel(model)) {\n\t\t// GovCloud Bedrock currently rejects the Claude thinking.display field.\n\t\t// Omit it there until the GovCloud Converse schema catches up.\n\t\tconst display = isGovCloudBedrockTarget(model, options) ? undefined : (options.thinkingDisplay ?? \"summarized\");\n\t\tconst result: Record<string, any> = supportsAdaptiveThinking(model.id, model.name)\n\t\t\t? {\n\t\t\t\t\tthinking: { type: \"adaptive\", ...(display !== undefined ? { display } : {}) },\n\t\t\t\t\toutput_config: { effort: mapThinkingLevelToEffort(model, options.reasoning) },\n\t\t\t\t}\n\t\t\t: (() => {\n\t\t\t\t\tconst defaultBudgets: Record<ThinkingLevel, number> = {\n\t\t\t\t\t\tminimal: 1024,\n\t\t\t\t\t\tlow: 2048,\n\t\t\t\t\t\tmedium: 8192,\n\t\t\t\t\t\thigh: 16384,\n\t\t\t\t\t\txhigh: 16384, // Budget-based Claude clamps extended levels to high\n\t\t\t\t\t\tmax: 16384,\n\t\t\t\t\t};\n\n\t\t\t\t\t// Custom budgets only cover token-based levels through high.\n\t\t\t\t\tconst level = options.reasoning === \"xhigh\" \|\| options.reasoning === \"max\" ? \"high\" : options.reasoning;\n\t\t\t\t\tconst budget = options.thinkingBudgets?.[level] ?? defaultBudgets[options.reasoning];\n\n\t\t\t\t\treturn {\n\t\t\t\t\t\tthinking: {\n\t\t\t\t\t\t\ttype: \"enabled\",\n\t\t\t\t\t\t\tbudget_tokens: budget,\n\t\t\t\t\t\t\t...(display !== undefined ? { display } : {}),\n\t\t\t\t\t\t},\n\t\t\t\t\t};\n\t\t\t\t})();\n\n\t\tif (!supportsAdaptiveThinking(model.id, model.name) && (options.interleavedThinking ?? true)) {\n\t\t\tresult.anthropic_beta = [\"interleaved-thinking-2025-05-14\"];\n\t\t}\n\n\t\treturn result;\n\t}\n\n\treturn undefined;\n}\n\nfunction createImageBlock(mimeType: string, data: string) {\n\tlet format: ImageFormat;\n\tswitch (mimeType) {\n\t\tcase \"image/jpeg\":\n\t\tcase \"image/jpg\":\n\t\t\tformat = ImageFormat.JPEG;\n\t\t\tbreak;\n\t\tcase \"image/png\":\n\t\t\tformat = ImageFormat.PNG;\n\t\t\tbreak;\n\t\tcase \"image/gif\":\n\t\t\tformat = ImageFormat.GIF;\n\t\t\tbreak;\n\t\tcase \"image/webp\":\n\t\t\tformat = ImageFormat.WEBP;\n\t\t\tbreak;\n\t\tdefault:\n\t\t\tthrow new Error(`Unknown image type: ${mimeType}`);\n\t}\n\n\tconst binaryString = atob(data);\n\tconst bytes = new Uint8Array(binaryString.length);\n\tfor (let i = 0; i < binaryString.length; i++) {\n\t\tbytes[i] = binaryString.charCodeAt(i);\n\t}\n\n\treturn { source: { bytes }, format };\n}\n"]}
1	+ {"version":3,"file":"bedrock-converse-stream.d.ts","sourceRoot":"","sources":["../../src/api/bedrock-converse-stream.ts"],"names":[],"mappings":"AA6BA,OAAO,KAAK,EASX,mBAAmB,EAEnB,cAAc,EACd,aAAa,EAEb,eAAe,EAEf,aAAa,EAIb,MAAM,aAAa,CAAC;AAkBrB,MAAM,MAAM,sBAAsB,GAAG,YAAY,GAAG,SAAS,CAAC;AAE9D,MAAM,WAAW,cAAe,SAAQ,aAAa;IACpD,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,UAAU,CAAC,EAAE,MAAM,GAAG,KAAK,GAAG,MAAM,GAAG;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAA;KAAE,CAAC;IAEtE,SAAS,CAAC,EAAE,aAAa,CAAC;IAE1B,eAAe,CAAC,EAAE,eAAe,CAAC;IAElC,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B;;;;;;;;;OASG;IACH,eAAe,CAAC,EAAE,sBAAsB,CAAC;IACzC;;;sGAGkG;IAClG,eAAe,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACzC;;;;yGAIqG;IACrG,WAAW,CAAC,EAAE,MAAM,CAAC;CACrB;AAcD,eAAO,MAAM,MAAM,EAAE,cAAc,CAAC,yBAAyB,EAAE,cAAc,CAmO5E,CAAC;AAwKF,eAAO,MAAM,YAAY,EAAE,cAAc,CAAC,yBAAyB,EAAE,mBAAmB,CAiDvF,CAAC","sourcesContent":["import type { Agent as HttpsAgent } from \"node:https\";\nimport {\n\tBedrockRuntimeClient,\n\ttype BedrockRuntimeClientConfig,\n\tBedrockRuntimeServiceException,\n\tStopReason as BedrockStopReason,\n\ttype Tool as BedrockTool,\n\tCachePointType,\n\tCacheTTL,\n\ttype ContentBlock,\n\ttype ContentBlockDeltaEvent,\n\ttype ContentBlockStartEvent,\n\ttype ContentBlockStopEvent,\n\tConversationRole,\n\tConverseStreamCommand,\n\ttype ConverseStreamMetadataEvent,\n\tImageFormat,\n\ttype Message,\n\ttype SystemContentBlock,\n\ttype ToolChoice,\n\ttype ToolConfiguration,\n\ttype ToolResultContentBlock,\n\tToolResultStatus,\n} from \"@aws-sdk/client-bedrock-runtime\";\nimport { NodeHttpHandler } from \"@smithy/node-http-handler\";\nimport type { BuildMiddleware, DeserializeMiddleware, DocumentType, HttpResponse, MetadataBearer } from \"@smithy/types\";\nimport { HttpProxyAgent } from \"http-proxy-agent\";\nimport { HttpsProxyAgent } from \"https-proxy-agent\";\nimport { calculateCost } from \"../models.ts\";\nimport type {\n\tApi,\n\tAssistantMessage,\n\tCacheRetention,\n\tContext,\n\tImageContent,\n\tModel,\n\tProviderEnv,\n\tProviderResponse,\n\tSimpleStreamOptions,\n\tStopReason,\n\tStreamFunction,\n\tStreamOptions,\n\tTextContent,\n\tThinkingBudgets,\n\tThinkingContent,\n\tThinkingLevel,\n\tTool,\n\tToolCall,\n\tToolResultMessage,\n} from \"../types.ts\";\nimport { appendAssistantMessageDiagnostic } from \"../utils/diagnostics.ts\";\nimport { normalizeProviderError } from \"../utils/error-body.ts\";\nimport { AssistantMessageEventStream } from \"../utils/event-stream.ts\";\nimport { providerHeadersToRecord } from \"../utils/headers.ts\";\nimport { parseStreamingJson } from \"../utils/json-parse.ts\";\nimport { resolveHttpProxyUrlForTarget } from \"../utils/node-http-proxy.ts\";\nimport { getProviderEnvValue } from \"../utils/provider-env.ts\";\nimport { sanitizeSurrogates } from \"../utils/sanitize-unicode.ts\";\nimport { getJsonSchemaToolParameters, resolveJsonSchemaStrictSampling } from \"./constrained-sampling.ts\";\nimport {\n\tadjustMaxTokensForThinking,\n\tbuildBaseOptions,\n\tclampMaxTokensToContext,\n\tclampReasoning,\n} from \"./simple-options.ts\";\nimport { transformMessages } from \"./transform-messages.ts\";\n\nexport type BedrockThinkingDisplay = \"summarized\" \| \"omitted\";\n\nexport interface BedrockOptions extends StreamOptions {\n\tregion?: string;\n\tprofile?: string;\n\ttoolChoice?: \"auto\" \| \"any\" \| \"none\" \| { type: \"tool\"; name: string };\n\t/* See https://docs.aws.amazon.com/bedrock/latest/userguide/inference-reasoning.html for supported models. /\n\treasoning?: ThinkingLevel;\n\t/ Custom token budgets per thinking level. Overrides default budgets. /\n\tthinkingBudgets?: ThinkingBudgets;\n\t/ Only supported by Claude 4.x models, see https://docs.aws.amazon.com/bedrock/latest/userguide/claude-messages-extended-thinking.html#claude-messages-extended-thinking-tool-use-interleaved /\n\tinterleavedThinking?: boolean;\n\t/\n\t Controls how Claude's thinking content is returned in responses.\n\t * - \"summarized\": Thinking blocks contain summarized thinking text (default here).\n\t * - \"omitted\": Thinking content is redacted but the signature still travels back\n\t * for multi-turn continuity, reducing time-to-first-text-token.\n\t \n\t Note: Anthropic's API default for Claude Opus 4.8 and Mythos Preview is\n\t * \"omitted\". We default to \"summarized\" here to keep behavior consistent with\n\t * older Claude 4 models. Only applies to Claude models on Bedrock.\n\t /\n\tthinkingDisplay?: BedrockThinkingDisplay;\n\t/* Key-value pairs attached to the inference request for cost allocation tagging.\n\t * Keys: max 64 chars, no `aws:` prefix. Values: max 256 chars. Max 50 pairs.\n\t * Tags appear in AWS Cost Explorer split cost allocation data.\n\t * @see https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ConverseStream.html /\n\trequestMetadata?: Record<string, string>;\n\t/* Bearer token for Bedrock API key authentication.\n\t * When set, bypasses SigV4 signing and sends Authorization: Bearer <token> instead.\n\t * Requires `bedrock:CallWithBearerToken` IAM permission on the token's identity.\n\t * Set via AWS_BEARER_TOKEN_BEDROCK env var or pass directly.\n\t * @see https://docs.aws.amazon.com/service-authorization/latest/reference/list_amazonbedrock.html /\n\tbearerToken?: string;\n}\n\ntype Block = (TextContent \| ThinkingContent \| ToolCall) & {\n\tindex?: number;\n\tpartialJson?: string;\n\t/* Scratch buffer for encrypted reasoning deltas, joined into `thinkingSignature`. /\n\tredactedChunks?: Uint8Array[];\n};\n\nconst EMPTY_TEXT_PLACEHOLDER = \"<empty>\";\n\n/* Matches the placeholder the Anthropic API path uses for redacted thinking. /\nconst REDACTED_THINKING_PLACEHOLDER = \"[Reasoning redacted]\";\n\nexport const stream: StreamFunction<\"bedrock-converse-stream\", BedrockOptions> = (\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcontext: Context,\n\toptions: BedrockOptions = {},\n): AssistantMessageEventStream => {\n\tconst stream = new AssistantMessageEventStream();\n\n\t(async () => {\n\t\tconst output: AssistantMessage = {\n\t\t\trole: \"assistant\",\n\t\t\tcontent: [],\n\t\t\tapi: \"bedrock-converse-stream\" as Api,\n\t\t\tprovider: model.provider,\n\t\t\tmodel: model.id,\n\t\t\tusage: {\n\t\t\t\tinput: 0,\n\t\t\t\toutput: 0,\n\t\t\t\tcacheRead: 0,\n\t\t\t\tcacheWrite: 0,\n\t\t\t\ttotalTokens: 0,\n\t\t\t\tcost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },\n\t\t\t},\n\t\t\tstopReason: \"pending\",\n\t\t\ttimestamp: Date.now(),\n\t\t};\n\n\t\tconst blocks = output.content as Block[];\n\n\t\t// A profile explicitly configured through pi's auth flow (the `profile`\n\t\t// option or scoped `AWS_PROFILE` on the stored credential's env) must win\n\t\t// over ambient AWS_ACCESS_KEY_ID/AWS_SECRET_ACCESS_KEY. The SDK default\n\t\t// chain already prefers a configured profile over env keys, but only when\n\t\t// `credentials` is not set on the client config. See #6957.\n\t\tconst optionsProfile = options.profile \|\| options.env?.AWS_PROFILE;\n\t\tconst config: BedrockRuntimeClientConfig = {\n\t\t\tprofile: optionsProfile \|\| getProviderEnvValue(\"AWS_PROFILE\", options.env),\n\t\t};\n\t\tconst configuredRegion = getConfiguredBedrockRegion(options);\n\t\tconst hasAmbientConfiguredProfile = Boolean(getProviderEnvValue(\"AWS_PROFILE\"));\n\t\tconst endpointRegion = getStandardBedrockEndpointRegion(model.baseUrl);\n\t\tconst useExplicitEndpoint = shouldUseExplicitBedrockEndpoint(\n\t\t\tmodel.baseUrl,\n\t\t\tconfiguredRegion,\n\t\t\thasAmbientConfiguredProfile,\n\t\t);\n\n\t\t// Only pin standard AWS Bedrock runtime endpoints when no region or ambient AWS_PROFILE is configured.\n\t\t// This preserves custom endpoints (VPC/proxy) from #3402 without forcing built-in\n\t\t// catalog defaults such as us-east-1 to override AWS_REGION/AWS_PROFILE.\n\t\tif (useExplicitEndpoint) {\n\t\t\tconfig.endpoint = model.baseUrl;\n\t\t}\n\n\t\t// Resolve bearer token for Bedrock API key auth.\n\t\tconst skipAuth = getProviderEnvValue(\"AWS_BEDROCK_SKIP_AUTH\", options.env) === \"1\";\n\t\tconst bearerToken =\n\t\t\toptions.bearerToken \|\|\n\t\t\toptions.apiKey \|\|\n\t\t\tgetProviderEnvValue(\"AWS_BEARER_TOKEN_BEDROCK\", options.env) \|\|\n\t\t\tundefined;\n\t\tconst useBearerToken = bearerToken !== undefined && !skipAuth;\n\n\t\t// in Node.js/Bun environment only\n\t\tif (typeof process !== \"undefined\" && (process.versions?.node \|\| process.versions?.bun)) {\n\t\t\t// Region resolution: ARN-embedded > explicit option > env vars > SDK default chain.\n\t\t\t// When the model ID is an inference profile ARN, extract the region from it.\n\t\t\t// This avoids conflicts with AWS_REGION set for other services.\n\t\t\tconst arnRegionMatch = model.id.match(/^arn:aws(?:-[a-z0-9-]+)?:bedrock:([a-z0-9-]+):/);\n\t\t\tif (arnRegionMatch) {\n\t\t\t\tconfig.region = arnRegionMatch[1];\n\t\t\t} else if (configuredRegion) {\n\t\t\t\tconfig.region = configuredRegion;\n\t\t\t} else if (endpointRegion && useExplicitEndpoint) {\n\t\t\t\tconfig.region = endpointRegion;\n\t\t\t} else if (!hasAmbientConfiguredProfile) {\n\t\t\t\tconfig.region = \"us-east-1\";\n\t\t\t}\n\n\t\t\t// Support proxies that don't need authentication\n\t\t\tif (skipAuth) {\n\t\t\t\tconfig.credentials = {\n\t\t\t\t\taccessKeyId: \"dummy-access-key\",\n\t\t\t\t\tsecretAccessKey: \"dummy-secret-key\",\n\t\t\t\t};\n\t\t\t}\n\n\t\t\tconst credentials = getConfiguredBedrockCredentials(options.env);\n\t\t\tif (!skipAuth && credentials && !optionsProfile) {\n\t\t\t\tconfig.credentials = credentials;\n\t\t\t}\n\n\t\t\tconst proxyUrl = resolveHttpProxyUrlForTarget(model.baseUrl, options.env);\n\t\t\tif (proxyUrl) {\n\t\t\t\t// Bedrock runtime uses NodeHttp2Handler by default since v3.798.0, which is based\n\t\t\t\t// on `http2` module and has no support for http agent.\n\t\t\t\t// Use NodeHttpHandler to support HTTP(S) proxy agents.\n\t\t\t\tconfig.requestHandler = new NodeHttpHandler({\n\t\t\t\t\thttpAgent: new HttpProxyAgent(proxyUrl),\n\t\t\t\t\thttpsAgent: new HttpsProxyAgent(proxyUrl) as unknown as HttpsAgent,\n\t\t\t\t});\n\t\t\t} else if (getProviderEnvValue(\"AWS_BEDROCK_FORCE_HTTP1\", options.env) === \"1\") {\n\t\t\t\t// Some custom endpoints require HTTP/1.1 instead of HTTP/2\n\t\t\t\tconfig.requestHandler = new NodeHttpHandler();\n\t\t\t}\n\t\t} else {\n\t\t\t// Non-Node environment (browser): fall back to us-east-1 since\n\t\t\t// there's no config file resolution available.\n\t\t\tconfig.region =\n\t\t\t\tconfiguredRegion \|\| (endpointRegion && useExplicitEndpoint ? endpointRegion : undefined) \|\| \"us-east-1\";\n\t\t}\n\n\t\tif (useBearerToken) {\n\t\t\tconfig.token = { token: bearerToken };\n\t\t\tconfig.authSchemePreference = [\"httpBearerAuth\"];\n\t\t}\n\n\t\t// Kept outside the try so the catch can still correlate a mid-stream failure:\n\t\t// exceptions delivered as stream events carry no HTTP metadata of their own.\n\t\tlet responseRequestId: string \| undefined;\n\n\t\ttry {\n\t\t\tconst supportsStrictMode = model.compat?.supportsStrictMode ?? false;\n\t\t\tconst client = new BedrockRuntimeClient(config);\n\t\t\tlet observedRawResponse = false;\n\t\t\tif (options.onResponse) {\n\t\t\t\taddResponseHeadersMiddleware(client, options.onResponse, model, () => {\n\t\t\t\t\tobservedRawResponse = true;\n\t\t\t\t});\n\t\t\t}\n\t\t\tconst customHeaders = providerHeadersToRecord(options.headers);\n\t\t\tif (customHeaders) {\n\t\t\t\taddCustomHeadersMiddleware(client, customHeaders);\n\t\t\t}\n\t\t\tconst cacheRetention = resolveCacheRetention(options.cacheRetention, options.env);\n\t\t\tconst inferenceMaxTokens = options.maxTokens ?? (isAnthropicClaudeModel(model) ? model.maxTokens : undefined);\n\t\t\tlet commandInput = {\n\t\t\t\tmodelId: model.id,\n\t\t\t\tmessages: convertMessages(context, model, cacheRetention, options.env),\n\t\t\t\tsystem: buildSystemPrompt(context.systemPrompt, model, cacheRetention, options.env),\n\t\t\t\tinferenceConfig: {\n\t\t\t\t\t...(inferenceMaxTokens !== undefined && { maxTokens: inferenceMaxTokens }),\n\t\t\t\t\t...(options.temperature !== undefined && { temperature: options.temperature }),\n\t\t\t\t},\n\t\t\t\ttoolConfig: convertToolConfig(context.tools, options.toolChoice, supportsStrictMode),\n\t\t\t\tadditionalModelRequestFields: buildAdditionalModelRequestFields(model, options),\n\t\t\t\t...(options.requestMetadata !== undefined && { requestMetadata: options.requestMetadata }),\n\t\t\t};\n\t\t\tconst nextCommandInput = await options?.onPayload?.(commandInput, model);\n\t\t\tif (nextCommandInput !== undefined) {\n\t\t\t\tcommandInput = nextCommandInput as typeof commandInput;\n\t\t\t}\n\t\t\tconst command = new ConverseStreamCommand(commandInput);\n\n\t\t\tconst response = await client.send(command, { abortSignal: options.signal });\n\t\t\tresponseRequestId = normalizeDiagnosticValue(response.$metadata.requestId);\n\t\t\tif (!observedRawResponse && response.$metadata.httpStatusCode !== undefined) {\n\t\t\t\tconst responseHeaders: Record<string, string> = {};\n\t\t\t\tif (response.$metadata.requestId) {\n\t\t\t\t\tresponseHeaders[\"x-amzn-requestid\"] = response.$metadata.requestId;\n\t\t\t\t}\n\t\t\t\tawait options?.onResponse?.({ status: response.$metadata.httpStatusCode, headers: responseHeaders }, model);\n\t\t\t}\n\n\t\t\tfor await (const item of response.stream!) {\n\t\t\t\tif (item.messageStart) {\n\t\t\t\t\tif (item.messageStart.role !== ConversationRole.ASSISTANT) {\n\t\t\t\t\t\tthrow new Error(\"Unexpected assistant message start but got user message start instead\");\n\t\t\t\t\t}\n\t\t\t\t\tstream.push({ type: \"start\", partial: output });\n\t\t\t\t} else if (item.contentBlockStart) {\n\t\t\t\t\thandleContentBlockStart(item.contentBlockStart, blocks, output, stream);\n\t\t\t\t} else if (item.contentBlockDelta) {\n\t\t\t\t\thandleContentBlockDelta(item.contentBlockDelta, blocks, output, stream);\n\t\t\t\t} else if (item.contentBlockStop) {\n\t\t\t\t\thandleContentBlockStop(item.contentBlockStop, blocks, output, stream);\n\t\t\t\t} else if (item.messageStop) {\n\t\t\t\t\toutput.rawStopReason = item.messageStop.stopReason;\n\t\t\t\t\tconst { stopReason, errorMessage } = mapStopReason(item.messageStop.stopReason);\n\t\t\t\t\toutput.stopReason = stopReason;\n\t\t\t\t\tif (errorMessage) {\n\t\t\t\t\t\toutput.errorMessage = errorMessage;\n\t\t\t\t\t}\n\t\t\t\t} else if (item.metadata) {\n\t\t\t\t\thandleMetadata(item.metadata, model, output);\n\t\t\t\t} else if (item.internalServerException) {\n\t\t\t\t\tthrow item.internalServerException;\n\t\t\t\t} else if (item.modelStreamErrorException) {\n\t\t\t\t\tthrow item.modelStreamErrorException;\n\t\t\t\t} else if (item.validationException) {\n\t\t\t\t\tthrow item.validationException;\n\t\t\t\t} else if (item.throttlingException) {\n\t\t\t\t\tthrow item.throttlingException;\n\t\t\t\t} else if (item.serviceUnavailableException) {\n\t\t\t\t\tthrow item.serviceUnavailableException;\n\t\t\t\t}\n\t\t\t}\n\n\t\t\tif (options.signal?.aborted) {\n\t\t\t\tthrow new Error(\"Request was aborted\");\n\t\t\t}\n\n\t\t\tif (output.stopReason === \"pending\") {\n\t\t\t\tthrow new Error(\"Bedrock stream ended without a stop reason\");\n\t\t\t}\n\t\t\tif (output.stopReason === \"error\" \|\| output.stopReason === \"aborted\") {\n\t\t\t\tthrow new Error(output.errorMessage \|\| \"An unknown error occurred\");\n\t\t\t}\n\n\t\t\t// A stream can settle without stopping every block, so finalize here too.\n\t\t\tfor (const block of output.content) finalizeStreamingBlock(block as Block);\n\t\t\tstream.push({ type: \"done\", reason: output.stopReason, message: output });\n\t\t\tstream.end();\n\t\t} catch (error) {\n\t\t\tfor (const block of output.content) {\n\t\t\t\tfinalizeStreamingBlock(block as Block);\n\t\t\t}\n\t\t\toutput.stopReason = options.signal?.aborted ? \"aborted\" : \"error\";\n\t\t\toutput.errorMessage = formatBedrockError(error);\n\t\t\tif (output.stopReason === \"error\") {\n\t\t\t\tappendBedrockFailureDiagnostic(output, error, responseRequestId);\n\t\t\t}\n\t\t\tstream.push({ type: \"error\", reason: output.stopReason, error: output });\n\t\t\tstream.end();\n\t\t}\n\t})();\n\n\treturn stream;\n};\n\n/\n Human-readable prefixes for Bedrock SDK exception names.\n * The downstream retry logic in agent-session matches patterns like\n * `server.?error` and `service.?unavailable`, so we preserve the legacy\n * prefix format rather than using the raw SDK exception name.\n /\nconst BEDROCK_ERROR_PREFIXES: Record<string, string> = {\n\tInternalServerException: \"Internal server error\",\n\tModelStreamErrorException: \"Model stream error\",\n\tValidationException: \"Validation error\",\n\tThrottlingException: \"Throttling error\",\n\tServiceUnavailableException: \"Service unavailable\",\n};\n\n/\n Some models reject the account/profile's configured Bedrock data retention mode\n * (e.g. \"data retention mode 'default' is not available for this model\"). Point\n * users at the AWS docs explaining how to configure a supported mode.\n /\nconst BEDROCK_DATA_RETENTION_DOCS_URL = \"https://docs.aws.amazon.com/bedrock/latest/userguide/data-retention.html\";\n\n/\n Format a Bedrock error with a human-readable prefix.\n * AWS SDK exceptions (both from `client.send()` and from stream event items)\n * extend BedrockRuntimeServiceException. We map the `.name` to a stable\n * human-readable prefix so downstream consumers (retry logic, context-overflow\n * detection) can distinguish error categories via simple string matching.\n /\nfunction formatBedrockError(error: unknown): string {\n\tconst norm = normalizeProviderError(error);\n\t// Surface the raw HTTP body (with status) when the SDK did not fold it into\n\t// the message; otherwise fall back to the message. This is what stops a\n\t// gateway 403 from collapsing to `Unknown: UnknownError`.\n\tconst core =\n\t\t!norm.messageCarriesBody && norm.status !== undefined && norm.body !== undefined\n\t\t\t? `${norm.status}: ${norm.body}`\n\t\t\t: norm.message;\n\tconst dataRetentionHint = /data retention mode/i.test(core)\n\t\t? ` See ${BEDROCK_DATA_RETENTION_DOCS_URL} for supported data retention modes.`\n\t\t: \"\";\n\tif (error instanceof BedrockRuntimeServiceException) {\n\t\tconst prefix = BEDROCK_ERROR_PREFIXES[error.name] ?? error.name;\n\t\treturn `${prefix}: ${core}${dataRetentionHint}`;\n\t}\n\treturn `${core}${dataRetentionHint}`;\n}\n\ntype SdkErrorMetadata = { $metadata?: { httpStatusCode?: unknown; requestId?: unknown } };\n\n/* Over-long header values are dropped rather than truncated: a truncated request id is not a request id. /\nconst MAX_BEDROCK_DIAGNOSTIC_VALUE_CHARS = 200;\n\nfunction normalizeDiagnosticValue(value: unknown): string \| undefined {\n\tif (typeof value !== \"string\") return undefined;\n\tconst trimmed = value.trim();\n\tif (trimmed.length === 0 \|\| trimmed.length > MAX_BEDROCK_DIAGNOSTIC_VALUE_CHARS) return undefined;\n\treturn trimmed;\n}\n\n/\n The SDK puts the modeled code on `error.name` for service exceptions and unmodeled stream errors alike, so\n * do not narrow to `BedrockRuntimeServiceException`. Modeled Bedrock errors all end in `Exception`, unlike\n * transport names such as `TimeoutError`.\n /\nfunction extractBedrockErrorCode(error: unknown): string \| undefined {\n\tif (!(error instanceof Error) \|\| !error.name.endsWith(\"Exception\")) return undefined;\n\treturn normalizeDiagnosticValue(error.name);\n}\n\n/\n Structured metadata alongside `errorMessage`, which stays byte-identical because `isRetryableAssistantError`\n * matches against it. Unknown fields are omitted, never guessed: a modeled mid-stream exception reaches us as\n * a bare object literal, leaving only `fallbackRequestId`. `details` only, as the throw is not always `Error`.\n /\nfunction appendBedrockFailureDiagnostic(\n\toutput: AssistantMessage,\n\terror: unknown,\n\tfallbackRequestId: string \| undefined,\n): void {\n\tconst metadata = (error as SdkErrorMetadata)?.$metadata;\n\tconst details: Record<string, unknown> = {};\n\n\tif (typeof metadata?.httpStatusCode === \"number\") details.status = metadata.httpStatusCode;\n\n\tconst errorCode = extractBedrockErrorCode(error);\n\tif (errorCode !== undefined) details.errorCode = errorCode;\n\n\tconst requestId = normalizeDiagnosticValue(metadata?.requestId) ?? fallbackRequestId;\n\tif (requestId !== undefined) details.requestId = requestId;\n\n\tif (Object.keys(details).length === 0) return;\n\n\tappendAssistantMessageDiagnostic(output, { type: \"bedrock_response_failure\", timestamp: Date.now(), details });\n}\n\n/\n Header keys that must never be overwritten by caller-supplied headers.\n * `host` and `x-amz-` participate in the SigV4 canonical request; `authorization`\n is owned by SigV4 or the bearer-token path (config.token + authSchemePreference).\n * Compared case-insensitively (caller key is lower-cased before lookup).\n /\nconst RESERVED_HEADER_EXACT = new Set([\"authorization\", \"host\"]);\n\nfunction isReservedHeader(key: string): boolean {\n\tconst lower = key.toLowerCase();\n\treturn lower.startsWith(\"x-amz-\") \|\| RESERVED_HEADER_EXACT.has(lower);\n}\n\n/\n Attach caller-supplied headers to the outgoing Bedrock request via a Smithy\n * `build`-step middleware. The `build` step runs after request serialisation but\n * before SigV4 signing, so injected headers are covered by the signature. Reserved\n * SigV4 / auth headers (`x-amz-`, `authorization`, `host`) are silently skipped;\n all other caller headers override any existing same-named header on the request.\n /\nfunction addCustomHeadersMiddleware(client: BedrockRuntimeClient, headers: Record<string, string>): void {\n\tconst middleware: BuildMiddleware<object, MetadataBearer> = (next) => async (args) => {\n\t\tconst request = args.request;\n\t\tif (request && typeof request === \"object\" && \"headers\" in request) {\n\t\t\tconst requestHeaders = (request as { headers: Record<string, string> }).headers;\n\t\t\tfor (const [key, value] of Object.entries(headers)) {\n\t\t\t\tif (!isReservedHeader(key)) {\n\t\t\t\t\trequestHeaders[key] = value;\n\t\t\t\t}\n\t\t\t}\n\t\t}\n\t\treturn next(args);\n\t};\n\tclient.middlewareStack.add(middleware, { step: \"build\", name: \"pi-ai-custom-headers\", priority: \"low\" });\n}\n\nfunction isSmithyHttpResponse(response: unknown): response is HttpResponse {\n\tif (!response \|\| typeof response !== \"object\") return false;\n\tconst candidate = response as Partial<HttpResponse>;\n\treturn typeof candidate.statusCode === \"number\" && !!candidate.headers && typeof candidate.headers === \"object\";\n}\n\nfunction toProviderResponse(response: unknown): ProviderResponse \| undefined {\n\tif (!isSmithyHttpResponse(response)) return undefined;\n\treturn { status: response.statusCode, headers: { ...response.headers } };\n}\n\n/\n Bedrock's modeled `$metadata` only preserves selected HTTP metadata (for example\n * requestId), so custom gateway headers are otherwise lost before callers see\n * `onResponse`. Capture the raw Smithy HTTP response at the deserialize step,\n * after the SDK receives the response but before the event stream is consumed.\n /\nfunction addResponseHeadersMiddleware(\n\tclient: BedrockRuntimeClient,\n\tonResponse: NonNullable<BedrockOptions[\"onResponse\"]>,\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tonObserved: () => void,\n): void {\n\tconst middleware: DeserializeMiddleware<object, MetadataBearer> = (next) => async (args) => {\n\t\tconst result = await next(args);\n\t\tconst providerResponse = toProviderResponse(result.response);\n\t\tif (providerResponse) {\n\t\t\tonObserved();\n\t\t\tawait onResponse(providerResponse, model);\n\t\t}\n\t\treturn result;\n\t};\n\tclient.middlewareStack.add(middleware, { step: \"deserialize\", name: \"pi-ai-response-headers\" });\n}\n\nexport const streamSimple: StreamFunction<\"bedrock-converse-stream\", SimpleStreamOptions> = (\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcontext: Context,\n\toptions?: SimpleStreamOptions,\n): AssistantMessageEventStream => {\n\tconst base = {\n\t\t...buildBaseOptions(model, context, options, undefined),\n\t\ttoolChoice: options?.toolChoice,\n\t} satisfies BedrockOptions;\n\tif (!options?.reasoning) {\n\t\treturn stream(model, context, { ...base, reasoning: undefined } satisfies BedrockOptions);\n\t}\n\n\tif (isAnthropicClaudeModel(model)) {\n\t\tif (supportsAdaptiveThinking(model.id, model.name)) {\n\t\t\treturn stream(model, context, {\n\t\t\t\t...base,\n\t\t\t\treasoning: options.reasoning,\n\t\t\t\tthinkingBudgets: options.thinkingBudgets,\n\t\t\t} satisfies BedrockOptions);\n\t\t}\n\n\t\t// Undefined means the caller did not request an output cap; let the helper use the model cap.\n\t\t// Do not coerce to 0 here, or the thinking budget would become the entire maxTokens value.\n\t\tconst adjusted = adjustMaxTokensForThinking(\n\t\t\tbase.maxTokens,\n\t\t\tmodel.maxTokens,\n\t\t\toptions.reasoning,\n\t\t\toptions.thinkingBudgets,\n\t\t);\n\n\t\tconst maxTokens = clampMaxTokensToContext(model, context, adjusted.maxTokens);\n\n\t\treturn stream(model, context, {\n\t\t\t...base,\n\t\t\tmaxTokens,\n\t\t\treasoning: options.reasoning,\n\t\t\tthinkingBudgets: {\n\t\t\t\t...(options.thinkingBudgets \|\| {}),\n\t\t\t\t[clampReasoning(options.reasoning)!]: Math.min(adjusted.thinkingBudget, Math.max(0, maxTokens - 1024)),\n\t\t\t},\n\t\t} satisfies BedrockOptions);\n\t}\n\n\treturn stream(model, context, {\n\t\t...base,\n\t\treasoning: options.reasoning,\n\t\tthinkingBudgets: options.thinkingBudgets,\n\t} satisfies BedrockOptions);\n};\n\nfunction handleContentBlockStart(\n\tevent: ContentBlockStartEvent,\n\tblocks: Block[],\n\toutput: AssistantMessage,\n\tstream: AssistantMessageEventStream,\n): void {\n\tconst index = event.contentBlockIndex!;\n\tconst start = event.start;\n\n\tif (start?.toolUse) {\n\t\tconst block: Block = {\n\t\t\ttype: \"toolCall\",\n\t\t\tid: start.toolUse.toolUseId \|\| \"\",\n\t\t\tname: start.toolUse.name \|\| \"\",\n\t\t\targuments: {},\n\t\t\tpartialJson: \"\",\n\t\t\tindex,\n\t\t};\n\t\toutput.content.push(block);\n\t\tstream.push({ type: \"toolcall_start\", contentIndex: blocks.length - 1, partial: output });\n\t}\n}\n\nfunction handleContentBlockDelta(\n\tevent: ContentBlockDeltaEvent,\n\tblocks: Block[],\n\toutput: AssistantMessage,\n\tstream: AssistantMessageEventStream,\n): void {\n\tconst contentBlockIndex = event.contentBlockIndex!;\n\tconst delta = event.delta;\n\tlet index = blocks.findIndex((b) => b.index === contentBlockIndex);\n\tlet block = blocks[index];\n\n\tif (delta?.text !== undefined) {\n\t\t// If no text block exists yet, create one, as `handleContentBlockStart` is not sent for text blocks\n\t\tif (!block) {\n\t\t\tconst newBlock: Block = { type: \"text\", text: \"\", index: contentBlockIndex };\n\t\t\toutput.content.push(newBlock);\n\t\t\tindex = blocks.length - 1;\n\t\t\tblock = blocks[index];\n\t\t\tstream.push({ type: \"text_start\", contentIndex: index, partial: output });\n\t\t}\n\t\tif (block.type === \"text\") {\n\t\t\tblock.text += delta.text;\n\t\t\tstream.push({ type: \"text_delta\", contentIndex: index, delta: delta.text, partial: output });\n\t\t}\n\t} else if (delta?.toolUse && block?.type === \"toolCall\") {\n\t\tblock.partialJson = (block.partialJson \|\| \"\") + (delta.toolUse.input \|\| \"\");\n\t\tblock.arguments = parseStreamingJson(block.partialJson);\n\t\tstream.push({ type: \"toolcall_delta\", contentIndex: index, delta: delta.toolUse.input \|\| \"\", partial: output });\n\t} else if (delta?.reasoningContent) {\n\t\tlet thinkingBlock = block;\n\t\tlet thinkingIndex = index;\n\n\t\tif (!thinkingBlock) {\n\t\t\tconst newBlock: Block = { type: \"thinking\", thinking: \"\", thinkingSignature: \"\", index: contentBlockIndex };\n\t\t\toutput.content.push(newBlock);\n\t\t\tthinkingIndex = blocks.length - 1;\n\t\t\tthinkingBlock = blocks[thinkingIndex];\n\t\t\tstream.push({ type: \"thinking_start\", contentIndex: thinkingIndex, partial: output });\n\t\t}\n\n\t\tif (thinkingBlock?.type === \"thinking\") {\n\t\t\tif (delta.reasoningContent.text) {\n\t\t\t\tthinkingBlock.thinking += delta.reasoningContent.text;\n\t\t\t\tstream.push({\n\t\t\t\t\ttype: \"thinking_delta\",\n\t\t\t\t\tcontentIndex: thinkingIndex,\n\t\t\t\t\tdelta: delta.reasoningContent.text,\n\t\t\t\t\tpartial: output,\n\t\t\t\t});\n\t\t\t}\n\t\t\t// `thinkingSignature` holds either an Anthropic signature or an opaque redacted\n\t\t\t// payload, never both: mixing them would corrupt whichever arrived first.\n\t\t\tif (delta.reasoningContent.signature && !thinkingBlock.redacted) {\n\t\t\t\tthinkingBlock.thinkingSignature =\n\t\t\t\t\t(thinkingBlock.thinkingSignature \|\| \"\") + delta.reasoningContent.signature;\n\t\t\t}\n\t\t\tif (delta.reasoningContent.redactedContent?.length) {\n\t\t\t\t// Encrypted reasoning from non-Anthropic models on Bedrock (e.g. OpenAI GPT-5.6).\n\t\t\t\t// The payload is opaque, so keep it verbatim in `thinkingSignature` the way the\n\t\t\t\t// Anthropic path stores redacted thinking, and replay it on the next turn.\n\t\t\t\tif (!thinkingBlock.redacted) {\n\t\t\t\t\tthinkingBlock.redacted = true;\n\t\t\t\t\tthinkingBlock.thinkingSignature = \"\";\n\t\t\t\t\tthinkingBlock.thinking += REDACTED_THINKING_PLACEHOLDER;\n\t\t\t\t\tstream.push({\n\t\t\t\t\t\ttype: \"thinking_delta\",\n\t\t\t\t\t\tcontentIndex: thinkingIndex,\n\t\t\t\t\t\tdelta: REDACTED_THINKING_PLACEHOLDER,\n\t\t\t\t\t\tpartial: output,\n\t\t\t\t\t});\n\t\t\t\t}\n\t\t\t\tthinkingBlock.redactedChunks ??= [];\n\t\t\t\tthinkingBlock.redactedChunks.push(delta.reasoningContent.redactedContent);\n\t\t\t}\n\t\t}\n\t}\n}\n\n/\n Encodes buffered encrypted reasoning into `thinkingSignature` and drops the scratch\n * buffer, which must never reach a persisted message: `Uint8Array` serializes to an\n * index-keyed object roughly ten times the size of the base64 payload.\n /\nfunction flushRedactedContent(block: Block): void {\n\tif (block.type !== \"thinking\" \|\| !block.redactedChunks) return;\n\tblock.thinkingSignature = bytesToBase64(block.redactedChunks);\n\tdelete block.redactedChunks;\n}\n\n/\n Strips every streaming scratch field. Runs from the terminal paths as well as\n * `contentBlockStop`, because a stream can settle without stopping each block.\n /\nfunction finalizeStreamingBlock(block: Block): void {\n\tdelete block.index;\n\t// partialJson is only a streaming scratch buffer; never persist it.\n\tdelete block.partialJson;\n\tflushRedactedContent(block);\n}\n\nfunction handleMetadata(\n\tevent: ConverseStreamMetadataEvent,\n\tmodel: Model<\"bedrock-converse-stream\">,\n\toutput: AssistantMessage,\n): void {\n\tif (event.usage) {\n\t\toutput.usage.input = event.usage.inputTokens \|\| 0;\n\t\toutput.usage.output = event.usage.outputTokens \|\| 0;\n\t\toutput.usage.cacheRead = event.usage.cacheReadInputTokens \|\| 0;\n\t\toutput.usage.cacheWrite = event.usage.cacheWriteInputTokens \|\| 0;\n\t\toutput.usage.totalTokens = event.usage.totalTokens \|\| output.usage.input + output.usage.output;\n\t\tcalculateCost(model, output.usage);\n\t}\n}\n\nfunction handleContentBlockStop(\n\tevent: ContentBlockStopEvent,\n\tblocks: Block[],\n\toutput: AssistantMessage,\n\tstream: AssistantMessageEventStream,\n): void {\n\tconst index = blocks.findIndex((b) => b.index === event.contentBlockIndex);\n\tconst block = blocks[index];\n\tif (!block) return;\n\tdelete (block as Block).index;\n\n\tswitch (block.type) {\n\t\tcase \"text\":\n\t\t\tstream.push({ type: \"text_end\", contentIndex: index, content: block.text, partial: output });\n\t\t\tbreak;\n\t\tcase \"thinking\":\n\t\t\tflushRedactedContent(block);\n\t\t\tstream.push({ type: \"thinking_end\", contentIndex: index, content: block.thinking, partial: output });\n\t\t\tbreak;\n\t\tcase \"toolCall\":\n\t\t\tblock.arguments = parseStreamingJson(block.partialJson);\n\t\t\t// Finalize in-place and strip the scratch buffer so replay only\n\t\t\t// carries parsed arguments.\n\t\t\tdelete (block as Block).partialJson;\n\t\t\tstream.push({ type: \"toolcall_end\", contentIndex: index, toolCall: block, partial: output });\n\t\t\tbreak;\n\t}\n}\n\n/\n Check if the model supports adaptive thinking (Opus 4.6+, Sonnet 4.6).\n * Checks both model ID and model name to support application inference profiles\n * whose ARNs don't contain the model name.\n /\nfunction getModelMatchCandidates(modelId: string, modelName?: string): string[] {\n\tconst values = modelName ? [modelId, modelName] : [modelId];\n\treturn values.flatMap((value) => {\n\t\tconst lower = value.toLowerCase();\n\t\treturn [lower, lower.replace(/[\\s_.:]+/g, \"-\")];\n\t});\n}\n\nfunction supportsAdaptiveThinking(modelId: string, modelName?: string): boolean {\n\tconst candidates = getModelMatchCandidates(modelId, modelName);\n\treturn candidates.some(\n\t\t(s) =>\n\t\t\ts.includes(\"opus-4-6\") \|\|\n\t\t\ts.includes(\"opus-4-7\") \|\|\n\t\t\ts.includes(\"opus-4-8\") \|\|\n\t\t\ts.includes(\"opus-5\") \|\|\n\t\t\ts.includes(\"sonnet-4-6\") \|\|\n\t\t\ts.includes(\"sonnet-5\") \|\|\n\t\t\ts.includes(\"fable-5\"),\n\t);\n}\n\nfunction supportsNativeXhighEffort(model: Model<\"bedrock-converse-stream\">): boolean {\n\tconst candidates = getModelMatchCandidates(model.id, model.name);\n\treturn candidates.some(\n\t\t(s) =>\n\t\t\ts.includes(\"opus-4-7\") \|\|\n\t\t\ts.includes(\"opus-4-8\") \|\|\n\t\t\ts.includes(\"opus-5\") \|\|\n\t\t\ts.includes(\"sonnet-5\") \|\|\n\t\t\ts.includes(\"fable-5\"),\n\t);\n}\n\nfunction mapThinkingLevelToEffort(\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tlevel: SimpleStreamOptions[\"reasoning\"],\n): \"low\" \| \"medium\" \| \"high\" \| \"xhigh\" \| \"max\" {\n\tif (level === \"xhigh\" && supportsNativeXhighEffort(model)) return \"xhigh\";\n\n\tconst mapped = level ? model.thinkingLevelMap?.[level] : undefined;\n\tif (typeof mapped === \"string\") return mapped as \"low\" \| \"medium\" \| \"high\" \| \"xhigh\" \| \"max\";\n\n\tswitch (level) {\n\t\tcase \"minimal\":\n\t\tcase \"low\":\n\t\t\treturn \"low\";\n\t\tcase \"medium\":\n\t\t\treturn \"medium\";\n\t\tcase \"high\":\n\t\t\treturn \"high\";\n\t\tdefault:\n\t\t\treturn \"high\";\n\t}\n}\n\n/\n Resolve cache retention preference.\n * Defaults to \"short\" and uses PI_CACHE_RETENTION for backward compatibility.\n /\nfunction resolveCacheRetention(cacheRetention?: CacheRetention, env?: ProviderEnv): CacheRetention {\n\tif (cacheRetention) {\n\t\treturn cacheRetention;\n\t}\n\tif (getProviderEnvValue(\"PI_CACHE_RETENTION\", env) === \"long\") {\n\t\treturn \"long\";\n\t}\n\treturn \"short\";\n}\n\n/\n Check if the model is an Anthropic Claude model on Bedrock.\n * Checks both model ID and model name to support application inference profiles\n * whose ARNs don't contain the model name.\n /\nfunction isAnthropicClaudeModel(model: Model<\"bedrock-converse-stream\">): boolean {\n\tconst id = model.id.toLowerCase();\n\tconst name = model.name?.toLowerCase() ?? \"\";\n\treturn (\n\t\tid.includes(\"anthropic.claude\") \|\|\n\t\tid.includes(\"anthropic/claude\") \|\|\n\t\tname.includes(\"anthropic.claude\") \|\|\n\t\tname.includes(\"anthropic/claude\") \|\|\n\t\tname.includes(\"claude\")\n\t);\n}\n\n/\n Check if the model supports prompt caching.\n * Supported: Claude 3.5 Haiku, Claude 3.7 Sonnet, Claude 4.x models, Claude 5 models\n \n For base models and system-defined inference profiles the model ID / ARN\n * contains the model name, so we can decide locally.\n \n For application inference profiles (whose ARNs don't contain the model name),\n * also checks model.name which is user-controlled via models.json or registerProvider.\n * As a last resort, set AWS_BEDROCK_FORCE_CACHE=1 to enable cache points.\n * Amazon Nova models have automatic caching and don't need explicit cache points.\n /\nfunction supportsPromptCaching(model: Model<\"bedrock-converse-stream\">, env?: ProviderEnv): boolean {\n\tconst candidates = getModelMatchCandidates(model.id, model.name);\n\n\tconst hasClaudeRef = candidates.some((s) => s.includes(\"claude\"));\n\tif (!hasClaudeRef) {\n\t\t// Application inference profiles don't contain the model name in the ARN.\n\t\t// Allow users to force cache points via environment variable.\n\t\tif (getProviderEnvValue(\"AWS_BEDROCK_FORCE_CACHE\", env) === \"1\") return true;\n\t\treturn false;\n\t}\n\t// Claude 5 models (fable-5, opus-5, sonnet-5)\n\tif (candidates.some((s) => s.includes(\"fable-5\") \|\| s.includes(\"opus-5\") \|\| s.includes(\"sonnet-5\"))) return true;\n\t// Claude 4.x models (opus-4, sonnet-4, haiku-4)\n\tif (candidates.some((s) => s.includes(\"-4-\"))) return true;\n\t// Claude 3.7 Sonnet\n\tif (candidates.some((s) => s.includes(\"claude-3-7-sonnet\"))) return true;\n\t// Claude 3.5 Haiku\n\tif (candidates.some((s) => s.includes(\"claude-3-5-haiku\"))) return true;\n\treturn false;\n}\n\n/\n Check if the model supports thinking signatures in reasoningContent.\n * Only Anthropic Claude models support the signature field.\n * Other models (OpenAI, Qwen, Minimax, Moonshot, etc.) reject it with:\n * \"This model doesn't support the reasoningContent.reasoningText.signature field\"\n \n Checks both model ID and model name to support application inference profiles.\n /\nfunction supportsThinkingSignature(model: Model<\"bedrock-converse-stream\">): boolean {\n\treturn isAnthropicClaudeModel(model);\n}\n\nfunction buildSystemPrompt(\n\tsystemPrompt: string \| undefined,\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcacheRetention: CacheRetention,\n\tenv?: ProviderEnv,\n): SystemContentBlock[] \| undefined {\n\tif (!systemPrompt) return undefined;\n\n\tconst blocks: SystemContentBlock[] = [{ text: sanitizeSurrogates(systemPrompt) }];\n\n\t// Add cache point for supported Claude models when caching is enabled\n\tif (cacheRetention !== \"none\" && supportsPromptCaching(model, env)) {\n\t\tblocks.push({\n\t\t\tcachePoint: { type: CachePointType.DEFAULT, ...(cacheRetention === \"long\" ? { ttl: CacheTTL.ONE_HOUR } : {}) },\n\t\t});\n\t}\n\n\treturn blocks;\n}\n\nfunction normalizeToolCallId(id: string): string {\n\tconst sanitized = id.replace(/[^a-zA-Z0-9_-]/g, \"_\");\n\treturn sanitized.length > 64 ? sanitized.slice(0, 64) : sanitized;\n}\n\nfunction createNonBlankTextBlock(text: string): ContentBlock.TextMember \| undefined {\n\tconst sanitized = sanitizeSurrogates(text);\n\treturn sanitized.trim().length === 0 ? undefined : { text: sanitized };\n}\n\nfunction createRequiredTextBlock(text: string): ContentBlock.TextMember {\n\treturn createNonBlankTextBlock(text) ?? { text: EMPTY_TEXT_PLACEHOLDER };\n}\n\nfunction sanitizeBedrockDocument(value: DocumentType): DocumentType {\n\tif (Array.isArray(value)) {\n\t\treturn value.map(sanitizeBedrockDocument);\n\t}\n\tif (value !== null && typeof value === \"object\") {\n\t\treturn Object.fromEntries(\n\t\t\tObject.entries(value)\n\t\t\t\t.filter(([key]) => key.length > 0)\n\t\t\t\t.map(([key, nestedValue]) => [key, sanitizeBedrockDocument(nestedValue)]),\n\t\t);\n\t}\n\treturn value;\n}\n\nfunction convertToolResultContent(content: (TextContent \| ImageContent)[]): ToolResultContentBlock[] {\n\tconst result: ToolResultContentBlock[] = [];\n\tfor (const c of content) {\n\t\tif (c.type === \"image\") {\n\t\t\tresult.push({ image: createImageBlock(c.mimeType, c.data) });\n\t\t} else {\n\t\t\tconst textBlock = createNonBlankTextBlock(c.text);\n\t\t\tif (textBlock) result.push(textBlock);\n\t\t}\n\t}\n\tif (result.length === 0) result.push({ text: EMPTY_TEXT_PLACEHOLDER });\n\treturn result;\n}\n\nfunction convertMessages(\n\tcontext: Context,\n\tmodel: Model<\"bedrock-converse-stream\">,\n\tcacheRetention: CacheRetention,\n\tenv?: ProviderEnv,\n): Message[] {\n\tconst result: Message[] = [];\n\tconst transformedMessages = transformMessages(context.messages, model, normalizeToolCallId);\n\n\tfor (let i = 0; i < transformedMessages.length; i++) {\n\t\tconst m = transformedMessages[i];\n\n\t\tswitch (m.role) {\n\t\t\tcase \"user\": {\n\t\t\t\tconst content: ContentBlock[] = [];\n\t\t\t\tif (typeof m.content === \"string\") {\n\t\t\t\t\tcontent.push(createRequiredTextBlock(m.content));\n\t\t\t\t} else {\n\t\t\t\t\tfor (const c of m.content) {\n\t\t\t\t\t\tswitch (c.type) {\n\t\t\t\t\t\t\tcase \"text\": {\n\t\t\t\t\t\t\t\tconst textBlock = createNonBlankTextBlock(c.text);\n\t\t\t\t\t\t\t\tif (textBlock) content.push(textBlock);\n\t\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\tcase \"image\":\n\t\t\t\t\t\t\t\tcontent.push({ image: createImageBlock(c.mimeType, c.data) });\n\t\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\t\tdefault:\n\t\t\t\t\t\t\t\tcontinue;\n\t\t\t\t\t\t}\n\t\t\t\t\t}\n\t\t\t\t\tif (content.length === 0) content.push({ text: EMPTY_TEXT_PLACEHOLDER });\n\t\t\t\t}\n\t\t\t\tresult.push({\n\t\t\t\t\trole: ConversationRole.USER,\n\t\t\t\t\tcontent,\n\t\t\t\t});\n\t\t\t\tbreak;\n\t\t\t}\n\t\t\tcase \"assistant\": {\n\t\t\t\t// Skip assistant messages with empty content (e.g., from aborted requests)\n\t\t\t\t// Bedrock rejects messages with empty content arrays\n\t\t\t\tif (m.content.length === 0) {\n\t\t\t\t\tcontinue;\n\t\t\t\t}\n\t\t\t\tconst contentBlocks: ContentBlock[] = [];\n\t\t\t\tfor (const c of m.content) {\n\t\t\t\t\tswitch (c.type) {\n\t\t\t\t\t\tcase \"text\": {\n\t\t\t\t\t\t\t// Skip empty text blocks\n\t\t\t\t\t\t\tconst textBlock = createNonBlankTextBlock(c.text);\n\t\t\t\t\t\t\tif (!textBlock) continue;\n\t\t\t\t\t\t\tcontentBlocks.push(textBlock);\n\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\t}\n\t\t\t\t\t\tcase \"toolCall\":\n\t\t\t\t\t\t\tcontentBlocks.push({\n\t\t\t\t\t\t\t\ttoolUse: { toolUseId: c.id, name: c.name, input: sanitizeBedrockDocument(c.arguments) },\n\t\t\t\t\t\t\t});\n\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\tcase \"thinking\": {\n\t\t\t\t\t\t\t// Encrypted reasoning is opaque: replay the stored payload as the\n\t\t\t\t\t\t\t// `redactedContent` member instead of lowering it to reasoning text.\n\t\t\t\t\t\t\tif (c.redacted) {\n\t\t\t\t\t\t\t\tconst redactedContent = decodeRedactedContent(c.thinkingSignature);\n\t\t\t\t\t\t\t\tif (redactedContent?.length) {\n\t\t\t\t\t\t\t\t\tcontentBlocks.push({ reasoningContent: { redactedContent } });\n\t\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\t\tcontinue;\n\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\t// Skip empty thinking blocks\n\t\t\t\t\t\t\tconst thinking = sanitizeSurrogates(c.thinking);\n\t\t\t\t\t\t\tif (thinking.trim().length === 0) continue;\n\t\t\t\t\t\t\t// Only Anthropic models support the signature field in reasoningText.\n\t\t\t\t\t\t\t// For other models, we omit the signature to avoid errors like:\n\t\t\t\t\t\t\t// \"This model doesn't support the reasoningContent.reasoningText.signature field\"\n\t\t\t\t\t\t\tif (supportsThinkingSignature(model)) {\n\t\t\t\t\t\t\t\t// Signatures arrive after thinking deltas. If a partial or externally\n\t\t\t\t\t\t\t\t// persisted message lacks a signature, Bedrock rejects the replayed\n\t\t\t\t\t\t\t\t// reasoning block. Fall back to plain text, matching Anthropic.\n\t\t\t\t\t\t\t\tif (!c.thinkingSignature \|\| c.thinkingSignature.trim().length === 0) {\n\t\t\t\t\t\t\t\t\tcontentBlocks.push({ text: thinking });\n\t\t\t\t\t\t\t\t} else {\n\t\t\t\t\t\t\t\t\tcontentBlocks.push({\n\t\t\t\t\t\t\t\t\t\treasoningContent: {\n\t\t\t\t\t\t\t\t\t\t\treasoningText: {\n\t\t\t\t\t\t\t\t\t\t\t\ttext: thinking,\n\t\t\t\t\t\t\t\t\t\t\t\tsignature: c.thinkingSignature,\n\t\t\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t\t\t\t});\n\t\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\t} else {\n\t\t\t\t\t\t\t\tcontentBlocks.push({\n\t\t\t\t\t\t\t\t\treasoningContent: {\n\t\t\t\t\t\t\t\t\t\treasoningText: { text: thinking },\n\t\t\t\t\t\t\t\t\t},\n\t\t\t\t\t\t\t\t});\n\t\t\t\t\t\t\t}\n\t\t\t\t\t\t\tbreak;\n\t\t\t\t\t\t}\n\t\t\t\t\t\tdefault:\n\t\t\t\t\t\t\tcontinue;\n\t\t\t\t\t}\n\t\t\t\t}\n\t\t\t\t// Skip if all content blocks were filtered out\n\t\t\t\tif (contentBlocks.length === 0) {\n\t\t\t\t\tcontinue;\n\t\t\t\t}\n\t\t\t\tresult.push({\n\t\t\t\t\trole: ConversationRole.ASSISTANT,\n\t\t\t\t\tcontent: contentBlocks,\n\t\t\t\t});\n\t\t\t\tbreak;\n\t\t\t}\n\t\t\tcase \"toolResult\": {\n\t\t\t\t// Collect all consecutive toolResult messages into a single user message\n\t\t\t\t// Bedrock requires all tool results to be in one message\n\t\t\t\tconst toolResults: ContentBlock.ToolResultMember[] = [];\n\n\t\t\t\t// Add current tool result with all content blocks combined\n\t\t\t\ttoolResults.push({\n\t\t\t\t\ttoolResult: {\n\t\t\t\t\t\ttoolUseId: m.toolCallId,\n\t\t\t\t\t\tcontent: convertToolResultContent(m.content),\n\t\t\t\t\t\tstatus: m.isError ? ToolResultStatus.ERROR : ToolResultStatus.SUCCESS,\n\t\t\t\t\t},\n\t\t\t\t});\n\n\t\t\t\t// Look ahead for consecutive toolResult messages\n\t\t\t\tlet j = i + 1;\n\t\t\t\twhile (j < transformedMessages.length && transformedMessages[j].role === \"toolResult\") {\n\t\t\t\t\tconst nextMsg = transformedMessages[j] as ToolResultMessage;\n\t\t\t\t\ttoolResults.push({\n\t\t\t\t\t\ttoolResult: {\n\t\t\t\t\t\t\ttoolUseId: nextMsg.toolCallId,\n\t\t\t\t\t\t\tcontent: convertToolResultContent(nextMsg.content),\n\t\t\t\t\t\t\tstatus: nextMsg.isError ? ToolResultStatus.ERROR : ToolResultStatus.SUCCESS,\n\t\t\t\t\t\t},\n\t\t\t\t\t});\n\t\t\t\t\tj++;\n\t\t\t\t}\n\n\t\t\t\t// Skip the messages we've already processed\n\t\t\t\ti = j - 1;\n\n\t\t\t\tresult.push({\n\t\t\t\t\trole: ConversationRole.USER,\n\t\t\t\t\tcontent: toolResults,\n\t\t\t\t});\n\t\t\t\tbreak;\n\t\t\t}\n\t\t\tdefault:\n\t\t\t\tcontinue;\n\t\t}\n\t}\n\n\t// Add cache point to the last user message for supported Claude models when caching is enabled\n\tif (cacheRetention !== \"none\" && supportsPromptCaching(model, env) && result.length > 0) {\n\t\tconst lastMessage = result[result.length - 1];\n\t\tif (lastMessage.role === ConversationRole.USER && lastMessage.content) {\n\t\t\t(lastMessage.content as ContentBlock[]).push({\n\t\t\t\tcachePoint: {\n\t\t\t\t\ttype: CachePointType.DEFAULT,\n\t\t\t\t\t...(cacheRetention === \"long\" ? { ttl: CacheTTL.ONE_HOUR } : {}),\n\t\t\t\t},\n\t\t\t});\n\t\t}\n\t}\n\n\treturn result;\n}\n\nfunction convertToolConfig(\n\ttools: Tool[] \| undefined,\n\ttoolChoice: BedrockOptions[\"toolChoice\"],\n\tsupportsStrictMode: boolean,\n): ToolConfiguration \| undefined {\n\tif (!tools?.length) return undefined;\n\tif (toolChoice === \"none\") return undefined;\n\n\tconst bedrockTools: BedrockTool[] = tools.map((tool) => {\n\t\tconst strict = resolveJsonSchemaStrictSampling(tool, supportsStrictMode);\n\t\treturn {\n\t\t\ttoolSpec: {\n\t\t\t\tname: tool.name,\n\t\t\t\tdescription: tool.description,\n\t\t\t\tinputSchema: { json: getJsonSchemaToolParameters(tool, strict) as unknown as DocumentType },\n\t\t\t\t...(strict === true ? { strict: true } : {}),\n\t\t\t},\n\t\t};\n\t});\n\n\tlet bedrockToolChoice: ToolChoice \| undefined;\n\tswitch (toolChoice) {\n\t\tcase \"auto\":\n\t\t\tbedrockToolChoice = { auto: {} };\n\t\t\tbreak;\n\t\tcase \"any\":\n\t\t\tbedrockToolChoice = { any: {} };\n\t\t\tbreak;\n\t\tdefault:\n\t\t\tif (toolChoice?.type === \"tool\") {\n\t\t\t\tbedrockToolChoice = { tool: { name: toolChoice.name } };\n\t\t\t}\n\t}\n\n\treturn { tools: bedrockTools, toolChoice: bedrockToolChoice };\n}\n\nfunction mapStopReason(reason: string \| undefined): { stopReason: StopReason; errorMessage?: string } {\n\tswitch (reason) {\n\t\tcase BedrockStopReason.END_TURN:\n\t\tcase BedrockStopReason.STOP_SEQUENCE:\n\t\t\treturn { stopReason: \"stop\" };\n\t\tcase BedrockStopReason.MAX_TOKENS:\n\t\tcase BedrockStopReason.MODEL_CONTEXT_WINDOW_EXCEEDED:\n\t\t\treturn { stopReason: \"length\" };\n\t\tcase BedrockStopReason.TOOL_USE:\n\t\t\treturn { stopReason: \"toolUse\" };\n\t\tdefault:\n\t\t\treturn reason\n\t\t\t\t? { stopReason: \"error\", errorMessage: `Provider stopped with: ${reason}` }\n\t\t\t\t: { stopReason: \"error\" };\n\t}\n}\n\nfunction getConfiguredBedrockRegion(options: BedrockOptions): string \| undefined {\n\treturn (\n\t\toptions.region \|\|\n\t\tgetProviderEnvValue(\"AWS_REGION\", options.env) \|\|\n\t\tgetProviderEnvValue(\"AWS_DEFAULT_REGION\", options.env) \|\|\n\t\tundefined\n\t);\n}\n\nfunction getConfiguredBedrockCredentials(env?: ProviderEnv): BedrockRuntimeClientConfig[\"credentials\"] \| undefined {\n\tconst accessKeyId = getProviderEnvValue(\"AWS_ACCESS_KEY_ID\", env);\n\tconst secretAccessKey = getProviderEnvValue(\"AWS_SECRET_ACCESS_KEY\", env);\n\tif (!accessKeyId \|\| !secretAccessKey) {\n\t\treturn undefined;\n\t}\n\tconst sessionToken = getProviderEnvValue(\"AWS_SESSION_TOKEN\", env);\n\treturn {\n\t\taccessKeyId,\n\t\tsecretAccessKey,\n\t\t...(sessionToken ? { sessionToken } : {}),\n\t};\n}\n\nfunction getStandardBedrockEndpointRegion(baseUrl: string \| undefined): string \| undefined {\n\tif (!baseUrl) {\n\t\treturn undefined;\n\t}\n\n\ttry {\n\t\tconst { hostname } = new URL(baseUrl);\n\t\tconst match = hostname.toLowerCase().match(/^bedrock-runtime(?:-fips)?\\.([a-z0-9-]+)\\.amazonaws\\.com(?:\\.cn)?$/);\n\t\treturn match?.[1];\n\t} catch {\n\t\treturn undefined;\n\t}\n}\n\nfunction shouldUseExplicitBedrockEndpoint(\n\tbaseUrl: string,\n\tconfiguredRegion: string \| undefined,\n\thasAmbientConfiguredProfile: boolean,\n): boolean {\n\tconst endpointRegion = getStandardBedrockEndpointRegion(baseUrl);\n\tif (!endpointRegion) {\n\t\treturn true;\n\t}\n\n\treturn !configuredRegion && !hasAmbientConfiguredProfile;\n}\n\nfunction isGovCloudBedrockTarget(model: Model<\"bedrock-converse-stream\">, options: BedrockOptions): boolean {\n\tconst region = getConfiguredBedrockRegion(options);\n\tif (region?.toLowerCase().startsWith(\"us-gov-\")) {\n\t\treturn true;\n\t}\n\n\tconst modelId = model.id.toLowerCase();\n\treturn modelId.startsWith(\"us-gov.\") \|\| modelId.startsWith(\"arn:aws-us-gov:\");\n}\n\nfunction buildAdditionalModelRequestFields(\n\tmodel: Model<\"bedrock-converse-stream\">,\n\toptions: BedrockOptions,\n): Record<string, any> \| undefined {\n\tif (!options.reasoning \|\| !model.reasoning) {\n\t\treturn undefined;\n\t}\n\n\tif (isAnthropicClaudeModel(model)) {\n\t\t// GovCloud Bedrock currently rejects the Claude thinking.display field.\n\t\t// Omit it there until the GovCloud Converse schema catches up.\n\t\tconst display = isGovCloudBedrockTarget(model, options) ? undefined : (options.thinkingDisplay ?? \"summarized\");\n\t\tconst result: Record<string, any> = supportsAdaptiveThinking(model.id, model.name)\n\t\t\t? {\n\t\t\t\t\tthinking: { type: \"adaptive\", ...(display !== undefined ? { display } : {}) },\n\t\t\t\t\toutput_config: { effort: mapThinkingLevelToEffort(model, options.reasoning) },\n\t\t\t\t}\n\t\t\t: (() => {\n\t\t\t\t\tconst defaultBudgets: Record<ThinkingLevel, number> = {\n\t\t\t\t\t\tminimal: 1024,\n\t\t\t\t\t\tlow: 2048,\n\t\t\t\t\t\tmedium: 8192,\n\t\t\t\t\t\thigh: 16384,\n\t\t\t\t\t\txhigh: 16384, // Budget-based Claude clamps extended levels to high\n\t\t\t\t\t\tmax: 16384,\n\t\t\t\t\t};\n\n\t\t\t\t\t// Custom budgets only cover token-based levels through high.\n\t\t\t\t\tconst level = options.reasoning === \"xhigh\" \|\| options.reasoning === \"max\" ? \"high\" : options.reasoning;\n\t\t\t\t\tconst budget = options.thinkingBudgets?.[level] ?? defaultBudgets[options.reasoning];\n\n\t\t\t\t\treturn {\n\t\t\t\t\t\tthinking: {\n\t\t\t\t\t\t\ttype: \"enabled\",\n\t\t\t\t\t\t\tbudget_tokens: budget,\n\t\t\t\t\t\t\t...(display !== undefined ? { display } : {}),\n\t\t\t\t\t\t},\n\t\t\t\t\t};\n\t\t\t\t})();\n\n\t\tif (!supportsAdaptiveThinking(model.id, model.name) && (options.interleavedThinking ?? true)) {\n\t\t\tresult.anthropic_beta = [\"interleaved-thinking-2025-05-14\"];\n\t\t}\n\n\t\treturn result;\n\t}\n\n\treturn undefined;\n}\n\nfunction createImageBlock(mimeType: string, data: string) {\n\tlet format: ImageFormat;\n\tswitch (mimeType) {\n\t\tcase \"image/jpeg\":\n\t\tcase \"image/jpg\":\n\t\t\tformat = ImageFormat.JPEG;\n\t\t\tbreak;\n\t\tcase \"image/png\":\n\t\t\tformat = ImageFormat.PNG;\n\t\t\tbreak;\n\t\tcase \"image/gif\":\n\t\t\tformat = ImageFormat.GIF;\n\t\t\tbreak;\n\t\tcase \"image/webp\":\n\t\t\tformat = ImageFormat.WEBP;\n\t\t\tbreak;\n\t\tdefault:\n\t\t\tthrow new Error(`Unknown image type: ${mimeType}`);\n\t}\n\n\treturn { source: { bytes: base64ToBytes(data) }, format };\n}\n\nfunction base64ToBytes(data: string): Uint8Array {\n\tconst binaryString = atob(data);\n\tconst bytes = new Uint8Array(binaryString.length);\n\tfor (let i = 0; i < binaryString.length; i++) {\n\t\tbytes[i] = binaryString.charCodeAt(i);\n\t}\n\treturn bytes;\n}\n\n/\n Decodes a stored redacted payload. The AWS SDK hands the blob over as bytes, but a\n * persisted session carries it as base64. A hand-edited or externally produced session\n * can hold a signature that is not base64; drop that block instead of failing the\n * whole request.\n */\nfunction decodeRedactedContent(signature: string \| undefined): Uint8Array \| undefined {\n\tif (!signature) return undefined;\n\ttry {\n\t\treturn base64ToBytes(signature);\n\t} catch {\n\t\treturn undefined;\n\t}\n}\n\nfunction bytesToBase64(chunks: Uint8Array[]): string {\n\t// Encrypted reasoning runs to tens of KB, so build the binary string in slices\n\t// rather than one concatenation per byte. The window stays under the engine's\n\t// argument-count limit for spread calls.\n\tconst WINDOW = 0x8000;\n\tlet binary = \"\";\n\tfor (const chunk of chunks) {\n\t\tfor (let i = 0; i < chunk.length; i += WINDOW) {\n\t\t\tbinary += String.fromCharCode(...chunk.subarray(i, i + WINDOW));\n\t\t}\n\t}\n\treturn btoa(binary);\n}\n"]}

package/node_modules/@earendil-works/pi-ai/dist/api/bedrock-converse-stream.js CHANGED Viewed

@@ -15,6 +15,8 @@ import { getJsonSchemaToolParameters, resolveJsonSchemaStrictSampling } from "./
 import { adjustMaxTokensForThinking, buildBaseOptions, clampMaxTokensToContext, clampReasoning, } from "./simple-options.js";
 import { transformMessages } from "./transform-messages.js";
 const EMPTY_TEXT_PLACEHOLDER = "<empty>";
+/** Matches the placeholder the Anthropic API path uses for redacted thinking. */
+const REDACTED_THINKING_PLACEHOLDER = "[Reasoning redacted]";
 export const stream = (model, context, options = {}) => {
     const stream = new AssistantMessageEventStream();
     (async () => {
@@ -122,6 +124,12 @@ export const stream = (model, context, options = {}) => {
         try {
             const supportsStrictMode = model.compat?.supportsStrictMode ?? false;
             const client = new BedrockRuntimeClient(config);
+            let observedRawResponse = false;
+            if (options.onResponse) {
+                addResponseHeadersMiddleware(client, options.onResponse, model, () => {
+                    observedRawResponse = true;
+                });
+            }
             const customHeaders = providerHeadersToRecord(options.headers);
             if (customHeaders) {
                 addCustomHeadersMiddleware(client, customHeaders);
@@ -147,7 +155,7 @@ export const stream = (model, context, options = {}) => {
             const command = new ConverseStreamCommand(commandInput);
             const response = await client.send(command, { abortSignal: options.signal });
             responseRequestId = normalizeDiagnosticValue(response.$metadata.requestId);
-            if (response.$metadata.httpStatusCode !== undefined) {
+            if (!observedRawResponse && response.$metadata.httpStatusCode !== undefined) {
                 const responseHeaders = {};
                 if (response.$metadata.requestId) {
                     responseHeaders["x-amzn-requestid"] = response.$metadata.requestId;
@@ -206,14 +214,15 @@ export const stream = (model, context, options = {}) => {
             if (output.stopReason === "error" || output.stopReason === "aborted") {
                 throw new Error(output.errorMessage || "An unknown error occurred");
             }
+            // A stream can settle without stopping every block, so finalize here too.
+            for (const block of output.content)
+                finalizeStreamingBlock(block);
             stream.push({ type: "done", reason: output.stopReason, message: output });
             stream.end();
         }
         catch (error) {
             for (const block of output.content) {
-                delete block.index;
-                // partialJson is only a streaming scratch buffer; never persist it.
-                delete block.partialJson;
+                finalizeStreamingBlock(block);
             }
             output.stopReason = options.signal?.aborted ? "aborted" : "error";
             output.errorMessage = formatBedrockError(error);
@@ -342,8 +351,40 @@ function addCustomHeadersMiddleware(client, headers) {
     };
     client.middlewareStack.add(middleware, { step: "build", name: "pi-ai-custom-headers", priority: "low" });
 }
+function isSmithyHttpResponse(response) {
+    if (!response || typeof response !== "object")
+        return false;
+    const candidate = response;
+    return typeof candidate.statusCode === "number" && !!candidate.headers && typeof candidate.headers === "object";
+}
+function toProviderResponse(response) {
+    if (!isSmithyHttpResponse(response))
+        return undefined;
+    return { status: response.statusCode, headers: { ...response.headers } };
+}
+/**
+ * Bedrock's modeled `$metadata` only preserves selected HTTP metadata (for example
+ * requestId), so custom gateway headers are otherwise lost before callers see
+ * `onResponse`. Capture the raw Smithy HTTP response at the deserialize step,
+ * after the SDK receives the response but before the event stream is consumed.
+ */
+function addResponseHeadersMiddleware(client, onResponse, model, onObserved) {
+    const middleware = (next) => async (args) => {
+        const result = await next(args);
+        const providerResponse = toProviderResponse(result.response);
+        if (providerResponse) {
+            onObserved();
+            await onResponse(providerResponse, model);
+        }
+        return result;
+    };
+    client.middlewareStack.add(middleware, { step: "deserialize", name: "pi-ai-response-headers" });
+}
 export const streamSimple = (model, context, options) => {
-    const base = buildBaseOptions(model, context, options, undefined);
+    const base = {
+        ...buildBaseOptions(model, context, options, undefined),
+        toolChoice: options?.toolChoice,
+    };
     if (!options?.reasoning) {
         return stream(model, context, { ...base, reasoning: undefined });
     }
@@ -435,13 +476,54 @@ function handleContentBlockDelta(event, blocks, output, stream) {
                     partial: output,
                 });
             }
-            if (delta.reasoningContent.signature) {
+            // `thinkingSignature` holds either an Anthropic signature or an opaque redacted
+            // payload, never both: mixing them would corrupt whichever arrived first.
+            if (delta.reasoningContent.signature && !thinkingBlock.redacted) {
                 thinkingBlock.thinkingSignature =
                     (thinkingBlock.thinkingSignature || "") + delta.reasoningContent.signature;
             }
+            if (delta.reasoningContent.redactedContent?.length) {
+                // Encrypted reasoning from non-Anthropic models on Bedrock (e.g. OpenAI GPT-5.6).
+                // The payload is opaque, so keep it verbatim in `thinkingSignature` the way the
+                // Anthropic path stores redacted thinking, and replay it on the next turn.
+                if (!thinkingBlock.redacted) {
+                    thinkingBlock.redacted = true;
+                    thinkingBlock.thinkingSignature = "";
+                    thinkingBlock.thinking += REDACTED_THINKING_PLACEHOLDER;
+                    stream.push({
+                        type: "thinking_delta",
+                        contentIndex: thinkingIndex,
+                        delta: REDACTED_THINKING_PLACEHOLDER,
+                        partial: output,
+                    });
+                }
+                thinkingBlock.redactedChunks ??= [];
+                thinkingBlock.redactedChunks.push(delta.reasoningContent.redactedContent);
+            }
         }
     }
 }
+/**
+ * Encodes buffered encrypted reasoning into `thinkingSignature` and drops the scratch
+ * buffer, which must never reach a persisted message: `Uint8Array` serializes to an
+ * index-keyed object roughly ten times the size of the base64 payload.
+ */
+function flushRedactedContent(block) {
+    if (block.type !== "thinking" || !block.redactedChunks)
+        return;
+    block.thinkingSignature = bytesToBase64(block.redactedChunks);
+    delete block.redactedChunks;
+}
+/**
+ * Strips every streaming scratch field. Runs from the terminal paths as well as
+ * `contentBlockStop`, because a stream can settle without stopping each block.
+ */
+function finalizeStreamingBlock(block) {
+    delete block.index;
+    // partialJson is only a streaming scratch buffer; never persist it.
+    delete block.partialJson;
+    flushRedactedContent(block);
+}
 function handleMetadata(event, model, output) {
     if (event.usage) {
         output.usage.input = event.usage.inputTokens || 0;
@@ -463,6 +545,7 @@ function handleContentBlockStop(event, blocks, output, stream) {
             stream.push({ type: "text_end", contentIndex: index, content: block.text, partial: output });
             break;
         case "thinking":
+            flushRedactedContent(block);
             stream.push({ type: "thinking_end", contentIndex: index, content: block.thinking, partial: output });
             break;
         case "toolCall":
@@ -705,6 +788,15 @@ function convertMessages(context, model, cacheRetention, env) {
                             });
                             break;
                         case "thinking": {
+                            // Encrypted reasoning is opaque: replay the stored payload as the
+                            // `redactedContent` member instead of lowering it to reasoning text.
+                            if (c.redacted) {
+                                const redactedContent = decodeRedactedContent(c.thinkingSignature);
+                                if (redactedContent?.length) {
+                                    contentBlocks.push({ reasoningContent: { redactedContent } });
+                                }
+                                continue;
+                            }
                             // Skip empty thinking blocks
                             const thinking = sanitizeSurrogates(c.thinking);
                             if (thinking.trim().length === 0)
@@ -957,11 +1049,43 @@ function createImageBlock(mimeType, data) {
         default:
             throw new Error(`Unknown image type: ${mimeType}`);
     }
+    return { source: { bytes: base64ToBytes(data) }, format };
+}
+function base64ToBytes(data) {
     const binaryString = atob(data);
     const bytes = new Uint8Array(binaryString.length);
     for (let i = 0; i < binaryString.length; i++) {
         bytes[i] = binaryString.charCodeAt(i);
     }
-    return { source: { bytes }, format };
+    return bytes;
+}
+/**
+ * Decodes a stored redacted payload. The AWS SDK hands the blob over as bytes, but a
+ * persisted session carries it as base64. A hand-edited or externally produced session
+ * can hold a signature that is not base64; drop that block instead of failing the
+ * whole request.
+ */
+function decodeRedactedContent(signature) {
+    if (!signature)
+        return undefined;
+    try {
+        return base64ToBytes(signature);
+    }
+    catch {
+        return undefined;
+    }
+}
+function bytesToBase64(chunks) {
+    // Encrypted reasoning runs to tens of KB, so build the binary string in slices
+    // rather than one concatenation per byte. The window stays under the engine's
+    // argument-count limit for spread calls.
+    const WINDOW = 0x8000;
+    let binary = "";
+    for (const chunk of chunks) {
+        for (let i = 0; i < chunk.length; i += WINDOW) {
+            binary += String.fromCharCode(...chunk.subarray(i, i + WINDOW));
+        }
+    }
+    return btoa(binary);
 }
 //# sourceMappingURL=bedrock-converse-stream.js.map