@jxburros/ai-nugget 0.7.0 → 0.7.3

package/README.md

@@ -1,6 +1,8 @@
 # AI Nugget
 
-**Version 0.7.0** · [What's changed since 0.6.0](#whats-changed-since-060) · [Changelog](./CHANGELOG.md) · [Upgrading](./UPGRADING.md)
+<img src="assets/ai-nugget-logo.png" alt="AI Nugget official logo" width="180" />
+
+**Version 0.7.3** · [What's changed in 0.7.x](#whats-changed-in-07x) · [Changelog](./CHANGELOG.md) · [Upgrading](./UPGRADING.md)
 
 A small, zero-dependency, isomorphic TypeScript nugget for talking to AI model
 providers through one pipeline:
@@ -24,6 +26,13 @@ Requires Node `^20.19.0` or `>=22.12.0` ([why](./docs/distribution.md#requiremen
 npm install @jxburros/ai-nugget
 ```
 
+> **0.7.1–0.7.3 are not on npm yet.** The registry's `latest` is still 0.7.0
+> until the 0.7.3 Release run publishes, so the command above may install 0.7.0
+> (without the 0.7.1 Anthropic fixes or the 0.7.2 `/agent` types fix). Until
+> then, pin a commit from this repository
+> (`npm install github:jxburros/AI-Nugget#<commit>`) or vendor `nugget/` — see
+> [distribution paths](./docs/distribution.md#distribution-paths).
+
 ```ts
 import { AIHandler, envKeySource } from '@jxburros/ai-nugget';
 
@@ -50,7 +59,9 @@ No key? Point at a local model instead — same code, no `keyRef`:
 const conn = { id: 'local', provider: 'ollama', baseUrl: 'http://127.0.0.1:11434' };
 ```
 
-CommonJS works too: `const { AIHandler } = require('@jxburros/ai-nugget')`.
+CommonJS works too: `const { AIHandler } = require('@jxburros/ai-nugget')`. TypeScript
+finds the root and `/agent` types under `node10` (classic `module: commonjs`)
+and `bundler` resolution, and under `node16`/`nodenext` from ESM files.
 
 For a running server, copy a starter from
 [`examples/integrations/`](./examples/integrations/) — Express, Next.js,
@@ -116,7 +127,48 @@ new AIHandler({
   honest `stopReason`s, an `ApprovalGate` for side-effecting tools, and
   `native`/`promptJson`/`auto` tool modes.
 
-## What's changed since 0.6.0
+## Anthropic compatibility
+
+Claude Opus/Sonnet/Haiku 5.5 requests omit unsupported sampling parameters.
+Modern Claude JSON schemas use `output_config.format`; requests without a schema
+use a JSON instruction and emit `json_mode_downgraded`. Older models retain the
+forced-tool fallback. Explicit forced-tool choices on models that reject them
+fail with `invalid_request` rather than silently changing the choice.
+
+Anthropic results include opaque `providerState`. Custom tool loops must copy it
+onto the corresponding assistant `ChatMessage`; `runAgent` does this automatically.
+Keep it unchanged and private: it contains signed thinking blocks needed for replay,
+not display or telemetry data. Replay is limited to the same provider and model.
+See [provider details](./docs/providers.md#anthropic-compatibility).
+
+## What's changed in 0.7.x
+
+### 0.7.3
+
+**Release-pipeline fix.** Package contents are identical to 0.7.2; 0.7.3 exists
+because the 0.7.1 and 0.7.2 Release runs failed before publishing (see the
+[changelog](./CHANGELOG.md)).
+
+### 0.7.2
+
+**`/agent` types under classic `node10` resolution.** A `typesVersions` entry
+lets TypeScript projects on `module: commonjs` (default `node10` resolution)
+resolve `@jxburros/ai-nugget/agent`. Otherwise documentation only — notably the
+[JX Runtime guidance](./docs/providers.md#pointing-at-a-jx-runtime-server) for
+JX 1.5, including the `stream_options` opt-in for real streamed token counts.
+No runtime behavior changed.
+
+### 0.7.1
+
+**Anthropic correctness for modern Claude models.** Unsupported sampling
+parameters are omitted, JSON schemas use native structured output, and signed
+thinking is preserved for tool-loop replay through the new opaque
+`providerState` on results (`runAgent` copies it for you; custom tool loops must
+copy it onto the assistant message). SSE API errors become typed failures.
+Details in [Anthropic compatibility](#anthropic-compatibility),
+[UPGRADING.md](./UPGRADING.md#070--071), and the [changelog](./CHANGELOG.md).
+
+### 0.7.0
 
 **0.7.0 is backward-compatible for ordinary consumers** — the first two changes are additive; the third changes what `delta` carries for reasoning models (see UPGRADING). Full detail in the
 [changelog](./CHANGELOG.md) and [UPGRADING.md](./UPGRADING.md#06x--070).
@@ -206,3 +258,11 @@ enforce rules, not a place the library imposes its own.
 ## Project Stewardship
 
 This project is developed by **Jeffrey** through **JX Holdings, LLC**. GitHub: [`jxburros`](https://github.com/jxburros).
+
+## Unified release procedure
+
+`release.json` is the authoritative release manifest. Keep configured embedded versions synchronized and advance affected apps (patch by default) before merging changes into main. The first adoption establishes a baseline; later PRs must pass **Release version validation**.
+
+Use **Actions → Release → Run workflow** from **main**, choose stable or preview, and leave **dry_run** enabled first. Only apps ahead of their published version in their own namespace are selected. Build/test/sign all required packages before publishing. Tag pushes and merges no longer publish migrated apps automatically. After inspecting the dry run, dispatch with dry_run disabled and satisfy configured approvals. Published versions are never overwritten; use a new version for a correction.
+
+See [.release/README.md](.release/README.md) for this repository's inventory, credentials, compatibility, and validation limits. Shared implementation: [JX Holdings release infrastructure](https://github.com/JX-Holdings-LLC/release-infrastructure).

package/UPGRADING.md

@@ -1,5 +1,23 @@
 # Upgrading
 
+## 0.7.2 → 0.7.3
+
+No changes: 0.7.3 republishes the 0.7.2 package contents after a release-pipeline fix.
+
+## 0.7.1 → 0.7.2
+
+No code changes required. `package.json` gains a `typesVersions` entry so
+TypeScript on classic `node10` resolution can find the `/agent` types; consumers
+on `node16`/`nodenext`/`bundler` resolve exactly as before.
+
+## 0.7.0 → 0.7.1
+
+Custom Anthropic tool loops should copy `result.providerState` onto their assistant
+messages to preserve signed thinking; `runAgent` already does this. Sampling fields
+are omitted on known modern Claude models. Native JSON schemas replace forced JSON
+tools there; schema-less requests disclose an instruction-only downgrade. Explicit
+unsupported forced-tool and thinking-off choices fail with `invalid_request`.
+
 ## 0.6.x → 0.7.0
 
 **Backward-compatible for ordinary consumers.** Two additive changes and one
@@ -86,7 +104,7 @@ signature changed and no default behavior changed, so an app on 0.4.x can bump
 without code edits and adopt the new capabilities as needed.
 
 The numbers in brackets are the suggestion numbers from the AI Server Studio
-production friction report (`docs/reviews/2026-08-09-ai-server-studio-friction-report.md`),
+production friction report ([`docs/archive/2026-08-09-ai-server-studio-friction-report.md`](./docs/archive/2026-08-09-ai-server-studio-friction-report.md)),
 so you can trace each change back to the friction it resolves.
 
 ### Packaging

package/dist/adapters/engines/anthropic.js

@@ -1,4 +1,4 @@
-import { AIError } from '../../errors.js';
+import { AIError, classify } from '../../errors.js';
 import { estimatedUsage } from '../../tokens.js';
 import { fetchJson, postResponse, sseLines } from '../../transport.js';
 import { applyProviderOptions, REASONING_BUDGET_TOKENS, asNumber, asRecord, asString, joinUrl, textFromMessages } from '../../util.js';
@@ -23,7 +23,8 @@ export class AnthropicAdapter {
     }
     async *stream(conn, req) {
         const started = Date.now();
-        const jsonMode = req.responseFormat?.type === 'json' && !req.tools?.length;
+        const nativeJson = modernModel(req.model);
+        const jsonMode = req.responseFormat?.type === 'json' && !nativeJson && !req.tools?.length;
         let firstTokenMs = null;
         let text = '';
         let inputTokens;
@@ -31,6 +32,7 @@ export class AnthropicAdapter {
         let stopReason;
         let sawTerminal = false;
         const emittedTools = [];
+        const responseBlocks = new Map();
         // Partial tool_use blocks keyed by content-block index (input_json_delta accumulation).
         const blocks = new Map();
         const timeout = streamTimeout(conn, req.signal);
@@ -38,19 +40,29 @@ export class AnthropicAdapter {
         // Anthropic JSON mode is implemented as a forced `json_output` tool, which
         // cannot coexist with the caller's own tools — same silent-downgrade shape
         // as Gemini, so it gets the same signal rather than quietly dropping.
-        if (req.responseFormat?.type === 'json' && req.tools?.length) {
+        if (req.responseFormat?.type === 'json' && !nativeJson && req.tools?.length) {
             yield {
                 type: 'context',
                 kind: 'json_mode_downgraded',
                 data: { reason: 'Anthropic JSON mode uses a forced tool and cannot be combined with caller tools; the request was sent without JSON mode', provider: conn.provider },
             };
         }
+        if (req.responseFormat?.type === 'json' && nativeJson && !req.responseFormat.schema) {
+            yield { type: 'context', kind: 'json_mode_downgraded', data: { provider: conn.provider, reason: 'Claude native JSON outputs require a schema; using a JSON instruction without constrained decoding.' } };
+        }
         try {
             const res = await postResponse(`${conn.baseUrl}/v1/messages`, body(req, jsonMode), conn.headers, timeout.signal, conn.provider);
             const contentType = res.headers.get('content-type') ?? '';
             if (!contentType.includes('text/event-stream')) {
                 const data = await res.json();
                 const parsed = parseResponse(data);
+                const content = asRecord(data)?.content;
+                if (Array.isArray(content))
+                    content.forEach((block, i) => {
+                        const record = asRecord(block);
+                        if (record)
+                            responseBlocks.set(i, record);
+                    });
                 inputTokens = parsed.inputTokens;
                 outputTokens = parsed.outputTokens;
                 stopReason = parsed.stopReason;
@@ -77,7 +89,12 @@ export class AnthropicAdapter {
                     if (!record)
                         continue;
                     const type = asString(record.type);
-                    if (type === 'message_start') {
+                    if (type === 'error') {
+                        const error = asRecord(record.error);
+                        const statuses = { overloaded_error: 529, rate_limit_error: 429, authentication_error: 401, permission_error: 403, invalid_request_error: 400, not_found_error: 404, api_error: 500, billing_error: 402, timeout_error: 504, request_too_large: 413 };
+                        throw classify(statuses[asString(error?.type) ?? ''] ?? 500, JSON.stringify(record), conn.provider);
+                    }
+                    else if (type === 'message_start') {
                         const usage = asRecord(asRecord(record.message)?.usage);
                         inputTokens = asNumber(usage?.input_tokens) ?? inputTokens;
                         outputTokens = asNumber(usage?.output_tokens) ?? outputTokens;
@@ -85,6 +102,8 @@ export class AnthropicAdapter {
                     else if (type === 'content_block_start') {
                         const index = asNumber(record.index) ?? 0;
                         const block = asRecord(record.content_block);
+                        if (block)
+                            responseBlocks.set(index, { ...block });
                         if (block?.type === 'tool_use') {
                             blocks.set(index, { id: asString(block.id) ?? randomId(), name: asString(block.name) ?? 'unknown', raw: '' });
                         }
@@ -92,6 +111,14 @@ export class AnthropicAdapter {
                     else if (type === 'content_block_delta') {
                         const index = asNumber(record.index) ?? 0;
                         const delta = asRecord(record.delta);
+                        const block = responseBlocks.get(index);
+                        if (block && delta) {
+                            const field = delta.type === 'text_delta' ? 'text' : delta.type === 'thinking_delta' ? 'thinking' : delta.type === 'signature_delta' ? 'signature' : undefined;
+                            if (field)
+                                block[field] = String(block[field] ?? '') + String(delta[field] ?? '');
+                            if (delta.type === 'citations_delta')
+                                block.citations = [...(Array.isArray(block.citations) ? block.citations : []), delta.citation];
+                        }
                         if (delta?.type === 'text_delta') {
                             const piece = asString(delta.text) ?? '';
                             if (piece) {
@@ -118,6 +145,9 @@ export class AnthropicAdapter {
                         const partial = blocks.get(index);
                         if (partial) {
                             const call = { id: partial.id, name: partial.name, raw: partial.raw, arguments: parseArgs(partial.raw) };
+                            const block = responseBlocks.get(index);
+                            if (block)
+                                block.input = call.arguments;
                             blocks.delete(index);
                             if (jsonMode && call.name === JSON_MODE_TOOL) {
                                 text = jsonTextFrom([call], text);
@@ -149,6 +179,7 @@ export class AnthropicAdapter {
             const hasTools = emittedTools.length > 0;
             yield { type: 'done', result: {
                     text,
+                    providerState: { provider: conn.provider, model: req.model, content: [...responseBlocks.entries()].sort(([a], [b]) => a - b).map(([, block]) => block) },
                     toolCalls: hasTools ? emittedTools : undefined,
                     finishReason: mapStop(stopReason, hasTools),
                     usage: inputTokens !== undefined || outputTokens !== undefined ? { inputTokens, outputTokens, estimated: false } : estimatedUsage(textFromMessages(req.messages), text),
@@ -192,9 +223,15 @@ function body(req, jsonMode) {
         top_p: req.topP,
         stop_sequences: req.stopSequences,
         system,
-        messages: toAnthropicMessages(req.messages.filter((m) => m.role !== 'system')),
+        messages: toAnthropicMessages(req.messages.filter((m) => m.role !== 'system'), req.model),
         stream: true,
     };
+    if (req.responseFormat?.type === 'json' && modernModel(req.model) && req.responseFormat.schema) {
+        base.output_config = { format: { type: 'json_schema', schema: schemaFor(req) } };
+    }
+    if (req.responseFormat?.type === 'json' && modernModel(req.model) && !req.responseFormat.schema) {
+        base.system = [system, 'Return only valid JSON, without markdown fences or a preamble.'].filter(Boolean).join('\n\n');
+    }
     if (jsonMode) {
         // Forced-tool JSON mode: Anthropic has no response_format, so we make the
         // model answer through a single required tool whose input is the JSON we want.
@@ -215,7 +252,14 @@ function body(req, jsonMode) {
         // `budget_tokens < max_tokens` and rejects temperature/top_p alongside
         // thinking, so the budget is fitted under max_tokens (raising max_tokens
         // when the caller's value leaves no room) and the samplers are dropped.
-        if (req.reasoningEffort === 'none') {
+        if (modernModel(req.model)) {
+            const none = req.reasoningEffort === 'none';
+            if (none && alwaysThinking(req.model))
+                throw new AIError('This Claude model cannot disable thinking; choose a reasoning effort instead.', { kind: 'invalid_request', provider: 'anthropic' });
+            base.thinking = { type: none ? (/^claude-sonnet-5-5(?:-|$)/.test(req.model) ? 'between_tools' : 'disabled') : 'adaptive' };
+            base.output_config = { ...asRecord(base.output_config), effort: none ? 'low' : req.reasoningEffort === 'minimal' ? 'low' : req.reasoningEffort };
+        }
+        else if (req.reasoningEffort === 'none') {
             base.thinking = { type: 'disabled' };
         }
         else {
@@ -230,14 +274,24 @@ function body(req, jsonMode) {
     }
     // providerOptions carries Anthropic-native fields (`thinking`, `metadata`,
     // top-level `cache_control` extras, `service_tier`, …) without a release.
-    return applyProviderOptions(base, req.providerOptions);
+    const result = applyProviderOptions(base, req.providerOptions, ['output_config']);
+    if (modernModel(req.model)) {
+        delete result.temperature;
+        delete result.top_p;
+        delete result.top_k;
+    }
+    const choice = asRecord(result.tool_choice);
+    if (noForcedTools(req.model) && (choice?.type === 'tool' || choice?.type === 'any')) {
+        throw new AIError('This Claude model does not support forced tool choice; use auto or structured outputs.', { kind: 'invalid_request', provider: 'anthropic' });
+    }
+    return result;
 }
-function toAnthropicMessages(messages) {
+function toAnthropicMessages(messages, model) {
     const out = [];
     for (let index = 0; index < messages.length; index += 1) {
         const message = messages[index];
         if (message.role !== 'tool') {
-            out.push(toAnthropicMessage(message));
+            out.push(toAnthropicMessage(message, model));
             continue;
         }
         const content = [];
@@ -251,7 +305,10 @@ function toAnthropicMessages(messages) {
     }
     return out;
 }
-function toAnthropicMessage(m) {
+function toAnthropicMessage(m, model) {
+    if (m.role === 'assistant' && m.providerState?.provider === 'anthropic' && m.providerState.model === model) {
+        return { role: 'assistant', content: m.providerState.content };
+    }
     // Tool-role messages are handled by toAnthropicMessages' batching loop and
     // never reach here, so no tool branch is needed.
     // assistant turns that carried tool calls replay them as tool_use blocks,
@@ -316,8 +373,21 @@ function jsonTextFrom(toolCalls, fallback) {
 function mapStop(stop, hasTools) {
     if (stop === 'tool_use' && hasTools)
         return 'tool';
+    if (stop === 'refusal')
+        return 'content_filter';
     if (stop === 'max_tokens')
         return 'length';
     return 'stop';
 }
+/** Models released after Opus 4.6 use adaptive effort and reject sampling knobs.
+ * Unknown/custom IDs retain legacy behavior rather than guessing capabilities. */
+function modernModel(model) {
+    return /^claude-(?:opus-(?:4-[78]|5(?:-5)?)|sonnet-5(?:-5)?|haiku-5-5|(?:fable|mythos)-5(?:-1)?|mythos-preview)(?:-\d{8}|-latest)?$/.test(model);
+}
+function alwaysThinking(model) {
+    return /^claude-(?:fable-|mythos-|opus-5-5(?:-|$))/.test(model);
+}
+function noForcedTools(model) {
+    return /^claude-(?:(?:opus|sonnet)-5-5(?:-|$)|(?:fable|mythos)-5-1(?:-|$))/.test(model);
+}
 //# sourceMappingURL=anthropic.js.map

package/dist/agent/loop.js

@@ -32,6 +32,7 @@ async function* run(opts, resolveResult) {
             yield emit(opts, { type: 'step_start', step });
             const calls = [];
             let stepText = '';
+            let providerState;
             let streamFailure;
             // In promptJson mode a tool directive must not leak into the visible
             // stream, so directive-looking text is withheld from `delta` events (still
@@ -65,6 +66,7 @@ async function* run(opts, resolveResult) {
                 if (event.type === 'error')
                     streamFailure = event.error;
                 if (event.type === 'done') {
+                    providerState = event.result.providerState;
                     usage = usage ? mergeUsage(usage, event.result.usage) : event.result.usage;
                     if (toolMode === 'promptJson' && calls.length === 0)
                         calls.push(...callsFromPromptJson(stepText));
@@ -85,7 +87,7 @@ async function* run(opts, resolveResult) {
             finalText = stepText;
             messages.push(toolMode === 'promptJson'
                 ? { role: 'assistant', content: stepText }
-                : { role: 'assistant', content: stepText, toolCalls: calls.length ? calls : undefined });
+                : { role: 'assistant', content: stepText, providerState, toolCalls: calls.length ? calls : undefined });
             if (calls.length === 0)
                 return yield* yieldDone('finished');
             for (const call of calls) {

package/dist/cjs/adapters/engines/anthropic.js

@@ -26,7 +26,8 @@ class AnthropicAdapter {
     }
     async *stream(conn, req) {
         const started = Date.now();
-        const jsonMode = req.responseFormat?.type === 'json' && !req.tools?.length;
+        const nativeJson = modernModel(req.model);
+        const jsonMode = req.responseFormat?.type === 'json' && !nativeJson && !req.tools?.length;
         let firstTokenMs = null;
         let text = '';
         let inputTokens;
@@ -34,6 +35,7 @@ class AnthropicAdapter {
         let stopReason;
         let sawTerminal = false;
         const emittedTools = [];
+        const responseBlocks = new Map();
         // Partial tool_use blocks keyed by content-block index (input_json_delta accumulation).
         const blocks = new Map();
         const timeout = (0, base_js_1.streamTimeout)(conn, req.signal);
@@ -41,19 +43,29 @@ class AnthropicAdapter {
         // Anthropic JSON mode is implemented as a forced `json_output` tool, which
         // cannot coexist with the caller's own tools — same silent-downgrade shape
         // as Gemini, so it gets the same signal rather than quietly dropping.
-        if (req.responseFormat?.type === 'json' && req.tools?.length) {
+        if (req.responseFormat?.type === 'json' && !nativeJson && req.tools?.length) {
             yield {
                 type: 'context',
                 kind: 'json_mode_downgraded',
                 data: { reason: 'Anthropic JSON mode uses a forced tool and cannot be combined with caller tools; the request was sent without JSON mode', provider: conn.provider },
             };
         }
+        if (req.responseFormat?.type === 'json' && nativeJson && !req.responseFormat.schema) {
+            yield { type: 'context', kind: 'json_mode_downgraded', data: { provider: conn.provider, reason: 'Claude native JSON outputs require a schema; using a JSON instruction without constrained decoding.' } };
+        }
         try {
             const res = await (0, transport_js_1.postResponse)(`${conn.baseUrl}/v1/messages`, body(req, jsonMode), conn.headers, timeout.signal, conn.provider);
             const contentType = res.headers.get('content-type') ?? '';
             if (!contentType.includes('text/event-stream')) {
                 const data = await res.json();
                 const parsed = parseResponse(data);
+                const content = (0, util_js_1.asRecord)(data)?.content;
+                if (Array.isArray(content))
+                    content.forEach((block, i) => {
+                        const record = (0, util_js_1.asRecord)(block);
+                        if (record)
+                            responseBlocks.set(i, record);
+                    });
                 inputTokens = parsed.inputTokens;
                 outputTokens = parsed.outputTokens;
                 stopReason = parsed.stopReason;
@@ -80,7 +92,12 @@ class AnthropicAdapter {
                     if (!record)
                         continue;
                     const type = (0, util_js_1.asString)(record.type);
-                    if (type === 'message_start') {
+                    if (type === 'error') {
+                        const error = (0, util_js_1.asRecord)(record.error);
+                        const statuses = { overloaded_error: 529, rate_limit_error: 429, authentication_error: 401, permission_error: 403, invalid_request_error: 400, not_found_error: 404, api_error: 500, billing_error: 402, timeout_error: 504, request_too_large: 413 };
+                        throw (0, errors_js_1.classify)(statuses[(0, util_js_1.asString)(error?.type) ?? ''] ?? 500, JSON.stringify(record), conn.provider);
+                    }
+                    else if (type === 'message_start') {
                         const usage = (0, util_js_1.asRecord)((0, util_js_1.asRecord)(record.message)?.usage);
                         inputTokens = (0, util_js_1.asNumber)(usage?.input_tokens) ?? inputTokens;
                         outputTokens = (0, util_js_1.asNumber)(usage?.output_tokens) ?? outputTokens;
@@ -88,6 +105,8 @@ class AnthropicAdapter {
                     else if (type === 'content_block_start') {
                         const index = (0, util_js_1.asNumber)(record.index) ?? 0;
                         const block = (0, util_js_1.asRecord)(record.content_block);
+                        if (block)
+                            responseBlocks.set(index, { ...block });
                         if (block?.type === 'tool_use') {
                             blocks.set(index, { id: (0, util_js_1.asString)(block.id) ?? (0, base_js_1.randomId)(), name: (0, util_js_1.asString)(block.name) ?? 'unknown', raw: '' });
                         }
@@ -95,6 +114,14 @@ class AnthropicAdapter {
                     else if (type === 'content_block_delta') {
                         const index = (0, util_js_1.asNumber)(record.index) ?? 0;
                         const delta = (0, util_js_1.asRecord)(record.delta);
+                        const block = responseBlocks.get(index);
+                        if (block && delta) {
+                            const field = delta.type === 'text_delta' ? 'text' : delta.type === 'thinking_delta' ? 'thinking' : delta.type === 'signature_delta' ? 'signature' : undefined;
+                            if (field)
+                                block[field] = String(block[field] ?? '') + String(delta[field] ?? '');
+                            if (delta.type === 'citations_delta')
+                                block.citations = [...(Array.isArray(block.citations) ? block.citations : []), delta.citation];
+                        }
                         if (delta?.type === 'text_delta') {
                             const piece = (0, util_js_1.asString)(delta.text) ?? '';
                             if (piece) {
@@ -121,6 +148,9 @@ class AnthropicAdapter {
                         const partial = blocks.get(index);
                         if (partial) {
                             const call = { id: partial.id, name: partial.name, raw: partial.raw, arguments: (0, base_js_1.parseArgs)(partial.raw) };
+                            const block = responseBlocks.get(index);
+                            if (block)
+                                block.input = call.arguments;
                             blocks.delete(index);
                             if (jsonMode && call.name === JSON_MODE_TOOL) {
                                 text = jsonTextFrom([call], text);
@@ -152,6 +182,7 @@ class AnthropicAdapter {
             const hasTools = emittedTools.length > 0;
             yield { type: 'done', result: {
                     text,
+                    providerState: { provider: conn.provider, model: req.model, content: [...responseBlocks.entries()].sort(([a], [b]) => a - b).map(([, block]) => block) },
                     toolCalls: hasTools ? emittedTools : undefined,
                     finishReason: mapStop(stopReason, hasTools),
                     usage: inputTokens !== undefined || outputTokens !== undefined ? { inputTokens, outputTokens, estimated: false } : (0, tokens_js_1.estimatedUsage)((0, util_js_1.textFromMessages)(req.messages), text),
@@ -196,9 +227,15 @@ function body(req, jsonMode) {
         top_p: req.topP,
         stop_sequences: req.stopSequences,
         system,
-        messages: toAnthropicMessages(req.messages.filter((m) => m.role !== 'system')),
+        messages: toAnthropicMessages(req.messages.filter((m) => m.role !== 'system'), req.model),
         stream: true,
     };
+    if (req.responseFormat?.type === 'json' && modernModel(req.model) && req.responseFormat.schema) {
+        base.output_config = { format: { type: 'json_schema', schema: schemaFor(req) } };
+    }
+    if (req.responseFormat?.type === 'json' && modernModel(req.model) && !req.responseFormat.schema) {
+        base.system = [system, 'Return only valid JSON, without markdown fences or a preamble.'].filter(Boolean).join('\n\n');
+    }
     if (jsonMode) {
         // Forced-tool JSON mode: Anthropic has no response_format, so we make the
         // model answer through a single required tool whose input is the JSON we want.
@@ -219,7 +256,14 @@ function body(req, jsonMode) {
         // `budget_tokens < max_tokens` and rejects temperature/top_p alongside
         // thinking, so the budget is fitted under max_tokens (raising max_tokens
         // when the caller's value leaves no room) and the samplers are dropped.
-        if (req.reasoningEffort === 'none') {
+        if (modernModel(req.model)) {
+            const none = req.reasoningEffort === 'none';
+            if (none && alwaysThinking(req.model))
+                throw new errors_js_1.AIError('This Claude model cannot disable thinking; choose a reasoning effort instead.', { kind: 'invalid_request', provider: 'anthropic' });
+            base.thinking = { type: none ? (/^claude-sonnet-5-5(?:-|$)/.test(req.model) ? 'between_tools' : 'disabled') : 'adaptive' };
+            base.output_config = { ...(0, util_js_1.asRecord)(base.output_config), effort: none ? 'low' : req.reasoningEffort === 'minimal' ? 'low' : req.reasoningEffort };
+        }
+        else if (req.reasoningEffort === 'none') {
             base.thinking = { type: 'disabled' };
         }
         else {
@@ -234,14 +278,24 @@ function body(req, jsonMode) {
     }
     // providerOptions carries Anthropic-native fields (`thinking`, `metadata`,
     // top-level `cache_control` extras, `service_tier`, …) without a release.
-    return (0, util_js_1.applyProviderOptions)(base, req.providerOptions);
+    const result = (0, util_js_1.applyProviderOptions)(base, req.providerOptions, ['output_config']);
+    if (modernModel(req.model)) {
+        delete result.temperature;
+        delete result.top_p;
+        delete result.top_k;
+    }
+    const choice = (0, util_js_1.asRecord)(result.tool_choice);
+    if (noForcedTools(req.model) && (choice?.type === 'tool' || choice?.type === 'any')) {
+        throw new errors_js_1.AIError('This Claude model does not support forced tool choice; use auto or structured outputs.', { kind: 'invalid_request', provider: 'anthropic' });
+    }
+    return result;
 }
-function toAnthropicMessages(messages) {
+function toAnthropicMessages(messages, model) {
     const out = [];
     for (let index = 0; index < messages.length; index += 1) {
         const message = messages[index];
         if (message.role !== 'tool') {
-            out.push(toAnthropicMessage(message));
+            out.push(toAnthropicMessage(message, model));
             continue;
         }
         const content = [];
@@ -255,7 +309,10 @@ function toAnthropicMessages(messages) {
     }
     return out;
 }
-function toAnthropicMessage(m) {
+function toAnthropicMessage(m, model) {
+    if (m.role === 'assistant' && m.providerState?.provider === 'anthropic' && m.providerState.model === model) {
+        return { role: 'assistant', content: m.providerState.content };
+    }
     // Tool-role messages are handled by toAnthropicMessages' batching loop and
     // never reach here, so no tool branch is needed.
     // assistant turns that carried tool calls replay them as tool_use blocks,
@@ -320,7 +377,20 @@ function jsonTextFrom(toolCalls, fallback) {
 function mapStop(stop, hasTools) {
     if (stop === 'tool_use' && hasTools)
         return 'tool';
+    if (stop === 'refusal')
+        return 'content_filter';
     if (stop === 'max_tokens')
         return 'length';
     return 'stop';
 }
+/** Models released after Opus 4.6 use adaptive effort and reject sampling knobs.
+ * Unknown/custom IDs retain legacy behavior rather than guessing capabilities. */
+function modernModel(model) {
+    return /^claude-(?:opus-(?:4-[78]|5(?:-5)?)|sonnet-5(?:-5)?|haiku-5-5|(?:fable|mythos)-5(?:-1)?|mythos-preview)(?:-\d{8}|-latest)?$/.test(model);
+}
+function alwaysThinking(model) {
+    return /^claude-(?:fable-|mythos-|opus-5-5(?:-|$))/.test(model);
+}
+function noForcedTools(model) {
+    return /^claude-(?:(?:opus|sonnet)-5-5(?:-|$)|(?:fable|mythos)-5-1(?:-|$))/.test(model);
+}

package/dist/cjs/agent/loop.js

@@ -35,6 +35,7 @@ async function* run(opts, resolveResult) {
             yield emit(opts, { type: 'step_start', step });
             const calls = [];
             let stepText = '';
+            let providerState;
             let streamFailure;
             // In promptJson mode a tool directive must not leak into the visible
             // stream, so directive-looking text is withheld from `delta` events (still
@@ -68,6 +69,7 @@ async function* run(opts, resolveResult) {
                 if (event.type === 'error')
                     streamFailure = event.error;
                 if (event.type === 'done') {
+                    providerState = event.result.providerState;
                     usage = usage ? (0, tokens_js_1.mergeUsage)(usage, event.result.usage) : event.result.usage;
                     if (toolMode === 'promptJson' && calls.length === 0)
                         calls.push(...callsFromPromptJson(stepText));
@@ -88,7 +90,7 @@ async function* run(opts, resolveResult) {
             finalText = stepText;
             messages.push(toolMode === 'promptJson'
                 ? { role: 'assistant', content: stepText }
-                : { role: 'assistant', content: stepText, toolCalls: calls.length ? calls : undefined });
+                : { role: 'assistant', content: stepText, providerState, toolCalls: calls.length ? calls : undefined });
             if (calls.length === 0)
                 return yield* yieldDone('finished');
             for (const call of calls) {

package/dist/cjs/handler.js

@@ -86,7 +86,7 @@ class AIHandler {
                             }
                             continue;
                         }
-                        if (event.type === 'delta' || event.type === 'tool_call')
+                        if (event.type === 'delta' || event.type === 'tool_call' || event.type === 'reasoning')
                             emittedOutput = true;
                         if (event.type === 'delta' && stripper) {
                             // Inline reasoning never reaches `delta`; it rides the reasoning channel like a

package/dist/handler.js

@@ -82,7 +82,7 @@ export class AIHandler {
                             }
                             continue;
                         }
-                        if (event.type === 'delta' || event.type === 'tool_call')
+                        if (event.type === 'delta' || event.type === 'tool_call' || event.type === 'reasoning')
                             emittedOutput = true;
                         if (event.type === 'delta' && stripper) {
                             // Inline reasoning never reaches `delta`; it rides the reasoning channel like a

package/dist/types.d.ts

@@ -7,9 +7,17 @@ export interface ContentPart {
     imageBase64?: string;
     mimeType?: string;
 }
+/** Opaque provider response content, for replay within the same model/tool workflow.
+ * Keep it unmodified; never include it in telemetry or display it as answer text. */
+export interface ProviderState {
+    provider: string;
+    model: string;
+    content: Record<string, unknown>[];
+}
 export interface ChatMessage {
     role: Role;
     content: string | ContentPart[];
+    providerState?: ProviderState;
     toolCalls?: ToolCall[];
     toolCallId?: string;
     name?: string;
@@ -130,6 +138,7 @@ export interface Usage {
 }
 export interface ChatResult {
     text: string;
+    providerState?: ProviderState;
     toolCalls?: ToolCall[];
     finishReason: 'stop' | 'length' | 'tool' | 'content_filter' | 'error' | 'canceled';
     usage: Usage;

package/nugget/VERSION.txt

@@ -1,2 +1,2 @@
-0.7.0
-e0e4c28d06eb5e7474c628652e1c56fa5f29ce41c24428270895d7af3b8cd75e
+0.7.3
+f6bc628594f887826274e9019dff75be686d5043e9823ccdbb0a4d9765552752

package/nugget/dist/adapters/engines/anthropic.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"anthropic.d.ts","sourceRoot":"","sources":["../../../src/adapters/engines/anthropic.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAe,WAAW,EAAE,UAAU,EAAE,SAAS,EAAE,eAAe,EAAE,kBAAkB,EAAE,WAAW,EAAY,MAAM,gBAAgB,CAAC;AAMlJ,qBAAa,gBAAiB,YAAW,eAAe;IACtD,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAC;gBACd,QAAQ,EAAE,MAAM;IAItB,IAAI,CAAC,IAAI,EAAE,kBAAkB,EAAE,GAAG,EAAE,WAAW,GAAG,OAAO,CAAC,UAAU,CAAC;IAUpE,MAAM,CAAC,IAAI,EAAE,kBAAkB,EAAE,GAAG,EAAE,WAAW,GAAG,aAAa,CAAC,WAAW,CAAC;IA2HrF;;;;OAIG;IACG,UAAU,CAAC,IAAI,EAAE,kBAAkB,GAAG,OAAO,CAAC,SAAS,EAAE,CAAC;CAajE"}
+{"version":3,"file":"anthropic.d.ts","sourceRoot":"","sources":["../../../src/adapters/engines/anthropic.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAe,WAAW,EAAE,UAAU,EAAE,SAAS,EAAE,eAAe,EAAE,kBAAkB,EAAE,WAAW,EAAY,MAAM,gBAAgB,CAAC;AAMlJ,qBAAa,gBAAiB,YAAW,eAAe;IACtD,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAC;gBACd,QAAQ,EAAE,MAAM;IAItB,IAAI,CAAC,IAAI,EAAE,kBAAkB,EAAE,GAAG,EAAE,WAAW,GAAG,OAAO,CAAC,UAAU,CAAC;IAUpE,MAAM,CAAC,IAAI,EAAE,kBAAkB,EAAE,GAAG,EAAE,WAAW,GAAG,aAAa,CAAC,WAAW,CAAC;IAmJrF;;;;OAIG;IACG,UAAU,CAAC,IAAI,EAAE,kBAAkB,GAAG,OAAO,CAAC,SAAS,EAAE,CAAC;CAajE"}