fix(kiro): normalize dashboard thinking intensity models

Strip the generic dashboard model(level) suffix before resolving Kiro
synthetic -thinking/-agentic variants so the upstream request no longer
carries an invalid parenthesized model id. Map explicit levels to native
Kiro effort fields only for supported Claude/GPT model families, and stop
advertising native levels for unsupported legacy Kiro models. Applies to
both OpenAI→Kiro and direct Claude→Kiro routes.

open-sse/config/kiroConstants.js

@@ -15,7 +15,7 @@
  * fiction. The suffix is stripped before the request leaves this process.
  */
 
-import { extractThinking } from "../translator/concerns/thinkingUnified.js";
+import { extractThinking, parseSuffix } from "../translator/concerns/thinkingUnified.js";
 import { effortToBudget } from "../translator/concerns/thinking.js";
 
 export const KIRO_AGENTIC_SUFFIX = "-agentic";
@@ -40,6 +40,39 @@ export function resolveDefaultProfileArn(authMethod) {
 
 export const KIRO_THINKING_BUDGET_DEFAULT = 16000;
 
+/**
+ * Resolve a Kiro model after consuming the generic model(level) suffix.
+ * The suffix is a 9router request override, not part of Kiro's upstream model id.
+ */
+export function resolveKiroModelIntent(model) {
+  const { cleanModel, override } = parseSuffix(model);
+  return {
+    model: cleanModel,
+    ...resolveKiroModel(cleanModel),
+    thinkingOverride: override,
+  };
+}
+
+/** Apply a parsed model(level) override without mutating the caller's body. */
+export function applyKiroThinkingOverride(body, override) {
+  if (!override) return body;
+
+  const next = { ...body };
+  if (override.mode === "budget") {
+    delete next.output_config;
+    delete next.reasoning_effort;
+    delete next.reasoning;
+    next.thinking = { type: "enabled", budget_tokens: override.budget };
+    return next;
+  }
+
+  next.output_config = {
+    ...(body.output_config || {}),
+    effort: override.mode === "level" ? override.level : override.mode,
+  };
+  return next;
+}
+
 export const KIRO_AGENTIC_SYSTEM_PROMPT = `
 # CRITICAL: CHUNKED WRITE PROTOCOL (MANDATORY)
 

open-sse/providers/thinkingLevels.js

@@ -2,6 +2,7 @@
 // Reuses capabilities.js (thinkingFormat/canDisable) so this file only maps format→levels (DRY).
 import { getCapabilitiesForModel } from "./capabilities.js";
 import { matchPattern } from "./pricing.js";
+import { resolveKiroEffortPath } from "../config/kiroConstants.js";
 
 // Shared level sets (deduped) — verified against provider docs + wire in thinkingUnified.applyFormat.
 const L = {
@@ -39,6 +40,7 @@ const PATTERN_THINKING = [
 
 // Returns valid thinking levels for a model, or null when the model has no reasoning.
 export function getThinkingLevels(provider, model) {
+  if (provider === "kiro" && resolveKiroEffortPath(model) === null) return null;
   const caps = getCapabilitiesForModel(provider, model);
   if (!caps.reasoning) return null;
   const hit = PATTERN_THINKING.find((p) => matchPattern(p.pattern, model));

open-sse/translator/request/claude-to-kiro.js

@@ -27,7 +27,8 @@ import { FORMATS } from "../formats.js";
 import { applyKiroSessionReplay } from "../../utils/kiroSessionReplay.js";
 import { resolveContinuationId, resolveSessionIdentity } from "../../utils/sessionManager.js";
 import {
-  resolveKiroModel,
+  resolveKiroModelIntent,
+  applyKiroThinkingOverride,
   resolveKiroThinkingBudget,
   buildThinkingSystemPrefix,
   KIRO_AGENTIC_SYSTEM_PROMPT,
@@ -389,10 +390,12 @@ export function claudeToKiroRequest(model, body, stream, credentials) {
   const temperature = body.temperature;
   const topP = body.top_p;
 
-  const { upstream: upstreamModel, agentic } = resolveKiroModel(model);
-  const thinkingBudget = resolveKiroThinkingBudget(body, credentials?.rawHeaders, model);
-  const additionalModelRequestFields = buildKiroAdditionalModelRequestFieldsForModel(body, upstreamModel);
-  const usesNativeGptEffort = usesKiroNativeGptEffort(body, upstreamModel);
+  const modelIntent = resolveKiroModelIntent(model);
+  const { upstream: upstreamModel, agentic } = modelIntent;
+  const thinkingBody = applyKiroThinkingOverride(body, modelIntent.thinkingOverride);
+  const thinkingBudget = resolveKiroThinkingBudget(thinkingBody, credentials?.rawHeaders, modelIntent.model);
+  const additionalModelRequestFields = buildKiroAdditionalModelRequestFieldsForModel(thinkingBody, upstreamModel);
+  const usesNativeGptEffort = usesKiroNativeGptEffort(thinkingBody, upstreamModel);
 
   // Guard 1: no client tools → flatten all tool interactions to text.
   if (!clientProvidedTools) {

open-sse/translator/request/openai-to-kiro.js

@@ -8,7 +8,8 @@ import { v4 as uuidv4 } from "uuid";
 import { applyKiroSessionReplay } from "../../utils/kiroSessionReplay.js";
 import { resolveContinuationId, resolveSessionIdentity } from "../../utils/sessionManager.js";
 import {
-  resolveKiroModel,
+  resolveKiroModelIntent,
+  applyKiroThinkingOverride,
   resolveKiroThinkingBudget,
   buildThinkingSystemPrefix,
   KIRO_AGENTIC_SYSTEM_PROMPT,
@@ -524,10 +525,12 @@ export function openaiToKiroRequest(model, body, stream, credentials) {
   const temperature = body.temperature;
   const topP = body.top_p;
 
-  const { upstream: upstreamModel, agentic } = resolveKiroModel(model);
-  const thinkingBudget = resolveKiroThinkingBudget(body, credentials?.rawHeaders, model);
-  const additionalModelRequestFields = buildKiroAdditionalModelRequestFieldsForModel(body, upstreamModel);
-  const usesNativeGptEffort = usesKiroNativeGptEffort(body, upstreamModel);
+  const modelIntent = resolveKiroModelIntent(model);
+  const { upstream: upstreamModel, agentic } = modelIntent;
+  const thinkingBody = applyKiroThinkingOverride(body, modelIntent.thinkingOverride);
+  const thinkingBudget = resolveKiroThinkingBudget(thinkingBody, credentials?.rawHeaders, modelIntent.model);
+  const additionalModelRequestFields = buildKiroAdditionalModelRequestFieldsForModel(thinkingBody, upstreamModel);
+  const usesNativeGptEffort = usesKiroNativeGptEffort(thinkingBody, upstreamModel);
 
   const { history, currentMessage } = convertMessages(messages, tools, upstreamModel);