feat: sampling knobs + live PTY stream-json + token UI (v2.7.3)

Three small wins from boocode_code_review_v2 §1 #11/#7/#8.

#11 sampling knobs: top_n_sigma + dry_* family as first-class Agent fields,
threaded into the request body via providerOptions.openaiCompatible. Fixes a
latent bug — top_k (rejected by the AI-SDK provider) and min_p (never passed to
streamText) were dead on the wire; both now route through the same channel.
--reasoning-budget documented in data/AGENTS.md.

#7 live PTY stream-json: new stream-json-parser.ts line-buffers qwen/claude
NDJSON and emits text/reasoning/tool frames live + persists, with a fallback to
the old opaque slice. claude gets --output-format stream-json --verbose.

#8 token UI: agent_sessions input/output_tokens/cost now flow through the route
+ type and render beside the AgentComposerBar session chip.

Built by 3 parallel agents. Server 523 + coder 245 tests passing; builds + web
tsc clean. Builds on v2.7.2. openspec sampling-streamjson-tokens.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

apps/server/src/services/inference/sentinel-summaries.ts

@@ -86,7 +86,7 @@ export async function runCapHitSummary(
       ctx,
       session.model,
       messages,
-      { tools: null, temperature: agent?.temperature, top_p: agent?.top_p ?? undefined, top_k: agent?.top_k ?? undefined, min_p: agent?.min_p ?? undefined, presence_penalty: agent?.presence_penalty ?? undefined },
+      { tools: null, temperature: agent?.temperature, top_p: agent?.top_p ?? undefined, top_k: agent?.top_k ?? undefined, min_p: agent?.min_p ?? undefined, presence_penalty: agent?.presence_penalty ?? undefined, top_n_sigma: agent?.top_n_sigma ?? undefined, dry_multiplier: agent?.dry_multiplier ?? undefined, dry_base: agent?.dry_base ?? undefined, dry_allowed_length: agent?.dry_allowed_length ?? undefined, dry_penalty_last_n: agent?.dry_penalty_last_n ?? undefined },
       (delta) => {
         accumulated += delta;
         ctx.publish(sessionId, {
@@ -346,7 +346,7 @@ export async function runDoomLoopSummary(
       ctx,
       session.model,
       messages,
-      { tools: null, temperature: agent?.temperature, top_p: agent?.top_p ?? undefined, top_k: agent?.top_k ?? undefined, min_p: agent?.min_p ?? undefined, presence_penalty: agent?.presence_penalty ?? undefined },
+      { tools: null, temperature: agent?.temperature, top_p: agent?.top_p ?? undefined, top_k: agent?.top_k ?? undefined, min_p: agent?.min_p ?? undefined, presence_penalty: agent?.presence_penalty ?? undefined, top_n_sigma: agent?.top_n_sigma ?? undefined, dry_multiplier: agent?.dry_multiplier ?? undefined, dry_base: agent?.dry_base ?? undefined, dry_allowed_length: agent?.dry_allowed_length ?? undefined, dry_penalty_last_n: agent?.dry_penalty_last_n ?? undefined },
       (delta) => {
         accumulated += delta;
         ctx.publish(sessionId, {
@@ -545,7 +545,7 @@ export async function runStepCapSummary(
       ctx,
       session.model,
       messages,
-      { tools: null, temperature: agent?.temperature, top_p: agent?.top_p ?? undefined, top_k: agent?.top_k ?? undefined, min_p: agent?.min_p ?? undefined, presence_penalty: agent?.presence_penalty ?? undefined },
+      { tools: null, temperature: agent?.temperature, top_p: agent?.top_p ?? undefined, top_k: agent?.top_k ?? undefined, min_p: agent?.min_p ?? undefined, presence_penalty: agent?.presence_penalty ?? undefined, top_n_sigma: agent?.top_n_sigma ?? undefined, dry_multiplier: agent?.dry_multiplier ?? undefined, dry_base: agent?.dry_base ?? undefined, dry_allowed_length: agent?.dry_allowed_length ?? undefined, dry_penalty_last_n: agent?.dry_penalty_last_n ?? undefined },
       (delta) => {
         accumulated += delta;
         ctx.publish(sessionId, {

apps/server/src/services/inference/stream-phase.ts

@@ -33,6 +33,39 @@ interface StreamOptions {
   top_k?: number | null;
   min_p?: number | null;
   presence_penalty?: number | null;
+  // v2.6 sampling-streamjson-tokens (#11): llama.cpp sampler extensions. These
+  // are NOT standard AI-SDK streamText options and are NOT serialized by the
+  // openai-compatible provider's standardized-settings path (topK is even
+  // explicitly dropped with an "unsupported feature: topK" warning). They reach
+  // llama-server only via providerOptions.openaiCompatible (see buildSamplerProviderOptions).
+  top_n_sigma?: number | null;
+  dry_multiplier?: number | null;
+  dry_base?: number | null;
+  dry_allowed_length?: number | null;
+  dry_penalty_last_n?: number | null;
+}
+
+// v2.6 #11: build the providerOptions.openaiCompatible extraBody object for the
+// llama.cpp sampler extensions. @ai-sdk/openai-compatible (2.0.47) merges every
+// non-reserved key under providerOptions.openaiCompatible straight into the
+// chat-completion request body (see its getArgs: the Object.fromEntries spread
+// filtered against openaiCompatibleLanguageModelChatOptions.shape). This is the
+// ONLY working passthrough for these params:
+//   - top_k / min_p were latently dropped before this: top_k was passed as the
+//     AI-SDK `topK` setting which the openai-compatible provider rejects as
+//     unsupported; min_p was never passed to streamText at all.
+//   - top_n_sigma + the dry_* family have no AI-SDK equivalent.
+// Keys use llama-server's snake_case body names so they land verbatim.
+function buildSamplerProviderOptions(opts: StreamOptions): Record<string, number> | undefined {
+  const body: Record<string, number> = {};
+  if (typeof opts.top_k === 'number') body.top_k = opts.top_k;
+  if (typeof opts.min_p === 'number') body.min_p = opts.min_p;
+  if (typeof opts.top_n_sigma === 'number') body.top_n_sigma = opts.top_n_sigma;
+  if (typeof opts.dry_multiplier === 'number') body.dry_multiplier = opts.dry_multiplier;
+  if (typeof opts.dry_base === 'number') body.dry_base = opts.dry_base;
+  if (typeof opts.dry_allowed_length === 'number') body.dry_allowed_length = opts.dry_allowed_length;
+  if (typeof opts.dry_penalty_last_n === 'number') body.dry_penalty_last_n = opts.dry_penalty_last_n;
+  return Object.keys(body).length > 0 ? body : undefined;
 }
 
 // v1.13.1-A: convert BooCode's OpenAI-shaped history into AI SDK
@@ -195,6 +228,14 @@ export async function streamCompletion(
     return toolCall;
   };
 
+  // v2.6 #11: llama.cpp sampler extensions (top_k, min_p, top_n_sigma, dry_*)
+  // ride providerOptions.openaiCompatible — they are NOT standardized streamText
+  // settings. NB: top_k used to be passed below as the AI-SDK `topK` setting;
+  // the openai-compatible provider dropped it with an "unsupported feature: topK"
+  // warning and min_p was never wired at all, so both were dead on the wire
+  // before this. They now go through the same extraBody path as the new params.
+  const samplerBody = buildSamplerProviderOptions(opts);
+
   const result = streamText({
     model: upstreamModel(ctx.config, model, agent ?? null),
     messages: aiMessages,
@@ -203,8 +244,8 @@ export async function streamCompletion(
       : {}),
     ...(typeof opts.temperature === 'number' ? { temperature: opts.temperature } : {}),
     ...(typeof opts.top_p === 'number' ? { topP: opts.top_p } : {}),
-    ...(typeof opts.top_k === 'number' ? { topK: opts.top_k } : {}),
     ...(typeof opts.presence_penalty === 'number' ? { presencePenalty: opts.presence_penalty } : {}),
+    ...(samplerBody ? { providerOptions: { openaiCompatible: samplerBody } } : {}),
     abortSignal: signal,
   });
 
@@ -398,6 +439,12 @@ export async function executeStreamPhase(
   const effectiveTopK = agent?.top_k ?? undefined;
   const effectiveMinP = agent?.min_p ?? undefined;
   const effectivePresencePenalty = agent?.presence_penalty ?? undefined;
+  // v2.6 #11: llama.cpp sampler extensions, threaded the same way as top_k/min_p.
+  const effectiveTopNSigma = agent?.top_n_sigma ?? undefined;
+  const effectiveDryMultiplier = agent?.dry_multiplier ?? undefined;
+  const effectiveDryBase = agent?.dry_base ?? undefined;
+  const effectiveDryAllowedLength = agent?.dry_allowed_length ?? undefined;
+  const effectiveDryPenaltyLastN = agent?.dry_penalty_last_n ?? undefined;
 
   // v1.12.2: ctx_max lookup is cached after the first hit per model, so this
   // is a Map probe in steady state. We capture nCtx once at the top of the
@@ -435,7 +482,19 @@ export async function executeStreamPhase(
       ctx,
       session.model,
       messages,
-      { tools: effectiveTools, temperature: effectiveTemperature, top_p: effectiveTopP, top_k: effectiveTopK, min_p: effectiveMinP, presence_penalty: effectivePresencePenalty },
+      {
+        tools: effectiveTools,
+        temperature: effectiveTemperature,
+        top_p: effectiveTopP,
+        top_k: effectiveTopK,
+        min_p: effectiveMinP,
+        presence_penalty: effectivePresencePenalty,
+        top_n_sigma: effectiveTopNSigma,
+        dry_multiplier: effectiveDryMultiplier,
+        dry_base: effectiveDryBase,
+        dry_allowed_length: effectiveDryAllowedLength,
+        dry_penalty_last_n: effectiveDryPenaltyLastN,
+      },
       (delta) => {
         state.accumulated += delta;
         ctx.publish(sessionId, {