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/web/src/api/client.ts

@@ -34,6 +34,12 @@ export interface AgentSessionInfo {
   status: string;
   has_session: boolean;
   last_active_at: string | null;
+  // v2.6.8 per-(chat,agent) running token/cost totals (sampling-streamjson-tokens
+  // #8). input_tokens/output_tokens are BIGINT and may arrive as strings; cost is
+  // DOUBLE. AgentComposerBar coerces with Number(...) before rendering.
+  input_tokens: number;
+  output_tokens: number;
+  cost: number;
 }
 
 // write-edit-robustness #4: a pre-turn worktree snapshot anchored to an

apps/web/src/components/AgentComposerBar.tsx

@@ -185,6 +185,14 @@ interface Props {
   hasPriorTurn?: boolean;
 }
 
+// Condensed token count: 950 → "950", 12_400 → "12.4K", 3_200_000 → "3.2M".
+// Sub-1000 stays exact; thousands/millions get one decimal, trailing .0 trimmed.
+function abbrevTokens(n: number): string {
+  if (!Number.isFinite(n) || n < 1000) return String(Math.max(0, Math.round(n)));
+  if (n < 1_000_000) return `${(n / 1000).toFixed(1).replace(/\.0$/, '')}K`;
+  return `${(n / 1_000_000).toFixed(1).replace(/\.0$/, '')}M`;
+}
+
 // Relative-time formatter for the resumed-chip title (e.g. "3m ago").
 function relativeTime(iso: string | null): string {
   if (!iso) return 'unknown';
@@ -353,6 +361,21 @@ export function AgentComposerBar({ projectPath, value, onChange, onProviderComma
           : { label: 'new session', title: `${value.provider} starts a fresh session this turn` }
       : null;
 
+  // sampling-streamjson-tokens #8: condensed per-(chat,agent) token/cost readout
+  // beside the session chip. Coerce — input/output are BIGINT (string over wire).
+  // Hidden when no session row or all totals are zero (e.g. native boocode, which
+  // holds no agent_sessions row, or a provider that hasn't run yet).
+  const usageReadout = (() => {
+    if (!sessionChip || !sessionRow) return null;
+    const inTok = Number(sessionRow.input_tokens) || 0;
+    const outTok = Number(sessionRow.output_tokens) || 0;
+    const cost = Number(sessionRow.cost) || 0;
+    if (inTok <= 0 && outTok <= 0 && cost <= 0) return null;
+    const parts = [`${abbrevTokens(inTok)} in`, `${abbrevTokens(outTok)} out`];
+    if (cost > 0) parts.push(`$${cost.toFixed(2)}`);
+    return parts.join(' · ');
+  })();
+
   return (
     <div className="flex flex-wrap items-center gap-1 px-2 py-1 border-b border-border bg-muted/20 shrink-0">
       <CompactPicker
@@ -374,6 +397,14 @@ export function AgentComposerBar({ projectPath, value, onChange, onProviderComma
           {sessionChip.label}
         </span>
       )}
+      {usageReadout && (
+        <span
+          className="text-[10px] text-muted-foreground tabular-nums whitespace-nowrap shrink-0"
+          title="Tokens in · out · cost for this agent session"
+        >
+          {usageReadout}
+        </span>
+      )}
       <CompactPicker
         label="Mode"
         value={value.modeId ?? ''}