jeo-code 0.6.28 → 0.6.29

package/CHANGELOG.md

@@ -6,6 +6,19 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 The README mirrors the latest 5 entries — regenerate with `bun run changelog:sync`.
 
+## [0.6.29] - 2026-06-19
+_Signature-only thinking-block replay (Anthropic opus-4-7/4-8), plus a tmux mouse-flood memory guard confirming `jeo --tmux` does not leak._
+
+### Fixed
+- **Anthropic thinking-block replay now covers signature-only artifacts.** Newer Opus models (opus-4-7/opus-4-8) think internally — tokens billed, a valid `signature` present — but return empty thinking text. The cross-turn replay required both `signature` AND `text`, so those models' reasoning was dropped between steps. Replay now sends a signed `thinking` block whenever a `signature` (or `redacted`) is present (text defaults to `""`), restoring multi-step reasoning continuity for signature-only models. API-key requests also send the `interleaved-thinking` + `prompt-caching-scope` betas so thinking+tools and scoped caching work outside OAuth.
+
+### Added
+- **`claude-opus-4-7` catalogued** (FULL thinking, 200k ctx) and a dynamic context-window fallback for uncatalogued ids (claude 200k / gpt-5 400k / gemini-3 1M).
+- **tmux mouse-report-flood memory guard** (`test/mouse-report-filter.test.ts`): 100k SGR mouse-move reports through `queuePromptInputChunk` leave the prompt queue at zero accumulation — the regression guard for the "`jeo --tmux` slows down over time" concern.
+
+### Verified
+- **`jeo --tmux` has no bun memory leak.** The in-process lifecycle probe (`scripts/mem-probe.ts`, 3000 turns) reports a per-turn heap slope of ≈0 (returns to baseline, exit-listeners flat); a real `jeo --tmux` process plateaus in RSS under sustained mouse/resize/keystroke churn instead of climbing; and mouse reports are filtered (not buffered) with `activityLog` bounded to a 200-entry per-turn ring.
+
 ## [0.6.28] - 2026-06-19
 _Signed thinking-block replay: native reasoning is now sent BACK to providers across steps/turns, restoring multi-step reasoning continuity (gajae parity)._
 

package/README.ja.md

@@ -200,11 +200,11 @@ CI は `.github/workflows/npm-publish.yml` で公開します — GitHub リリ
 ## 変更履歴 (Changelog)
 
 <!-- CHANGELOG:START (auto-generated from CHANGELOG.md — run `bun run changelog:sync`) -->
+- **[0.6.29]** (2026-06-19) — Signature-only thinking-block replay (Anthropic opus-4-7/4-8), plus a tmux mouse-flood memory guard confirming `jeo --tmux` does not leak.
 - **[0.6.28]** (2026-06-19) — Signed thinking-block replay: native reasoning is now sent BACK to providers across steps/turns, restoring multi-step reasoning continuity (gajae parity).
 - **[0.6.27]** (2026-06-19) — Ponytail pass on the reasoning-tier mapper, plus a real-tmux verification of `jeo --tmux`.
 - **[0.6.26]** (2026-06-19) — The forge emblem is redrawn again as the mascot crayfish, foregrounding its signature pincer claws (집게).
 - **[0.6.25]** (2026-06-19) — Reasoning works at every thinking level (gajae parity), and the forge emblem is redrawn as the neon-lens coding wizard.
-- **[0.6.24]** (2026-06-19) — `/provider` opens an interactive onboarding selector (OAuth vs API-compatible), and OpenAI-compatible backends gain per-vendor native-reasoning formats.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.ko.md

@@ -200,11 +200,11 @@ CI는 `.github/workflows/npm-publish.yml`로 배포합니다 — GitHub 릴리
 ## 변경 이력 (Changelog)
 
 <!-- CHANGELOG:START (auto-generated from CHANGELOG.md — run `bun run changelog:sync`) -->
+- **[0.6.29]** (2026-06-19) — Signature-only thinking-block replay (Anthropic opus-4-7/4-8), plus a tmux mouse-flood memory guard confirming `jeo --tmux` does not leak.
 - **[0.6.28]** (2026-06-19) — Signed thinking-block replay: native reasoning is now sent BACK to providers across steps/turns, restoring multi-step reasoning continuity (gajae parity).
 - **[0.6.27]** (2026-06-19) — Ponytail pass on the reasoning-tier mapper, plus a real-tmux verification of `jeo --tmux`.
 - **[0.6.26]** (2026-06-19) — The forge emblem is redrawn again as the mascot crayfish, foregrounding its signature pincer claws (집게).
 - **[0.6.25]** (2026-06-19) — Reasoning works at every thinking level (gajae parity), and the forge emblem is redrawn as the neon-lens coding wizard.
-- **[0.6.24]** (2026-06-19) — `/provider` opens an interactive onboarding selector (OAuth vs API-compatible), and OpenAI-compatible backends gain per-vendor native-reasoning formats.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.md

@@ -200,11 +200,11 @@ Required npm token permissions (repository secret `NPM_TOKEN`):
 ## Changelog
 
 <!-- CHANGELOG:START (auto-generated from CHANGELOG.md — run `bun run changelog:sync`) -->
+- **[0.6.29]** (2026-06-19) — Signature-only thinking-block replay (Anthropic opus-4-7/4-8), plus a tmux mouse-flood memory guard confirming `jeo --tmux` does not leak.
 - **[0.6.28]** (2026-06-19) — Signed thinking-block replay: native reasoning is now sent BACK to providers across steps/turns, restoring multi-step reasoning continuity (gajae parity).
 - **[0.6.27]** (2026-06-19) — Ponytail pass on the reasoning-tier mapper, plus a real-tmux verification of `jeo --tmux`.
 - **[0.6.26]** (2026-06-19) — The forge emblem is redrawn again as the mascot crayfish, foregrounding its signature pincer claws (집게).
 - **[0.6.25]** (2026-06-19) — Reasoning works at every thinking level (gajae parity), and the forge emblem is redrawn as the neon-lens coding wizard.
-- **[0.6.24]** (2026-06-19) — `/provider` opens an interactive onboarding selector (OAuth vs API-compatible), and OpenAI-compatible backends gain per-vendor native-reasoning formats.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.zh.md

@@ -200,11 +200,11 @@ CI 通过 `.github/workflows/npm-publish.yml` 发布 — GitHub 发布 release
 ## 更新日志 (Changelog)
 
 <!-- CHANGELOG:START (auto-generated from CHANGELOG.md — run `bun run changelog:sync`) -->
+- **[0.6.29]** (2026-06-19) — Signature-only thinking-block replay (Anthropic opus-4-7/4-8), plus a tmux mouse-flood memory guard confirming `jeo --tmux` does not leak.
 - **[0.6.28]** (2026-06-19) — Signed thinking-block replay: native reasoning is now sent BACK to providers across steps/turns, restoring multi-step reasoning continuity (gajae parity).
 - **[0.6.27]** (2026-06-19) — Ponytail pass on the reasoning-tier mapper, plus a real-tmux verification of `jeo --tmux`.
 - **[0.6.26]** (2026-06-19) — The forge emblem is redrawn again as the mascot crayfish, foregrounding its signature pincer claws (집게).
 - **[0.6.25]** (2026-06-19) — Reasoning works at every thinking level (gajae parity), and the forge emblem is redrawn as the neon-lens coding wizard.
-- **[0.6.24]** (2026-06-19) — `/provider` opens an interactive onboarding selector (OAuth vs API-compatible), and OpenAI-compatible backends gain per-vendor native-reasoning formats.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jeo-code",
-  "version": "0.6.28",
+  "version": "0.6.29",
   "description": "Clean, highly optimized AI coding agent using spec-first loop",
   "type": "module",
   "main": "src/cli.ts",

package/src/ai/model-catalog.ts

@@ -37,6 +37,8 @@ const STD: ThinkLevel[] = ["minimal", "low", "medium", "high"];
 export const ANTIGRAVITY_MODELS = [
   "claude-opus-4-5-thinking",
   "claude-opus-4-6-thinking",
+  "claude-opus-4-7",
+  "claude-opus-4-7-thinking",
   "claude-opus-4-8",
   "claude-opus-4-8-thinking",
   "claude-sonnet-4-5",
@@ -52,6 +54,7 @@ export const ANTIGRAVITY_MODELS = [
   "gemini-3.1-pro-high",
   "gemini-3.1-pro-low",
   "gpt-oss-120b-medium",
+  "gpt-5.5",
 ] as const;
 
 /** A curated set of common public models with their documented capabilities. */
@@ -62,9 +65,13 @@ export const MODEL_CATALOG: readonly CatalogModel[] = [
   { canonical: "claude-sonnet-4-5", provider: "anthropic", providerModel: "claude-sonnet-4-5-20250929", contextTokens: 200_000, maxOutputTokens: 64_000, thinking: FULL, images: true },
   { canonical: "claude-opus-4-1", provider: "anthropic", providerModel: "claude-opus-4-1-20250805", contextTokens: 200_000, maxOutputTokens: 32_000, thinking: FULL, images: true },
   { canonical: "claude-opus-4-5", provider: "anthropic", providerModel: "claude-opus-4-5-20251101", contextTokens: 200_000, maxOutputTokens: 64_000, thinking: FULL, images: true },
-  // NOTE: confirm exact dated provider ids when these ship publicly; the family
-  // heuristic in `catalogMetadata` keeps reasoning working even before that.
+  // NOTE: opus-4-7 accepts extended thinking but currently returns 0 thinking tokens
+  // (model-internal, no visible thought). opus-4-8 thinks internally (tokens billed,
+  // signature present) but returns empty thinking text. Both are FULL-capable in the
+  // catalog so the budget is always sent — the nativizable path handles signature-only
+  // artifacts for cross-turn continuity.
   { canonical: "claude-opus-4-6", provider: "anthropic", providerModel: "claude-opus-4-6", contextTokens: 200_000, maxOutputTokens: 64_000, thinking: FULL, images: true },
+  { canonical: "claude-opus-4-7", provider: "anthropic", providerModel: "claude-opus-4-7", contextTokens: 200_000, maxOutputTokens: 64_000, thinking: FULL, images: true },
   { canonical: "claude-opus-4-8", provider: "anthropic", providerModel: "claude-opus-4-8", contextTokens: 200_000, maxOutputTokens: 64_000, thinking: FULL, images: true },
   // OpenAI
   { canonical: "gpt-4o", provider: "openai", providerModel: "gpt-4o", contextTokens: 128_000, maxOutputTokens: 16_384, thinking: [], images: true },
@@ -96,9 +103,9 @@ export const MODEL_CATALOG: readonly CatalogModel[] = [
     canonical: `antigravity/${id}`,
     provider: "antigravity",
     providerModel: id,
-    contextTokens: id.includes("claude") ? 200_000 : id.includes("gemini-3") ? 1_000_000 : 1_000_000,
-    maxOutputTokens: id.includes("claude") ? 64_000 : 65_536,
-    thinking: id.includes("thinking") || id.includes("-high") || id.includes("-low") || id.includes("gemini-3") ? FULL : STD,
+    contextTokens: id.includes("claude") ? 200_000 : id.startsWith("gpt-5") ? 400_000 : id.includes("gemini-3") ? 1_000_000 : 1_000_000,
+    maxOutputTokens: id.includes("claude") ? 64_000 : id.startsWith("gpt-5") ? 128_000 : 65_536,
+    thinking: id.includes("thinking") || id.includes("-high") || id.includes("-low") || id.includes("gemini-3") || id.startsWith("gpt-5") ? FULL : STD,
     images: !id.includes("gpt-oss"),
     company: id.includes("claude") ? "Anthropic via Antigravity" : id.includes("gpt") ? "OpenAI via Antigravity" : "Google Antigravity",
   })),

package/src/ai/providers/anthropic.ts

@@ -11,6 +11,12 @@ const DEPRECATED_TEMPERATURE = "`temperature` is deprecated for this model.";
 const CLAUDE_CODE_VERSION = "2.1.63";
 const CLAUDE_CODE_SYSTEM_INSTRUCTION = "You are a Claude agent, built on Anthropic's Claude Agent SDK.";
 const CLAUDE_BILLING_HEADER_PREFIX = "x-anthropic-billing-header:";
+/** Betas needed for API-key requests: interleaved-thinking enables thinking+tools,
+ *  prompt-caching-scope gives scoped cache breakpoints. */
+const ANTHROPIC_API_KEY_BETA = [
+  "interleaved-thinking-2025-05-14",
+  "prompt-caching-scope-2026-01-05",
+].join(",");
 const ANTHROPIC_OAUTH_BETA = [
   "claude-code-20250219",
   "oauth-2025-04-20",
@@ -99,7 +105,7 @@ type AnthropicMessage = { role: string; content: string | AnthropicContentBlock[
 export function anthropicNativizable(m: Message, model: string, thinkingEnabled: boolean): boolean {
   return thinkingEnabled
     && !!m.toolUse?.length
-    && !!m.reasoningArtifacts?.some(a => a.provider === "anthropic" && a.model === model && ((!!a.signature && !!a.text) || !!a.redacted));
+    && !!m.reasoningArtifacts?.some(a => a.provider === "anthropic" && a.model === model && (!!a.signature || !!a.redacted));
 }
 
 /** Build Anthropic wire messages, reconstructing native tool_use / tool_result / thinking
@@ -121,7 +127,7 @@ export function buildAnthropicMessages(messages: Message[], model: string, think
       const blocks: AnthropicContentBlock[] = [];
       for (const a of m.reasoningArtifacts!) {
         if (a.provider !== "anthropic" || a.model !== model) continue;
-        if (a.signature && a.text) blocks.push({ type: "thinking", thinking: a.text, signature: a.signature });
+        if (a.signature) blocks.push({ type: "thinking", thinking: a.text ?? "", signature: a.signature });
         else if (a.redacted) blocks.push({ type: "redacted_thinking", data: a.redacted });
       }
       for (const tu of m.toolUse!) blocks.push({ type: "tool_use", id: tu.id, name: tu.tool, input: tu.arguments });
@@ -454,6 +460,7 @@ function headersFor(credential: Credential, stream: boolean): Record<string, str
       "content-type": "application/json",
       "x-api-key": credential.token,
       "anthropic-version": "2023-06-01",
+      "anthropic-beta": ANTHROPIC_API_KEY_BETA,
     };
   }
   throw new Error("anthropic adapter requires a credential");