jeo-code 0.8.7 → 0.8.9

package/CHANGELOG.md

@@ -6,6 +6,27 @@ 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`.
 
+## [0.8.9] - 2026-07-08
+_"프롬프트 라우팅 속도 문제가 있는거같은데 근본원인 알려줘" — prompt routing incurred significant latency due to a design oversight in LLM-based escalation: when heuristic confidence falls below threshold (standard conceptual questions with no code blocks/file paths conflict-trigger 0.35 confidence), it makes a blocking, synchronous LLM classifier call. If the user's global `thinkingLevel` is enabled (medium/high/xhigh), the cheap classifier model (Haiku 4.5 / GPT-4o-mini) also ran with reasoning enabled, wasting 500ms–1500ms on internal thoughts for a simple 1-word JSON response. The same reasoning-latency leak existed on all other background/internal LLM calls (compaction summarizer, goal verifier, memory distiller), blocking user turns on compaction boundaries._
+
+### Fixed
+- **Exposed explicit reasoning disable (`reasoningEffort: "none"`)** (`src/ai/types.ts`, `src/ai/model-manager.ts`) — added `"none"` option to `CallOptions["reasoningEffort"]`. `resolveCall` maps `"none"` to a wire-level value of `undefined` (disabling thinking) while bypassing the global config's `thinkingLevel` fallback.
+- **Optimized prompt routing classifier latency** (`src/agent/prompt-router.ts`) — passed `reasoningEffort: "none"` to `escalateToLlm`'s `callLlm` options, cutting the classifier's thinking tokens entirely.
+- **Optimized background LLM call latency** (`src/agent/compaction.ts`, `src/agent/goal-verifier.ts`, `src/agent/memory.ts`) — passed `reasoningEffort: "none"` to the compaction summarizer, goal verifier, and memory distiller calls, preventing the model from thinking about summaries or logs and unblocking turn boundaries.
+
+### Added
+- **Reasoning-disable unit tests** (`test/model-manager.test.ts`) — added tests verifying that `resolveCall` with `reasoningEffort: "none"` resolves to `undefined` (thinking disabled) even when the global default is enabled, while ordinary levels and default values resolve correctly.
+
+## [0.8.8] - 2026-07-08
+_"실동작검증을 통해서 유효성 평가하고 개선해줘" — live-verified the v0.8.5 fallback mechanism using active Claude Code OAuth credentials on this machine (confirmed 200 OK for both Fable 5 and Opus 4.8 via the proxy). Identified two critical improvement vectors during verification: (1) server-side fallback was previously scoped strictly to API-key credentials, leaving OAuth users (who also hit `reasoning_extraction` refusals) with today's reactive-only recovery; (2) the sequential `postAnthropic` retry ladder could throw immediately on a combination of different error types (e.g. temperature error first, then fallback error, then success)._
+
+### Fixed
+- **OAuth support for server-side fallback** (`src/ai/providers/anthropic.ts`) — removed the `credential.kind !== "api_key"` constraint. The Claude Code OAuth proxy has been verified to fully support both the `fallbacks` parameter and the `server-side-fallback-2026-06-01` beta header. `headersFor` now dynamically injects the fallback beta header into the OAuth request headers when applicable, extending the refusal-avoidance benefit to all subscription users.
+- **Loop-based unified retry handling** (`src/ai/providers/anthropic.ts`) — refactored the sequential `if (isXError)` retry lines into a clean, unified `for` loop. The loop dynamically flips state flags (`includeTemperature`, `stripArtifacts`, `disableFallback`) and retries up to 4 times, allowing successful recovery from any combination of errors.
+
+### Added
+- **Combination retry test** (`test/anthropic-fallback.test.ts`) — added a robust regression test verifying that `postAnthropic` recovers successfully when multiple orthogonal errors occur in sequence (temperature error first, then fallback error, then success) and yields the correct final payload.
+
 ## [0.8.7] - 2026-07-08
 _Fix-forward for a CI-caught release failure in v0.8.6 (this same session): `test/launch-prompt-routing.test.ts` shipped with a dropped closing brace (a git 3-way merge misaligned on a duplicate `});` line during this session's own working-tree isolation, then a subsequent `git stash push --keep-index` silently reset the working tree to the pre-fix staged content — the fix was applied once, verified once, then invisibly reverted before the commit that actually shipped). The v0.8.6 GitHub Actions release workflow correctly caught the syntax error at `bun test` and failed BEFORE the npm publish step ran; `npm view jeo-code version` confirmed 0.8.5 remained latest throughout — nothing broken ever reached the registry. Per this repo's established pattern for a same-day CI-caught regression (v0.8.0 → v0.8.1), shipping forward rather than retargeting the already-publicly-failed v0.8.6 tag._
 

package/README.ja.md

@@ -262,11 +262,11 @@ 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`) -->
+- **[0.8.9]** (2026-07-08) — "프롬프트 라우팅 속도 문제가 있는거같은데 근본원인 알려줘" — prompt routing incurred significant latency due to a design oversight in LLM-based escalation: when heuristic confidence falls below threshold (standard conceptual questions with no code blocks/file paths conflict-trigger 0.35 confidence), it makes a blocking, synchronous LLM classifier call. If the user's global `thinkingLevel` is enabled (medium/high/xhigh), the cheap classifier model (Haiku 4.5 / GPT-4o-mini) also ran with reasoning enabled, wasting 500ms–1500ms on internal thoughts for a simple 1-word JSON response. The same reasoning-latency leak existed on all other background/internal LLM calls (compaction summarizer, goal verifier, memory distiller), blocking user turns on compaction boundaries.
+- **[0.8.8]** (2026-07-08) — "실동작검증을 통해서 유효성 평가하고 개선해줘" — live-verified the v0.8.5 fallback mechanism using active Claude Code OAuth credentials on this machine (confirmed 200 OK for both Fable 5 and Opus 4.8 via the proxy). Identified two critical improvement vectors during verification: (1) server-side fallback was previously scoped strictly to API-key credentials, leaving OAuth users (who also hit `reasoning_extraction` refusals) with today's reactive-only recovery; (2) the sequential `postAnthropic` retry ladder could throw immediately on a combination of different error types (e.g. temperature error first, then fallback error, then success).
 - **[0.8.7]** (2026-07-08) — Fix-forward for a CI-caught release failure in v0.8.6 (this same session): `test/launch-prompt-routing.test.ts` shipped with a dropped closing brace (a git 3-way merge misaligned on a duplicate `});` line during this session's own working-tree isolation, then a subsequent `git stash push --keep-index` silently reset the working tree to the pre-fix staged content — the fix was applied once, verified once, then invisibly reverted before the commit that actually shipped). The v0.8.6 GitHub Actions release workflow correctly caught the syntax error at `bun test` and failed BEFORE the npm publish step ran; `npm view jeo-code version` confirmed 0.8.5 remained latest throughout — nothing broken ever reached the registry. Per this repo's established pattern for a same-day CI-caught regression (v0.8.0 → v0.8.1), shipping forward rather than retargeting the already-publicly-failed v0.8.6 tag.
 - **[0.8.6]** (2026-07-08) — Explicit `/model` pin always winning over PromptRouter was correct but opaque: `/route status` showed "routing: on" even while a session pin blocked routing from ever evaluating a prompt, and there was no way back to routed mode short of restarting the session. Also closed a related escalation gap: `routing.enabled` with `roles.smol` unset made ambiguous-prompt LLM escalation silently skip every turn, even when a cheaper credentialed model existed to run the classifier.
 - **[0.8.5]** (2026-07-08) — "딥리서치 다음과같이 페이블5 모델이 응답하게 되는경우를 피하기 위해" — a claude-fable-5 turn hit `Error: Refusal (reasoning_extraction): This request was blocked as it seems to violate Anthropic's Terms of Service.` jeo already had a full reactive recovery ladder (context reset → thinking-artifact strip → guidance strip → fail-fast on a category-shaped refusal), but every rung still resends to the SAME model — a deterministic classifier trip re-refuses identically no matter how much context gets stripped. Deep-researched Anthropic's current docs and found the actual fix: a documented, dedicated **server-side fallback** beta released alongside Fable 5 that retries a safety-classifier decline against a different model inside the SAME request, before the caller ever sees an error.
-- **[0.8.4]** (2026-07-08) — Follow-up to the 0.8.3 `jeo --tmux` E2E verification, which surfaced two real bugs: (1) the fake `test-anthropic-key` fixture found sitting in the user's REAL `~/.jeo/config.json` turned out to be reproducible — jeo's own test suite could silently write to the real config with no guard, and a prior session's routing tests had done exactly that; (2) the E2E run's TUI showed `'antigravity/gemini-pro-agent' is not in the live antigravity catalog` for a model that WAS live — traced to the note firing on a FAILED provider discovery (timeout/expired OAuth) rather than a genuinely absent model.
-- **[0.8.3]** (2026-07-08) — "잘못된 모델 설정하는 경우가 있는데" — the static Antigravity catalog had drifted badly from the LIVE Cloud Code Assist agent backend, and several current wire ids actively LIE about their tier: `gemini-3-flash-agent` is really "Gemini 3.5 Flash (High)" (the flagship agent model, which the name-suffix heuristic filed under the SMALL flash tier), `gemini-pro-agent` is really "Gemini 3.1 Pro (High)" (the code-agent model), and `gemini-3.1-pro-high` is DEPRECATED by the backend in favor of `gemini-pro-agent`. Probed the real `fetchAvailableModels` response (displayNames + agentModelSorts + deprecatedModelIds) and made it the single source of truth.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.ko.md

@@ -263,11 +263,11 @@ 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`) -->
+- **[0.8.9]** (2026-07-08) — "프롬프트 라우팅 속도 문제가 있는거같은데 근본원인 알려줘" — prompt routing incurred significant latency due to a design oversight in LLM-based escalation: when heuristic confidence falls below threshold (standard conceptual questions with no code blocks/file paths conflict-trigger 0.35 confidence), it makes a blocking, synchronous LLM classifier call. If the user's global `thinkingLevel` is enabled (medium/high/xhigh), the cheap classifier model (Haiku 4.5 / GPT-4o-mini) also ran with reasoning enabled, wasting 500ms–1500ms on internal thoughts for a simple 1-word JSON response. The same reasoning-latency leak existed on all other background/internal LLM calls (compaction summarizer, goal verifier, memory distiller), blocking user turns on compaction boundaries.
+- **[0.8.8]** (2026-07-08) — "실동작검증을 통해서 유효성 평가하고 개선해줘" — live-verified the v0.8.5 fallback mechanism using active Claude Code OAuth credentials on this machine (confirmed 200 OK for both Fable 5 and Opus 4.8 via the proxy). Identified two critical improvement vectors during verification: (1) server-side fallback was previously scoped strictly to API-key credentials, leaving OAuth users (who also hit `reasoning_extraction` refusals) with today's reactive-only recovery; (2) the sequential `postAnthropic` retry ladder could throw immediately on a combination of different error types (e.g. temperature error first, then fallback error, then success).
 - **[0.8.7]** (2026-07-08) — Fix-forward for a CI-caught release failure in v0.8.6 (this same session): `test/launch-prompt-routing.test.ts` shipped with a dropped closing brace (a git 3-way merge misaligned on a duplicate `});` line during this session's own working-tree isolation, then a subsequent `git stash push --keep-index` silently reset the working tree to the pre-fix staged content — the fix was applied once, verified once, then invisibly reverted before the commit that actually shipped). The v0.8.6 GitHub Actions release workflow correctly caught the syntax error at `bun test` and failed BEFORE the npm publish step ran; `npm view jeo-code version` confirmed 0.8.5 remained latest throughout — nothing broken ever reached the registry. Per this repo's established pattern for a same-day CI-caught regression (v0.8.0 → v0.8.1), shipping forward rather than retargeting the already-publicly-failed v0.8.6 tag.
 - **[0.8.6]** (2026-07-08) — Explicit `/model` pin always winning over PromptRouter was correct but opaque: `/route status` showed "routing: on" even while a session pin blocked routing from ever evaluating a prompt, and there was no way back to routed mode short of restarting the session. Also closed a related escalation gap: `routing.enabled` with `roles.smol` unset made ambiguous-prompt LLM escalation silently skip every turn, even when a cheaper credentialed model existed to run the classifier.
 - **[0.8.5]** (2026-07-08) — "딥리서치 다음과같이 페이블5 모델이 응답하게 되는경우를 피하기 위해" — a claude-fable-5 turn hit `Error: Refusal (reasoning_extraction): This request was blocked as it seems to violate Anthropic's Terms of Service.` jeo already had a full reactive recovery ladder (context reset → thinking-artifact strip → guidance strip → fail-fast on a category-shaped refusal), but every rung still resends to the SAME model — a deterministic classifier trip re-refuses identically no matter how much context gets stripped. Deep-researched Anthropic's current docs and found the actual fix: a documented, dedicated **server-side fallback** beta released alongside Fable 5 that retries a safety-classifier decline against a different model inside the SAME request, before the caller ever sees an error.
-- **[0.8.4]** (2026-07-08) — Follow-up to the 0.8.3 `jeo --tmux` E2E verification, which surfaced two real bugs: (1) the fake `test-anthropic-key` fixture found sitting in the user's REAL `~/.jeo/config.json` turned out to be reproducible — jeo's own test suite could silently write to the real config with no guard, and a prior session's routing tests had done exactly that; (2) the E2E run's TUI showed `'antigravity/gemini-pro-agent' is not in the live antigravity catalog` for a model that WAS live — traced to the note firing on a FAILED provider discovery (timeout/expired OAuth) rather than a genuinely absent model.
-- **[0.8.3]** (2026-07-08) — "잘못된 모델 설정하는 경우가 있는데" — the static Antigravity catalog had drifted badly from the LIVE Cloud Code Assist agent backend, and several current wire ids actively LIE about their tier: `gemini-3-flash-agent` is really "Gemini 3.5 Flash (High)" (the flagship agent model, which the name-suffix heuristic filed under the SMALL flash tier), `gemini-pro-agent` is really "Gemini 3.1 Pro (High)" (the code-agent model), and `gemini-3.1-pro-high` is DEPRECATED by the backend in favor of `gemini-pro-agent`. Probed the real `fetchAvailableModels` response (displayNames + agentModelSorts + deprecatedModelIds) and made it the single source of truth.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.md

@@ -265,11 +265,11 @@ Huge thanks to [gajae-code](https://github.com/Yeachan-Heo/gajae-code) for the i
 ## Changelog
 
 <!-- CHANGELOG:START (auto-generated from CHANGELOG.md — run `bun run changelog:sync`) -->
+- **[0.8.9]** (2026-07-08) — "프롬프트 라우팅 속도 문제가 있는거같은데 근본원인 알려줘" — prompt routing incurred significant latency due to a design oversight in LLM-based escalation: when heuristic confidence falls below threshold (standard conceptual questions with no code blocks/file paths conflict-trigger 0.35 confidence), it makes a blocking, synchronous LLM classifier call. If the user's global `thinkingLevel` is enabled (medium/high/xhigh), the cheap classifier model (Haiku 4.5 / GPT-4o-mini) also ran with reasoning enabled, wasting 500ms–1500ms on internal thoughts for a simple 1-word JSON response. The same reasoning-latency leak existed on all other background/internal LLM calls (compaction summarizer, goal verifier, memory distiller), blocking user turns on compaction boundaries.
+- **[0.8.8]** (2026-07-08) — "실동작검증을 통해서 유효성 평가하고 개선해줘" — live-verified the v0.8.5 fallback mechanism using active Claude Code OAuth credentials on this machine (confirmed 200 OK for both Fable 5 and Opus 4.8 via the proxy). Identified two critical improvement vectors during verification: (1) server-side fallback was previously scoped strictly to API-key credentials, leaving OAuth users (who also hit `reasoning_extraction` refusals) with today's reactive-only recovery; (2) the sequential `postAnthropic` retry ladder could throw immediately on a combination of different error types (e.g. temperature error first, then fallback error, then success).
 - **[0.8.7]** (2026-07-08) — Fix-forward for a CI-caught release failure in v0.8.6 (this same session): `test/launch-prompt-routing.test.ts` shipped with a dropped closing brace (a git 3-way merge misaligned on a duplicate `});` line during this session's own working-tree isolation, then a subsequent `git stash push --keep-index` silently reset the working tree to the pre-fix staged content — the fix was applied once, verified once, then invisibly reverted before the commit that actually shipped). The v0.8.6 GitHub Actions release workflow correctly caught the syntax error at `bun test` and failed BEFORE the npm publish step ran; `npm view jeo-code version` confirmed 0.8.5 remained latest throughout — nothing broken ever reached the registry. Per this repo's established pattern for a same-day CI-caught regression (v0.8.0 → v0.8.1), shipping forward rather than retargeting the already-publicly-failed v0.8.6 tag.
 - **[0.8.6]** (2026-07-08) — Explicit `/model` pin always winning over PromptRouter was correct but opaque: `/route status` showed "routing: on" even while a session pin blocked routing from ever evaluating a prompt, and there was no way back to routed mode short of restarting the session. Also closed a related escalation gap: `routing.enabled` with `roles.smol` unset made ambiguous-prompt LLM escalation silently skip every turn, even when a cheaper credentialed model existed to run the classifier.
 - **[0.8.5]** (2026-07-08) — "딥리서치 다음과같이 페이블5 모델이 응답하게 되는경우를 피하기 위해" — a claude-fable-5 turn hit `Error: Refusal (reasoning_extraction): This request was blocked as it seems to violate Anthropic's Terms of Service.` jeo already had a full reactive recovery ladder (context reset → thinking-artifact strip → guidance strip → fail-fast on a category-shaped refusal), but every rung still resends to the SAME model — a deterministic classifier trip re-refuses identically no matter how much context gets stripped. Deep-researched Anthropic's current docs and found the actual fix: a documented, dedicated **server-side fallback** beta released alongside Fable 5 that retries a safety-classifier decline against a different model inside the SAME request, before the caller ever sees an error.
-- **[0.8.4]** (2026-07-08) — Follow-up to the 0.8.3 `jeo --tmux` E2E verification, which surfaced two real bugs: (1) the fake `test-anthropic-key` fixture found sitting in the user's REAL `~/.jeo/config.json` turned out to be reproducible — jeo's own test suite could silently write to the real config with no guard, and a prior session's routing tests had done exactly that; (2) the E2E run's TUI showed `'antigravity/gemini-pro-agent' is not in the live antigravity catalog` for a model that WAS live — traced to the note firing on a FAILED provider discovery (timeout/expired OAuth) rather than a genuinely absent model.
-- **[0.8.3]** (2026-07-08) — "잘못된 모델 설정하는 경우가 있는데" — the static Antigravity catalog had drifted badly from the LIVE Cloud Code Assist agent backend, and several current wire ids actively LIE about their tier: `gemini-3-flash-agent` is really "Gemini 3.5 Flash (High)" (the flagship agent model, which the name-suffix heuristic filed under the SMALL flash tier), `gemini-pro-agent` is really "Gemini 3.1 Pro (High)" (the code-agent model), and `gemini-3.1-pro-high` is DEPRECATED by the backend in favor of `gemini-pro-agent`. Probed the real `fetchAvailableModels` response (displayNames + agentModelSorts + deprecatedModelIds) and made it the single source of truth.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.zh.md

@@ -262,11 +262,11 @@ 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`) -->
+- **[0.8.9]** (2026-07-08) — "프롬프트 라우팅 속도 문제가 있는거같은데 근본원인 알려줘" — prompt routing incurred significant latency due to a design oversight in LLM-based escalation: when heuristic confidence falls below threshold (standard conceptual questions with no code blocks/file paths conflict-trigger 0.35 confidence), it makes a blocking, synchronous LLM classifier call. If the user's global `thinkingLevel` is enabled (medium/high/xhigh), the cheap classifier model (Haiku 4.5 / GPT-4o-mini) also ran with reasoning enabled, wasting 500ms–1500ms on internal thoughts for a simple 1-word JSON response. The same reasoning-latency leak existed on all other background/internal LLM calls (compaction summarizer, goal verifier, memory distiller), blocking user turns on compaction boundaries.
+- **[0.8.8]** (2026-07-08) — "실동작검증을 통해서 유효성 평가하고 개선해줘" — live-verified the v0.8.5 fallback mechanism using active Claude Code OAuth credentials on this machine (confirmed 200 OK for both Fable 5 and Opus 4.8 via the proxy). Identified two critical improvement vectors during verification: (1) server-side fallback was previously scoped strictly to API-key credentials, leaving OAuth users (who also hit `reasoning_extraction` refusals) with today's reactive-only recovery; (2) the sequential `postAnthropic` retry ladder could throw immediately on a combination of different error types (e.g. temperature error first, then fallback error, then success).
 - **[0.8.7]** (2026-07-08) — Fix-forward for a CI-caught release failure in v0.8.6 (this same session): `test/launch-prompt-routing.test.ts` shipped with a dropped closing brace (a git 3-way merge misaligned on a duplicate `});` line during this session's own working-tree isolation, then a subsequent `git stash push --keep-index` silently reset the working tree to the pre-fix staged content — the fix was applied once, verified once, then invisibly reverted before the commit that actually shipped). The v0.8.6 GitHub Actions release workflow correctly caught the syntax error at `bun test` and failed BEFORE the npm publish step ran; `npm view jeo-code version` confirmed 0.8.5 remained latest throughout — nothing broken ever reached the registry. Per this repo's established pattern for a same-day CI-caught regression (v0.8.0 → v0.8.1), shipping forward rather than retargeting the already-publicly-failed v0.8.6 tag.
 - **[0.8.6]** (2026-07-08) — Explicit `/model` pin always winning over PromptRouter was correct but opaque: `/route status` showed "routing: on" even while a session pin blocked routing from ever evaluating a prompt, and there was no way back to routed mode short of restarting the session. Also closed a related escalation gap: `routing.enabled` with `roles.smol` unset made ambiguous-prompt LLM escalation silently skip every turn, even when a cheaper credentialed model existed to run the classifier.
 - **[0.8.5]** (2026-07-08) — "딥리서치 다음과같이 페이블5 모델이 응답하게 되는경우를 피하기 위해" — a claude-fable-5 turn hit `Error: Refusal (reasoning_extraction): This request was blocked as it seems to violate Anthropic's Terms of Service.` jeo already had a full reactive recovery ladder (context reset → thinking-artifact strip → guidance strip → fail-fast on a category-shaped refusal), but every rung still resends to the SAME model — a deterministic classifier trip re-refuses identically no matter how much context gets stripped. Deep-researched Anthropic's current docs and found the actual fix: a documented, dedicated **server-side fallback** beta released alongside Fable 5 that retries a safety-classifier decline against a different model inside the SAME request, before the caller ever sees an error.
-- **[0.8.4]** (2026-07-08) — Follow-up to the 0.8.3 `jeo --tmux` E2E verification, which surfaced two real bugs: (1) the fake `test-anthropic-key` fixture found sitting in the user's REAL `~/.jeo/config.json` turned out to be reproducible — jeo's own test suite could silently write to the real config with no guard, and a prior session's routing tests had done exactly that; (2) the E2E run's TUI showed `'antigravity/gemini-pro-agent' is not in the live antigravity catalog` for a model that WAS live — traced to the note firing on a FAILED provider discovery (timeout/expired OAuth) rather than a genuinely absent model.
-- **[0.8.3]** (2026-07-08) — "잘못된 모델 설정하는 경우가 있는데" — the static Antigravity catalog had drifted badly from the LIVE Cloud Code Assist agent backend, and several current wire ids actively LIE about their tier: `gemini-3-flash-agent` is really "Gemini 3.5 Flash (High)" (the flagship agent model, which the name-suffix heuristic filed under the SMALL flash tier), `gemini-pro-agent` is really "Gemini 3.1 Pro (High)" (the code-agent model), and `gemini-3.1-pro-high` is DEPRECATED by the backend in favor of `gemini-pro-agent`. Probed the real `fetchAvailableModels` response (displayNames + agentModelSorts + deprecatedModelIds) and made it the single source of truth.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jeo-code",
-  "version": "0.8.7",
+  "version": "0.8.9",
   "description": "Clean, highly optimized AI coding agent using spec-first loop",
   "type": "module",
   "main": "src/cli.ts",

package/src/agent/compaction.ts

@@ -403,6 +403,7 @@ export async function maybeCompact(
         {
           model: opts.model,
           systemPrompt,
+          reasoningEffort: "none",
           signal: opts.signal,
         }
       );

package/src/agent/goal-verifier.ts

@@ -56,7 +56,8 @@ Do not include any other text, markdown formatting, or code blocks. Output raw J
     ], {
       model,
       jsonMode: true,
-      maxTokens: 1000
+      maxTokens: 1000,
+      reasoningEffort: "none",
     });
 
     const parsed = JSON.parse(response.trim());

package/src/agent/memory.ts

@@ -929,7 +929,7 @@ export async function distillSessionMemory(
 
     const timeoutMs = opts.timeoutMs ?? 20_000;
     const distilled = await Promise.race([
-      callLlm(prompt, { model: opts.model, jsonMode: true, maxTokens: 2_000 }),
+      callLlm(prompt, { model: opts.model, jsonMode: true, maxTokens: 2_000, reasoningEffort: "none" }),
       new Promise<never>((_, reject) => setTimeout(() => reject(new Error(`memory distill timed out after ${timeoutMs}ms`)), timeoutMs)),
     ]);
 

package/src/agent/prompt-router.ts

@@ -477,6 +477,7 @@ async function escalateToLlm(prompt: string, smolModel: string, signal: AbortSig
       model: smolModel,
       jsonMode: true,
       maxTokens: 200,
+      reasoningEffort: "none",
       signal,
     });
     const parsed = tryExtractJsonObject<{ tier?: unknown }>(raw);

package/src/ai/model-manager.ts

@@ -404,7 +404,7 @@ export function credentialForCall(
   return effective;
 }
 
-async function resolveCall(options: Partial<CallOptions>, kind: "request" | "stream" = "request"): Promise<Resolved> {
+export async function resolveCall(options: Partial<CallOptions>, kind: "request" | "stream" = "request"): Promise<Resolved> {
   const config = await readGlobalConfig();
   const aliases = { ...((config as { modelAliases?: Record<string, string> }).modelAliases ?? {}) };
   const model = expandAlias(options.model ?? config.defaultModel, { ...BUILTIN_ALIASES, ...aliases });
@@ -429,7 +429,9 @@ async function resolveCall(options: Partial<CallOptions>, kind: "request" | "str
     numCtx: options.numCtx ?? (provider === "ollama" ? (config as { ollamaNumCtx?: number }).ollamaNumCtx : undefined),
     onUsage: options.onUsage,
     signal: options.signal,
-    reasoningEffort: options.reasoningEffort ?? thinkingToReasoningEffort(config.thinkingLevel),
+    reasoningEffort: options.reasoningEffort === "none"
+      ? undefined
+      : (options.reasoningEffort ?? thinkingToReasoningEffort(config.thinkingLevel)),
     onReasoning: options.onReasoning,
     onReasoningArtifact: options.onReasoningArtifact,
     tools: options.tools,

package/src/ai/providers/anthropic.ts

@@ -137,14 +137,14 @@ function parseAnthropicVersion(model: string): { kind: "opus" | "sonnet" | "haik
  *  artifact strip, guidance strip) because every rung resent the SAME model. Scoped to
  *  `claude-fable-5` (the model this beta's docs are written against — Mythos-5's
  *  invite-only status makes its fallback support unconfirmed) on a DIRECT api.anthropic.com
- *  API-key call only: the beta's request/response shape is undocumented for the
- *  Claude-Code OAuth cloak or a custom baseUrl (Anthropic-compatible third-party hosts),
- *  so those paths keep today's reactive (post-refusal) recovery unchanged.
+ *  API-key or Claude-Code OAuth call: the beta's request/response shape is undocumented for
+ *  a custom baseUrl (Anthropic-compatible third-party hosts), so those paths keep today's
+ *  reactive (post-refusal) recovery unchanged.
  *  `JEO_ANTHROPIC_FALLBACK=0` opts out entirely. */
 const FALLBACK_BETA = "server-side-fallback-2026-06-01";
 function anthropicFallbackModels(model: string, credential: Credential, baseUrl: string | undefined): string[] {
   if (jeoEnv("ANTHROPIC_FALLBACK") === "0") return [];
-  if (credential.kind !== "api_key" || baseUrl) return [];
+  if (baseUrl) return [];
   const v = parseAnthropicVersion(model);
   if (!v || v.kind !== "fable") return [];
   return ["claude-opus-4-8"];
@@ -189,6 +189,7 @@ function anthropicAdaptiveEffort(effort: NonNullable<CallOptions["reasoningEffor
     case "low": return "low";
     case "medium": return "medium";
     case "high": return "high";
+    default: return "medium";
   }
 }
 
@@ -397,44 +398,48 @@ async function postAnthropic(
   credential: Credential,
   stream: boolean,
 ): Promise<Response> {
-  const send = (includeTemperature: boolean, stripArtifacts = false, disableFallback = false) => {
-    const { url, headers, body } = anthropicRequest(messages, options, credential, stream, includeTemperature, stripArtifacts, disableFallback);
-    return fetch(url, { method: "POST", headers, body, signal: options.signal });
-  };
+  let includeTemperature = true;
+  let stripArtifacts = false;
+  let disableFallback = false;
+
+  for (let attempt = 1; attempt <= 4; attempt++) {
+    const { url, headers, body } = anthropicRequest(
+      messages,
+      options,
+      credential,
+      stream,
+      includeTemperature,
+      stripArtifacts,
+      disableFallback,
+    );
+    const response = await fetch(url, { method: "POST", headers, body, signal: options.signal });
+    if (response.ok) return response;
 
-  let response = await send(true);
-  if (response.ok) return response;
+    const detail = await response.text().catch(() => "");
+    if (isDeprecatedTemperatureError(response.status, detail) && includeTemperature) {
+      includeTemperature = false;
+      continue;
+    }
+    if (isReasoningArtifactError(response.status, detail) && !stripArtifacts) {
+      stripArtifacts = true;
+      continue;
+    }
+    if (isFallbackUnsupportedError(response.status, detail) && !disableFallback) {
+      disableFallback = true;
+      continue;
+    }
 
-  const detail = await response.text().catch(() => "");
-  if (isDeprecatedTemperatureError(response.status, detail)) {
-    response = await send(false);
-    if (response.ok) return response;
-    throw await providerHttpError("Anthropic", response, stream ? "(stream)" : undefined);
-  }
-  // Fail-safe: a rejected replay artifact → retry once with artifacts stripped (plain history).
-  if (isReasoningArtifactError(response.status, detail)) {
-    response = await send(true, true);
-    if (response.ok) return response;
-    throw await providerHttpError("Anthropic", response, stream ? "(stream)" : undefined);
-  }
-  // Fail-safe: the account/endpoint doesn't support server-side fallback (or the
-  // named fallback model rejected THIS request's shape) → retry once without it.
-  if (isFallbackUnsupportedError(response.status, detail)) {
-    response = await send(true, false, true);
-    if (response.ok) return response;
-    throw await providerHttpError("Anthropic", response, stream ? "(stream)" : undefined);
+    // Unrecoverable error, or all retries for the active error type spent
+    const enrichedDetail = response.status === 429 ? `${detail}${anthropicRateLimitEvidence(response.headers)}` : detail;
+    throw new ProviderHttpError(
+      "Anthropic",
+      response.status,
+      enrichedDetail,
+      stream ? "(stream)" : undefined,
+      parseRetryAfter(response.headers.get("retry-after")) ?? parseRetryFromBody(detail),
+    );
   }
-
-  // 429s carry their rate-limit headers in the DETAIL so isUsageLimitError /
-  // friendlyProviderError can classify on the full evidence (gjc parity).
-  const enrichedDetail = response.status === 429 ? `${detail}${anthropicRateLimitEvidence(response.headers)}` : detail;
-  throw new ProviderHttpError(
-    "Anthropic",
-    response.status,
-    enrichedDetail,
-    stream ? "(stream)" : undefined,
-    parseRetryAfter(response.headers.get("retry-after")) ?? parseRetryFromBody(detail),
-  );
+  throw new Error("Anthropic request failed: maximum retries reached without response");
 }
 
 /** Anthropic usage: with prompt caching the input splits into uncached + cache read +
@@ -665,12 +670,20 @@ function headersFor(credential: Credential, stream: boolean, model: string, base
         "anthropic-version": "2023-06-01",
       };
     }
-    return {
+    const headers: Record<string, string> = {
       "content-type": "application/json",
       authorization: `Bearer ${credential.token}`,
       "anthropic-version": "2023-06-01",
       ...claudeCodeOAuthHeaders(stream, model),
     };
+    if (!disableFallback && anthropicFallbackModels(model, credential, baseUrl).length) {
+      const betas = headers["anthropic-beta"] ? headers["anthropic-beta"].split(",") : [];
+      if (!betas.includes(FALLBACK_BETA)) {
+        betas.push(FALLBACK_BETA);
+        headers["anthropic-beta"] = betas.join(",");
+      }
+    }
+    return headers;
   }
   if (credential.kind === "api_key") {
     const betas = ANTHROPIC_API_KEY_BETA.slice();

package/src/ai/providers/gemini.ts

@@ -69,6 +69,7 @@ export function geminiThinkingLevel(effort: NonNullable<CallOptions["reasoningEf
     case "medium": return "MEDIUM";
     case "high":
     case "xhigh": return "HIGH";
+    default: return "MEDIUM";
   }
 }
 

package/src/ai/types.ts

@@ -107,7 +107,7 @@ export interface CallOptions {
   /** Abort in-flight provider requests (Ctrl-C / timeout / supersede). */
   signal?: AbortSignal;
   /** Reasoning effort for reasoning models (o-series / gpt-5), mapped from thinkingLevel. */
-  reasoningEffort?: "low" | "medium" | "high";
+  reasoningEffort?: "low" | "medium" | "high" | "none";
   /** How an OpenAI-compatible backend enables/streams native reasoning (gjc parity):
    *  "openai" → `reasoning_effort`; "openrouter" → `reasoning: {effort}`; "qwen" →
    *  `enable_thinking: true`; "zai" → `thinking: {type:"enabled"}`. Set per provider by