jeo-code 0.7.22 → 0.7.23

package/CHANGELOG.md

@@ -6,6 +6,26 @@ 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`.
 
+## [0.7.23] - 2026-07-01
+_Anthropic 5th-generation model catalog: adds Sonnet 5, Fable 5, and Mythos 5, promotes the 4.6 generation to 1M context / 128k output, and retires the superseded 4.5/3.5/4.1 ids. Bumps the default model to Sonnet 4.6, prices the new tiers, and fixes the thinking transport for Haiku 4.5 and every 5th-gen model._
+
+### Added
+- **Anthropic 5th-generation models.** New catalog entries `claude-sonnet-5`, `claude-fable-5` (most capable widely-released, adaptive thinking always on), and `claude-mythos-5` (limited-availability, callable by id). `inferCatalogMetadata` now recognizes the `fable`/`mythos` families, and the Anthropic version parser accepts dateless single-major ids (e.g. `claude-sonnet-5`).
+- **1M context / 128k output for the 4.6 generation onward.** `claude-opus-4-6/4-7/4-8`, `claude-sonnet-4-6`, and all 5th-gen ids now advertise 1,000,000-token context and 128,000-token max output (Anthropic docs); dated pre-4.6 ids stay at 200k/64k.
+- **Pricing for the new tiers.** Opus 4.8 (`$5`/`$25` per M), Fable/Mythos (`$10`/`$50`), and Sonnet 5 (`$2`/`$10`), ordered ahead of the generic Opus/Sonnet families so the newer tiers win.
+
+### Fixed
+- **Haiku 4.5 thinking transport.** Haiku 4.5 supports `budget_tokens` thinking but rejects `output_config.effort` ("This model does not support the effort parameter"), so it now uses the plain budget transport instead of its sonnet/opus 4.5 siblings' budget-effort mode.
+- **Adaptive thinking display for 5th-gen models.** `display: "summarized"` is now enabled for every 5th-generation+ model (Sonnet 5, Fable 5, Mythos 5) in addition to Opus ≥ 4.7, so their reasoning streams instead of being silently omitted.
+- **Gemini path no longer inherits a `claude-` model id.** A `claude-`-prefixed model falls back to `gemini-2.0-flash` on the Gemini transport instead of forwarding an incompatible id.
+
+### Changed
+- **Default model bumped to `claude-sonnet-4-6`.** Runtime default, setup defaults, recommended-model set, and the `sonnet`/`opus` aliases now point at the 4.6 generation.
+- **Retired superseded ids.** Removed `claude-3-5-sonnet`, `claude-opus-4-1`, `claude-opus-4-5`, and `claude-sonnet-4-5` (plus their Antigravity `-thinking` variants) from the catalog.
+
+### Verified
+- `bun run typecheck` clean; full `bun test` suite green. Updated model-catalog, pricing, registry, and Anthropic-stream tests cover the new families, 1M/128k metadata, and the Haiku 4.5 transport.
+
 ## [0.7.22] - 2026-06-30
 _gajae-code 0.7.3–0.7.8 parity sweep: terminal-bell notifications, a gruvbox-dark TUI theme, a resilient `jeo update` runtime check, and an ultragoal artifact gate. Ports the user-facing improvements from upstream gajae-code that jeo did not yet have, re-implemented to fit jeo's config, command, theming, and skill surfaces._
 

package/README.ja.md

@@ -205,11 +205,11 @@ 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`) -->
+- **[0.7.23]** (2026-07-01) — Anthropic 5th-generation model catalog: adds Sonnet 5, Fable 5, and Mythos 5, promotes the 4.6 generation to 1M context / 128k output, and retires the superseded 4.5/3.5/4.1 ids. Bumps the default model to Sonnet 4.6, prices the new tiers, and fixes the thinking transport for Haiku 4.5 and every 5th-gen model.
 - **[0.7.22]** (2026-06-30) — gajae-code 0.7.3–0.7.8 parity sweep: terminal-bell notifications, a gruvbox-dark TUI theme, a resilient `jeo update` runtime check, and an ultragoal artifact gate. Ports the user-facing improvements from upstream gajae-code that jeo did not yet have, re-implemented to fit jeo's config, command, theming, and skill surfaces.
 - **[0.7.21]** (2026-06-26) — Global llm-wiki vault integration, Gemini/Antigravity thinking indicators, generous file-reading windows, and autopilot flag validation. Adds a shared global wiki root configuration with a /wiki slash command, fires reasoning start signals up front for Gemini/Antigravity models, adjusts the large-file reading discipline to use generous windows, and validates autopilot goal and integer flags.
 - **[0.7.20]** (2026-06-26) — OKF concept-memory retrieval gains a hybrid reranker ported from memsearch. Injection priority no longer rides one raw keyword score — it fuses two complementary ranked channels by Reciprocal Rank Fusion (RRF): IDF-weighted lexical relevance (the sparse/BM25 channel, so rare discriminating terms steer recall) and concept-graph proximity (the local dense/semantic-neighbour channel, so a hub linked from multiple query hits surfaces even with no keyword of its own). All embedding-free and deterministic, layered atop the existing failure-first tier and pinned-invariant reserved budget.
 - **[0.7.19]** (2026-06-26) — The live model picker gains gajae-code's `/model` provider tabs, and skill invocation is consolidated onto a single `$` entrypoint. The picker now shows an `ALL` tab plus one tab per provider that `tab`/`shift+tab` cycles, and skills (including their declared aliases) are invoked only via `$` — the slash palette stays builtins-only.
-- **[0.7.18]** (2026-06-26) — Slash-command discovery and the `/model` flow reach gajae-code parity. The slash palette/autocomplete now fuzzy-matches command names (with a description fallback for intent-style queries), resolved skills can contribute their own `/aliases` as real dispatchable commands, and `/model` runs gjc's two-menu target → reasoning flow so a picked model can be assigned to the default or any subagent role with its own thinking budget.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.ko.md

@@ -205,11 +205,11 @@ 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`) -->
+- **[0.7.23]** (2026-07-01) — Anthropic 5th-generation model catalog: adds Sonnet 5, Fable 5, and Mythos 5, promotes the 4.6 generation to 1M context / 128k output, and retires the superseded 4.5/3.5/4.1 ids. Bumps the default model to Sonnet 4.6, prices the new tiers, and fixes the thinking transport for Haiku 4.5 and every 5th-gen model.
 - **[0.7.22]** (2026-06-30) — gajae-code 0.7.3–0.7.8 parity sweep: terminal-bell notifications, a gruvbox-dark TUI theme, a resilient `jeo update` runtime check, and an ultragoal artifact gate. Ports the user-facing improvements from upstream gajae-code that jeo did not yet have, re-implemented to fit jeo's config, command, theming, and skill surfaces.
 - **[0.7.21]** (2026-06-26) — Global llm-wiki vault integration, Gemini/Antigravity thinking indicators, generous file-reading windows, and autopilot flag validation. Adds a shared global wiki root configuration with a /wiki slash command, fires reasoning start signals up front for Gemini/Antigravity models, adjusts the large-file reading discipline to use generous windows, and validates autopilot goal and integer flags.
 - **[0.7.20]** (2026-06-26) — OKF concept-memory retrieval gains a hybrid reranker ported from memsearch. Injection priority no longer rides one raw keyword score — it fuses two complementary ranked channels by Reciprocal Rank Fusion (RRF): IDF-weighted lexical relevance (the sparse/BM25 channel, so rare discriminating terms steer recall) and concept-graph proximity (the local dense/semantic-neighbour channel, so a hub linked from multiple query hits surfaces even with no keyword of its own). All embedding-free and deterministic, layered atop the existing failure-first tier and pinned-invariant reserved budget.
 - **[0.7.19]** (2026-06-26) — The live model picker gains gajae-code's `/model` provider tabs, and skill invocation is consolidated onto a single `$` entrypoint. The picker now shows an `ALL` tab plus one tab per provider that `tab`/`shift+tab` cycles, and skills (including their declared aliases) are invoked only via `$` — the slash palette stays builtins-only.
-- **[0.7.18]** (2026-06-26) — Slash-command discovery and the `/model` flow reach gajae-code parity. The slash palette/autocomplete now fuzzy-matches command names (with a description fallback for intent-style queries), resolved skills can contribute their own `/aliases` as real dispatchable commands, and `/model` runs gjc's two-menu target → reasoning flow so a picked model can be assigned to the default or any subagent role with its own thinking budget.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.md

@@ -232,11 +232,11 @@ 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`) -->
+- **[0.7.23]** (2026-07-01) — Anthropic 5th-generation model catalog: adds Sonnet 5, Fable 5, and Mythos 5, promotes the 4.6 generation to 1M context / 128k output, and retires the superseded 4.5/3.5/4.1 ids. Bumps the default model to Sonnet 4.6, prices the new tiers, and fixes the thinking transport for Haiku 4.5 and every 5th-gen model.
 - **[0.7.22]** (2026-06-30) — gajae-code 0.7.3–0.7.8 parity sweep: terminal-bell notifications, a gruvbox-dark TUI theme, a resilient `jeo update` runtime check, and an ultragoal artifact gate. Ports the user-facing improvements from upstream gajae-code that jeo did not yet have, re-implemented to fit jeo's config, command, theming, and skill surfaces.
 - **[0.7.21]** (2026-06-26) — Global llm-wiki vault integration, Gemini/Antigravity thinking indicators, generous file-reading windows, and autopilot flag validation. Adds a shared global wiki root configuration with a /wiki slash command, fires reasoning start signals up front for Gemini/Antigravity models, adjusts the large-file reading discipline to use generous windows, and validates autopilot goal and integer flags.
 - **[0.7.20]** (2026-06-26) — OKF concept-memory retrieval gains a hybrid reranker ported from memsearch. Injection priority no longer rides one raw keyword score — it fuses two complementary ranked channels by Reciprocal Rank Fusion (RRF): IDF-weighted lexical relevance (the sparse/BM25 channel, so rare discriminating terms steer recall) and concept-graph proximity (the local dense/semantic-neighbour channel, so a hub linked from multiple query hits surfaces even with no keyword of its own). All embedding-free and deterministic, layered atop the existing failure-first tier and pinned-invariant reserved budget.
 - **[0.7.19]** (2026-06-26) — The live model picker gains gajae-code's `/model` provider tabs, and skill invocation is consolidated onto a single `$` entrypoint. The picker now shows an `ALL` tab plus one tab per provider that `tab`/`shift+tab` cycles, and skills (including their declared aliases) are invoked only via `$` — the slash palette stays builtins-only.
-- **[0.7.18]** (2026-06-26) — Slash-command discovery and the `/model` flow reach gajae-code parity. The slash palette/autocomplete now fuzzy-matches command names (with a description fallback for intent-style queries), resolved skills can contribute their own `/aliases` as real dispatchable commands, and `/model` runs gjc's two-menu target → reasoning flow so a picked model can be assigned to the default or any subagent role with its own thinking budget.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.zh.md

@@ -205,11 +205,11 @@ 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`) -->
+- **[0.7.23]** (2026-07-01) — Anthropic 5th-generation model catalog: adds Sonnet 5, Fable 5, and Mythos 5, promotes the 4.6 generation to 1M context / 128k output, and retires the superseded 4.5/3.5/4.1 ids. Bumps the default model to Sonnet 4.6, prices the new tiers, and fixes the thinking transport for Haiku 4.5 and every 5th-gen model.
 - **[0.7.22]** (2026-06-30) — gajae-code 0.7.3–0.7.8 parity sweep: terminal-bell notifications, a gruvbox-dark TUI theme, a resilient `jeo update` runtime check, and an ultragoal artifact gate. Ports the user-facing improvements from upstream gajae-code that jeo did not yet have, re-implemented to fit jeo's config, command, theming, and skill surfaces.
 - **[0.7.21]** (2026-06-26) — Global llm-wiki vault integration, Gemini/Antigravity thinking indicators, generous file-reading windows, and autopilot flag validation. Adds a shared global wiki root configuration with a /wiki slash command, fires reasoning start signals up front for Gemini/Antigravity models, adjusts the large-file reading discipline to use generous windows, and validates autopilot goal and integer flags.
 - **[0.7.20]** (2026-06-26) — OKF concept-memory retrieval gains a hybrid reranker ported from memsearch. Injection priority no longer rides one raw keyword score — it fuses two complementary ranked channels by Reciprocal Rank Fusion (RRF): IDF-weighted lexical relevance (the sparse/BM25 channel, so rare discriminating terms steer recall) and concept-graph proximity (the local dense/semantic-neighbour channel, so a hub linked from multiple query hits surfaces even with no keyword of its own). All embedding-free and deterministic, layered atop the existing failure-first tier and pinned-invariant reserved budget.
 - **[0.7.19]** (2026-06-26) — The live model picker gains gajae-code's `/model` provider tabs, and skill invocation is consolidated onto a single `$` entrypoint. The picker now shows an `ALL` tab plus one tab per provider that `tab`/`shift+tab` cycles, and skills (including their declared aliases) are invoked only via `$` — the slash palette stays builtins-only.
-- **[0.7.18]** (2026-06-26) — Slash-command discovery and the `/model` flow reach gajae-code parity. The slash palette/autocomplete now fuzzy-matches command names (with a description fallback for intent-style queries), resolved skills can contribute their own `/aliases` as real dispatchable commands, and `/model` runs gjc's two-menu target → reasoning flow so a picked model can be assigned to the default or any subagent role with its own thinking budget.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jeo-code",
-  "version": "0.7.22",
+  "version": "0.7.23",
   "description": "Clean, highly optimized AI coding agent using spec-first loop",
   "type": "module",
   "main": "src/cli.ts",

package/src/agent/state.ts

@@ -174,7 +174,7 @@ export interface WorkflowState {
 /** The built-in default model when neither disk config nor JEO_DEFAULT_MODEL provides one.
  *  Shared by envDefaultConfig (runtime) and readRawGlobalConfig (persistence base) so a
  *  fresh-install saveConfigPatch never bakes a DIFFERENT default than the runtime resolves. */
-const DEFAULT_MODEL = "claude-sonnet-4-5";
+const DEFAULT_MODEL = "claude-sonnet-4-6";
 
 /**
  * Resolve the global config directory at call time (not import time) so that a

package/src/ai/model-catalog-compat.ts

@@ -22,7 +22,7 @@ export interface ModelCatalogEntry {
 }
 
 /** Canonical ids that should be surfaced as a provider's recommended default. */
-const RECOMMENDED = new Set(["claude-sonnet-4-5", "gpt-4o", "gemini-2.0-flash", "antigravity/gemini-3-pro-low", "qwen2.5"]);
+const RECOMMENDED = new Set(["claude-sonnet-4-6", "gpt-4o", "gemini-2.0-flash", "antigravity/gemini-3-pro-low", "qwen2.5"]);
 
 export function normalizeModelId(id: string): string {
   return (id ?? "").trim().toLowerCase();

package/src/ai/model-catalog.ts

@@ -35,14 +35,11 @@ const FULL: ThinkLevel[] = ["minimal", "low", "medium", "high", "xhigh"];
 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",
-  "claude-sonnet-4-5-thinking",
   "claude-sonnet-4-6",
   "claude-sonnet-4-6-thinking",
   "gemini-2.5-flash",
@@ -60,18 +57,23 @@ export const ANTIGRAVITY_MODELS = [
 /** A curated set of common public models with their documented capabilities. */
 export const MODEL_CATALOG: readonly CatalogModel[] = [
   // Anthropic
-  { canonical: "claude-3-5-sonnet", provider: "anthropic", providerModel: "claude-3-5-sonnet-20241022", contextTokens: 200_000, maxOutputTokens: 8192, thinking: [], images: true },
   { canonical: "claude-haiku-4-5", provider: "anthropic", providerModel: "claude-haiku-4-5-20251001", contextTokens: 200_000, maxOutputTokens: 64_000, thinking: FULL, images: true },
-  { 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: opus 4.6+ use Anthropic ADAPTIVE thinking (type:"adaptive" + output_config.effort).
   // opus 4.7/4.8 OMIT visible thought unless the request opts into `display: "summarized"` —
   // anthropic.ts sets that on the adaptive transport so reasoning streams again (gjc parity).
   // The nativizable path still replays signature-only thinking blocks 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 },
+  // The 4.6 generation onward is 1M context / 128k sync max output (Anthropic docs:
+  // Opus 4.8 & Sonnet 5 comparison table; Opus 4.6/4.7, Sonnet 4.6 share the gen's
+  // dateless-snapshot 1M/128k + 300k batch-output beta). Dated pre-4.6 ids keep 200k/64k.
+  { canonical: "claude-opus-4-6", provider: "anthropic", providerModel: "claude-opus-4-6", contextTokens: 1_000_000, maxOutputTokens: 128_000, thinking: FULL, images: true },
+  { canonical: "claude-opus-4-7", provider: "anthropic", providerModel: "claude-opus-4-7", contextTokens: 1_000_000, maxOutputTokens: 128_000, thinking: FULL, images: true },
+  { canonical: "claude-opus-4-8", provider: "anthropic", providerModel: "claude-opus-4-8", contextTokens: 1_000_000, maxOutputTokens: 128_000, thinking: FULL, images: true },
+  { canonical: "claude-sonnet-4-6", provider: "anthropic", providerModel: "claude-sonnet-4-6", contextTokens: 1_000_000, maxOutputTokens: 128_000, thinking: FULL, images: true },
+  { canonical: "claude-sonnet-5", provider: "anthropic", providerModel: "claude-sonnet-5", contextTokens: 1_000_000, maxOutputTokens: 128_000, thinking: FULL, images: true },
+  // Fable 5 = Anthropic's most capable widely-released model (adaptive thinking always on);
+  // Mythos 5 is limited-availability (Project Glasswing) but callable by id for approved accounts.
+  { canonical: "claude-fable-5", provider: "anthropic", providerModel: "claude-fable-5", contextTokens: 1_000_000, maxOutputTokens: 128_000, thinking: FULL, images: true },
+  { canonical: "claude-mythos-5", provider: "anthropic", providerModel: "claude-mythos-5", contextTokens: 1_000_000, maxOutputTokens: 128_000, thinking: FULL, images: true },
   // OpenAI
   { canonical: "gpt-4o", provider: "openai", providerModel: "gpt-4o", contextTokens: 128_000, maxOutputTokens: 16_384, thinking: [], images: true },
   { canonical: "gpt-4o-mini", provider: "openai", providerModel: "gpt-4o-mini", contextTokens: 128_000, maxOutputTokens: 16_384, thinking: [], images: true },
@@ -200,7 +202,7 @@ export function inferCatalogMetadata(modelId: string): CatalogModel | undefined
 
   // Anthropic Claude: opus/sonnet/haiku. Major version >= 4 ships extended
   // thinking (mirrors every catalogued claude-4-x entry); claude-3-x does not.
-  const claude = id.match(/^claude-(opus|sonnet|haiku)-(\d+)(?:[-.](\d+))?/);
+  const claude = id.match(/^claude-(opus|sonnet|haiku|fable|mythos)-(\d+)(?:[-.](\d+))?/);
   if (claude) {
     const major = Number(claude[2]);
     const thinking = major >= 4 ? FULL : [];
@@ -208,8 +210,8 @@ export function inferCatalogMetadata(modelId: string): CatalogModel | undefined
       canonical: raw,
       provider: antigravity ? "antigravity" : "anthropic",
       providerModel: id,
-      contextTokens: 200_000,
-      maxOutputTokens: claude[1] === "haiku" ? 64_000 : 64_000,
+      contextTokens: major >= 5 ? 1_000_000 : 200_000,
+      maxOutputTokens: claude[1] === "haiku" ? 64_000 : major >= 5 ? 128_000 : 64_000,
       thinking,
       images: true,
       company: antigravity ? "Anthropic via Antigravity" : "Anthropic",

package/src/ai/model-manager.ts

@@ -160,7 +160,7 @@ export interface ModelManager {
   resolveProvider: typeof resolveProvider;
 }
 
-const ALIAS_DEFAULTS = { fast: "ollama/qwen2.5:0.5b", local: "ollama/qwen2.5:0.5b", sonnet: "claude-sonnet-4-5", opus: "claude-opus-4-5", haiku: "claude-haiku-4-5", gpt: "gpt-5.5", flash: "gemini-2.5-flash", grok: "grok-4.3" };
+const ALIAS_DEFAULTS = { fast: "ollama/qwen2.5:0.5b", local: "ollama/qwen2.5:0.5b", sonnet: "claude-sonnet-4-6", opus: "claude-opus-4-6", haiku: "claude-haiku-4-5", gpt: "gpt-5.5", flash: "gemini-2.5-flash", grok: "grok-4.3" };
 
 /**
  * Build retry options from a config `retry` budget (gjc parity). `requestMaxRetries`

package/src/ai/model-registry.ts

@@ -9,8 +9,8 @@ export interface ModelAliases {
 export const BUILTIN_ALIASES: ModelAliases = {
   fast: "ollama/qwen2.5:0.5b",
   local: "ollama/qwen2.5:0.5b",
-  sonnet: "claude-sonnet-4-5",
-  opus: "claude-opus-4-5",
+  sonnet: "claude-sonnet-4-6",
+  opus: "claude-opus-4-6",
   haiku: "claude-haiku-4-5",
   gpt: "gpt-5.5",
   flash: "gemini-2.5-flash",

package/src/ai/pricing.ts

@@ -25,7 +25,13 @@ export interface TokenUsage {
  */
 const PRICE_TABLE: ReadonlyArray<readonly [pattern: string, price: ModelPrice]> = [
   // Anthropic Claude
+  // 4.6-generation specifics (Anthropic docs pricing) — MUST precede the generic
+  // `claude-opus`/`claude-sonnet` families so the newer, cheaper Opus tier wins.
+  ["claude-opus-4-8", { inPerM: 5, outPerM: 25 }],
+  ["claude-fable", { inPerM: 10, outPerM: 50 }],
+  ["claude-mythos", { inPerM: 10, outPerM: 50 }],
   ["claude-opus", { inPerM: 15, outPerM: 75 }],
+  ["claude-sonnet-5", { inPerM: 2, outPerM: 10 }],
   ["claude-sonnet", { inPerM: 3, outPerM: 15 }],
   ["claude-haiku", { inPerM: 0.8, outPerM: 4 }],
   ["opus", { inPerM: 15, outPerM: 75 }],

package/src/ai/providers/anthropic.ts

@@ -108,34 +108,44 @@ function anthropicThinkingBudget(effort: CallOptions["reasoningEffort"], maxToke
 /** Parse an Anthropic model id's family + version for thinking-transport selection.
  *  Matches the modern `claude-<family>-<major>-<minor>[...]` naming (opus/sonnet/haiku 4.x+);
  *  legacy ids (claude-3-5-sonnet) and non-Anthropic-compatible names return undefined. */
-function parseAnthropicVersion(model: string): { kind: "opus" | "sonnet" | "haiku"; major: number; minor: number } | undefined {
-  const m = /claude-(opus|sonnet|haiku)-(\d+)-(\d+)/.exec(model);
+function parseAnthropicVersion(model: string): { kind: "opus" | "sonnet" | "haiku" | "fable" | "mythos"; major: number; minor: number } | undefined {
+  // `<major>-<minor>` (opus/sonnet/haiku 4.x) OR a single `<major>` (Sonnet 5, Fable 5,
+  // Mythos 5 — the dateless 5th-gen ids), with new families fable/mythos. Legacy ids
+  // (claude-3-5-sonnet: number before family) and non-Anthropic names return undefined.
+  const m = /claude-(opus|sonnet|haiku|fable|mythos)-(\d+)(?:-(\d+))?/.exec(model);
   if (!m) return undefined;
-  return { kind: m[1] as "opus" | "sonnet" | "haiku", major: Number(m[2]), minor: Number(m[3]) };
+  return { kind: m[1] as "opus" | "sonnet" | "haiku" | "fable" | "mythos", major: Number(m[2]), minor: m[3] !== undefined ? Number(m[3]) : 0 };
 }
 
 /** Adaptive thinking `display` is supported starting with Opus 4.7. Without it, Opus 4.7/4.8
  *  OMIT thinking content entirely (tokens billed, signature present, but zero visible thought —
  *  the "reasoning doesn't show" bug). Older adaptive models (Opus 4.6, Sonnet 4.6+) reject the
- *  field, so it is gated to Opus ≥ 4.7. (gjc: supportsAdaptiveThinkingDisplay) */
+ *  field, so it is gated to Opus ≥ 4.7 and every 5th-gen+ model. (gjc: supportsAdaptiveThinkingDisplay) */
 function supportsAdaptiveThinkingDisplay(model: string): boolean {
   const v = parseAnthropicVersion(model);
-  if (!v || v.kind !== "opus") return false;
-  return v.major > 4 || (v.major === 4 && v.minor >= 7);
+  if (!v) return false;
+  // display:"summarized" was introduced at Opus 4.7 and carried forward, so every
+  // 5th-generation+ model (Sonnet 5, Fable 5, Mythos 5, …) supports it too. Only the
+  // first adaptive gen (Opus 4.6, Sonnet 4.6) rejects the field.
+  if (v.major >= 5) return true;
+  return v.kind === "opus" && v.major === 4 && v.minor >= 7;
 }
 
 /** Thinking transport for a model (gjc parity — inferThinkingControlMode):
  *  - Anthropic ≥ 4.6 → "adaptive" (model decides depth; effort rides output_config, NO budget)
- *  - Anthropic 4.5   → "budget-effort" (budget_tokens + output_config effort)
- *  - otherwise       → "budget" (budget_tokens only).
+ *  - Anthropic 4.5 sonnet/opus → "budget-effort" (budget_tokens + output_config effort)
+ *  - otherwise (incl. Haiku 4.5) → "budget" (budget_tokens only).
  *  The adaptive shift is the core opus-4.7/4.8 reasoning fix: those models reject the legacy
- *  budget transport's visible-thought contract and require type:"adaptive" + display:summarized. */
+ *  budget transport's visible-thought contract and require type:"adaptive" + display:summarized.
+ *  Haiku 4.5 supports budget_tokens thinking but REJECTS output_config.effort ("This model does
+ *  not support the effort parameter"), so it stays on the plain budget transport unlike its
+ *  sonnet/opus 4.5 siblings. */
 type AnthropicThinkingMode = "adaptive" | "budget-effort" | "budget";
 function anthropicThinkingMode(model: string): AnthropicThinkingMode {
   const v = parseAnthropicVersion(model);
   if (!v) return "budget";
   if (v.major > 4 || (v.major === 4 && v.minor >= 6)) return "adaptive";
-  if (v.major === 4 && v.minor === 5) return "budget-effort";
+  if (v.major === 4 && v.minor === 5 && v.kind !== "haiku") return "budget-effort";
   return "budget";
 }
 

package/src/ai/providers/gemini.ts

@@ -73,7 +73,7 @@ export function geminiNativizable(m: Message, modelKey: string, thinkingEnabled:
 export function buildGeminiPayload(messages: Message[], options: CallOptions, stripArtifacts = false): { geminiModel: string; payload: Record<string, unknown> } {
   const resolvedModel = options.model.replace(/^(google|gemini)\//, "");
   let geminiModel = resolvedModel;
-  if (!geminiModel || geminiModel === "claude-3-5-sonnet") geminiModel = "gemini-2.0-flash";
+  if (!geminiModel || geminiModel.startsWith("claude-")) geminiModel = "gemini-2.0-flash";
 
   const systemPrompt = options.systemPrompt ?? messages.find(m => m.role === "system")?.content;
   const thinkingBudget = geminiThinkingBudget(geminiModel, options.reasoningEffort, options.maxTokens);

package/src/commands/setup.ts

@@ -27,7 +27,7 @@ function reportModelChoice(r: { warning?: string; suggestions: string[] }): void
 type ProviderChoice = "anthropic" | "openai" | "gemini" | "ollama" | "lmstudio" | "openai-compatible";
 
 const DEFAULT_MODELS: Record<ProviderChoice, string> = {
-  anthropic: "claude-sonnet-4-5",
+  anthropic: "claude-sonnet-4-6",
   openai: "gpt-4o",
   gemini: "gemini-2.0-flash",
   ollama: "ollama/llama3.1:8b",

package/src/tui/components/themes.ts

@@ -236,7 +236,7 @@ export function resetThemeConfigCache(): void {
 
 function getExplicitThemeFromConfig(env: EnvLike): string | undefined {
   const home = os.homedir ? os.homedir() : undefined;
-  const dir = env.JEO_CONFIG_DIR || env.JEO_CONFIG_DIR || (home ? path.join(home, ".jeo") : undefined);
+  const dir = env.JEO_CONFIG_DIR || (home ? path.join(home, ".jeo") : undefined);
   if (!dir) return undefined;
   if (configThemeCache && configThemeCache.dir === dir) return configThemeCache.value;
   const filePath = path.join(dir, "config.json");