jeo-code 0.7.57 → 0.7.58

package/CHANGELOG.md

@@ -6,6 +6,23 @@ 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`.
 
+## [0.7.58] - 2026-07-07
+_Applied the previous entry's `routing.crossProviderPool` to the real live session config, then deep-researched every catalogued model's actual public release date (2026-07 sourced, per-provider parallel research with citations) to answer "모델 설정은 2026년도 기준으로 딥서치해서 모델리스트 최신순으로 정렬" — while researching, found and fixed a genuine ranking bug this surfaced: `strongestCredentialed`'s tiebreak on a full capability tie (identical thinking/output/context) fell through to a raw alphabetical canonical-id compare, which silently picked the OLDEST model in a same-spec family (`claude-opus-4-6` over `claude-opus-4-7`/`4-8`, purely because `"4-6" < "4-8"` as a string) — confirmed reproducible before the fix, confirmed corrected after._
+
+### Added
+- **`CatalogModel.releaseDate`** (`"YYYY-MM"`) on every catalog entry — deep-research sourced from each provider's own announcement (Anthropic/OpenAI/Google/xAI/Moonshot direct web_search per family; Tencent-hosted rebrands (DeepSeek/MiniMax/Zhipu GLM/Hunyuan) traced to the ORIGINAL developer's release, not Tencent's hosting-catalog appearance date). `gpt-5.4-mini` was never added to the catalog — confirmed absent both before and after this pass, per explicit request.
+
+### Changed
+- **`MODEL_CATALOG` reordered newest-first within every provider block** for human readability (routing correctness never depended on array order — the ranking functions below now sort/tiebreak explicitly).
+- **Recency tiebreak replaces the arbitrary alphabetical one** in `cheapestCredentialed`/`strongestCredentialed`/`compareStrengthAscending` (`src/agent/prompt-router.ts`) — on an exact capability/cost tie, the NEWER `releaseDate` now wins (a missing date always sorts as oldest, so an unconfirmed date can never silently outrank a verified-newer model). Fixes the confirmed opus-4-6/4-7/4-8 bug above.
+- **`catalogForProvider`'s secondary sort** (`src/ai/model-catalog-compat.ts`) now orders by `releaseDate` (newest first) instead of alphabetical id — this is the actual list order `/model`'s live picker and `jeo setup` show a user, so "정렬" now reaches the real user-facing surface, not just the raw catalog array.
+- **`RECOMMENDED` provider defaults refreshed** to the current (2026-07) general-availability flagship per provider: `claude-sonnet-5` (was `claude-sonnet-4-6`), `gpt-5.5` (was `gpt-4o`), `gemini-3-flash` (was `gemini-2.0-flash`), `antigravity/gpt-5.5` (was `antigravity/gemini-3-pro-low`).
+
+### Verified
+- `bun run typecheck` clean; full suite 2710/2710 pass across 281 files (1 pre-existing unrelated flaky test — `session.test.ts`'s global-`JSON.parse`-mock count assertion, confirmed passing in isolation and on rerun — not a regression from this change).
+- Live-executed the exact reported bug before AND after the fix: `strongestCredentialed(anthropicOnlyConfig, m => m.canonical.startsWith("claude-opus"))` returned `claude-opus-4-6` (oldest) before, `claude-opus-4-8` (newest, correct) after.
+- Re-applied `routing.crossProviderPool: true` to the live user config (a concurrent interactive session had reset it via an unrelated `/model` command mid-turn) and reconfirmed via `jeo doctor`: all 4 tiers correctly resolve through the cross-provider pool across anthropic/gemini/antigravity.
+
 ## [0.7.57] - 2026-07-07
 _"동급모델간 크로스 프로바이더 라우팅이 동작하게 개선" — v0.7.56's tier auto-select was single-winner by design (always the one cheapest/strongest model), so a user with `roles.smol` pinned (or simply multiple credentialed providers) never saw actual distribution across equivalent-class models. Deep-research-informed redesign: production LLM routers (LiteLLM, Bifrost/VoidLLM) model this as a named "model group" spanning provider deployments with a distribution strategy, not a single deterministic pick — jeo now supports both, opt-in._
 

package/README.ja.md

@@ -259,11 +259,11 @@ 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`) -->
+- **[0.7.58]** (2026-07-07) — Applied the previous entry's `routing.crossProviderPool` to the real live session config, then deep-researched every catalogued model's actual public release date (2026-07 sourced, per-provider parallel research with citations) to answer "모델 설정은 2026년도 기준으로 딥서치해서 모델리스트 최신순으로 정렬" — while researching, found and fixed a genuine ranking bug this surfaced: `strongestCredentialed`'s tiebreak on a full capability tie (identical thinking/output/context) fell through to a raw alphabetical canonical-id compare, which silently picked the OLDEST model in a same-spec family (`claude-opus-4-6` over `claude-opus-4-7`/`4-8`, purely because `"4-6" < "4-8"` as a string) — confirmed reproducible before the fix, confirmed corrected after.
 - **[0.7.57]** (2026-07-07) — "동급모델간 크로스 프로바이더 라우팅이 동작하게 개선" — v0.7.56's tier auto-select was single-winner by design (always the one cheapest/strongest model), so a user with `roles.smol` pinned (or simply multiple credentialed providers) never saw actual distribution across equivalent-class models. Deep-research-informed redesign: production LLM routers (LiteLLM, Bifrost/VoidLLM) model this as a named "model group" spanning provider deployments with a distribution strategy, not a single deterministic pick — jeo now supports both, opt-in.
 - **[0.7.56]** (2026-07-07) — "서로다른 프로바이더로 급에 따라 나눠서 설정하도록 개선" — PromptRouter's `trivial`/`complex` tiers previously collapsed to `defaultModel` whenever `roles.smol`/`roles.slow`/`routing.tiers.*` were left unconfigured (the documented "safe no-op absent configuration" contract), which meant a user with multiple providers credentialed never actually got cross-provider routing without hand-picking a model per tier. Also the long-term ask: routing must stay correct as jeo's model catalog evolves, never a hand-maintained tier→model table that goes stale.
 - **[0.7.55]** (2026-07-07) — Cross-provider routing (PromptRouter, v0.7.47+) already named the routed tier in the status bar (v0.7.52), but nothing surfaced WHICH model/provider actually produced a turn's reasoning in the Thinking-block surfaces — a gap noticed while manually verifying the v0.7.52 status-bar work end-to-end.
 - **[0.7.54]** (2026-07-06) — Root-cause fix for a live-reported GPT-5.5 (Codex/ChatGPT OAuth backend) failure: "Error: stream exceeded the overall deadline (JEO_STREAM_MAX_MS) — slow-drip stream aborted". Deep-dive traced this to a REGRESSION in v0.7.42 — a separate, correct fix for a genuinely-different bug (a connected-but-never-terminating stream) silently flipped `streamMaxMs()`'s default from opt-in-off to an ALWAYS-ON 300s overall wall-clock cap, which then killed any HIGH/XHIGH-reasoning-effort completion (GPT-5.5/o3-class) whose ACTIVELY-emitting generation legitimately ran past 5 minutes — OpenAI's own guidance states xhigh trades latency for depth by design. The non-streaming `call()` path (used by every subagent, compaction, and goal-verify call, since none wire `onModelStream`) carried the IDENTICAL bug with zero idle/activity tracking at all, exposed under a different, unhelpful raw `DOMException: The operation timed out.` message instead.
-- **[0.7.53]** (2026-07-06) — Verified PromptRouter end-to-end (63 pre-existing tests re-run, all passing; a live `jeo doctor --json`/human-output smoke test confirms real wiring, not just mocks) and closed the one genuine remaining gap: the v0.7.51 per-turn credential-readiness veto protected a running session reactively, but nothing caught a misconfigured `roles.smol`/`roles.slow`/`routing.tiers.*.model` proactively at setup time.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.ko.md

@@ -260,11 +260,11 @@ 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`) -->
+- **[0.7.58]** (2026-07-07) — Applied the previous entry's `routing.crossProviderPool` to the real live session config, then deep-researched every catalogued model's actual public release date (2026-07 sourced, per-provider parallel research with citations) to answer "모델 설정은 2026년도 기준으로 딥서치해서 모델리스트 최신순으로 정렬" — while researching, found and fixed a genuine ranking bug this surfaced: `strongestCredentialed`'s tiebreak on a full capability tie (identical thinking/output/context) fell through to a raw alphabetical canonical-id compare, which silently picked the OLDEST model in a same-spec family (`claude-opus-4-6` over `claude-opus-4-7`/`4-8`, purely because `"4-6" < "4-8"` as a string) — confirmed reproducible before the fix, confirmed corrected after.
 - **[0.7.57]** (2026-07-07) — "동급모델간 크로스 프로바이더 라우팅이 동작하게 개선" — v0.7.56's tier auto-select was single-winner by design (always the one cheapest/strongest model), so a user with `roles.smol` pinned (or simply multiple credentialed providers) never saw actual distribution across equivalent-class models. Deep-research-informed redesign: production LLM routers (LiteLLM, Bifrost/VoidLLM) model this as a named "model group" spanning provider deployments with a distribution strategy, not a single deterministic pick — jeo now supports both, opt-in.
 - **[0.7.56]** (2026-07-07) — "서로다른 프로바이더로 급에 따라 나눠서 설정하도록 개선" — PromptRouter's `trivial`/`complex` tiers previously collapsed to `defaultModel` whenever `roles.smol`/`roles.slow`/`routing.tiers.*` were left unconfigured (the documented "safe no-op absent configuration" contract), which meant a user with multiple providers credentialed never actually got cross-provider routing without hand-picking a model per tier. Also the long-term ask: routing must stay correct as jeo's model catalog evolves, never a hand-maintained tier→model table that goes stale.
 - **[0.7.55]** (2026-07-07) — Cross-provider routing (PromptRouter, v0.7.47+) already named the routed tier in the status bar (v0.7.52), but nothing surfaced WHICH model/provider actually produced a turn's reasoning in the Thinking-block surfaces — a gap noticed while manually verifying the v0.7.52 status-bar work end-to-end.
 - **[0.7.54]** (2026-07-06) — Root-cause fix for a live-reported GPT-5.5 (Codex/ChatGPT OAuth backend) failure: "Error: stream exceeded the overall deadline (JEO_STREAM_MAX_MS) — slow-drip stream aborted". Deep-dive traced this to a REGRESSION in v0.7.42 — a separate, correct fix for a genuinely-different bug (a connected-but-never-terminating stream) silently flipped `streamMaxMs()`'s default from opt-in-off to an ALWAYS-ON 300s overall wall-clock cap, which then killed any HIGH/XHIGH-reasoning-effort completion (GPT-5.5/o3-class) whose ACTIVELY-emitting generation legitimately ran past 5 minutes — OpenAI's own guidance states xhigh trades latency for depth by design. The non-streaming `call()` path (used by every subagent, compaction, and goal-verify call, since none wire `onModelStream`) carried the IDENTICAL bug with zero idle/activity tracking at all, exposed under a different, unhelpful raw `DOMException: The operation timed out.` message instead.
-- **[0.7.53]** (2026-07-06) — Verified PromptRouter end-to-end (63 pre-existing tests re-run, all passing; a live `jeo doctor --json`/human-output smoke test confirms real wiring, not just mocks) and closed the one genuine remaining gap: the v0.7.51 per-turn credential-readiness veto protected a running session reactively, but nothing caught a misconfigured `roles.smol`/`roles.slow`/`routing.tiers.*.model` proactively at setup time.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.md

@@ -264,11 +264,11 @@ 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`) -->
+- **[0.7.58]** (2026-07-07) — Applied the previous entry's `routing.crossProviderPool` to the real live session config, then deep-researched every catalogued model's actual public release date (2026-07 sourced, per-provider parallel research with citations) to answer "모델 설정은 2026년도 기준으로 딥서치해서 모델리스트 최신순으로 정렬" — while researching, found and fixed a genuine ranking bug this surfaced: `strongestCredentialed`'s tiebreak on a full capability tie (identical thinking/output/context) fell through to a raw alphabetical canonical-id compare, which silently picked the OLDEST model in a same-spec family (`claude-opus-4-6` over `claude-opus-4-7`/`4-8`, purely because `"4-6" < "4-8"` as a string) — confirmed reproducible before the fix, confirmed corrected after.
 - **[0.7.57]** (2026-07-07) — "동급모델간 크로스 프로바이더 라우팅이 동작하게 개선" — v0.7.56's tier auto-select was single-winner by design (always the one cheapest/strongest model), so a user with `roles.smol` pinned (or simply multiple credentialed providers) never saw actual distribution across equivalent-class models. Deep-research-informed redesign: production LLM routers (LiteLLM, Bifrost/VoidLLM) model this as a named "model group" spanning provider deployments with a distribution strategy, not a single deterministic pick — jeo now supports both, opt-in.
 - **[0.7.56]** (2026-07-07) — "서로다른 프로바이더로 급에 따라 나눠서 설정하도록 개선" — PromptRouter's `trivial`/`complex` tiers previously collapsed to `defaultModel` whenever `roles.smol`/`roles.slow`/`routing.tiers.*` were left unconfigured (the documented "safe no-op absent configuration" contract), which meant a user with multiple providers credentialed never actually got cross-provider routing without hand-picking a model per tier. Also the long-term ask: routing must stay correct as jeo's model catalog evolves, never a hand-maintained tier→model table that goes stale.
 - **[0.7.55]** (2026-07-07) — Cross-provider routing (PromptRouter, v0.7.47+) already named the routed tier in the status bar (v0.7.52), but nothing surfaced WHICH model/provider actually produced a turn's reasoning in the Thinking-block surfaces — a gap noticed while manually verifying the v0.7.52 status-bar work end-to-end.
 - **[0.7.54]** (2026-07-06) — Root-cause fix for a live-reported GPT-5.5 (Codex/ChatGPT OAuth backend) failure: "Error: stream exceeded the overall deadline (JEO_STREAM_MAX_MS) — slow-drip stream aborted". Deep-dive traced this to a REGRESSION in v0.7.42 — a separate, correct fix for a genuinely-different bug (a connected-but-never-terminating stream) silently flipped `streamMaxMs()`'s default from opt-in-off to an ALWAYS-ON 300s overall wall-clock cap, which then killed any HIGH/XHIGH-reasoning-effort completion (GPT-5.5/o3-class) whose ACTIVELY-emitting generation legitimately ran past 5 minutes — OpenAI's own guidance states xhigh trades latency for depth by design. The non-streaming `call()` path (used by every subagent, compaction, and goal-verify call, since none wire `onModelStream`) carried the IDENTICAL bug with zero idle/activity tracking at all, exposed under a different, unhelpful raw `DOMException: The operation timed out.` message instead.
-- **[0.7.53]** (2026-07-06) — Verified PromptRouter end-to-end (63 pre-existing tests re-run, all passing; a live `jeo doctor --json`/human-output smoke test confirms real wiring, not just mocks) and closed the one genuine remaining gap: the v0.7.51 per-turn credential-readiness veto protected a running session reactively, but nothing caught a misconfigured `roles.smol`/`roles.slow`/`routing.tiers.*.model` proactively at setup time.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.zh.md

@@ -259,11 +259,11 @@ 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`) -->
+- **[0.7.58]** (2026-07-07) — Applied the previous entry's `routing.crossProviderPool` to the real live session config, then deep-researched every catalogued model's actual public release date (2026-07 sourced, per-provider parallel research with citations) to answer "모델 설정은 2026년도 기준으로 딥서치해서 모델리스트 최신순으로 정렬" — while researching, found and fixed a genuine ranking bug this surfaced: `strongestCredentialed`'s tiebreak on a full capability tie (identical thinking/output/context) fell through to a raw alphabetical canonical-id compare, which silently picked the OLDEST model in a same-spec family (`claude-opus-4-6` over `claude-opus-4-7`/`4-8`, purely because `"4-6" < "4-8"` as a string) — confirmed reproducible before the fix, confirmed corrected after.
 - **[0.7.57]** (2026-07-07) — "동급모델간 크로스 프로바이더 라우팅이 동작하게 개선" — v0.7.56's tier auto-select was single-winner by design (always the one cheapest/strongest model), so a user with `roles.smol` pinned (or simply multiple credentialed providers) never saw actual distribution across equivalent-class models. Deep-research-informed redesign: production LLM routers (LiteLLM, Bifrost/VoidLLM) model this as a named "model group" spanning provider deployments with a distribution strategy, not a single deterministic pick — jeo now supports both, opt-in.
 - **[0.7.56]** (2026-07-07) — "서로다른 프로바이더로 급에 따라 나눠서 설정하도록 개선" — PromptRouter's `trivial`/`complex` tiers previously collapsed to `defaultModel` whenever `roles.smol`/`roles.slow`/`routing.tiers.*` were left unconfigured (the documented "safe no-op absent configuration" contract), which meant a user with multiple providers credentialed never actually got cross-provider routing without hand-picking a model per tier. Also the long-term ask: routing must stay correct as jeo's model catalog evolves, never a hand-maintained tier→model table that goes stale.
 - **[0.7.55]** (2026-07-07) — Cross-provider routing (PromptRouter, v0.7.47+) already named the routed tier in the status bar (v0.7.52), but nothing surfaced WHICH model/provider actually produced a turn's reasoning in the Thinking-block surfaces — a gap noticed while manually verifying the v0.7.52 status-bar work end-to-end.
 - **[0.7.54]** (2026-07-06) — Root-cause fix for a live-reported GPT-5.5 (Codex/ChatGPT OAuth backend) failure: "Error: stream exceeded the overall deadline (JEO_STREAM_MAX_MS) — slow-drip stream aborted". Deep-dive traced this to a REGRESSION in v0.7.42 — a separate, correct fix for a genuinely-different bug (a connected-but-never-terminating stream) silently flipped `streamMaxMs()`'s default from opt-in-off to an ALWAYS-ON 300s overall wall-clock cap, which then killed any HIGH/XHIGH-reasoning-effort completion (GPT-5.5/o3-class) whose ACTIVELY-emitting generation legitimately ran past 5 minutes — OpenAI's own guidance states xhigh trades latency for depth by design. The non-streaming `call()` path (used by every subagent, compaction, and goal-verify call, since none wire `onModelStream`) carried the IDENTICAL bug with zero idle/activity tracking at all, exposed under a different, unhelpful raw `DOMException: The operation timed out.` message instead.
-- **[0.7.53]** (2026-07-06) — Verified PromptRouter end-to-end (63 pre-existing tests re-run, all passing; a live `jeo doctor --json`/human-output smoke test confirms real wiring, not just mocks) and closed the one genuine remaining gap: the v0.7.51 per-turn credential-readiness veto protected a running session reactively, but nothing caught a misconfigured `roles.smol`/`roles.slow`/`routing.tiers.*.model` proactively at setup time.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jeo-code",
-  "version": "0.7.57",
+  "version": "0.7.58",
   "description": "Clean, highly optimized AI coding agent using spec-first loop",
   "type": "module",
   "main": "src/cli.ts",

package/src/agent/prompt-router.ts

@@ -233,6 +233,21 @@ function sizeClassFor(canonical: string): "small" | "mid" | "large" | null {
 
 const TIER_TO_SIZE_CLASS: Record<PromptTier, "small" | "mid" | "large"> = { trivial: "small", standard: "mid", high: "mid", complex: "large" };
 
+/** Compares `releaseDate` ("YYYY-MM", lexicographically sortable). `>0` when `a`
+ *  is NEWER than `b`. A missing date sorts as OLDEST on that side — an
+ *  unconfirmed date can never silently outrank a verified-newer model. Shared
+ *  recency tiebreak for `compareStrengthAscending`/`cheapestCredentialed`/
+ *  `strongestCredentialed`, replacing the arbitrary alphabetical canonical-id
+ *  tiebreak those used before (which, on a full capability tie, picked the
+ *  OLDEST id alphabetically — e.g. `claude-opus-4-6` beating `claude-opus-4-8`
+ *  as "strongest" purely because "4-6" < "4-8" as a string). */
+function compareRecency(a: CatalogModel, b: CatalogModel): number {
+  if (a.releaseDate === b.releaseDate) return 0;
+  if (!a.releaseDate) return -1;
+  if (!b.releaseDate) return 1;
+  return a.releaseDate < b.releaseDate ? -1 : 1;
+}
+
 /** Multi-key strength comparator (ascending: weakest first) — same ranking signals
  *  as `strongestCredentialed`'s single-winner tiebreak, reused here to bucket
  *  UNCLASSIFIED (no size-suffix) models into a tercile fallback. */
@@ -242,6 +257,8 @@ function compareStrengthAscending(a: CatalogModel, b: CatalogModel): number {
   if (xhighA !== xhighB) return xhighA - xhighB;
   if (a.maxOutputTokens !== b.maxOutputTokens) return a.maxOutputTokens - b.maxOutputTokens;
   if (a.contextTokens !== b.contextTokens) return a.contextTokens - b.contextTokens;
+  const recency = compareRecency(a, b);
+  if (recency !== 0) return recency;
   return a.canonical < b.canonical ? -1 : a.canonical > b.canonical ? 1 : 0;
 }
 
@@ -297,8 +314,10 @@ export function selectFromPool(pool: readonly string[], sessionId: string | unde
 /** Cheapest cloud model jeo has a credential for, computed LIVE off
  *  `MODEL_CATALOG`/`priceForModel` — picks up new/repriced catalog entries
  *  automatically, never a hand-maintained id. `null` when no credentialed
- *  model has a known price (caller falls back to `defaultModel`). Tiebreak:
- *  canonical id (deterministic across otherwise-equal candidates). */
+ *  model has a known price (caller falls back to `defaultModel`). Tiebreak on
+ *  an exact cost tie: NEWER `releaseDate` wins (a same-priced newer model is
+ *  likely a refined successor), then canonical id (deterministic fallback
+ *  when recency also ties or is unconfirmed on both sides). */
 export function cheapestCredentialed(config: RoutingConfig): string | null {
   let best: CatalogModel | null = null;
   let bestCost = Infinity;
@@ -312,9 +331,12 @@ export function cheapestCredentialed(config: RoutingConfig): string | null {
     const price = priceForModel(m.canonical);
     if (!price) continue;
     const cost = price.inPerM + price.outPerM;
-    if (cost < bestCost || (cost === bestCost && best && m.canonical < best.canonical)) {
+    if (cost < bestCost) {
       best = m;
       bestCost = cost;
+    } else if (cost === bestCost && best) {
+      const recency = compareRecency(m, best);
+      if (recency > 0 || (recency === 0 && m.canonical < best.canonical)) best = m;
     }
   }
   return best?.canonical ?? null;
@@ -322,13 +344,16 @@ export function cheapestCredentialed(config: RoutingConfig): string | null {
 
 /** Most capable cloud model jeo has a credential for, computed LIVE off
  *  `MODEL_CATALOG` — ranks by full (xhigh) thinking support first, then max
- *  output tokens, then context window, so a newly catalogued frontier model
- *  is picked up automatically without a hand-maintained id. `null` when no
- *  credentialed model qualifies (caller falls back to `defaultModel`).
- *  Tiebreak: canonical id (deterministic). Excludes `limitedAvailability`
- *  models (e.g. `claude-mythos-5`) — a provider credential doesn't imply
- *  access to a specific invite-only model; explicit `/model`/`routing.tiers`
- *  can still target one by id for approved accounts. */
+ *  output tokens, then context window, then NEWER `releaseDate` (a same-specs
+ *  model with a later release date is presumptively a refined successor — e.g.
+ *  `claude-opus-4-8` over `claude-opus-4-6`, which the OLD alphabetical
+ *  canonical-id tiebreak got backwards, since `"4-6" < "4-8"` picked the
+ *  OLDEST opus as "strongest"), then canonical id (final deterministic
+ *  fallback). `null` when no credentialed model qualifies (caller falls back
+ *  to `defaultModel`). Excludes `limitedAvailability` models (e.g.
+ *  `claude-mythos-5`) — a provider credential doesn't imply access to a
+ *  specific invite-only model; explicit `/model`/`routing.tiers` can still
+ *  target one by id for approved accounts. */
 export function strongestCredentialed(
   config: RoutingConfig,
   filter?: (m: CatalogModel) => boolean
@@ -344,6 +369,8 @@ export function strongestCredentialed(
     if (xhighM !== xhighBest) { if (xhighM > xhighBest) best = m; continue; }
     if (m.maxOutputTokens !== best.maxOutputTokens) { if (m.maxOutputTokens > best.maxOutputTokens) best = m; continue; }
     if (m.contextTokens !== best.contextTokens) { if (m.contextTokens > best.contextTokens) best = m; continue; }
+    const recency = compareRecency(m, best);
+    if (recency !== 0) { if (recency > 0) best = m; continue; }
     if (m.canonical < best.canonical) best = m;
   }
   return best?.canonical ?? null;

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

@@ -19,10 +19,18 @@ export interface ModelCatalogEntry {
   recommended?: boolean;
   note?: string;
   company?: string;
+  /** Public release date, `"YYYY-MM"` — see `CatalogModel.releaseDate`. Drives
+   *  `catalogForProvider`'s newest-first secondary sort. */
+  releaseDate?: string;
 }
 
-/** Canonical ids that should be surfaced as a provider's recommended default. */
-const RECOMMENDED = new Set(["claude-sonnet-4-6", "gpt-4o", "gemini-2.0-flash", "antigravity/gemini-3-pro-low", "qwen2.5"]);
+/** Canonical ids surfaced as a provider's recommended default — the current
+ *  (2026-07 deep-research verified) general-availability flagship per provider,
+ *  NOT necessarily the single most expensive/most-capable model (e.g. Anthropic's
+ *  actual top tier, claude-fable-5, is pricier than the "recommended" sonnet-5 —
+ *  recommended means "solid everyday default", not "strongest"). Re-verify and
+ *  update whenever a provider ships a new default-tier release. */
+const RECOMMENDED: Record<string, true> = { "claude-sonnet-5": true, "gpt-5.5": true, "gemini-3-flash": true, "antigravity/gpt-5.5": true, "qwen2.5": true };
 
 export function normalizeModelId(id: string): string {
   return (id ?? "").trim().toLowerCase();
@@ -35,9 +43,10 @@ function adapt(m: CatalogModel): ModelCatalogEntry {
     provider: m.provider,
     contextWindow: m.contextTokens,
     reasoning,
-    recommended: RECOMMENDED.has(m.canonical),
+    recommended: !!RECOMMENDED[m.canonical],
     note: `${formatTokens(m.contextTokens)} ctx${reasoning ? ", reasoning" : ""}`,
     company: m.company,
+    releaseDate: m.releaseDate,
   };
 }
 
@@ -50,12 +59,19 @@ export function findCatalogEntry(id: string): ModelCatalogEntry | undefined {
   return hit ? adapt(hit) : undefined;
 }
 
-/** Entries for a provider, recommended first then by id. */
+/** Entries for a provider, recommended first, then NEWEST-FIRST by `releaseDate`
+ *  (undated entries sort last, tiebroken by id) — this is the actual list order
+ *  `/model`'s live picker and `jeo setup`'s recommendation prompt show a user. */
 export function catalogForProvider(provider: ProviderName): ModelCatalogEntry[] {
   return catalogByProvider(provider)
     .map(adapt)
     .sort((a, b) => {
       if (!!b.recommended !== !!a.recommended) return b.recommended ? 1 : -1;
+      if (a.releaseDate !== b.releaseDate) {
+        if (!a.releaseDate) return 1;
+        if (!b.releaseDate) return -1;
+        return b.releaseDate.localeCompare(a.releaseDate);
+      }
       return a.id.localeCompare(b.id);
     });
 }

package/src/ai/model-catalog.ts

@@ -36,35 +36,59 @@ export interface CatalogModel {
    *  selection) excludes these; explicit `/model` or `routing.tiers.*.model`
    *  can still target them by id for approved accounts. */
   limitedAvailability?: boolean;
+  /** Public release date, `"YYYY-MM"` (lexicographically sortable) — deep-research
+   *  sourced from each provider's own announcement. Drives newest-first catalog
+   *  ordering and recency-based tiebreaks in prompt-router.ts's ranking functions
+   *  (`compareStrengthAscending`, `cheapestCredentialed`, `strongestCredentialed`)
+   *  so a genuinely newer same-tier model wins a tie instead of an arbitrary
+   *  alphabetical pick. Omitted (undefined) for ids with no confirmed public
+   *  date — these sort AFTER every dated entry within their block, never before,
+   *  so an unconfirmed date can never silently outrank a verified-newer model. */
+  releaseDate?: string;
 }
 
 const FULL: ThinkLevel[] = ["low", "medium", "high", "xhigh"];
 const STD: ThinkLevel[] = ["low", "medium", "high"];
 
+// [canonical model id, release YYYY-MM] tuples, deep-research sourced (Anthropic/
+// OpenAI/Google base-model announcement dates — antigravity is a hosting layer over
+// the SAME underlying models, not a separate release). Newest-first per family below;
+// -thinking/-high/-low suffixes are reasoning-effort variants of the SAME release.
 export const ANTIGRAVITY_MODELS = [
-  "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-4-6",
-  "claude-sonnet-4-6-thinking",
-  "gemini-2.5-flash",
-  "gemini-2.5-flash-thinking",
-  "gemini-2.5-pro",
-  "gemini-3-flash",
-  "gemini-3-pro-high",
-  "gemini-3-pro-low",
-  "gemini-3.1-pro-high",
-  "gemini-3.1-pro-low",
-  "gpt-oss-120b-medium",
-  "gpt-5.5",
+  ["gpt-5.5", "2026-04"],
+  ["gemini-3.1-pro-high", "2026-02"],
+  ["gemini-3.1-pro-low", "2026-02"],
+  ["claude-opus-4-8", "2026-05"],
+  ["claude-opus-4-8-thinking", "2026-05"],
+  ["claude-opus-4-7", "2026-04"],
+  ["claude-opus-4-7-thinking", "2026-04"],
+  ["claude-sonnet-4-6", "2026-02"],
+  ["claude-sonnet-4-6-thinking", "2026-02"],
+  ["claude-opus-4-6-thinking", "2026-02"],
+  ["gemini-3-flash", "2025-12"],
+  ["gemini-3-pro-high", "2025-11"],
+  ["gemini-3-pro-low", "2025-11"],
+  ["gpt-oss-120b-medium", "2025-08"],
+  ["gemini-2.5-flash", "2025-06"],
+  ["gemini-2.5-flash-thinking", "2025-06"],
+  ["gemini-2.5-pro", "2025-03"],
 ] as const;
 
-/** A curated set of common public models with their documented capabilities. */
+/** A curated set of common public models with their documented capabilities.
+ *  Ordered NEWEST-FIRST within each provider block per `releaseDate`
+ *  (deep-research sourced from each provider's own announcement — see the
+ *  v0.7.58 CHANGELOG entry for the full per-model source list). Purely for
+ *  human readability / "what's current" at a glance — routing correctness
+ *  does not depend on array order: `prompt-router.ts`'s ranking functions
+ *  (`cheapestCredentialed`/`strongestCredentialed`/`compareStrengthAscending`)
+ *  now tiebreak on `releaseDate` directly rather than relying on position. */
 export const MODEL_CATALOG: readonly CatalogModel[] = [
-  // Anthropic
-  { canonical: "claude-haiku-4-5", provider: "anthropic", providerModel: "claude-haiku-4-5-20251001", contextTokens: 200_000, maxOutputTokens: 64_000, thinking: FULL, images: true },
+  // Anthropic (newest first: sonnet-5 > fable-5 > opus-4-8 > opus-4-7 > sonnet-4-6 > opus-4-6 > haiku-4-5)
+  { canonical: "claude-sonnet-5", provider: "anthropic", providerModel: "claude-sonnet-5", contextTokens: 1_000_000, maxOutputTokens: 128_000, thinking: FULL, images: true, releaseDate: "2026-06" },
+  // 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, releaseDate: "2026-06" },
+  { canonical: "claude-mythos-5", provider: "anthropic", providerModel: "claude-mythos-5", contextTokens: 1_000_000, maxOutputTokens: 128_000, thinking: FULL, images: true, limitedAvailability: true, releaseDate: "2026-06" },
   // 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).
@@ -72,50 +96,54 @@ export const MODEL_CATALOG: readonly CatalogModel[] = [
   // 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, limitedAvailability: 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 },
-  { canonical: "gpt-4.1", provider: "openai", providerModel: "gpt-4.1", contextTokens: 1_000_000, maxOutputTokens: 32_768, thinking: [], images: true },
-  { canonical: "o3", provider: "openai", providerModel: "o3", contextTokens: 200_000, maxOutputTokens: 100_000, thinking: STD, images: true },
-  { canonical: "o3-mini", provider: "openai", providerModel: "o3-mini", contextTokens: 200_000, maxOutputTokens: 100_000, thinking: STD, images: false },
-  { canonical: "o4-mini", provider: "openai", providerModel: "o4-mini", contextTokens: 200_000, maxOutputTokens: 100_000, thinking: STD, images: true },
-  { canonical: "gpt-5.5", provider: "openai", providerModel: "gpt-5.5", contextTokens: 400_000, maxOutputTokens: 128_000, thinking: FULL, images: true },
-  { canonical: "gpt-5.4", provider: "openai", providerModel: "gpt-5.4", contextTokens: 400_000, maxOutputTokens: 128_000, thinking: FULL, images: true },
-  // xAI (Grok) — OpenAI-compatible at https://api.x.ai/v1 (XAI_API_KEY)
-  { canonical: "grok-4.3", provider: "xai", providerModel: "grok-4.3", contextTokens: 256_000, maxOutputTokens: 64_000, thinking: FULL, images: true },
-  { canonical: "grok-4-fast-reasoning", provider: "xai", providerModel: "grok-4-fast-reasoning", contextTokens: 2_000_000, maxOutputTokens: 64_000, thinking: FULL, images: true },
-  { canonical: "grok-4-fast-non-reasoning", provider: "xai", providerModel: "grok-4-fast-non-reasoning", contextTokens: 2_000_000, maxOutputTokens: 64_000, thinking: [], images: true },
-  { canonical: "grok-code-fast-1", provider: "xai", providerModel: "grok-code-fast-1", contextTokens: 256_000, maxOutputTokens: 64_000, thinking: FULL, images: false },
-  // Kimi (Moonshot) — OpenAI-compatible at https://api.moonshot.ai/v1 (KIMI_API_KEY)
-  { canonical: "kimi-k2-0711-preview", provider: "kimi", providerModel: "kimi-k2-0711-preview", contextTokens: 128_000, maxOutputTokens: 16_384, thinking: [], images: false },
-  { canonical: "kimi-thinking-preview", provider: "kimi", providerModel: "kimi-thinking-preview", contextTokens: 128_000, maxOutputTokens: 32_000, thinking: FULL, images: true },
-  { canonical: "kimi-latest", provider: "kimi", providerModel: "kimi-latest", contextTokens: 128_000, maxOutputTokens: 16_384, thinking: [], images: true },
-  { canonical: "moonshot-v1-128k", provider: "kimi", providerModel: "moonshot-v1-128k", contextTokens: 128_000, maxOutputTokens: 16_384, thinking: [], images: false },
+  { canonical: "claude-opus-4-8", provider: "anthropic", providerModel: "claude-opus-4-8", contextTokens: 1_000_000, maxOutputTokens: 128_000, thinking: FULL, images: true, releaseDate: "2026-05" },
+  { canonical: "claude-opus-4-7", provider: "anthropic", providerModel: "claude-opus-4-7", contextTokens: 1_000_000, maxOutputTokens: 128_000, thinking: FULL, images: true, releaseDate: "2026-04" },
+  { canonical: "claude-sonnet-4-6", provider: "anthropic", providerModel: "claude-sonnet-4-6", contextTokens: 1_000_000, maxOutputTokens: 128_000, thinking: FULL, images: true, releaseDate: "2026-02" },
+  { canonical: "claude-opus-4-6", provider: "anthropic", providerModel: "claude-opus-4-6", contextTokens: 1_000_000, maxOutputTokens: 128_000, thinking: FULL, images: true, releaseDate: "2026-02" },
+  { canonical: "claude-haiku-4-5", provider: "anthropic", providerModel: "claude-haiku-4-5-20251001", contextTokens: 200_000, maxOutputTokens: 64_000, thinking: FULL, images: true, releaseDate: "2025-10" },
+  // OpenAI (newest first: gpt-5.5 > gpt-5.4 > o4-mini/o3/gpt-4.1 > o3-mini > gpt-4o-mini > gpt-4o)
+  { canonical: "gpt-5.5", provider: "openai", providerModel: "gpt-5.5", contextTokens: 400_000, maxOutputTokens: 128_000, thinking: FULL, images: true, releaseDate: "2026-04" },
+  { canonical: "gpt-5.4", provider: "openai", providerModel: "gpt-5.4", contextTokens: 400_000, maxOutputTokens: 128_000, thinking: FULL, images: true, releaseDate: "2026-03" },
+  { canonical: "o4-mini", provider: "openai", providerModel: "o4-mini", contextTokens: 200_000, maxOutputTokens: 100_000, thinking: STD, images: true, releaseDate: "2025-04" },
+  { canonical: "o3", provider: "openai", providerModel: "o3", contextTokens: 200_000, maxOutputTokens: 100_000, thinking: STD, images: true, releaseDate: "2025-04" },
+  { canonical: "gpt-4.1", provider: "openai", providerModel: "gpt-4.1", contextTokens: 1_000_000, maxOutputTokens: 32_768, thinking: [], images: true, releaseDate: "2025-04" },
+  { canonical: "o3-mini", provider: "openai", providerModel: "o3-mini", contextTokens: 200_000, maxOutputTokens: 100_000, thinking: STD, images: false, releaseDate: "2025-01" },
+  { canonical: "gpt-4o-mini", provider: "openai", providerModel: "gpt-4o-mini", contextTokens: 128_000, maxOutputTokens: 16_384, thinking: [], images: true, releaseDate: "2024-07" },
+  { canonical: "gpt-4o", provider: "openai", providerModel: "gpt-4o", contextTokens: 128_000, maxOutputTokens: 16_384, thinking: [], images: true, releaseDate: "2024-05" },
+  // xAI (Grok) — OpenAI-compatible at https://api.x.ai/v1 (XAI_API_KEY). Newest first.
+  { canonical: "grok-4.3", provider: "xai", providerModel: "grok-4.3", contextTokens: 256_000, maxOutputTokens: 64_000, thinking: FULL, images: true, releaseDate: "2026-04" },
+  { canonical: "grok-4-fast-reasoning", provider: "xai", providerModel: "grok-4-fast-reasoning", contextTokens: 2_000_000, maxOutputTokens: 64_000, thinking: FULL, images: true, releaseDate: "2025-09" },
+  { canonical: "grok-4-fast-non-reasoning", provider: "xai", providerModel: "grok-4-fast-non-reasoning", contextTokens: 2_000_000, maxOutputTokens: 64_000, thinking: [], images: true, releaseDate: "2025-09" },
+  { canonical: "grok-code-fast-1", provider: "xai", providerModel: "grok-code-fast-1", contextTokens: 256_000, maxOutputTokens: 64_000, thinking: FULL, images: false, releaseDate: "2025-08" },
+  // Kimi (Moonshot) — OpenAI-compatible at https://api.moonshot.ai/v1 (KIMI_API_KEY). Newest first.
+  { canonical: "kimi-k2-0711-preview", provider: "kimi", providerModel: "kimi-k2-0711-preview", contextTokens: 128_000, maxOutputTokens: 16_384, thinking: [], images: false, releaseDate: "2025-07" },
+  { canonical: "kimi-thinking-preview", provider: "kimi", providerModel: "kimi-thinking-preview", contextTokens: 128_000, maxOutputTokens: 32_000, thinking: FULL, images: true, releaseDate: "2025-05" },
+  { canonical: "kimi-latest", provider: "kimi", providerModel: "kimi-latest", contextTokens: 128_000, maxOutputTokens: 16_384, thinking: [], images: true, releaseDate: "2025-02" },
+  { canonical: "moonshot-v1-128k", provider: "kimi", providerModel: "moonshot-v1-128k", contextTokens: 128_000, maxOutputTokens: 16_384, thinking: [], images: false, releaseDate: "2024-01" },
   // Kimi Code (Moonshot coding subscription, device-code OAuth) — Anthropic-compatible
   // at https://api.kimi.com/coding. Provider-qualified (`kimi/…`) to avoid canonical
   // collisions (kimi-k2.5 also exists under tencent). gjc catalog parity: kimi-code.
-  { canonical: "kimi-for-coding", provider: "kimi", providerModel: "kimi/kimi-for-coding", contextTokens: 262_144, maxOutputTokens: 32_000, thinking: FULL, images: true, company: "Moonshot (Kimi Code)" },
-  { canonical: "kimi-k2.7-code", provider: "kimi", providerModel: "kimi/kimi-k2.7-code", contextTokens: 262_144, maxOutputTokens: 65_536, thinking: FULL, images: true, company: "Moonshot (Kimi Code)" },
-  { canonical: "kimi/kimi-k2.5", provider: "kimi", providerModel: "kimi/kimi-k2.5", contextTokens: 262_144, maxOutputTokens: 65_536, thinking: FULL, images: true, company: "Moonshot (Kimi Code)" },
-  { canonical: "kimi/kimi-k2-turbo-preview", provider: "kimi", providerModel: "kimi/kimi-k2-turbo-preview", contextTokens: 262_144, maxOutputTokens: 32_000, thinking: FULL, images: false, company: "Moonshot (Kimi Code)" },
-  { canonical: "kimi/kimi-k2", provider: "kimi", providerModel: "kimi/kimi-k2", contextTokens: 262_144, maxOutputTokens: 262_144, thinking: [], images: false, company: "Moonshot (Kimi Code)" },
-  // Google
-  { canonical: "gemini-1.5-pro", provider: "gemini", providerModel: "gemini-1.5-pro", contextTokens: 1_000_000, maxOutputTokens: 8_192, thinking: [], images: true },
-  { canonical: "gemini-2.0-flash", provider: "gemini", providerModel: "gemini-2.0-flash", contextTokens: 1_000_000, maxOutputTokens: 8_192, thinking: [], images: true },
-  { canonical: "gemini-2.5-flash", provider: "gemini", providerModel: "gemini-2.5-flash", contextTokens: 1_000_000, maxOutputTokens: 65_536, thinking: STD, images: true },
-  { canonical: "gemini-2.5-pro", provider: "gemini", providerModel: "gemini-2.5-pro", contextTokens: 1_000_000, maxOutputTokens: 65_536, thinking: STD, images: true },
+  // Newest first.
+  { canonical: "kimi-k2.7-code", provider: "kimi", providerModel: "kimi/kimi-k2.7-code", contextTokens: 262_144, maxOutputTokens: 65_536, thinking: FULL, images: true, company: "Moonshot (Kimi Code)", releaseDate: "2026-06" },
+  { canonical: "kimi-for-coding", provider: "kimi", providerModel: "kimi/kimi-for-coding", contextTokens: 262_144, maxOutputTokens: 32_000, thinking: FULL, images: true, company: "Moonshot (Kimi Code)", releaseDate: "2026-01" }, // [INFERENCE] alias-registration date approximated from Kimi CLI's 2026-01 launch — no primary-source changelog entry found
+  { canonical: "kimi/kimi-k2.5", provider: "kimi", providerModel: "kimi/kimi-k2.5", contextTokens: 262_144, maxOutputTokens: 65_536, thinking: FULL, images: true, company: "Moonshot (Kimi Code)", releaseDate: "2026-01" },
+  { canonical: "kimi/kimi-k2-turbo-preview", provider: "kimi", providerModel: "kimi/kimi-k2-turbo-preview", contextTokens: 262_144, maxOutputTokens: 32_000, thinking: FULL, images: false, company: "Moonshot (Kimi Code)", releaseDate: "2025-08" },
+  { canonical: "kimi/kimi-k2", provider: "kimi", providerModel: "kimi/kimi-k2", contextTokens: 262_144, maxOutputTokens: 262_144, thinking: [], images: false, company: "Moonshot (Kimi Code)", releaseDate: "2025-07" },
+  // Google (newest first: gemini-3.1-pro > gemini-3-* > gemini-2.5-* > gemini-2.0-flash > gemini-1.5-pro)
+  { canonical: "gemini-3.1-pro-high", provider: "gemini", providerModel: "gemini-3.1-pro-high", contextTokens: 1_000_000, maxOutputTokens: 65_536, thinking: FULL, images: true, releaseDate: "2026-02" },
+  { canonical: "gemini-3.1-pro-low", provider: "gemini", providerModel: "gemini-3.1-pro-low", contextTokens: 1_000_000, maxOutputTokens: 65_536, thinking: FULL, images: true, releaseDate: "2026-02" },
+  { canonical: "gemini-3-flash", provider: "gemini", providerModel: "gemini-3-flash", contextTokens: 1_000_000, maxOutputTokens: 65_536, thinking: FULL, images: true, releaseDate: "2025-12" },
+  { canonical: "gemini-3-pro-high", provider: "gemini", providerModel: "gemini-3-pro-high", contextTokens: 1_000_000, maxOutputTokens: 65_536, thinking: FULL, images: true, releaseDate: "2025-11" },
+  { canonical: "gemini-3-pro-low", provider: "gemini", providerModel: "gemini-3-pro-low", contextTokens: 1_000_000, maxOutputTokens: 65_536, thinking: FULL, images: true, releaseDate: "2025-11" },
+  { canonical: "gemini-2.5-flash", provider: "gemini", providerModel: "gemini-2.5-flash", contextTokens: 1_000_000, maxOutputTokens: 65_536, thinking: STD, images: true, releaseDate: "2025-06" },
+  { canonical: "gemini-2.5-pro", provider: "gemini", providerModel: "gemini-2.5-pro", contextTokens: 1_000_000, maxOutputTokens: 65_536, thinking: STD, images: true, releaseDate: "2025-03" },
+  { canonical: "gemini-2.0-flash", provider: "gemini", providerModel: "gemini-2.0-flash", contextTokens: 1_000_000, maxOutputTokens: 8_192, thinking: [], images: true, releaseDate: "2025-02" },
+  { canonical: "gemini-1.5-pro", provider: "gemini", providerModel: "gemini-1.5-pro", contextTokens: 1_000_000, maxOutputTokens: 8_192, thinking: [], images: true, releaseDate: "2024-02" },
   // Google Antigravity / Gemini CLI (Cloud Code Assist) — provider-qualified to avoid
-  // collisions with public Gemini, Anthropic, and OpenAI/Codex ids.
-  ...ANTIGRAVITY_MODELS.map((id): CatalogModel => ({
+  // collisions with public Gemini, Anthropic, and OpenAI/Codex ids. A hosting layer
+  // over the SAME underlying models researched above, not a separate release —
+  // releaseDate comes from the [id, date] tuple, not re-derived.
+  ...ANTIGRAVITY_MODELS.map(([id, releaseDate]): CatalogModel => ({
     canonical: `antigravity/${id}`,
     provider: "antigravity",
     providerModel: id,
@@ -124,31 +152,30 @@ export const MODEL_CATALOG: readonly CatalogModel[] = [
     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",
+    releaseDate,
   })),
-  // Tencent
-  // Tencent — DeepSeek
-  { canonical: "deepseek-v4-pro", provider: "tencent", providerModel: "deepseek-v4-pro", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  { canonical: "deepseek-v4-pro-202606", provider: "tencent", providerModel: "deepseek-v4-pro-202606", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  { canonical: "deepseek-v4-flash", provider: "tencent", providerModel: "deepseek-v4-flash", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  { canonical: "deepseek-v4-flash-202605", provider: "tencent", providerModel: "deepseek-v4-flash-202605", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  { canonical: "deepseek-v3.2", provider: "tencent", providerModel: "deepseek-v3.2", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  // Tencent — MiniMax
-  { canonical: "minimax-m3", provider: "tencent", providerModel: "minimax-m3", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  { canonical: "minimax-m2.7", provider: "tencent", providerModel: "minimax-m2.7", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  { canonical: "minimax-m2.5", provider: "tencent", providerModel: "minimax-m2.5", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  // Tencent — Zhipu GLM
-  { canonical: "glm-5.2", provider: "tencent", providerModel: "glm-5.2", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  { canonical: "glm-5.1", provider: "tencent", providerModel: "glm-5.1", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  { canonical: "glm-5", provider: "tencent", providerModel: "glm-5", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  { canonical: "glm-5-turbo", provider: "tencent", providerModel: "glm-5-turbo", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  { canonical: "glm-5v-turbo", provider: "tencent", providerModel: "glm-5v-turbo", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: true, company: "Tencent" },
-  // Tencent — Moonshot Kimi
-  { canonical: "kimi-k2.6", provider: "tencent", providerModel: "kimi-k2.6", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  { canonical: "kimi-k2.5", provider: "tencent", providerModel: "kimi-k2.5", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent" },
-  // Tencent — Hunyuan MT
-  { canonical: "hy-mt2-plus", provider: "tencent", providerModel: "hy-mt2-plus", contextTokens: 128_000, maxOutputTokens: 8192, thinking: STD, images: false, company: "Tencent" },
+  // Tencent — hosts the same underlying models under its own cloud brand; dates
+  // below are the ORIGINAL developer's release (DeepSeek/MiniMax/Zhipu/Moonshot),
+  // not Tencent's hosting-catalog appearance date, except where the id itself pins
+  // a Tencent-specific snapshot (the two `-2026XX` suffixed DeepSeek ids). Newest first overall.
+  { canonical: "glm-5.2", provider: "tencent", providerModel: "glm-5.2", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2026-06" },
+  { canonical: "hy-mt2-plus", provider: "tencent", providerModel: "hy-mt2-plus", contextTokens: 128_000, maxOutputTokens: 8192, thinking: STD, images: false, company: "Tencent", releaseDate: "2026-06" },
+  { canonical: "deepseek-v4-pro-202606", provider: "tencent", providerModel: "deepseek-v4-pro-202606", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2026-06" },
+  { canonical: "minimax-m3", provider: "tencent", providerModel: "minimax-m3", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2026-06" },
+  { canonical: "deepseek-v4-flash-202605", provider: "tencent", providerModel: "deepseek-v4-flash-202605", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2026-05" },
+  { canonical: "glm-5v-turbo", provider: "tencent", providerModel: "glm-5v-turbo", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: true, company: "Tencent", releaseDate: "2026-04" },
+  { canonical: "deepseek-v4-pro", provider: "tencent", providerModel: "deepseek-v4-pro", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2026-04" },
+  { canonical: "deepseek-v4-flash", provider: "tencent", providerModel: "deepseek-v4-flash", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2026-04" },
+  { canonical: "kimi-k2.6", provider: "tencent", providerModel: "kimi-k2.6", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2026-04" },
+  { canonical: "minimax-m2.7", provider: "tencent", providerModel: "minimax-m2.7", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2026-03" },
+  { canonical: "glm-5.1", provider: "tencent", providerModel: "glm-5.1", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2026-03" },
+  { canonical: "glm-5-turbo", provider: "tencent", providerModel: "glm-5-turbo", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2026-03" },
+  { canonical: "minimax-m2.5", provider: "tencent", providerModel: "minimax-m2.5", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2026-02" },
+  { canonical: "glm-5", provider: "tencent", providerModel: "glm-5", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2026-02" },
+  { canonical: "kimi-k2.5", provider: "tencent", providerModel: "kimi-k2.5", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2026-01" },
+  { canonical: "deepseek-v3.2", provider: "tencent", providerModel: "deepseek-v3.2", contextTokens: 128_000, maxOutputTokens: 8192, thinking: FULL, images: false, company: "Tencent", releaseDate: "2025-12" },
   // Ollama (local)
-  { canonical: "qwen2.5", provider: "ollama", providerModel: "ollama/qwen2.5:0.5b", contextTokens: 32_768, maxOutputTokens: 8_192, thinking: [], images: false },
+  { canonical: "qwen2.5", provider: "ollama", providerModel: "ollama/qwen2.5:0.5b", contextTokens: 32_768, maxOutputTokens: 8_192, thinking: [], images: false, releaseDate: "2024-09" },
 ];
 
 /**