From b4d36334bff69538bbfe66f3d3ba10de075187a5 Mon Sep 17 00:00:00 2001
From: infosave2007 <urevich55@gmail.com>
Date: Fri, 7 Aug 2026 22:25:52 +0300
Subject: [PATCH] chore: release 0.2.39

---
 CHANGELOG.md       | 42 ++++++++++++++++++++++++++++++++++++++++++
 Cargo.lock         |  2 +-
 Cargo.toml         |  2 +-
 docs/ROUTING.md    |  8 +++++++-
 docs/ROUTING.ru.md |  8 +++++++-
 5 files changed, 58 insertions(+), 4 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 369ad7a..614178b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -3,6 +3,48 @@
 All notable changes to this project are documented here.
 The format is based on [Keep a Changelog](https://keepachangelog.com/).
 
+## [0.2.39] - 2026-08-07
+
+### Added
+- **Benchmark, redesigned into the console** (⏱ sidebar entry): two explicit modes. **Smart
+  routing** (default) sends every probe through `cortiq-auto` and judges the ROUTER — task label
+  vs expected (✓/✗), complexity tier, chosen model with per-request cost, task-rule badge —
+  with KPIs for answer quality, classification accuracy, TTFT, tok/s and money spent, plus a
+  "requests went to" per-model distribution. **Individual models** compares pinned models
+  head-to-head. Results render live row-by-row, runs land in a browser-side history (per-run ×
+  and Clear-all), custom tests supported, ⚡ quick subset (7) vs full suite (17).
+- **Hard probes that exercise the high tier**: two route-judged tests (science / ops pools)
+  generated fresh each run — interdisciplinary prompts rate high reliably while fixed wordings
+  decay with the router's novelty signal. Pass = the router said `high` and the request escalated;
+  the tiny token budget keeps them at cents even on the priciest model.
+- **One-paste harness setup** on the API-keys page: Claude Code (native Anthropic `/v1/messages`,
+  now on by default, one-click enable for older configs), Codex, OpenCode, Continue and Cline —
+  each pre-filled with the gateway URL and the freshly created key. The gateway detects harnesses
+  already installed on its machine (✓ on the tab, "already configured for this gateway" status).
+- **Stale-tab detection**: open consoles notice a gateway restart via the meta start marker and
+  show a reload banner instead of silently running an old interface.
+- Log viewer Clear button (`DELETE /admin/api/logs`).
+
+### Changed
+- **High complexity escalates over task rules**: at tier `high` the tier chain leads and the task
+  rule demotes to fallback — a `code → cheap-model` rule no longer pins the hardest prompts to
+  the cheap model. Low/medium keep task-rule-first semantics (documented in docs/ROUTING).
+- **Honest stream costs**: the final cost rides a closing SSE event (`cortiq_cost_usd`) since the
+  initial header is written before generation; money renders with 4 decimals (last two smaller)
+  and grows precision below $0.0001 instead of collapsing to $0.0000.
+- **Oracle-sized timeouts**: router default 800 ms → 15 s (hosted escalations take ~10 s);
+  provider clients gained a 10 s connect timeout (dead upstreams fail over fast) with no overall
+  cap so long generations and streams are never cut.
+- Benchmark fairness: +256-token reasoning headroom (thinking models aren't cut mid-`<think>`),
+  router degradation shown as "⚠ router degraded" and excluded from accuracy, "budget spent on
+  reasoning" instead of a misleading "empty answer", creative-writing budget 96 → 512.
+- New-key dialog simplified to account / rate limit / optional custom value.
+
+### Fixed
+- `cortiq bench` results showed "error" with newer cortiq releases that pretty-print `--json`:
+  the parser now finds the last balanced JSON object anywhere in the output, and tok/s prefers
+  steady decode speed (the old heuristic could report `allocs_per_token` as tok/s).
+
 ## [0.2.38] - 2026-08-07
 
 ### Added
diff --git a/Cargo.lock b/Cargo.lock
index c5adcbf..24abd44 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -285,7 +285,7 @@ checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
 
 [[package]]
 name = "cortiq-gateway"
-version = "0.2.38"
+version = "0.2.39"
 dependencies = [
  "anyhow",
  "arc-swap",
diff --git a/Cargo.toml b/Cargo.toml
index f9d5aed..c4665fb 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "cortiq-gateway"
-version = "0.2.38"
+version = "0.2.39"
 edition = "2021"
 rust-version = "1.75"
 license = "Apache-2.0"
diff --git a/docs/ROUTING.md b/docs/ROUTING.md
index 2260833..22aa2a4 100644
--- a/docs/ROUTING.md
+++ b/docs/ROUTING.md
@@ -177,7 +177,13 @@ code        = ["claude-sonnet", "gpt"] # code goes to the strongest coder first
 
 A matching rule's models go **first** in the candidate chain; the complexity
 chain follows as fallback, so a task pin never weakens failover. Tasks without
-a rule route by complexity alone. The available labels come from the router
+a rule route by complexity alone.
+
+**Exception — high complexity escalates.** When the router rates a request
+`high` (and a `high` chain is configured), the tier chain leads and the task
+rule demotes to fallback. Otherwise a rule like `code → cheap-model` would pin
+even the hardest prompts to the cheap model and the tier system would never
+get a say. Low/medium keep task-rule-first semantics. The available labels come from the router
 (`GET /v1/taxonomies`) — the admin console's Routing page builds the editor
 from your account's live taxonomy and shows each task's share of recent
 traffic. When a rule supplied the head of the chain the response reports
diff --git a/docs/ROUTING.ru.md b/docs/ROUTING.ru.md
index 0daf794..e71d138 100644
--- a/docs/ROUTING.ru.md
+++ b/docs/ROUTING.ru.md
@@ -175,7 +175,13 @@ code        = ["claude-sonnet", "gpt"] # код — сильнейшему ко
 
 Модели подходящего правила идут **первыми** в цепочке кандидатов; цепочка по
 сложности следует за ними как резерв — правило по задаче не ослабляет failover.
-Задачи без правила маршрутизируются только по сложности. Список меток приходит
+Задачи без правила маршрутизируются только по сложности.
+
+**Исключение — высокая сложность эскалирует.** Когда роутер оценил запрос как
+`high` (и цепочка `high` настроена), цепочка уровня идёт первой, а правило
+задачи становится резервом. Иначе правило вида `code → дешёвая-модель`
+приковало бы к дешёвой модели даже самые сложные запросы, и система уровней
+не имела бы права голоса. Для low/medium правило задачи ведёт, как и раньше. Список меток приходит
 с роутера (`GET /v1/taxonomies`) — вкладка Роутинг строит редактор по живой
 таксономии аккаунта и показывает долю каждой задачи в трафике. Когда цепочку
 возглавило правило задачи, ответ сообщает `route_source: "router+task-rule"`.