From b161c674edc5e47547a483c25e69012144c6ebef Mon Sep 17 00:00:00 2001 From: mlsmaycon Date: Wed, 22 Jul 2026 04:16:01 +0000 Subject: [PATCH] Drop kimi-k2-thinking from the catalog; remove temporary e2e trigger - Moonshot serves newer platform accounts exactly one model, kimi-k3: K2-era ids and the kimi-latest alias return resource_not_found_error on both API surfaces (verified live 2026-07-21). Drop kimi-k2-thinking from the kimi_api catalog entry and the pricing defaults so the dashboard doesn't advertise a model that 404s; grandfathered accounts can still type K2 ids on the provider's model rows. - Remove the temporary push trigger from agent-network-e2e.yml now that the branch validated green (run #76); nightly + workflow_dispatch remain. - Remove CLAUDE.md from the repository. --- .github/workflows/agent-network-e2e.yml | 4 ---- CLAUDE.md | 6 ------ .../modules/agentnetwork/catalog/catalog.go | 14 ++++++++------ proxy/internal/llm/pricing/defaults_pricing.yaml | 14 ++++---------- 4 files changed, 12 insertions(+), 26 deletions(-) delete mode 100644 CLAUDE.md diff --git a/.github/workflows/agent-network-e2e.yml b/.github/workflows/agent-network-e2e.yml index 55e126342..bf4868871 100644 --- a/.github/workflows/agent-network-e2e.yml +++ b/.github/workflows/agent-network-e2e.yml @@ -5,10 +5,6 @@ on: schedule: - cron: "0 3 * * *" workflow_dispatch: - # TEMPORARY: run on pushes to the Kimi feature branch to exercise the new - # provider scenarios with E2E_KIMI_TOKEN. Remove before merging. - push: - branches: [feat/kimi-3-agent-networks] concurrency: group: ${{ github.workflow }}-${{ github.ref }} diff --git a/CLAUDE.md b/CLAUDE.md deleted file mode 100644 index cde3904c5..000000000 --- a/CLAUDE.md +++ /dev/null @@ -1,6 +0,0 @@ -# Repository guidance for Claude - -## Git conventions - -- Do not add `Co-Authored-By` or other AI attribution trailers to commit messages. -- Do not use `claude/` (or otherwise Claude-named) branch names; use conventional prefixes like `feat/`, `fix/`, `chore/`. diff --git a/management/internals/modules/agentnetwork/catalog/catalog.go b/management/internals/modules/agentnetwork/catalog/catalog.go index 3c57ce5b7..f82e94bf3 100644 --- a/management/internals/modules/agentnetwork/catalog/catalog.go +++ b/management/internals/modules/agentnetwork/catalog/catalog.go @@ -449,14 +449,16 @@ var providers = []Provider{ // meterable platform key, so it's deliberately not the default. ParserID: "", // Pricing per Moonshot's platform rates at K3 launch (July 2026): - // K3 $3/$15 per MTok with $0.30 cached input, flat across the - // 1M-token window; K2 Thinking $0.60/$2.50 with $0.15 cache hits. - // Kimi K3 has a single always-on-reasoning SKU — no mini/turbo - // variants at launch. The consumer app's "K3 Swarm Max" mode is - // not an API SKU, so it doesn't appear here. + // $3/$15 per MTok with $0.30 cached input, flat across the 1M-token + // window. kimi-k3 is the ONLY model the platform serves newer + // accounts — K2-era ids (kimi-k2-thinking) and even the kimi-latest + // alias return resource_not_found_error, verified live 2026-07-21 — + // so it's the only catalog entry. Grandfathered accounts with K2 + // access can still type those ids on the provider's model rows. + // The consumer app's "K3 Swarm Max" mode is not an API SKU, so it + // doesn't appear here. Models: []Model{ {ID: "kimi-k3", Label: "Kimi K3", InputPer1k: 0.003, OutputPer1k: 0.015, ContextWindow: 1000000}, - {ID: "kimi-k2-thinking", Label: "Kimi K2 Thinking", InputPer1k: 0.0006, OutputPer1k: 0.0025, ContextWindow: 262144}, }, }, { diff --git a/proxy/internal/llm/pricing/defaults_pricing.yaml b/proxy/internal/llm/pricing/defaults_pricing.yaml index 9f9f4ae78..3fba8fe3f 100644 --- a/proxy/internal/llm/pricing/defaults_pricing.yaml +++ b/proxy/internal/llm/pricing/defaults_pricing.yaml @@ -163,15 +163,13 @@ openai: # Kimi / Moonshot AI (kimi_api) — OpenAI-compatible /v1 endpoint. Moonshot # reports cache hits OpenAI-style when present; cached input is 10% of - # input for K3 ($0.30 vs $3.00 per MTok) and $0.15/MTok for K2 Thinking. + # input ($0.30 vs $3.00 per MTok). kimi-k3 is the only model the platform + # serves newer accounts (K2-era ids and kimi-latest 404), matching the + # management catalog. kimi-k3: input_per_1k: 0.003 output_per_1k: 0.015 cached_input_per_1k: 0.0003 - kimi-k2-thinking: - input_per_1k: 0.0006 - output_per_1k: 0.0025 - cached_input_per_1k: 0.00015 anthropic: # Claude 4.x family — cache reads ≈10% of input, cache writes ≈125% of input. @@ -220,7 +218,7 @@ anthropic: # Kimi / Moonshot AI (kimi_api) via the Anthropic-compatible endpoint # (/anthropic/v1/messages — the official Claude Code setup). Same rates - # as the OpenAI-shape entries above. "kimi-k3[1m]" is the model id some + # as the OpenAI-shape entry above. "kimi-k3[1m]" is the model id some # Claude Code guides set for the 1M-context alias; priced identically so # cost metering doesn't silently skip those requests. kimi-k3: @@ -231,10 +229,6 @@ anthropic: input_per_1k: 0.003 output_per_1k: 0.015 cache_read_per_1k: 0.0003 - kimi-k2-thinking: - input_per_1k: 0.0006 - output_per_1k: 0.0025 - cache_read_per_1k: 0.00015 bedrock: # AWS Bedrock model ids, normalised by the request parser (cross-region