From c36eb1d96c90239fe60b12192c9fd7ef082495a9 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Mon, 27 Jul 2026 23:55:03 +0800 Subject: [PATCH 01/18] feat: litellm-config-yaml --- agent/compose.yaml | 2 +- agent/litellm/config.yaml | 86 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 87 insertions(+), 1 deletion(-) create mode 100644 agent/litellm/config.yaml diff --git a/agent/compose.yaml b/agent/compose.yaml index ab68989d..ecdb0eea 100644 --- a/agent/compose.yaml +++ b/agent/compose.yaml @@ -113,7 +113,7 @@ services: - no-new-privileges:true read_only: true volumes: - - /apps/litellm/config.yaml:/app/config.yaml:ro + - ./config.yaml:/app/config.yaml:ro tmpfs: - /app/cache - /app/migrations diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml new file mode 100644 index 00000000..bfc1a465 --- /dev/null +++ b/agent/litellm/config.yaml @@ -0,0 +1,86 @@ +model_list: + - model_name: cerebras/gemma-4-31b + litellm_params: + model: gemma-4-31b + litellm_credential_name: cerebras + + - model_name: google/gemini-flash-lite-latest + litellm_params: + model: gemini/gemini-flash-lite-latest + litellm_credential_name: google + + - model_name: google/gemma-4-31b-it + litellm_params: + model: gemini/gemma-4-31b-it + litellm_credential_name: google + + - model_name: groq/gpt-oss-120b + litellm_params: + model: openai/gpt-oss-120b + litellm_credential_name: groq + + - model_name: nous/hy3:free + litellm_params: + model: tencent/hy3:free + litellm_credential_name: nous + + - model_name: nvidia/deepseek-v4-pro + litellm_params: + model: deepseek-ai/deepseek-v4-pro + litellm_credential_name: nvidia + + - model_name: opencode-zen/deepseek-v4-flash-free + litellm_params: + model: deepseek-v4-flash-free + litellm_credential_name: opencode_zen + + - model_name: opencode-zen/mimo-v2.5-free + litellm_params: + model: mimo-v2.5-free + litellm_credential_name: opencode_zen + +credential_list: + - credential_name: cerebras + credential_values: + api_key: os.environ/CEREBRAS_API_KEY + api_base: https://api.cerebras.ai/v1 + credential_info: {} + + - credential_name: google + credential_values: + api_key: os.environ/GOOGLE_API_KEY + api_base: https://generativelanguage.googleapis.com/v1beta/interactions + credential_info: {} + + - credential_name: groq + credential_values: + api_key: os.environ/GROQ_API_KEY + api_base: https://api.groq.com/openai/v1 + credential_info: {} + + - credential_name: nous + credential_values: + api_key: os.environ/NOUS_API_KEY + api_base: https://inference-api.nousresearch.com/v1 + credential_info: {} + + - credential_name: nvidia + credential_values: + api_key: os.environ/NVIDIA_API_KEY + api_base: https://integrate.api.nvidia.com/v1 + credential_info: {} + + - credential_name: opencode_zen + credential_values: + api_key: os.environ/OPENCODE_ZEN_API_KEY + api_base: https://opencode.ai/zen/v1 + credential_info: {} + + - credential_name: opencode_go + credential_values: + api_key: os.environ/OPENCODE_GO_API_KEY + api_base: https://opencode.ai/zen/go/v1 + credential_info: {} + +general_settings: + store_model_in_db: true From 2c9da880fb69d63219904a6c4bb2fc71ef6752a7 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Mon, 27 Jul 2026 23:57:42 +0800 Subject: [PATCH 02/18] Update compose.yaml --- agent/compose.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/agent/compose.yaml b/agent/compose.yaml index ecdb0eea..3e074cc2 100644 --- a/agent/compose.yaml +++ b/agent/compose.yaml @@ -113,7 +113,7 @@ services: - no-new-privileges:true read_only: true volumes: - - ./config.yaml:/app/config.yaml:ro + - ./litellm/config.yaml:/app/config.yaml:ro tmpfs: - /app/cache - /app/migrations From 6d1cc3fa9126e8398a3dbfe36014a6ce130a89d5 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 00:11:58 +0800 Subject: [PATCH 03/18] simplify supported --- agent/litellm/config.yaml | 44 +++++++++------------------------------ 1 file changed, 10 insertions(+), 34 deletions(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index bfc1a465..4f6a831c 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -1,75 +1,51 @@ model_list: - model_name: cerebras/gemma-4-31b litellm_params: - model: gemma-4-31b - litellm_credential_name: cerebras + model: cerebras/gemma-4-31b + api_key: os.environ/CEREBRAS_API_KEY - model_name: google/gemini-flash-lite-latest litellm_params: model: gemini/gemini-flash-lite-latest - litellm_credential_name: google + api_key: os.environ/GOOGLE_API_KEY - model_name: google/gemma-4-31b-it litellm_params: model: gemini/gemma-4-31b-it - litellm_credential_name: google + api_key: os.environ/GOOGLE_API_KEY - model_name: groq/gpt-oss-120b litellm_params: - model: openai/gpt-oss-120b - litellm_credential_name: groq + model: groq/gpt-oss-120b + api_key: os.environ/GROQ_API_KEY - model_name: nous/hy3:free litellm_params: - model: tencent/hy3:free + model: openai/tencent/hy3:free litellm_credential_name: nous - model_name: nvidia/deepseek-v4-pro litellm_params: - model: deepseek-ai/deepseek-v4-pro + model: nvidia_nim/deepseek-ai/deepseek-v4-pro litellm_credential_name: nvidia - model_name: opencode-zen/deepseek-v4-flash-free litellm_params: - model: deepseek-v4-flash-free + model: openai/deepseek-v4-flash-free litellm_credential_name: opencode_zen - model_name: opencode-zen/mimo-v2.5-free litellm_params: - model: mimo-v2.5-free + model: openai/mimo-v2.5-free litellm_credential_name: opencode_zen credential_list: - - credential_name: cerebras - credential_values: - api_key: os.environ/CEREBRAS_API_KEY - api_base: https://api.cerebras.ai/v1 - credential_info: {} - - - credential_name: google - credential_values: - api_key: os.environ/GOOGLE_API_KEY - api_base: https://generativelanguage.googleapis.com/v1beta/interactions - credential_info: {} - - - credential_name: groq - credential_values: - api_key: os.environ/GROQ_API_KEY - api_base: https://api.groq.com/openai/v1 - credential_info: {} - - credential_name: nous credential_values: api_key: os.environ/NOUS_API_KEY api_base: https://inference-api.nousresearch.com/v1 credential_info: {} - - credential_name: nvidia - credential_values: - api_key: os.environ/NVIDIA_API_KEY - api_base: https://integrate.api.nvidia.com/v1 - credential_info: {} - - credential_name: opencode_zen credential_values: api_key: os.environ/OPENCODE_ZEN_API_KEY From fb9379f646caadbbc4c836f660229f7881e36f80 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 00:17:42 +0800 Subject: [PATCH 04/18] Update config.yaml --- agent/litellm/config.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index 4f6a831c..525992d4 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -16,7 +16,7 @@ model_list: - model_name: groq/gpt-oss-120b litellm_params: - model: groq/gpt-oss-120b + model: groq/openai/gpt-oss-120b api_key: os.environ/GROQ_API_KEY - model_name: nous/hy3:free From 67c22bb67556b44989de55d06e0eab35525a56f3 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 08:37:51 +0800 Subject: [PATCH 05/18] Update config.yaml --- agent/litellm/config.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index 525992d4..1453cf6b 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -27,7 +27,7 @@ model_list: - model_name: nvidia/deepseek-v4-pro litellm_params: model: nvidia_nim/deepseek-ai/deepseek-v4-pro - litellm_credential_name: nvidia + api_key: os.environ/NVIDIA_API_KEY - model_name: opencode-zen/deepseek-v4-flash-free litellm_params: From 919bcab7b57beaf5119f85c7ec649e57de02ea18 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 08:48:49 +0800 Subject: [PATCH 06/18] Update config.yaml --- agent/litellm/config.yaml | 5 ----- 1 file changed, 5 deletions(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index 1453cf6b..d6caad34 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -2,22 +2,18 @@ model_list: - model_name: cerebras/gemma-4-31b litellm_params: model: cerebras/gemma-4-31b - api_key: os.environ/CEREBRAS_API_KEY - model_name: google/gemini-flash-lite-latest litellm_params: model: gemini/gemini-flash-lite-latest - api_key: os.environ/GOOGLE_API_KEY - model_name: google/gemma-4-31b-it litellm_params: model: gemini/gemma-4-31b-it - api_key: os.environ/GOOGLE_API_KEY - model_name: groq/gpt-oss-120b litellm_params: model: groq/openai/gpt-oss-120b - api_key: os.environ/GROQ_API_KEY - model_name: nous/hy3:free litellm_params: @@ -27,7 +23,6 @@ model_list: - model_name: nvidia/deepseek-v4-pro litellm_params: model: nvidia_nim/deepseek-ai/deepseek-v4-pro - api_key: os.environ/NVIDIA_API_KEY - model_name: opencode-zen/deepseek-v4-flash-free litellm_params: From cd7081ab1413600822efbdd9617d3b13b54774b1 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 09:10:35 +0800 Subject: [PATCH 07/18] Update config.yaml --- agent/litellm/config.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index d6caad34..71103632 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -15,6 +15,10 @@ model_list: litellm_params: model: groq/openai/gpt-oss-120b + - model_name: openrouter/free + litellm_params: + model: openrouter/free + - model_name: nous/hy3:free litellm_params: model: openai/tencent/hy3:free @@ -55,3 +59,6 @@ credential_list: general_settings: store_model_in_db: true + +litellm_settings: + drop_params: true From 9d055b1e8557ec07b4a87331d1f6a13c97160421 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 09:44:32 +0800 Subject: [PATCH 08/18] Update config.yaml --- agent/litellm/config.yaml | 42 +++++++++++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 8 deletions(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index 71103632..e95ad9f4 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -15,18 +15,22 @@ model_list: litellm_params: model: groq/openai/gpt-oss-120b - - model_name: openrouter/free - litellm_params: - model: openrouter/free - - model_name: nous/hy3:free litellm_params: model: openai/tencent/hy3:free litellm_credential_name: nous - - model_name: nvidia/deepseek-v4-pro + - model_name: nvidia/deepseek-v4-pro:max + litellm_params: + model: nvidia_nim/deepseek-ai/deepseek-v4-pro + thinking: + type: enabled + budget_tokens: 32000 + + - model_name: nvidia/deepseek-v4-pro:high litellm_params: model: nvidia_nim/deepseek-ai/deepseek-v4-pro + reasoning_effort: high - model_name: opencode-zen/deepseek-v4-flash-free litellm_params: @@ -38,27 +42,49 @@ model_list: model: openai/mimo-v2.5-free litellm_credential_name: opencode_zen + - model_name: openrouter/free + litellm_params: + model: openrouter/free + + - model_name: smart-router + litellm_params: + model: auto_router/complexity_router + complexity_router_config: + tiers: + SIMPLE: opencode-zen/deepseek-v4-flash-free + MEDIUM: opencode-zen/deepseek-v4-flash-free + COMPLEX: ['nous/hy3:free'] + REASONING: ['nous/hy3:free'] + adaptive: true + session_affinity: true + complexity_router_default_model: nous/hy3:free + credential_list: - credential_name: nous credential_values: api_key: os.environ/NOUS_API_KEY api_base: https://inference-api.nousresearch.com/v1 - credential_info: {} - credential_name: opencode_zen credential_values: api_key: os.environ/OPENCODE_ZEN_API_KEY api_base: https://opencode.ai/zen/v1 - credential_info: {} - credential_name: opencode_go credential_values: api_key: os.environ/OPENCODE_GO_API_KEY api_base: https://opencode.ai/zen/go/v1 - credential_info: {} general_settings: store_model_in_db: true + background_health_checks: true + health_check_interval: 300 litellm_settings: drop_params: true + request_timeout: 120 + json_logs: true + +router_settings: + cooldown_time: 60 + allowed_fails: 3 From f6b4fa46ec8319ade3d15bcddf691849b44bf9d7 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 09:46:57 +0800 Subject: [PATCH 09/18] Update config.yaml --- agent/litellm/config.yaml | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index e95ad9f4..af25a47f 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -53,8 +53,8 @@ model_list: tiers: SIMPLE: opencode-zen/deepseek-v4-flash-free MEDIUM: opencode-zen/deepseek-v4-flash-free - COMPLEX: ['nous/hy3:free'] - REASONING: ['nous/hy3:free'] + COMPLEX: nous/hy3:free + REASONING: nous/hy3:free adaptive: true session_affinity: true complexity_router_default_model: nous/hy3:free @@ -64,16 +64,19 @@ credential_list: credential_values: api_key: os.environ/NOUS_API_KEY api_base: https://inference-api.nousresearch.com/v1 + credential_info: {} - credential_name: opencode_zen credential_values: api_key: os.environ/OPENCODE_ZEN_API_KEY api_base: https://opencode.ai/zen/v1 + credential_info: {} - credential_name: opencode_go credential_values: api_key: os.environ/OPENCODE_GO_API_KEY api_base: https://opencode.ai/zen/go/v1 + credential_info: {} general_settings: store_model_in_db: true From 6968903468c6c65e590b70c9ac62af6695cd2408 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 09:49:12 +0800 Subject: [PATCH 10/18] Update config.yaml --- agent/litellm/config.yaml | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index af25a47f..eeb74c8e 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -46,18 +46,18 @@ model_list: litellm_params: model: openrouter/free - - model_name: smart-router - litellm_params: - model: auto_router/complexity_router - complexity_router_config: - tiers: - SIMPLE: opencode-zen/deepseek-v4-flash-free - MEDIUM: opencode-zen/deepseek-v4-flash-free - COMPLEX: nous/hy3:free - REASONING: nous/hy3:free - adaptive: true - session_affinity: true - complexity_router_default_model: nous/hy3:free +# - model_name: smart-router +# litellm_params: +# model: auto_router/complexity_router +# complexity_router_config: +# tiers: +# SIMPLE: opencode-zen/deepseek-v4-flash-free +# MEDIUM: opencode-zen/deepseek-v4-flash-free +# COMPLEX: nous/hy3:free +# REASONING: nous/hy3:free +# adaptive: true +# session_affinity: true +# complexity_router_default_model: nous/hy3:free credential_list: - credential_name: nous From bee6f8bc127a91f425e5875a51bbdcd45ebecd33 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 09:50:55 +0800 Subject: [PATCH 11/18] Update config.yaml --- agent/litellm/config.yaml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index eeb74c8e..2be525a9 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -42,9 +42,9 @@ model_list: model: openai/mimo-v2.5-free litellm_credential_name: opencode_zen - - model_name: openrouter/free - litellm_params: - model: openrouter/free +# - model_name: openrouter/free +# litellm_params: +# model: openrouter/free # - model_name: smart-router # litellm_params: From 6fa9a98513c7f5dcf51276dbdef99dc2105fe0d4 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 09:53:23 +0800 Subject: [PATCH 12/18] Update config.yaml --- agent/litellm/config.yaml | 84 +++++++++++++++++++-------------------- 1 file changed, 42 insertions(+), 42 deletions(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index 2be525a9..068621e5 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -1,46 +1,46 @@ model_list: - - model_name: cerebras/gemma-4-31b - litellm_params: - model: cerebras/gemma-4-31b + # - model_name: cerebras/gemma-4-31b + # litellm_params: + # model: cerebras/gemma-4-31b - - model_name: google/gemini-flash-lite-latest - litellm_params: - model: gemini/gemini-flash-lite-latest + # - model_name: google/gemini-flash-lite-latest + # litellm_params: + # model: gemini/gemini-flash-lite-latest - model_name: google/gemma-4-31b-it litellm_params: model: gemini/gemma-4-31b-it - - model_name: groq/gpt-oss-120b - litellm_params: - model: groq/openai/gpt-oss-120b +# - model_name: groq/gpt-oss-120b +# litellm_params: +# model: groq/openai/gpt-oss-120b - - model_name: nous/hy3:free - litellm_params: - model: openai/tencent/hy3:free - litellm_credential_name: nous +# - model_name: nous/hy3:free +# litellm_params: +# model: openai/tencent/hy3:free +# litellm_credential_name: nous - - model_name: nvidia/deepseek-v4-pro:max - litellm_params: - model: nvidia_nim/deepseek-ai/deepseek-v4-pro - thinking: - type: enabled - budget_tokens: 32000 +# - model_name: nvidia/deepseek-v4-pro:max +# litellm_params: +# model: nvidia_nim/deepseek-ai/deepseek-v4-pro +# thinking: +# type: enabled +# budget_tokens: 32000 - - model_name: nvidia/deepseek-v4-pro:high - litellm_params: - model: nvidia_nim/deepseek-ai/deepseek-v4-pro - reasoning_effort: high +# - model_name: nvidia/deepseek-v4-pro:high +# litellm_params: +# model: nvidia_nim/deepseek-ai/deepseek-v4-pro +# reasoning_effort: high - - model_name: opencode-zen/deepseek-v4-flash-free - litellm_params: - model: openai/deepseek-v4-flash-free - litellm_credential_name: opencode_zen +# - model_name: opencode-zen/deepseek-v4-flash-free +# litellm_params: +# model: openai/deepseek-v4-flash-free +# litellm_credential_name: opencode_zen - - model_name: opencode-zen/mimo-v2.5-free - litellm_params: - model: openai/mimo-v2.5-free - litellm_credential_name: opencode_zen +# - model_name: opencode-zen/mimo-v2.5-free +# litellm_params: +# model: openai/mimo-v2.5-free +# litellm_credential_name: opencode_zen # - model_name: openrouter/free # litellm_params: @@ -78,16 +78,16 @@ credential_list: api_base: https://opencode.ai/zen/go/v1 credential_info: {} -general_settings: - store_model_in_db: true - background_health_checks: true - health_check_interval: 300 +# general_settings: +# store_model_in_db: true +# background_health_checks: true +# health_check_interval: 300 -litellm_settings: - drop_params: true - request_timeout: 120 - json_logs: true +# litellm_settings: +# drop_params: true +# request_timeout: 120 +# json_logs: true -router_settings: - cooldown_time: 60 - allowed_fails: 3 +# router_settings: +# cooldown_time: 60 +# allowed_fails: 3 From 47f7479fcb994574683b5cf4566c8ebe2e4422b4 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 09:54:35 +0800 Subject: [PATCH 13/18] Update config.yaml --- agent/litellm/config.yaml | 106 +++++++++++++++++++------------------- 1 file changed, 53 insertions(+), 53 deletions(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index 068621e5..85f14299 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -1,63 +1,63 @@ model_list: - # - model_name: cerebras/gemma-4-31b - # litellm_params: - # model: cerebras/gemma-4-31b + - model_name: cerebras/gemma-4-31b + litellm_params: + model: cerebras/gemma-4-31b - # - model_name: google/gemini-flash-lite-latest - # litellm_params: - # model: gemini/gemini-flash-lite-latest + - model_name: google/gemini-flash-lite-latest + litellm_params: + model: gemini/gemini-flash-lite-latest - model_name: google/gemma-4-31b-it litellm_params: model: gemini/gemma-4-31b-it -# - model_name: groq/gpt-oss-120b -# litellm_params: -# model: groq/openai/gpt-oss-120b - -# - model_name: nous/hy3:free -# litellm_params: -# model: openai/tencent/hy3:free -# litellm_credential_name: nous - -# - model_name: nvidia/deepseek-v4-pro:max -# litellm_params: -# model: nvidia_nim/deepseek-ai/deepseek-v4-pro -# thinking: -# type: enabled -# budget_tokens: 32000 - -# - model_name: nvidia/deepseek-v4-pro:high -# litellm_params: -# model: nvidia_nim/deepseek-ai/deepseek-v4-pro -# reasoning_effort: high - -# - model_name: opencode-zen/deepseek-v4-flash-free -# litellm_params: -# model: openai/deepseek-v4-flash-free -# litellm_credential_name: opencode_zen - -# - model_name: opencode-zen/mimo-v2.5-free -# litellm_params: -# model: openai/mimo-v2.5-free -# litellm_credential_name: opencode_zen - -# - model_name: openrouter/free -# litellm_params: -# model: openrouter/free - -# - model_name: smart-router -# litellm_params: -# model: auto_router/complexity_router -# complexity_router_config: -# tiers: -# SIMPLE: opencode-zen/deepseek-v4-flash-free -# MEDIUM: opencode-zen/deepseek-v4-flash-free -# COMPLEX: nous/hy3:free -# REASONING: nous/hy3:free -# adaptive: true -# session_affinity: true -# complexity_router_default_model: nous/hy3:free + - model_name: groq/gpt-oss-120b + litellm_params: + model: groq/openai/gpt-oss-120b + + - model_name: nous/hy3:free + litellm_params: + model: openai/tencent/hy3:free + litellm_credential_name: nous + + # - model_name: nvidia/deepseek-v4-pro:max + # litellm_params: + # model: nvidia_nim/deepseek-ai/deepseek-v4-pro + # thinking: + # type: enabled + # budget_tokens: 32000 + + # - model_name: nvidia/deepseek-v4-pro:high + # litellm_params: + # model: nvidia_nim/deepseek-ai/deepseek-v4-pro + # reasoning_effort: high + + - model_name: opencode-zen/deepseek-v4-flash-free + litellm_params: + model: openai/deepseek-v4-flash-free + litellm_credential_name: opencode_zen + + - model_name: opencode-zen/mimo-v2.5-free + litellm_params: + model: openai/mimo-v2.5-free + litellm_credential_name: opencode_zen + + - model_name: openrouter/free + litellm_params: + model: openrouter/free + + - model_name: smart-router + litellm_params: + model: auto_router/complexity_router + complexity_router_config: + tiers: + SIMPLE: opencode-zen/deepseek-v4-flash-free + MEDIUM: opencode-zen/deepseek-v4-flash-free + COMPLEX: nous/hy3:free + REASONING: nous/hy3:free + adaptive: true + session_affinity: true + complexity_router_default_model: nous/hy3:free credential_list: - credential_name: nous From faf1cf42aaf2d34d5c3a37359ebda7aa43a02726 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 09:58:38 +0800 Subject: [PATCH 14/18] Update config.yaml --- agent/litellm/config.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index 85f14299..470d70e8 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -44,7 +44,7 @@ model_list: - model_name: openrouter/free litellm_params: - model: openrouter/free + model: openrouter/openrouter/free - model_name: smart-router litellm_params: From 9146c60e44195e9f93b2b60dd92f3d616f40c15f Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 09:59:53 +0800 Subject: [PATCH 15/18] Update config.yaml --- agent/litellm/config.yaml | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index 470d70e8..1df7f846 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -78,16 +78,16 @@ credential_list: api_base: https://opencode.ai/zen/go/v1 credential_info: {} -# general_settings: -# store_model_in_db: true -# background_health_checks: true -# health_check_interval: 300 - -# litellm_settings: -# drop_params: true -# request_timeout: 120 -# json_logs: true - -# router_settings: -# cooldown_time: 60 -# allowed_fails: 3 +general_settings: + store_model_in_db: true + background_health_checks: true + health_check_interval: 300 + +litellm_settings: + drop_params: true + request_timeout: 120 + json_logs: true + +router_settings: + cooldown_time: 60 + allowed_fails: 3 From dba1cb61b51316025e8cba3abe0437c924dd77e5 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 10:01:28 +0800 Subject: [PATCH 16/18] Update config.yaml --- agent/litellm/config.yaml | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index 1df7f846..def09f70 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -20,17 +20,17 @@ model_list: model: openai/tencent/hy3:free litellm_credential_name: nous - # - model_name: nvidia/deepseek-v4-pro:max - # litellm_params: - # model: nvidia_nim/deepseek-ai/deepseek-v4-pro - # thinking: - # type: enabled - # budget_tokens: 32000 - - # - model_name: nvidia/deepseek-v4-pro:high - # litellm_params: - # model: nvidia_nim/deepseek-ai/deepseek-v4-pro - # reasoning_effort: high + - model_name: nvidia/deepseek-v4-pro:max + litellm_params: + model: nvidia_nim/deepseek-ai/deepseek-v4-pro + thinking: + type: enabled + budget_tokens: 32000 + + - model_name: nvidia/deepseek-v4-pro:high + litellm_params: + model: nvidia_nim/deepseek-ai/deepseek-v4-pro + reasoning_effort: high - model_name: opencode-zen/deepseek-v4-flash-free litellm_params: From d251cd08aea34ef5b70d986d25e871891a163674 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 10:58:51 +0800 Subject: [PATCH 17/18] Update config.yaml --- agent/litellm/config.yaml | 40 +++++++++++++++------------------------ 1 file changed, 15 insertions(+), 25 deletions(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index def09f70..f43012b5 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -1,3 +1,12 @@ +general_settings: + store_model_in_db: true + +litellm_settings: + drop_params: true + request_timeout: 60 + set_verbose: false + json_logs: true + model_list: - model_name: cerebras/gemma-4-31b litellm_params: @@ -20,18 +29,6 @@ model_list: model: openai/tencent/hy3:free litellm_credential_name: nous - - model_name: nvidia/deepseek-v4-pro:max - litellm_params: - model: nvidia_nim/deepseek-ai/deepseek-v4-pro - thinking: - type: enabled - budget_tokens: 32000 - - - model_name: nvidia/deepseek-v4-pro:high - litellm_params: - model: nvidia_nim/deepseek-ai/deepseek-v4-pro - reasoning_effort: high - - model_name: opencode-zen/deepseek-v4-flash-free litellm_params: model: openai/deepseek-v4-flash-free @@ -78,16 +75,9 @@ credential_list: api_base: https://opencode.ai/zen/go/v1 credential_info: {} -general_settings: - store_model_in_db: true - background_health_checks: true - health_check_interval: 300 - -litellm_settings: - drop_params: true - request_timeout: 120 - json_logs: true - -router_settings: - cooldown_time: 60 - allowed_fails: 3 +# guardrails: +# - guardrail_name: headroom +# litellm_params: +# guardrail: headroom +# mode: pre_call +# api_base: http://headroom:8787 From ace752c65ac9aceb4bd44f2656de8fb0d59f2801 Mon Sep 17 00:00:00 2001 From: yxtay <5795122+yxtay@users.noreply.github.com> Date: Tue, 28 Jul 2026 11:05:22 +0800 Subject: [PATCH 18/18] Update config.yaml --- agent/litellm/config.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml index f43012b5..69462f00 100644 --- a/agent/litellm/config.yaml +++ b/agent/litellm/config.yaml @@ -4,7 +4,6 @@ general_settings: litellm_settings: drop_params: true request_timeout: 60 - set_verbose: false json_logs: true model_list: @@ -81,3 +80,4 @@ credential_list: # guardrail: headroom # mode: pre_call # api_base: http://headroom:8787 +# default_on: true