feat(agent): hierarchical executor with path resolve, runtime probe, quiet UI
Make Zed Agent closer to Cursor: deterministic DevOps path index, live Traefik port probe before blind edits, stop-after-edit, and quieter Russian progress.
This commit is contained in:
+22
-50
@@ -1,104 +1,76 @@
|
||||
# tier × lane (A/B/C) → Novita model id + LiteLLM fallbacks
|
||||
# Tier × lane orchestration metadata (model IDs → config/providers.yaml)
|
||||
|
||||
lanes:
|
||||
A: economy
|
||||
B: balanced
|
||||
C: max
|
||||
|
||||
# LiteLLM per-lane RPM (proxy-side). Zed agent bursts tool calls — keep high for personal IFT.
|
||||
# OpenRouter :free upstream may still 429; router fallbacks + cooldown_time apply separately.
|
||||
models:
|
||||
a-simple:
|
||||
novita: novita/qwen/qwen3-4b-fp8
|
||||
fallbacks: [b-simple, groq-llama-8b]
|
||||
rpm: 60
|
||||
rpm: 300
|
||||
b-simple:
|
||||
novita: novita/meta-llama/llama-3.1-8b-instruct
|
||||
fallbacks: [a-simple, groq-llama-8b]
|
||||
rpm: 60
|
||||
rpm: 300
|
||||
c-simple:
|
||||
novita: novita/qwen/qwen3-8b-fp8
|
||||
fallbacks: [b-simple]
|
||||
rpm: 60
|
||||
rpm: 300
|
||||
|
||||
a-medium-ops:
|
||||
novita: novita/qwen/qwen3-8b-fp8
|
||||
fallbacks: [a-medium-code, b-medium-ops]
|
||||
rpm: 40
|
||||
rpm: 240
|
||||
b-medium-ops:
|
||||
novita: novita/deepseek/deepseek-v3.2
|
||||
fallbacks: [a-medium-code, c-medium-ops]
|
||||
rpm: 40
|
||||
rpm: 240
|
||||
c-medium-ops:
|
||||
novita: novita/deepseek/deepseek-v3.2
|
||||
fallbacks: [b-medium-ops]
|
||||
rpm: 40
|
||||
rpm: 240
|
||||
|
||||
a-medium-code:
|
||||
novita: novita/qwen/qwen3-coder-30b-a3b-instruct
|
||||
fallbacks: [a-medium-ops, groq-qwen-coder]
|
||||
rpm: 40
|
||||
rpm: 240
|
||||
b-medium-code:
|
||||
novita: novita/qwen/qwen3-coder-30b-a3b-instruct
|
||||
fallbacks: [b-medium-ops, c-medium-code]
|
||||
rpm: 40
|
||||
rpm: 240
|
||||
c-medium-code:
|
||||
novita: novita/qwen/qwen3-coder-30b-a3b-instruct
|
||||
fallbacks: [b-medium-code, c-medium-ops]
|
||||
rpm: 30
|
||||
rpm: 180
|
||||
|
||||
a-complex:
|
||||
novita: novita/deepseek/deepseek-v3.2
|
||||
fallbacks: [b-complex, a-reasoning]
|
||||
rpm: 30
|
||||
rpm: 180
|
||||
b-complex:
|
||||
novita: novita/deepseek/deepseek-r1-0528
|
||||
fallbacks: [a-complex, c-complex]
|
||||
rpm: 20
|
||||
rpm: 120
|
||||
c-complex:
|
||||
novita: novita/deepseek/deepseek-r1-turbo
|
||||
fallbacks: [b-complex]
|
||||
rpm: 15
|
||||
rpm: 120
|
||||
|
||||
a-reasoning:
|
||||
novita: novita/deepseek/deepseek-r1-0528-qwen3-8b
|
||||
fallbacks: [b-reasoning, gemini-flash]
|
||||
rpm: 30
|
||||
rpm: 120
|
||||
b-reasoning:
|
||||
novita: novita/deepseek/deepseek-r1-0528
|
||||
fallbacks: [a-reasoning, c-reasoning]
|
||||
rpm: 20
|
||||
rpm: 120
|
||||
c-reasoning:
|
||||
novita: novita/deepseek/deepseek-r1-turbo
|
||||
fallbacks: [b-reasoning, gemini-flash]
|
||||
rpm: 15
|
||||
rpm: 120
|
||||
|
||||
a-vision-ocr:
|
||||
novita: novita/paddlepaddle/paddleocr-vl
|
||||
fallbacks: [a-vision]
|
||||
rpm: 30
|
||||
rpm: 120
|
||||
no_escalation: true
|
||||
a-vision:
|
||||
novita: novita/qwen/qwen3-vl-30b-a3b-instruct
|
||||
fallbacks: [a-vision-ocr]
|
||||
rpm: 20
|
||||
rpm: 120
|
||||
b-vision:
|
||||
novita: novita/qwen/qwen2.5-vl-72b-instruct
|
||||
fallbacks: [a-vision, c-vision]
|
||||
rpm: 15
|
||||
rpm: 90
|
||||
c-vision:
|
||||
novita: novita/qwen/qwen3-vl-235b-a22b-instruct
|
||||
fallbacks: [b-vision]
|
||||
rpm: 10
|
||||
|
||||
optional_providers:
|
||||
groq-llama-8b:
|
||||
model: groq/llama-3.1-8b-instant
|
||||
api_key: os.environ/GROQ_API_KEY
|
||||
groq-qwen-coder:
|
||||
model: groq/qwen-qwen-2.5-coder-32b
|
||||
api_key: os.environ/GROQ_API_KEY
|
||||
gemini-flash:
|
||||
model: gemini/gemini-2.0-flash
|
||||
api_key: os.environ/GEMINI_API_KEY
|
||||
rpm: 90
|
||||
|
||||
audit:
|
||||
price_drift_threshold_pct: 10
|
||||
|
||||
Reference in New Issue
Block a user