diff --git a/config.yaml b/config.yaml index a8bc9754..bac56e2e 100644 --- a/config.yaml +++ b/config.yaml @@ -9,10 +9,10 @@ providers: cost_factor: 0.0 default_model: nvidia/nemotron-3-super-120b-a12b models: - - nvidia/nemotron-mini-4b-instruct - - openai/gpt-oss-120b - - nvidia/nvidia-nemotron-nano-9b-v2 - - meta/llama-3.1-8b-instruct + - nvidia/nemotron-mini-4b-instruct + - openai/gpt-oss-120b + - nvidia/nvidia-nemotron-nano-9b-v2 + - meta/llama-3.1-8b-instruct rate_limit: 1000 timeout: 30 omniroute-local: @@ -21,9 +21,9 @@ providers: cost_factor: 0.0 default_model: auto/chat models: - - auto/chat - - auto/best-free - - auto/coding + - auto/chat + - auto/best-free + - auto/coding rate_limit: 1000 timeout: 30 deepseek: @@ -32,14 +32,24 @@ providers: cost_factor: 0.0 default_model: deepseek-v4-flash models: - - deepseek-v4-flash - - deepseek-v4-pro + - deepseek-v4-flash + - deepseek-v4-pro rate_limit: 1000 timeout: 30 + agnes: + key_env: AGNES_API_KEY + base_url: https://apihub.agnes-ai.com/v1 + cost_factor: 0.0 + default_model: agnes-2.0-flash + models: + - agnes-2.0-flash + - agnes-2.5-flash + rate_limit: 1000 + timeout: 60 fallback_providers: '["deepseek"]' toolsets: -- hermes-cli -- web + - hermes-cli + - web agent: max_turns: 90 gateway_timeout: 1800 @@ -264,9 +274,9 @@ display: ephemeral_system_ttl: 0 runtime_footer: fields: - - model - - context_pct - - cwd + - model + - context_pct + - cwd copy_shortcut: auto tool_progress: all tool_progress_style: accumulate @@ -357,12 +367,12 @@ moa: presets: expert-panel: reference_models: - - provider: newapi-local - model: openai/gpt-oss-120b - - provider: newapi-local - model: nvidia/llama-3.3-nemotron-super-49b-v1 - - provider: newapi-local - model: mistralai/mistral-large-3-675b-instruct-2512 + - provider: newapi-local + model: openai/gpt-oss-120b + - provider: newapi-local + model: nvidia/llama-3.3-nemotron-super-49b-v1 + - provider: newapi-local + model: mistralai/mistral-large-3-675b-instruct-2512 aggregator: provider: newapi-local model: openai/gpt-oss-120b @@ -420,37 +430,38 @@ approvals: mcp_reload_confirm: true destructive_slash_confirm: false command_allowlist: -- kill process via pgrep expansion (self-termination) -- pipe remote content to shell -- sudo with privilege flag (stdin/askpass/shell/list) -- git force push (rewrites remote history) -- kill hermes/gateway process (self-termination) -- overwrite system config -- SQL TRUNCATE -- find -delete -- copy/move file into /etc/ -- script execution via -e/-c flag -- stop/restart system service -- shell command via -c/-lc flag -- script execution via heredoc -- world/other-writable permissions -- delete in root path -- copy/move file into system config path -- overwrite system file via redirection -- in-place edit of Hermes config/env -- force kill processes -- hermes update (restarts gateway, kills running agents) -- in-place edit of system config -- start gateway outside systemd (use 'systemctl --user restart hermes-gateway') -- git force push short flag (rewrites remote history) -- overwrite system file via tee -- sudo with combined-flag privilege escalation -- overwrite project env/config via redirection -- disk copy -- force kill processes (killall -KILL) -- stop/restart hermes gateway (kills running agents) -- command parser limit or malformed executable payload -- recursive delete + - find -delete + - force kill processes (killall -KILL) + - script execution via -e/-c flag + - overwrite project env/config file + - git force push short flag (rewrites remote history) + - in-place edit of Hermes config/env + - SQL TRUNCATE + - recursive delete + - in-place edit of system config + - shell command via -c/-lc flag + - copy/move file into /etc/ + - overwrite system file via redirection + - hermes update (restarts gateway, kills running agents) + - world/other-writable permissions + - disk copy + - kill process via pgrep expansion (self-termination) + - kill hermes/gateway process (self-termination) + - delete in root path + - start gateway outside systemd (use 'systemctl --user restart hermes-gateway') + - stop/restart system service + - force kill processes + - overwrite system config + - overwrite system file via tee + - copy/move file into system config path + - git force push (rewrites remote history) + - pipe remote content to shell + - sudo with combined-flag privilege escalation + - script execution via heredoc + - stop/restart hermes gateway (kills running agents) + - command parser limit or malformed executable payload + - overwrite project env/config via redirection + - sudo with privilege flag (stdin/askpass/shell/list) hooks_auto_accept: false security: allow_private_urls: false @@ -547,16 +558,16 @@ _config_version: 33 mcp_servers: codegraph: args: - - serve - - --mcp + - serve + - --mcp command: codegraph connect_timeout: 60 enabled: true timeout: 120 github: args: - - -y - - '@modelcontextprotocol/server-github' + - -y + - '@modelcontextprotocol/server-github' command: npx enabled: true env: @@ -565,8 +576,8 @@ mcp_servers: openclaw: command: openclaw args: - - mcp - - serve + - mcp + - serve connect_timeout: 60 timeout: 300 codebase-memory-mcp: @@ -575,30 +586,30 @@ mcp_servers: dbx: command: npx args: - - -y - - '@dbx-app/mcp-server' + - -y + - '@dbx-app/mcp-server' enabled: true timeout: 120 connect_timeout: 60 platform_toolsets: cli: - - browser - - clarify - - code_execution - - computer_use - - cronjob - - delegation - - file - - image_gen - - memory - - session_search - - skills - - terminal - - todo - - tts - - vision - - web - - mcp-codegraph + - browser + - clarify + - code_execution + - computer_use + - cronjob + - delegation + - file + - image_gen + - memory + - session_search + - skills + - terminal + - todo + - tts + - vision + - web + - mcp-codegraph platforms: webhook: enabled: true @@ -612,9 +623,9 @@ platforms: plugins: disabled: [] enabled: - - agentic-sms-gateway - - cronalytics - - rtk-rewrite + - agentic-sms-gateway + - cronalytics + - rtk-rewrite weixin: enabled: true extra: @@ -627,4 +638,26 @@ weixin: session_reset: {} known_plugin_toolsets: cli: - - spotify + - spotify + +# ── Fallback Model ──────────────────────────────────────────────────── +# Automatic provider failover when primary is unavailable. +# Uncomment and configure to enable. Triggers on rate limits (429), +# overload (529), service errors (503), or connection failures. +# +# Supported providers: +# openrouter (OPENROUTER_API_KEY) — routes to any model +# openai-codex (OAuth — hermes auth) — OpenAI Codex +# nous (OAuth — hermes auth) — Nous Portal +# zai (ZAI_API_KEY) — Z.AI / GLM +# kimi-coding (KIMI_API_KEY) — Kimi / Moonshot +# kimi-coding-cn (KIMI_CN_API_KEY) — Kimi / Moonshot (China) +# minimax (MINIMAX_API_KEY) — MiniMax +# minimax-cn (MINIMAX_CN_API_KEY) — MiniMax (China) +# bedrock (AWS IAM / boto3) — AWS Bedrock (Converse API) +# +# For custom OpenAI-compatible endpoints, add base_url and key_env. +# +# fallback_model: +# provider: openrouter +# model: anthropic/claude-sonnet-4 diff --git a/scripts/model-health.py b/scripts/model-health.py index 09ca252c..44107e75 100755 --- a/scripts/model-health.py +++ b/scripts/model-health.py @@ -19,6 +19,31 @@ API = "http://127.0.0.1:3000/v1" KEY = "0ExNiLblJvIWBDpkS50fwOBw4MmqLyKdHJK5iQtlw9dOMWBP" OUTPUT = os.path.expanduser("~/.hermes/model-health.json") +# ============ Agnes 模型（2026-08-17 新增：优先巡检） ============ +# Agnes 是稳定备用 LLM（cron/distill 已切换），巡检必须优先 +AGNES_API = "https://apihub.agnes-ai.com/v1" +AGNES_KEY = "" +for _l in open(os.path.expanduser("~/.hermes/.env"), encoding="utf-8"): + if _l.startswith("AGNES_API_KEY=") and not _l.startswith("#"): + AGNES_KEY = _l.strip().split("=", 1)[1] + break +# Agnes 模型（排最前 = 优先巡检） +AGNES_MODELS = [ + "agnes-2.0-flash", # 稳定主力（cron/distill 在用） + "agnes-2.5-flash", # 新版备用 +] +# Agnes 上下文长度（K） +CONTEXT_LENGTHS_AGNES = { + "agnes-2.0-flash": 128, + "agnes-2.5-flash": 128, +} + +def _get_endpoint(model: str) -> dict: + """返回 (base_url, headers) — agnes 模型走独立端点，其余走 NewAPI""" + if model.startswith("agnes-"): + return AGNES_API, {"Authorization": f"Bearer {AGNES_KEY}", "Content-Type": "application/json"} + return API, HEADERS + # ============ 配置自愈 ============ CONFIG_PATH = os.path.expanduser("~/.hermes/config.yaml") # 配置中声明的模型 — 巡检会交叉验证 @@ -104,10 +129,15 @@ OPENCLAW_MODELS = [ "qwen/qwen3-next-80b-a3b-thinking", ] -ALL_MODELS = [m for m in ( - CONFIG_DECLARED_MODELS + [m for m in CANDIDATE_POOL if m not in CONFIG_DECLARED_MODELS] - + [m for m in OPENCLAW_MODELS if m not in CONFIG_DECLARED_MODELS and m not in CANDIDATE_POOL] -) if m not in KNOWN_PAID] +# Agnes 优先测试（排在 ALL_MODELS 最前）；后面的非 agnes 模型才做去重过滤 +_OTHER_MODELS = [ + m for m in ( + CONFIG_DECLARED_MODELS + + [m for m in CANDIDATE_POOL if m not in CONFIG_DECLARED_MODELS] + + [m for m in OPENCLAW_MODELS if m not in CONFIG_DECLARED_MODELS and m not in CANDIDATE_POOL] + ) if m not in KNOWN_PAID and m not in AGNES_MODELS +] +ALL_MODELS = AGNES_MODELS + _OTHER_MODELS HEADERS = { "Authorization": f"Bearer {KEY}", @@ -197,7 +227,7 @@ def _speed_score(latency_ms: int, fastest_latency: int) -> float: def _context_score(model: str) -> float: """上下文长度分：越长越高 256K→100, 128K→80, 64K→60, 32K→40, 8K→10""" - ctx = CONTEXT_LENGTHS.get(model, 128) # 未知默认128 + ctx = CONTEXT_LENGTHS_AGNES.get(model, CONTEXT_LENGTHS.get(model, 128)) # 未知默认128 if ctx >= 256: return 100 if ctx >= 128: @@ -224,10 +254,11 @@ def _run_quality_probe(model: str, trials: int = 3) -> dict: "max_tokens": 200, "temperature": 0.1, }).encode() + base_url, hdrs = _get_endpoint(model) req = urllib.request.Request( - f"{API}/chat/completions", + f"{base_url}/chat/completions", data=payload, - headers=HEADERS, + headers=hdrs, method="POST", ) try: @@ -309,10 +340,11 @@ def test_model(model: str, fastest_latency: int = None) -> dict: "max_tokens": 20, }).encode() + base_url, hdrs = _get_endpoint(model) req = urllib.request.Request( - f"{API}/chat/completions", + f"{base_url}/chat/completions", data=payload, - headers=HEADERS, + headers=hdrs, method="POST", ) @@ -415,8 +447,9 @@ def _verify_model_usable(model: str) -> bool: "messages": [{"role": "user", "content": "hi"}], "max_tokens": 5, }).encode() + base_url, hdrs = _get_endpoint(model) req = urllib.request.Request( - f"{API}/chat/completions", data=payload, headers=HEADERS, method="POST" + f"{base_url}/chat/completions", data=payload, headers=hdrs, method="POST" ) try: with urllib.request.urlopen(req, timeout=20) as resp: diff --git a/skills/creative/agnes-ai/SKILL.md b/skills/creative/agnes-ai/SKILL.md index 069f4289..2e923f69 100644 --- a/skills/creative/agnes-ai/SKILL.md +++ b/skills/creative/agnes-ai/SKILL.md @@ -17,7 +17,7 @@ homepage: https://platform.agnes-ai.com |------|-----| | **Base URL** | `https://apihub.agnes-ai.com/v1` | | **国内新域名** | `https://agnes-ai.cn`（2026-08-15 文章宣布，**实测 HTTP 403 需要 API key**，作为备用入口；主入口仍是 apihub.agnes-ai.com）| -| **API Key** | ⚠️ **2026-08-15 实测：`~/.hermes/.env` 无 AGNES_API_KEY，key 已丢失**（织忆只留 sk-7k9e9... 前段）。需要牧尘从 https://platform.agnes-ai.com 个人中心重新获取 | +| **API Key** | ✅ **2026-08-17 已恢复**：完整 51 字符 key 在 `~/.hermes/.env`（`AGNES_API_KEY=sk-7k9e...2ikW`），来源 obsidian `/home/muc/mc/牧尘/claw/key.md`。⚠️ 注意：Hermes 工具输出会把 key 显示成脱敏版（sk-7k9...2ikW 带省略号），但文件里存的是完整 key——显示脱敏≠存储脱敏，别误判"key 丢失" | | **鉴权方式** | `Authorization: Bearer {key}` | | **日额限制** | 文本 50万 token/天，图像 500张/天，视频 150条/天 | | **2.5 Pro Alpha 定价** | 输入缓存命中 0.025元/百万token，未命中 3元/百万token，输出 6元/百万token（≈DeepSeek V4 涨价前）| diff --git a/skills/creative/comfyui-rtx3050/SKILL.md b/skills/creative/comfyui-rtx3050/SKILL.md index 832b6619..30e946f9 100644 --- a/skills/creative/comfyui-rtx3050/SKILL.md +++ b/skills/creative/comfyui-rtx3050/SKILL.md @@ -162,6 +162,7 @@ cp ~/ComfyUI/models/ultralytics/face_yolov8m.onnx ~/ComfyUI/models/onnx/ 5. Impact Pack 加载时 `SAM2 functionality unavailable` 是正常警告（只影响 SAM 高级分割，FaceDetailer 的 YOLO 路径不受影响） > 📎 相关文件：`references/face-detailer-workflow-20260801.md`（FaceDetailer 完整可执行工作流 + 坑速查表） +> 📎 相关文件：`references/dual-pipeline-comfyui-vs-agnes-20260817.md`（ComfyUI vs Agnes 双管线对比 + Agnes 2.0/2.1 稳定性 + SD 人影实化坑） ## ControlNet OpenPose（2026-08-01 已验证） @@ -239,6 +240,51 @@ rm models/checkpoints/xxx.safetensors - **背景**：月光海边/城市夜景，统一色调 `cool blue and teal tones` - **禁止**：`monochrome, grayscale`（压制色彩），`warm colors, orange, yellow, sunset`（色调混乱） +## 生成场景/建筑概念图（MajicMIX v6，2026-08-17 实测 12.7s） + +国风建筑/场景类需求（宫殿/水乡/古城/仙宫）同样可用 ComfyUI 出**写实概念图**，与 Agnes 云端对比各有优势： + +- 参数与人物相同：MajicMIX v6 + 512×768 + dpmpp_2m/karras 25 步 cfg 7 → **~12.7s（3.16 it/s）** +- 中文提示词直接可用（urllib JSON 自动编码），来自 palace-prompts / prompt-cli 的成品词直接喂 +- 负向必加建筑类词：`distorted architecture, duplicate buildings, readable text, logo, low detail, flat image` + +⚠️ **「人影」实化坑（2026-08-17 实测）**：SD 模型会把提示词里「阴影中的人影」「远景人影」「人物剪影」实化成**画面主角**（暗黑诡城图前景多了一位红衣女子，Agnes 版则正确保持纯场景）。纯场景出图必须：删掉人影类词，或改「空无一人/无人物」；人物只做尺度锚点时用「极小背影、占画面 1-4%」。 + +### 双管线选择（ComfyUI vs Agnes，2026-08-17 实测对比） + +| 需求 | 管线 | 依据 | +|------|------|------| +| 写实质感/材质细节 | **ComfyUI MajicMIX v6** | 纹理真实，建筑/材质表现强 | +| 大场景概念/构图大胆 | **Agnes 云端** | 想象力放得开，氛围宏大 | +| 人物四视图一致性 | **Agnes** | SD 多视图/人物一致性弱（易实化、变形） | +| 免费额度 | ComfyUI 本地免费 | Agnes 500张/天 | +| 速度 | ComfyUI ~13s | Agnes ~30-60s | + +> 结论：互补使用。要真实感走本地，要概念氛围走云端。交付后立即 kill ComfyUI（资源铁律见下）。 + +## 大场景全景三件套（2026-08-17 实测：SD1.5 默认出局部特写+人影实化） + +> 用户反馈「comfyui出的图都是局部，体现不了大场景」「第一张出的是人物」。SD1.5 的 512x768 竖构图天然偏局部特写；「阴影中的人影」会被实化成人物主角。修复三件套： + +1. **横版 768x512**：全景/场景图用横版（竖版适合人物/单体建筑） +2. **全景引导词**（正向加）： + ``` + ultra-wide aerial panoramic establishing shot, vast sprawling cityscape, + entire city/town visible in frame, high aerial view looking down, wide angle, + endless layers of rooftops extending to the horizon + ``` +3. **去人物**（负向加）： + ``` + person, people, woman, man, human, figure, character, portrait, close-up, + single building, zoomed in, closeup, macro, isolated building, head and shoulders + ``` + ⚠️ 正向里**不要写**「人影/人物剪影/阴影中的人影」——SD 会把它当主角画出来，要写「no people, empty streets」。 + +- 效果：鸟瞰全景、整座城尽收眼底、无人物、无文字水印（2026-08-17 实测两张全过） +- 参数：steps 28, cfg 7.5（比默认略高，场景更稳），dpmpp_2m + karras + +> ⚠️ **牧尘最终结论（2026-08-17）**：即使三件套修好局部/人物问题，**大场景图也别用 ComfyUI 出**——SD1.5 上限就在 512-768px，宏大感与 Agnes 云端差太远（牧尘原话"比起Agnes出图还是差太远"）。三件套只在"快速本地示意/离线"时用；**大场景/概念图默认走 Agnes 云端**，ComfyUI 正确定位 = **写实人物/半身/网红脸**（MajicMIX v6 强项）。 + ## 生成国风/汉服美女（MajicMIX v6，2026-08-03 实测 9s 无缺陷） 用户点名"小红书风格美女图，国风"时的标准姿势。**MajicMIX v6 + 512×768 竖版**（小红书比例），dpmpp_2m + karras 25 步，9 秒出图，vision_analyze 自评无手部/脸部缺陷。 diff --git a/skills/creative/comfyui-rtx3050/references/dual-pipeline-comfyui-vs-agnes-20260817.md b/skills/creative/comfyui-rtx3050/references/dual-pipeline-comfyui-vs-agnes-20260817.md new file mode 100644 index 00000000..0e99352e --- /dev/null +++ b/skills/creative/comfyui-rtx3050/references/dual-pipeline-comfyui-vs-agnes-20260817.md @@ -0,0 +1,40 @@ +# 双管线出图对比（ComfyUI vs Agnes）— 2026-08-17 实测 + +> 场景：用户让同一批 palace-prompts 提示词分别走 ComfyUI 和 Agnes 出图对比。 +> 结论：**互补使用**，不是替代关系。 + +## 对比结果（同 prompt：暗黑东方诡城 / 江南水乡古城） + +| 维度 | ComfyUI (MajicMIX v6) | Agnes (agnes-image-2.0-flash) | +|------|----------------------|------------------------------| +| 写实质感 | ✅ 强（纹理/材质真实） | 偏概念插画 | +| 场景氛围 | 构图略保守 | 大场景/概念氛围更宏大 | +| 速度 | ~12.7s（3.16 it/s） | ~30-60s | +| 成本 | 本地免费 | 免费 500张/天 | +| 中文提示词 | ✅ 直接可用 | ✅ 直接可用 | +| 模型理解 | 字面实化（见坑） | 抽象氛围还原好 | + +## 管线选择规则 + +- **要真实感/写实** → ComfyUI（MajicMIX v6 亚洲写实最强） +- **要大场景/概念氛围** → Agnes（云端想象力放得开） +- **人物四视图一致性** → Agnes（SD 多视图/人物一致性弱） +- **批量/要快** → ComfyUI（本地快） + +## ⚠️ SD「人影实化」坑（关键！） + +SD 1.5 系模型会把提示词里「阴影中的人影」「远景人影」「人物剪影」等词**实化成画面主角**。 +- 实测：暗黑诡城 prompt 含「阴影中的人影」→ ComfyUI 版前景多了一位红衣女子；Agnes 版正确保持纯场景。 +- **修法**：纯场景出图删掉人影类词，或改成「空无一人/无人物」；人物只做尺度锚点时用「极小背影、占画面 1-4%」。 + +## Agnes 模型稳定性实测 + +- `agnes-image-2.1-flash`：1/2 成功，另 1 次 read timeout（长 prompt 更明显） +- `agnes-image-2.0-flash`：4/4 成功，稳定 +- **图像生成默认用 2.0-flash**；超时重试时 timeout 提到 180s + +## 操作注意 + +- ComfyUI 用 `HF_ENDPOINT=https://hf-mirror.com` 启动（防 ControlNet aux 卡死） +- ComfyUI 交付后**立即 kill**（占 ~2.2GB 内存 + 1.1GB 显存，长期挂着触发系统看门狗告警） +- 生成产物统一存 `~/projects/quark-prompts/实测/` diff --git a/skills/palace-prompts/prompt-engineering/SKILL.md b/skills/palace-prompts/prompt-engineering/SKILL.md index ed9e1ac5..6e9a8fec 100644 --- a/skills/palace-prompts/prompt-engineering/SKILL.md +++ b/skills/palace-prompts/prompt-engineering/SKILL.md @@ -72,6 +72,17 @@ prompt-cli stats # 统计 | 人物过大抢戏 | 尺度锚点失效 | 锁 1-4% 画面占比 | | 颜色全橙金污染 | 色彩预算失控 | 选择性高饱和，不全局 | +## 管线选择（2026-08-17 实测结论，牧尘确认） + +| 需求 | 用哪个 | 原因 | +|------|--------|------| +| **大场景/概念图/全景**（国风古城/仙宫/现代建筑群） | **Agnes 云端** | 本地 SD1.5 出 512-768px 局部特写，宏大感差太远；Agnes 1024px+ 构图想象力碾压 | +| **写实人物/半身/网红脸**（四视图角色卡/穿搭） | **ComfyUI + MajicMIX v6** | 本地写实亚洲脸最强，免费，12-14s/张 | +| **任何要惊艳感的人像** | ComfyUI + Hires Fix | 见 comfyui-rtx3050 skill 三招 | +| 快速出图不想等 | Agnes 2.0-flash | ~30-60s，免费 500 张/天 | + +⚠️ 铁律：**大场景图别用 ComfyUI 出**（牧尘 2026-08-17 实测结论"比起Agnes出图还是差太远"）；ComfyUI 定位 = 写实人物/细节。 + ## 资源 - 领域 skills：`char-palace-prompts` / `guofeng-palace-prompts` / `modern-palace-prompts` / `xian-palace-prompts` / `prompt-template-kit`