moritz/infrapuzzle
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(openclaw): configure 64k completion headroom for deepseek-v4.1-flash, promote cloudflare, and onboard fireworks

Browse Source
This commit is contained in:
Moritz Graf
2026-10-18 11:06:50 +02:00
parent dd60a095c6
commit c33b6e94fb
3 changed files with 44 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/adr/0002-openclaw-model-selection-tiering-and-economics.md
+5 -2
View File
@@ -90,8 +90,11 @@ How do we architect the full-spectrum model selection across **all modalities**
* **Primary (Fleet-Wide Standard as of 2026-10-17)**: `openrouter/deepseek/deepseek-v4.1-flash-1017`
- **1017 Snapshot Upgrade (Pareto Jump in Quality & Price)**: Released on October 17, 2026, `deepseek/deepseek-v4.1-flash-1017` boosts the Artificial Analysis Intelligence Index from **24.7 to 39.5** (+60%) via Reinforcement Learning with Self-Feedback (RLSF) while cutting DeepInfra `fp8` pricing by an additional **30%** (`$0.098/M` prompt, `$0.294/M` completion, and **`$0.00294/M` `cacheRead`** vs. `$0.140/$0.420/$0.0042` on the 0910 baseline).
- **Provider Pinning & Tool-Compatibility Verification**:
- Pinned `order: ["deepinfra", "inference-net", "parasail", "cloudflare"]`, `quantizations: ["fp8", "bf16", "unknown"]`, and `ignore: ["morph", "baseten", "deepseek", "open-inference", "decart", "sail-research", "wafer"]`.
- Live OpenRouter routing forensics verified that `morph/fp8` is filtered out by OpenRouter's `Filter by Tool Compatibility` when `tools` are passed, `deepseek` (official) is filtered by account privacy guardrails (`Paid model training violation`), and `baseten` returns `HTTP 429`. Meanwhile, `deepinfra`, `inference-net`, `parasail`, and `cloudflare` deliver 100% tool-calling reliability and 2–5s latency.
- Pinned `order: ["deepinfra", "cloudflare", "inference-net", "fireworks", "parasail"]`, `quantizations: ["fp8", "bf16", "unknown"]`, and `ignore: ["morph", "baseten", "deepseek", "open-inference", "decart", "sail-research", "wafer"]`.
- **Cloudflare (#2 Promotion)**: Promoted ahead of InferenceNet and Parasail because Cloudflare delivers a 97% cache discount (`$0.003/M` `cacheRead`), 3× lower completion costs (`$0.60/M` vs. `$1.20/M` on Parasail), and a massive **943,718** completion token limit.
- **Fireworks (#4 Addition)**: Onboarded as a high-reliability enterprise tier-1 provider (`$0.30/M` prompt, `$1.20/M` completion, `$0.006/M` `cacheRead`, 100% uptime, 943k max completion tokens, full tool choice and structured outputs support).
- **Completion Token Headroom Guardrail (`maxTokens: 65536`)**: Because reasoning models share the completion token budget between internal chain-of-thought (`reasoningTokens`, typically 2k–4k tokens) and the actual tool-call payload, omitting `maxTokens` previously allowed OpenClaw/OpenRouter to default to an 8,192 token ceiling. During large multi-kilobyte code or website generation, hitting 8,192 tokens abruptly truncated tool-call JSON mid-payload (`Provider returned an incomplete or malformed tool call`). Explicitly configuring `maxTokens: 65536` and `params.max_tokens: 65536` provides ample headroom for complex reasoning and large outputs.
- Live OpenRouter routing forensics verified that `morph/fp8` is filtered out by OpenRouter's `Filter by Tool Compatibility` when `tools` are passed, `deepseek` (official) is filtered by account privacy guardrails (`Paid model training violation`), and `baseten` returns `HTTP 429`. Meanwhile, `deepinfra`, `cloudflare`, `inference-net`, `fireworks`, and `parasail` deliver 100% tool-calling reliability and sub-second to 3s latency.
- **Post-Trial Evaluation of `z-ai/glm-5.3-flash` (2026-09-13 to 2026-10-17)**:
- While `z-ai/glm-5.3-flash` was trialed as primary conductor, 17-day production telemetry (Oct 1–17, 2026) revealed **12 mid-stream tool-call aborts** (`stopReason: "error"`, `errorMessage: "Provider returned an incomplete or malformed tool call"`) across 5 agents (`main`, `grabengasse_media`, `koch`, `hebamme`, `doktor`) when generating nested `tool_call({ id, args })` payloads after `tool_describe`, as well as occasional thinking-only whitespace stalls (Issue 23) and long-context attention drift (Issues 22 & 25).
- Promoting `deepseek/deepseek-v4.1-flash-1017` to primary across all agents eliminates malformed tool-call stream aborts AND lowers total monthly cost by >50% compared to GLM 5.3 Flash.