From 4ae16b26402afb996f630d3e54248bb7d3af3c95 Mon Sep 17 00:00:00 2001 From: Moritz Graf Date: Mon, 14 Sep 2026 07:35:32 +0200 Subject: [PATCH] docs(adr): update ADR 0002 open questions following DeepSeek conductor promotion --- .../0002-openclaw-model-selection-tiering-and-economics.md | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/docs/adr/0002-openclaw-model-selection-tiering-and-economics.md b/docs/adr/0002-openclaw-model-selection-tiering-and-economics.md index eb1947a..c480e4b 100644 --- a/docs/adr/0002-openclaw-model-selection-tiering-and-economics.md +++ b/docs/adr/0002-openclaw-model-selection-tiering-and-economics.md @@ -158,10 +158,9 @@ To balance the user's desire to retain full conversation context across the enti To align on remaining edge cases before final sign-off: -1. **Telegram Interactive Latency vs. Model Cost**: - - `z-ai/glm-5.3-flash` is 50% cheaper (\$0.075 vs \$0.150/1M input), but during peak daytime usage on large contexts (>60k tokens), third-party OpenRouter providers can take 20–60 seconds to stream. - - `deepseek/deepseek-v4.1-flash` costs slightly more (\$0.150–\$0.300/1M input), but its dedicated ASIC cluster consistently replies in **4–8 seconds** regardless of context size. - - *Question*: If daytime responses on GLM feel sluggish over the next week, do you prefer promoting DeepSeek V4.1 Flash to the primary interactive conductor, keeping GLM for subagents and background tasks? +1. **Conductor Allocation Confirmed**: + - Following the tool-calling XML leakage diagnosed on September 14, `deepseek/deepseek-v4.1-flash` has been promoted to Primary Conductor for interactive chat and autonomous subagents. Its dedicated ASIC cluster provides instant tool execution and 2–4s response times at ~\$0.02–\$0.04/day. + - `z-ai/glm-5.3-flash` remains active for vision input and lightweight background heartbeats. 2. **Thinking / Reasoning Mode on Telegram**: - Currently, `thinking: medium` is enabled, emitting 100–300 reasoning tokens before generating conversational text. - *Question*: Would you like to disable thinking mode (`thinking: none`) for standard Telegram chat turns (for near-instant replies) and keep reasoning active only for subagents?