claude-code-sdk Import Errors After the June 2026 Rename: Why and the Fix
ModuleNotFoundError: claude_code_sdk or no export from @anthropic-ai/claude-code? The SDK moved to claude-agent-sdk. Before/after fix for TS + Python.
Claude Tag in Slack (2026): 4-Step Setup, Ambient Mode, Aug 3 Deadline
Claude Tag is a shared @Claude teammate in Slack on Opus 4.8. Setup in 4 steps, ambient mode, admin scopes, and the Aug 3, 2026 cutover from Claude in Slack.
Run GLM 5.2 Locally (2026): 2-bit on a 256GB Mac or 4090 box
Run GLM 5.2 (753B) locally: 2-bit fits a 256GB Mac Studio, 4-bit wants 512GB, ~3-9 tok/s. GGUF quant picks for llama.cpp, LM Studio, and a 4090 box.
Routing GLM-5.2, DeepSeek V4, MiniMax M3 & Kimi K2.6 Through One API (2026)
Route 4 models on one ofox key: blended $0.19/M (V4 Flash) to $2.40/M (GLM-5.2), 12.86x spread. 1M context, free V4 cache. A 1,000-job/day table cuts $4,205/mo to $1,453 (-65.5%). Python + Node.
GLM-5.2 vs GPT-5.5 Cost: Per-Token Math at 10K/100K/1M Req/Day (2026)
GLM-5.2 ($1.4/$4.4 per M) vs GPT-5.5 ($5/$30): blended $2.40 vs $13.33 per M, 5.56x ratio. Daily bills at 10K/100K/1M req/day, 50% cache impact, A/B both via ofox in one string swap.
Self-Host GLM 5.2 (2026): 8×H200 vLLM Cost vs $30/mo Cloud
Self-host GLM 5.2 (753B MIT weights): 8×H200 vLLM FP8, 4×H100 Q4, or Mac Studio 2-bit. Hardware sizing + cloud GPU $/hr breakeven vs Z.ai's $30/mo plan.
Codex Weekly Limit Drained: 5 Fixes and a Drop-In API That Caps Spend (2026)
Codex weekly limit 96%→0% in a day (May 17 2026)? 5 fixes—banked resets (June 12 update), referral credits, drop-in API, prepaid cap, tier downgrade. 1 line: wire_api='responses'.
Codex Weekly Limit Drained? 7 Fixes + a $1.49/M Drop-in API (2026)
Codex weekly limit drained on $20 Plus or $100 Pro? 7 working fixes: credit-reset banking, /status debug, and a $1.49/M drop-in API so you keep coding now.
DeepSeek V3.2 Prompt Caching on ofox: 10-Min Setup, 80% Savings (2026)
DeepSeek V3.2 caching: $0.06/M cache read vs $0.29/M miss (4.8× cheaper), $0.43/M output, 128K context. Set up on ofox in 10 minutes. Cut team bills 80% with prefix-stable requests.
How to Access GLM 5.2 (2026): Step-by-Step API Setup & Pricing
GLM 5.2 access, step by step: Z.ai API setup, $10–$80/mo Coding Plan pricing, the 6 common errors to avoid, plus MIT open-weights and ofox alternatives you can use today.
MiniMax M3 vs GPT-5.5: SWE-Bench Pro, 8× Price Gap, A/B Both via ofox (2026)
MiniMax M3 (SWE-Bench Pro 59.0%) vs GPT-5.5 (58.6%): same 1M context, $0.60 vs $5 input, $2.40 vs $30 output. ~11× cheaper per benchmark point, A/B both via ofox in 10 lines of code.