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.
Rate Limit Reached in Claude Code: 429 Causes and 6 Fixes (2026)
Claude Code 429 rate limit? Start tier gives Opus 5 and Sonnet 5 2M ITPM / 1,000 RPM. Read retry-after, add jitter, cut ITPM with caching. 6 fixes.
Claude Code Usage Limit Hit Too Fast: Why + 7 Fixes (2026)
Claude Code usage limit gone by lunch? Opus burns several times Sonnet, subagents 7x tokens, MCP eats 33% of context. See it with /usage, 7 fixes.
Claude Tag in Slack (2026): 4-Step Setup, Ambient Mode, Aug 3 Deadline
Claude Tag is a shared @Claude teammate in Slack running on Opus 4.8. Setup in four steps, ambient mode, admin scopes, and the Aug 3, 2026 cutover.
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.
GLM-5.2 vs GPT-5.5 Cost: Per-Token Math at 10K/100K/1M Req/Day (2026)
GLM-5.2 at $1.4/$4.4 per M against GPT-5.5 at $5/$30 — a 5.56x blended ratio. Daily bills at three request volumes, and how to A/B both via ofox.
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 Banked Rate-Limit Reset: How the Weekly Reset Works (2026)
What a Codex banked rate-limit reset is, who gets one, and how to spend it when the weekly cap hits 0%. Plus four other ways out, including a metered API.
When Does Codex Reset? Check Your Weekly Limit Reset Time
Codex reset times come from the server as a resetsAt timestamp, not a clock rule. Read yours directly, redeem a reset credit, or move to a metered API.