Cloud routine outcomes config creates a feature branch, so the agent commits and pushes there instead of main. Fix: remove outcomes + add explicit git checkout main in skills. Also hit a list API pagination bug (cursor never advances) along the way.
Entering '我想找入門的ai課程' in Ask AI showed zero searched posts and triggered a refusal, while Related Reading recommended exactly the right article. The first fix addressed Chinese tokenization, the LIKE fallback, and the Vectorize data path. A second pass added short Han-and-number tokens, post metadata retrieval, and a rule that exposes sources only after both Validation and Critic pass.
Querying “認證” returned only ~10 hits while 149 files (509 occurrences) matched; 41 posts and 76 chunks were found via LIKE, but D1 chunks_fts had 0 rows and unicode61/trigram both returned 0 for 2-char CJK terms. Fix: LIKE fallback with char-level OR first, then trigram migration + pnpm sync, then pagination beyond the hard limit of 12.
When mobile Chrome keeps redirecting back to the login page after sign-in, the culprit isn't always OAuth or broken frontend state. In this case, the root cause was that the HTTP entry point for app-dev.daodao.so wasn't issuing a 301 redirect to HTTPS, so /auth/me requests sent with an http origin didn't include the auth_token cookie.
Rewriting tool descriptions from soft suggestions to hard rules (whitelist + consequence explanation) eliminated the LLM's incorrect tool selection; adding skip_signal=True fixed vector store double-indexing.
The main backend runs on a remote HTTPS server, so the auth_token cookie is scoped to that domain. The browser never sends it to the local AI backend, causing the API to treat every request as unauthenticated.
The original Claude Code troubleshooting collection has been split into orders 33-35: installation & login, runtime problems, and config diagnosis. This page is their index.
Global skills live in ~/.claude/skills/, but they go missing in new sessions or the Desktop App? The problem usually isn't a missing file — it's that the skill descriptions aren't being loaded into context. This post clarifies the CLI vs Desktop App differences, the role of settings.json, and the most reliable fix.
The MCP tool was returning a description field that caused 1,033 job listings to exceed the token limit. The fix: exclude description by default and add pagination.
Even when a route has prerender = true, Cloudflare Workers' Rollup bundler still attempts to bundle native modules, causing the build to fail. The fix is to move any native module work into a postbuild script.
Astro scoped CSS appends a scope hash to each selector, but elements rendered by <Content /> don't receive that hash — causing all prose styles to silently break.
In wrangler.jsonc, use custom_domain: true in routes with only the hostname as the pattern — no /* wildcard