feat: return readable Claude reasoning, and render absent reasoning honestly

[saucam]

The reasoning expander always read "reasoning (1 lines)" and expanded onto nothing. Two independent causes — one API, one UI.

1. Claude was never asked for readable reasoning

thinking.display defaults to "omitted" on Opus 5 / 4.8 / 4.7, Sonnet 5, and Fable 5 — which streams thinking blocks whose text is empty. codeoid then committed them as a placeholder.

Measured on live data:

• 3,445 of 3,450 thinking records in one session were the placeholder
• 635 of 635 raw SDK thinking blocks across six transcripts had empty thinking text

ClaudeProvider now passes display: "summarized".

This is free. display controls visibility only — thinking happens and is billed identically either way. The tokens were already being spent; we just weren't being shown anything for them. (The raw chain of thought is never exposed on any model; this is a summary of it.)

2. The UI promised content it could not have

A <details> expander over the placeholder advertised reasoning, counted it as 1 lines, and opened onto the placeholder — which reads as a counting bug rather than absent data.

state	before	after
Reasoning present	expander, (N lines)	expander, (N lines) / (1 line)
No reasoning	expander → placeholder	flat marker, no expander, no count

Both branches are live, and neither is an error state — which is why this is a render-time decision rather than something to "fix" in a backend. qwen-code and OSS models behind an OpenAI-compatible gateway stream plaintext reasoning today (qwen-ledger has real thinking content in its transcript), while Claude only does under the setting above. The same UI now serves both.

Pluralisation is fixed as a side effect — (1 line), not (1 lines).

Shared constant

The placeholder moves to REASONING_UNAVAILABLE in the protocol package. The daemon writes it and the client keys off it, so the two sides can't drift over a prose string — the same class of bug as the memory-server name in #307.

Its wording also changes from "(reasoning elided)": codeoid elides nothing, the backend returned none. The old phrasing pointed the finger in the wrong direction while debugging this.

Note: packages/protocol is a bun file: copy in web/, so editing it requires bun install in web/ to refresh. CI installs fresh every run.

Verification

Daemon: lint + typecheck clean, 2382 pass / 0 fail.
Web: typecheck + build clean, 425 pass / 0 fail (41 files) — 3 new tests covering the absent-reasoning marker, the present-reasoning expander, and whitespace-only treated as absent; 3 existing assertions updated for the pluralisation fix.

🤖 Generated with Claude Code