claude code agent 227 d88fe4cde7 feat(ai-chat): context badge shows current/max (#189) ...

The header badge in the floating AI-chat window flipped meaning between
states (a live per-turn token counter while streaming vs. the context
size at rest), which made it "reset to 1" on each prompt and confused
users. Make it consistently show the current context size, with the
model's context window as an optional "/ max" denominator.

The max comes from a new admin-set AI setting (chatContextWindow, in
tokens) — provider-independent and always exact. The server stamps it
onto the assistant message metadata (maxContextTokens) next to
contextTokens, so the client reads both from the last row with no
client-side model resolution (survives shares / future per-role models).

- server: chatContextWindow in AiProviderSettings/keys/masked/resolved,
  DTO (@IsInt @Min(0)), settings-service resolve/getMasked, repo parity
  allowlist; flushAssistant writes metadata.maxContextTokens when > 0.
- client: ContextBadge component (extracted, shows "current [/ max]",
  no live mode); removed the liveTurnTokens header path + dead util fn;
  Context-window NumberInput in AI settings; i18n strings.
- live "Thinking · N tokens" feedback in the chat body is unchanged.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-26 06:27:45 +03:00

75 KiB

Raw Blame History

View Raw