Connects the inbound SenderID, which was already carried end-to-end via
InboundContext to PromptBuildRequest, into the per-turn user message so
historical messages remember who said what.
- userPromptMessage gains a senderID parameter. Real human IDs are
sanitized via SanitizeMessageName; synthetic triggers (cron,
heartbeat, async:*) are filtered out via IsSystemSenderID so they
do not surface as distinct users.
- pipeline_setup.go now passes ts.opts.Dispatch.SenderID() and uses
AddFullMessage unconditionally. The previous AddMessage(role,
content) shortcut for media-less turns silently dropped the new
Name field, breaking history disambiguation.
- context.go (BuildMessagesFromPrompt) propagates req.SenderID onto
the current-turn user message that goes to the LLM.
After this commit, sessions persist sender attribution and provider
adapters receive it on each user message. Adapters that consume Name
(OpenAI native field, Anthropic-style content prefix) land in
follow-up commits.
The existing "## Current Sender" block in buildDynamicContext is
unchanged; it continues to describe the latest speaker in the system
prompt while Name covers the per-message channel for history.
Refs #2702.
- centralize web search provider readiness and resolution logic
- fall back when the configured provider is unavailable or invalid
- allow native-search-capable models to use built-in search without the client tool
- simplify the tools page and add direct access to web search settings
- add backend, agent, and integration tests for the new selection behavior
* refactor: support explicit model list providers
* fix(web): preserve explicit model providers
* fix(web): preserve legacy provider prefixes on model updates
fix(models): normalize explicit provider-prefixed ids
fix(api): preserve legacy model updates across providers
fix(agent): preserve config identity for explicit provider refs
* fix ci
* feat(web): download attachments in frontend
* fix: proxy pico media and force svg downloads
* feat(web): hide ephemeral media refs from persisted session history
Add a context window usage indicator to the web chat UI and a /context
slash command that works across all channels.
Backend:
- Add computeContextUsage() estimating history + system + tool tokens
- Attach ContextUsage to outbound messages via the pico WebSocket protocol
- Add /context command showing context stats as formatted text
- Add EstimateSystemTokens() on ContextBuilder for system prompt estimation
Frontend:
- Add ContextUsageRing component (SVG ring + hover/tap popover)
- Show usage percentage, token counts, and compression threshold
- Hover on desktop (150ms leave delay), tap on mobile
- "View Details" sends /context with 1s cooldown
- i18n support (en/zh) for popover labels
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Scope tool result deduplication to each assistant tool-call block so providers
that reuse call IDs across separate turns do not lose valid tool results. Also
drop invalid empty tool call IDs and orphaned tool messages after validation.
- Add Clear(ctx, sessionKey) to ContextManager interface
- Implement Clear for legacy (JSONL) and seahorse (DB + JSONL)
- Add Engine.ClearSession + Store.ClearConversation
- Fix FTS5 DELETE trigger syntax in schema (was using wrong
external-content FTS5 syntax; now uses standard DELETE FROM)
- Fix ClearSession to skip sessions never ingested (was creating
blank conversations record via GetOrCreateConversation)
- Simplify summary_parents DELETE into single OR statement
- Add TestStoreClearConversation unit test
