Extend the panel engine with a layer loop: Fusion is one proposer round,
MoA runs N rounds where each round after the first sees the previous
round's responses via <previous_layer_responses> and refines its answer.
Only the final round is persisted; intermediate rounds are live-only.
Rounds are clamped to 1-5.
- SessionRecord + migration: moa_layers column (default 2)
- RunPanel: layer loop with per-member cloned message injection
- CloneForMember / BuildPreviousLayerBlock helpers for member isolation
- SSE: panel_layer_start / panel_layer_done events
- Frontend: layer_index composite keying, round dividers, MoA option
- Docs: ARCHITECTURE + ARCHITECTURE_QUICK updated
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Panel agents answer the user prompt in parallel (read-only, non-streaming);
their responses are merged into the worker's last user message as a
<panel_responses> block, and the session agent synthesizes one final
streamed answer. The RunPanel engine is built layer-ready for future MoA.
- New session fields: multi_model_mode (off/fusion), panel_agent_ids (CSV)
with idempotent column migration
- New partial Services/AnthropicService.Panel.cs holding the RunPanel engine
- Provider-agnostic members: Anthropic RunNonStreamingToolLoop / OpenAI
CompleteText / CLI plan-mode; all forced read-only, persisted with Tag=panel
- SSE events: panel_start, panel_member_start, panel_member_done, panel_done
- Frontend: multi-agent picker, live panel bubbles, history rendering
- Graceful degradation: panel errors fall back to worker-only
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Opus 4.5+ and Sonnet 4.6+ support a new "effort" knob that controls how
much budget the model spends on thinking and tool calls. Plumb it through
end to end so each agent can pick its own level.
Storage & shape:
- New TEXT column agents.effort (default '') added via TryAddColumn.
- AgentRecord.Effort + INSERT/UPDATE in DatabaseService.Agents.cs.
- ChatContext.Effort + SubAgentContext.Effort so the value travels with the
request alongside model and tool settings.
Agent editor:
- Effort dropdown above git-commit behavior in the agent form (low/medium/
high/xhigh/max plus empty = "use default"). Always visible; on OpenAI
providers the value is sent but silently ignored.
- agent-page.js load/save and AgentEndpoint create/update wired up.
Anthropic API path:
- StreamChat and RunNonStreamingToolLoop add output_config: { effort } when
effort is set and not "high" – empty/null/"high" means "omit and let the
API pick its default".
- Sub-agents (preparer/review/finalizer) get the parameter through
RunAgentChat so each step uses its own agent's effort.
Anthropic CLI path:
- ClaudeCliService.ChatStreamingAsync takes an effort parameter and exports
CLAUDE_CODE_EFFORT_LEVEL on the spawned process. Env-var beats the
--effort flag because it also covers "max" and "ultracode".
- StreamChatViaCli, ChatNonStreamingViaCli, RunSubAgentViaCli, and the
ChatEndpoint anthropic branches all hand the value through.
ARCHITECTURE.md / ARCHITECTURE_QUICK.md updated with the new field.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Neuer ServerSettingsService: zentrale Settings in SQLite mit In-Memory-Cache
- Auto-Migration: bestehende appsettings.Production.json wird einmalig in DB übernommen
- Alle Services umgestellt: IConfiguration → ServerSettingsService (dynamisch, kein Neustart)
- Port bleibt als einziges Setting in appsettings.Production.json (erfordert Neustart)
- ServerSettingsEndpoint: liest/schreibt DB statt JSON-Datei, Port als Sonder-Setting
- IConfiguration komplett entfernt aus allen Services (ChatService, ToolService, AnthropicService,
OpenAiService, KreaService, TelegramService, KeyScannerService, GitHubEventScannerService)
- AuthMiddleware: KreaApiKey dynamisch aus DB
- appsettings.json bereinigt: nur noch Port und Logging
- Dokumentation aktualisiert (ARCHITECTURE.md, ARCHITECTURE_QUICK.md, README.md)
Plattformspezifische bin/obj/publish-Ordner unter Build/Linux/
und Build/Windows/ statt bin-linux/, obj-linux/, publish/ etc.
- Directory.Build.props: OS-Erkennung setzt BaseOutputPath,
BaseIntermediateOutputPath und MSBuildProjectExtensionsPath
auf Build/{Linux|Windows|macOS}/
- gott.csproj: Vereinfacht auf ein einziges Build/** Exclude
- deploy.sh: publish-Output nach Build/Linux/publish
- OpenClawEndpoint.cs: DB-Pfad relativ zu AppContext.BaseDirectory
- Doku (README, ARCHITECTURE, ARCHITECTURE_QUICK) aktualisiert
BuildReviewMessages() komplett umgebaut:
- Tool-Calls und Tool-Results werden nicht mehr übergeben
- Nur noch die reine Text-Konversation (user/assistant) wird extrahiert
- Aufeinanderfolgende Messages gleicher Rolle werden zusammengeführt
- Korrekte user/assistant-Abwechslung sichergestellt
- Fallback wenn nur Tool-Calls ohne Text vorhanden
- Unnötigen Serialisierungs-Roundtrip für Rollen-Prüfung entfernt
Erwartete Token-Ersparnis: 50-100k+ Input-Tokens pro Review-Runde
bei typischen Worker-Sessions mit vielen write_file/edit_file-Calls.
ARCHITECTURE.md:
- Inhaltsverzeichnis-Nummerierung korrigiert (22-28 statt doppelt 20-21)
- ServerSettingsEndpoint.cs in Projektstruktur ergänzt
- Tabellenbeschreibungen vervollständigt (users, agents, sessions, chains,
messages, cronjobs) mit allen fehlenden Feldern
- ChainRecord/MessageRecord/SessionWithStats Felder aktualisiert
- AutoCommit mention-Beschreibung korrigiert
ARCHITECTURE_QUICK.md:
- ToolService 12 → 13 Tools korrigiert
- Tabellenbeschreibungen analog zur Hauptdoku aktualisiert
- AuthMiddleware: X-Api-Key Header-Prüfung für /api/images/* Routen
- Neues Config-Feld KreaApiKey in appsettings.json
- Bei gültigem API-Key wird Request ohne Cookie-Auth durchgelassen
- Normaler User-Auth funktioniert weiterhin als Fallback
- ARCHITECTURE.md + ARCHITECTURE_QUICK.md aktualisiert
- ARCHITECTURE.md: comprehensive project documentation (868 lines)
covering all 21 chapters (data model, services, endpoints,
chat pipeline, tool system, agents, memory, skills, telegram,
cronjobs, krea, auth, workspace, deployment, config)
- ARCHITECTURE_QUICK.md: compact quick-reference (223 lines)
for fast lookups during development
- chat.css: add .msg.user.markdown pre selector so code blocks
in user messages get correct background color (was only on code)
