3 Commits

Author	SHA1	Message	Date
m4	194402fc88	fix(usage): stop sharing EVOSCIENTIST_DEPLOYMENT_ID with scope partitioning ... The usage identity exported the same variable the scope registry reads to partition workspace scopes, so a backend started with the usage environment (61d1b61b) could not see scopes provisioned under the workspace-derived id (5a882492) and every scope lookup 404'd. Usage attribution now reads EVOSCIENTIST_USAGE_DEPLOYMENT_ID; the scope side keeps the original variable. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>	2026-07-30 22:08:21 +08:00
m4	57176b359a	feat(runtime)!: switch middleware and agent factories to snapshot-driven models ... Replace config.yaml-driven model selection with registry snapshot resolution across the runtime chain: - ConfigurableModelMiddleware reads configurable["runtime_snapshot_id"] only; model/model_provider overrides are rejected with MODEL_CONFIG_OUTSIDE_SNAPSHOT - MessageBudgetMiddleware derives budgets from snapshot reserves (system/tools/attachments) and re-resolves the summarizer per snapshot - Agent factory and subagent factory resolve models via SnapshotRuntime (auxiliary/tool_selector/scheduler -> defaults.auxiliary ?? defaults.primary) - Remove ModelFallbackMiddleware, /model-fallback command, and fallback chain - Add model_registry/runtime.py SnapshotRuntime glue layer Legacy config.yaml LLM fields, /model command, and llm/models.py remain for Task 7. Report: .superpowers/sdd/briefs/task-6-report.md	2026-07-21 12:54:35 +08:00
m4	38668c4ce5	feat: add workspace isolation and provider administration	2026-07-19 12:17:18 +08:00