Search
@knyazevai/dsh-llm
knyazevai
Provider-neutral LLM service interface for the DeepSeek Harness
@knyazevai/dsh-storage
knyazevai
Storage hub (ctx.storage): named backend registry plus mounted data-form facilities for the DeepSeek Harness
@knyazevai/dsh-storage-domain
knyazevai
Domain data form (ctx.storage.domain): schema-validated, event-emitting KV domains over storage backends for the DeepSeek Harness
...more@knyazevai/dsh-llm-retry
knyazevai
Provider-routed LLM request retry policy for the DeepSeek Harness
@knyazevai/dsh-llm-pi-ai
knyazevai
pi-ai-backed DeepSeek adapter for the DeepSeek Harness LLM seam (design-verification twin of dsh-llm-deepseek)
@knyazevai/dsh-session-title-llm
knyazevai
Shared LLM generation policy for DeepSeek Harness session-title providers
@knyazevai/dsh-session-title-first-prompt-llm
knyazevai
First-message LLM provider plugin for DeepSeek Harness session titles
@knyazevai/dsh-storage-json
knyazevai
JSON file KV storage backend for the DeepSeek Harness storage hub
@knyazevai/dsh-llm-deepseek
knyazevai
DeepSeek chat-completions adapter for the DeepSeek Harness LLM seam
@knyazevai/dsh-fork-llm-rate-limit-cooldown
knyazevai
Fork-owned LLM plugin that waits a long cooldown and retries a rate-limited request whose bounded retry budget is exhausted
...more@knyazevai/dsh-fork-llm-first-chunk-timeout
knyazevai
Fork-owned LLM stream plugin that bounds idle time before the first chunk
@knyazevai/dsh-session-title-all-prompts-llm
knyazevai
All-user-messages LLM provider plugin for DeepSeek Harness session titles
@knyazevai/dsh-llm-mock-server
knyazevai
Scriptable OpenAI-compatible HTTP/SSE fault server for LLM recovery tests
@knyazevai/dsh-llm-replay
knyazevai
Replay LLM plugin: short-circuits llm/stream with model chunks reconstructed from a recorded session JSONL (keyless snapshot tests)
...more@knyazevai/dsh-storage-sqlite
knyazevai
SQLite storage backend (kv facet) for the DeepSeek Harness storage hub
boruna
escapeboy
Boruna: a deterministic, capability-safe programming language and framework for LLM-native applications