LABEL CHECK / DOSSIERS
5 dossiers — we audit claims, we don't review tools.
Each dossier scores a tool's material self-claims for fidelity: claimed → observed → status → evidence. Deltas close only when Theory Delta re-verifies the stated falsification criterion — vendor issue-closure alone never closes a row.
toolverdictclaimsas labeledopen deltasverified
Hermes AgentA fast-moving, well-connected personal agent chassis whose headline self-improvement claim is not functional in any released version.145/1462026-07-09Claude CodeClaude Code's capability claims largely hold as labeled, but its enforcement-language claims — deny rules, hook exit-code blocking, managed-policy precedence, shell-operator awareness, and per-provider model-alias resolution — are each contradicted by confirmed silent failures, several of which the vendor closed as stale rather than fixed.144/14112026-06-28LangGraphLangGraph's orchestration, streaming, and adoption claims hold as labeled, but its durable-execution and persistence label rests on a checkpoint layer whose documented enum and failure handling silently corrupts state — four serialization bugs, a double-interrupt snapshot bug, and a sync/async recovery divergence all re-verified open on 2026-06-28 against the 1.2.6 release line, the entire v1.0.10→1.2.4 span since Theory Delta first published them on 2026-03-29.123/12142026-06-28LiteLLMThe unified-API and provider-breadth claims hold as labeled, but the production-control claims — budgets, rate limits, fallback, and the README's 8ms-P95-at-1k-RPS figure — are contradicted by issue-traced behavior under exactly the concurrent multi-tenant conditions the proxy is marketed for, with the key fixes unmerged and the backing issues stale-bot closed unfixed.133/13112026-06-28OllamaOllama's simplicity, model-library, platform, and context-default documentation claims hold as labeled, but its tool-calling label is contradicted where it matters for agents — documented streaming tool support drops tool_calls chunks silently in production, and the get-running-in-minutes agent framing inherits a default context below the vendor's own agentic guidance on common hardware.116/1162026-06-28Statuses use the fixed vocabulary: as labeled,partial, not as labeled,not implemented. Dossiers are living pages — the last-verified date is each dossier's staleness signal.