{"schema":"seenrelay-public-updates-v1","generated_from":"canonical_public_product_facts_and_verified_public_evidence","canonical_url":"https://seenrelay.com/updates","json_url":"https://seenrelay.com/updates.json","atom_url":"https://seenrelay.com/updates.atom","count":29,"updates":[{"id":"company-fleet-operating-receipt-2026-10-02","date":"2026-10-02","title":"8-agent verified savings record: shared evidence, independent reasoning","summary":"Eight department agents preserved eight independent role analyses while paid web-search actions fell from 13 to 4 and measured provider cost fell from $0.16499684 to $0.05560972 in the completed paired first-party run.","kind":"operating_proof","url":"https://seenrelay.com/case-studies/company-fleet","machine_url":"https://seenrelay.com/case-studies/company-fleet.json","claim_boundary":"First-party operating evidence with one explicitly synthetic external-client rehearsal tenant; not customer ROI or net customer savings. The savings record is measurement evidence, not an invoice or payment receipt; SeenRelay billing is OFF."},{"id":"safe-to-try-agent-adoption-2026-10-02","date":"2026-10-02","title":"Safe-to-try trust posture and machine-first agent adoption","summary":"SeenRelay now publishes a machine-readable adoption contract for autonomous agents plus explicit safe-to-try controls: local scan, shadow-first measurement, fail-open fallback, shared CHECK off by default in Zero-State, zero default completed-result TTL, no implicit mutation suppression, and an easy remove path.","kind":"trust_and_agent_adoption","url":"https://seenrelay.com/agents","machine_url":"https://seenrelay.com/agent-adoption.json","claim_boundary":"Verifiable technical controls; not a third-party security certification or vulnerability-free claim."},{"id":"verified-update-2026-10-02-0-public-client-0-2-25","date":"2026-10-02","title":"Public client 0.2.25","summary":"SeenRelay 0.2.25 is published through trusted publishing on npm and PyPI. JavaScript / TypeScript adds `seenrelay guide`, which combines the local static prescreen and non-mutating adoption plan into one machine-readable next-action surface for agents/operators. It uploads no source, contacts no SeenRelay service, modifies no project, enables no reuse and cannot return a USE verdict. Python remains behaviorally unchanged.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-10-02-0"},{"id":"verified-update-2026-09-30-1-public-client-0-2-24","date":"2026-09-30","title":"Public client 0.2.24","summary":"SeenRelay 0.2.24 is published through trusted publishing on npm and PyPI. JavaScript / TypeScript static prescreen recognizes MCP 2026-07-28 cacheable-result ttlMs/cacheScope freshness only alongside compatible cacheable MCP operations; generic callTool code with the same words remains a shadow-measurement candidate. Python remains behaviorally unchanged.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-09-30-1"},{"id":"verified-update-2026-09-29-2-public-client-0-2-23","date":"2026-09-29","title":"Public client 0.2.23","summary":"SeenRelay 0.2.23 is published through trusted publishing on npm and PyPI. JavaScript / TypeScript adds a local Langfuse TOOL-observation candidate census that hashes exact tool inputs locally, measures exact recurrence and in-flight overlap, and reports Langfuse-recorded TOOL cost when present. The output remains NEEDS_POLICY_REVIEW and cannot authorize reuse or claim actual avoided executions/net savings. Python remains behaviorally unchanged.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-09-29-2"},{"id":"verified-update-2026-09-29-3-public-client-0-2-22","date":"2026-09-29","title":"Public client 0.2.22","summary":"SeenRelay 0.2.22 is published through trusted publishing on npm and PyPI. JavaScript / TypeScript packages the local OpenTelemetry/OTLP trace census for agent-agnostic overlap discovery below individual agent frameworks; admission requires an opaque exact coordinate and explicit SeenRelay policy, and the adapter does not copy generic raw prompts, URLs or tool payloads into the census. Python remains behaviorally unchanged.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-09-29-3"},{"id":"verified-update-2026-09-29-4-public-client-0-2-20","date":"2026-09-29","title":"Public client 0.2.20","summary":"SeenRelay 0.2.20 is published through trusted publishing on npm and PyPI. JavaScript / TypeScript adds a generic `wrapFleetShadowCall()` helper and fail-open coordinate canonicalization for fleet shadow measurement and active coordination: non-JSON or cyclic coordinates never suppress the authoritative call and remain unclassified instead. Python remains behaviorally unchanged.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-09-29-4"},{"id":"verified-update-2026-09-29-5-public-client-0-2-19","date":"2026-09-29","title":"Public client 0.2.19","summary":"SeenRelay 0.2.19 is published through trusted publishing on npm and PyPI. JavaScript / TypeScript adds distributed shadow measurement for exact eligible in-flight overlap across workers while every authoritative operation still runs; no result is shared, and observed overlap cost is kept distinct from actual avoided-execution receipts. Python remains behaviorally unchanged.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-09-29-5"},{"id":"verified-update-2026-09-28-6-public-client-0-2-18","date":"2026-09-28","title":"Public client 0.2.18","summary":"SeenRelay 0.2.18 is published through trusted publishing on npm and PyPI. JavaScript / TypeScript adds conservative local savings receipts and an aggregation ledger to fleet-level exact in-flight coordination: only actual follower reuse counts as avoided execution, dollar values require explicit cost provenance, and receipt failures cannot change the application result. Python remains behaviorally unchanged.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-09-28-6"},{"id":"verified-update-2026-09-24-7-public-client-0-2-16","date":"2026-09-24","title":"Public client 0.2.16","summary":"SeenRelay 0.2.16 is published through trusted publishing on npm and PyPI. The local static prescreen now treats Firecrawl provider cache/freshness semantics as a stronger native control that must be measured before shared SeenRelay. No CHECK/OBSERVE protocol, billing, reuse-policy or hosted-runtime semantics changed.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-09-24-7"},{"id":"verified-update-2026-09-23-8-public-client-0-2-15","date":"2026-09-23","title":"Public client 0.2.15","summary":"SeenRelay 0.2.15 is published through trusted publishing on npm and PyPI. The npm package adds `seenrelay scan`, a local-only static prescreen for recurring metered/read-only validation candidates and stronger native/local controls. Static analysis is deliberately pre-evidentiary: it cannot emit USE, authorize reuse, upload source code or modify the scanned project. JavaScript/TypeScript and Python runtime semantics are otherwise unchanged.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-09-23-8"},{"id":"verified-update-2026-09-11-9-public-client-0-2-14","date":"2026-09-11","title":"Public client 0.2.14","summary":"SeenRelay 0.2.14 is published through trusted publishing on npm and PyPI. JavaScript/TypeScript and Python expose matching deterministic single-workload audit verdict helpers: USE only for complete natural evidence that safely beats the best measured non-shared path on both cost and latency; DO NOT USE for unsafe comparisons or complete non-winning evidence; otherwise INSUFFICIENT EVIDENCE. The evaluator never enables reuse.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-09-11-9"},{"id":"verified-update-2026-09-08-10-public-client-0-2-13","date":"2026-09-08","title":"Public client 0.2.13","summary":"SeenRelay 0.2.13 is published through trusted publishing and independently verified from npm and PyPI. The public npm package has a valid declared export map, includes its package-local prepack validator, imports every declared export from a clean install, and successfully repacks from the installed registry artifact; runtime semantics are otherwise unchanged.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-09-08-10"},{"id":"verified-update-2026-09-06-11-public-client-0-2-11","date":"2026-09-06","title":"Public client 0.2.11","summary":"SeenRelay 0.2.11 is published and independently clean-install verified on npm and PyPI. Python adds bounded sanitized natural-workload evidence parity and hostile economics evaluation; authoritative validation always runs during measurement, ambiguous per-call timing attribution fails closed, and the evaluator never enables reuse.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-09-06-11"},{"id":"verified-update-2026-09-06-12-public-client-0-2-10","date":"2026-09-06","title":"Public client 0.2.10","summary":"SeenRelay 0.2.10 is published and independently clean-install verified on npm and PyPI. Python adds provider-independent Zero-State with caller-owned private L1, source-native conditional validation and authoritative fallback; the base package remains dependency-free and AES-256-GCM support is optional. JavaScript/TypeScript and Python both fail closed on negative-age private entries caused by worker clock skew.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-09-06-12"},{"id":"verified-update-2026-09-01-13-public-client-0-2-9","date":"2026-09-01","title":"Public client 0.2.9","summary":"SeenRelay 0.2.9 is published and independently clean-install verified on npm and PyPI. JavaScript/TypeScript and Python add multi-signal shared-evidence assurance helpers and deterministic Fact Coordinate Kit v1. Shared evidence remains explicit caller policy and does not establish truth or independent real-world actors.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-09-01-13"},{"id":"verified-update-2026-08-31-14-public-client-0-2-7","date":"2026-08-31","title":"Public client 0.2.7","summary":"SeenRelay 0.2.7 is published and independently clean-install verified on npm and PyPI. JavaScript/TypeScript adds Ambient framework routing for LangChain plus a local integration catalog; Python adds Ambient integrations for LangChain and PydanticAI plus a local integration catalog. Ambient measurement remains local-only by default and automatic reuse is not authorized.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-08-31-14"},{"id":"verified-update-2026-08-31-15-public-client-0-2-6","date":"2026-08-31","title":"Public client 0.2.6","summary":"SeenRelay 0.2.6 is published and clean-install verified on npm and PyPI. JavaScript/TypeScript adds Ambient MCP integration that starts local-shadow by default and can opt exact reviewed tools into the existing local-first guard; Python adds local-only Ambient MCP measurement and an OpenAI Agents adapter while active Ambient reuse remains disabled.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-08-31-15"},{"id":"verified-update-2026-08-30-16-benchmark-fit-tightened","date":"2026-08-30","title":"Benchmark fit tightened","summary":"Historical example.com Firecrawl smoke measurements remain unchanged as provider-path mechanics evidence. Their workload fit is now poor because the tested facts were directly source-resolvable; better local, source-native or provider-native controls remain ahead of shared CHECK.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-08-30-16"},{"id":"verified-update-2026-08-30-17-public-client-0-2-5","date":"2026-08-30","title":"Public client 0.2.5","summary":"SeenRelay 0.2.5 is published on npm and PyPI. JavaScript/TypeScript adds a measurement-only direct Firecrawl SDK shadow adapter supporting current scrape() and legacy scrapeUrl(); the provider call remains authoritative, original arguments and raw result are preserved, provider-cache hits are not relabeled as independent observations, and automatic reuse remains disabled. Python remains shadow-first.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-08-30-17"},{"id":"verified-update-2026-08-30-18-public-client-0-2-4","date":"2026-08-30","title":"Public client 0.2.4","summary":"SeenRelay 0.2.4 is published on npm and PyPI. JavaScript/TypeScript adds a measurement-only Firecrawl shadow pilot and a packaged hostile benchmark evaluator; Firecrawl remains authoritative during measurement, provider-cache hits are not relabeled as independent observations, and the evaluator never enables reuse. Python remains shadow-first.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-08-30-18"},{"id":"verified-update-2026-08-29-19-public-client-0-2-3","date":"2026-08-29","title":"Public client 0.2.3","summary":"SeenRelay 0.2.3 is published on npm and PyPI. JavaScript/TypeScript Shadow Proof can export bounded, sanitized natural-workload records directly into the hostile benchmark format while authoritative validation continues; unavailable CHECKs remain in the sample and unsafe or uncomparable hypothetical reuse cannot be reported as safe. Python remains shadow-first.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-08-29-19"},{"id":"verified-update-2026-08-29-20-public-client-0-2-2","date":"2026-08-29","title":"Public client 0.2.2","summary":"SeenRelay 0.2.2 is published on npm and PyPI. JavaScript/TypeScript Shadow Proof adds local agreement counters for hypothetical SAME_OBSERVED reuse while authoritative validation still runs; compared raw values are not retained in snapshots or reports. Python remains shadow-first.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-08-29-20"},{"id":"verified-update-2026-08-29-21-public-client-0-2-1","date":"2026-08-29","title":"Public client 0.2.1","summary":"SeenRelay 0.2.1 is published on npm and PyPI. It is behavior-equivalent to 0.2.0 and refreshes package discovery metadata and documentation; JavaScript/TypeScript remains provider-independent and local-first, while Python remains shadow-first.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-08-29-21"},{"id":"verified-update-2026-08-28-22-public-client-0-2-0","date":"2026-08-28","title":"Public client 0.2.0","summary":"SeenRelay 0.2.0 is published on npm and PyPI. JavaScript/TypeScript adds provider-independent Zero-State local-first optimization; Python remains shadow-first in this release.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-08-28-22"},{"id":"verified-update-2026-08-28-23-local-first-javascript-typescript-path","date":"2026-08-28","title":"Local-first JavaScript/TypeScript path","summary":"Eligible read-only validation can use in-flight L0 reuse, explicit-TTL local reuse, optional encrypted caller-owned L1 storage and source-native conditional validation before any shared CHECK is considered.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-08-28-23"},{"id":"verified-update-2026-08-28-24-shared-evidence-remains-optional","date":"2026-08-28","title":"Shared evidence remains optional","summary":"Zero-State does not put a shared CHECK on the hot path by default. Fresh independent validation can contribute OBSERVE evidence; intermediary provider-cache hits are not re-labeled as a new independent observation.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-08-28-24"},{"id":"verified-update-2026-08-26-25-measured-firecrawl-structured-extraction-savings","date":"2026-08-26","title":"Measured Firecrawl structured-extraction savings","summary":"In a first-party n=3 smoke benchmark, bounded reuse avoided 3/3 Firecrawl JSON extraction calls, 15 provider credits, and reduced median latency from 1.266 s fresh / 1.040 s provider-cached to 0.618 s.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-08-26-25"},{"id":"verified-update-2026-08-26-26-measured-browser-interaction-savings","date":"2026-08-26","title":"Measured browser-interaction savings","summary":"In a first-party n=3 Firecrawl browser-interaction smoke benchmark, bounded reuse avoided 3/3 equivalent provider calls, 9 reported provider credits, and reduced median validation latency from 4.385 s to 0.661 s.","kind":"verified_release_or_evidence","url":"https://seenrelay.com/updates#2026-08-26-26"}]}