Öffentliches Register
Software-GesundheitsberichtSchema 0.27.0 · Metriken 1.13.0 · 2026-07-27 19:49 UTC

sanjay920 / llmshim

A pure-Rust LLM API translation layer — one OpenAI-shaped request, routed and translated to OpenAI, Anthropic, Gemini, and xAI.

RustApache-2.0★ 2 Sterne⑂ 0 Forksseit März 2026Auf GitHub ansehen ↗

sanjay920/llmshim erreicht einen Gesundheitsindex von 57 von 100 und liegt damit im Bereich Mittel. Am stärksten schneidet es bei Vitality (80/100) ab, am schwächsten bei Security (38/100). Zuletzt heute aktualisiert. Ein einzelner Mitwirkender trägt den Großteil der jüngsten Arbeit.

57
gesamt / 100
Mittel

Software-Gesundheitsindex

Metriken werden auf einer Skala von 1–100 in gewichtete Kategorien gruppiert. Der Gesamtwert beginnt als ihr Mittel; sobald öffentliche Evidenz die Richtlinie für Hochrisikojurisdiktionen auslöst, wird die Bewertung angepasst und erhält die Obergrenze 49 (Gefährdet). AI Readiness liegt außerhalb.

57
Exzellent85-100Vorbildlich; erfüllt im Wesentlichen alle geprüften Kriterien
Gut70-84Gesund; geringfügige Lücken
Mittel50-69Akzeptabel mit deutlichen Lücken; Überprüfung empfohlen
Gefährdet30-49Erhebliche Schwächen; eine Übernahme erfordert Vorsicht
Kritisch1-29Schwerwiegende Probleme (aufgegeben, nur ein Maintainer, keine Hygiene)
VitalitätCommunity &VerbreitungNachhaltigkeit &GovernanceEngineering-QualitätSicherheitAI Readiness

Bewertungsprofil

Jede Achse ist eine Kategorie. Die Form zählt mehr als der Durchschnitt — ein gesundes Projekt füllt die gesamte Fläche, während ein Profil aus Spitzen und Kratern bedeutet, dass Stärke in einer Dimension Risiken in einer anderen verdeckt.

Eigentümerschaft

Sanjay NadhavajhalaPersönliches Konto
24 Follower50 öffentliche Reposseit Jan. 2014

Dieses Repository gehört einem persönlichen Konto. Ein Projekt mit nur einem Eigentümer trägt ein höheres Kontinuitätsrisiko als ein organisationsgetragenes.

Paket-Ökosysteme

RegistryPaketVersionDownloads / MonatVersionenZuletzt veröffentlichtTags
crates.iollmshim0.3.112132vor 0 Tagenaianthropicgeminillmopenaiapi-bindingsweb-programming

Metriken nach Kategorie

Vitalität

Lebt das Projekt — wird Code geschrieben und werden Releases ausgeliefert?

80Gut · 22 % des Gesamtindex
Wie die Bewertung erfolgt
36/36Push-Aktualität — letzter Push vor 0 Tagen
9/36Commit-Rhythmus — 13/52 Wochen mit Commits
18/18Commit-Volumen — 185 Commits im letzten Jahr
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 3 issue activity found in the last 90 days -- score normalized to 10
Verwendete Eingangsdaten
commits_last_year185
human_commit_share1
days_since_last_push0
active_weeks_last_year13
Wie die Bewertung erfolgt
27/27Liefert Releases aus — 22 Releases veröffentlicht
36/36Release-Aktualität — letztes Release vor 0 Tagen
27/27Release-Rhythmus — ein Release etwa alle 2,6 Tage
0/10OpenSSF Scorecard: Signed-Releases — Project has not signed or included provenance with any releases.
Verwendete Eingangsdaten
releases_count22
latest_release_tagv0.3.1
releases_from_tagsnein
days_since_latest_release0
mean_days_between_releases2,6

Community & Verbreitung

Hat das Projekt Nutzer, Downloads, Aufmerksamkeit und ein einladendes Umfeld für Beitragende?

41Gefährdet · 18 % des Gesamtindex
Wie die Bewertung erfolgt
0/60Stars — 2 Stars
0/25Forks — 0 Forks
0/15Watcher — 0 Watcher
Verwendete Eingangsdaten
forks0
stars2
watchers0
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history
Wie die Bewertung erfolgt
22.5/22.5README
22.5/22.5Lizenz — anerkannte Lizenz (Apache-2.0)
18/18CONTRIBUTING-Leitfaden
13.5/13.5Verhaltenskodex
0/7.2Issue-Vorlage
6.3/6.3PR-Vorlage
Verwendete Eingangsdaten
has_readmeja
has_licenseja
has_contributingja
has_issue_templatenein
has_code_of_conductja
has_pull_request_templateja
Wie die Bewertung erfolgt
27.8/80Downloads pro Monat — 121 Downloads/Monat über crates
0/20Abhängige in der Registry — von diesem Ökosystem nicht ausgewiesen
Verwendete Eingangsdaten
packagesllmshim
dependents
ecosystemscrates
total_downloads639
monthly_downloads121
Von der Bewertung ausgeschlossen (keine Daten oder nicht anwendbar): Abhängige in der Registry. Die verbleibenden Gewichte wurden renormalisiert.

Nachhaltigkeit & Governance

Überdauert das Projekt die Menschen, die es tragen — Bus-Faktor, Reaktionsfähigkeit, Trägerschaft und Paketpflege?

55Mittel · 24 % des Gesamtindex
Wie die Bewertung erfolgt
9/54Bus-Faktor — 1 Beitragende decken die Hälfte aller Commits ab
0/22.5Commit-Verteilung — wichtigste beitragende Person verfasste 100 % der Commits
1.4/13.5Breite der Beitragenden — 1 Beitragende
0/10OpenSSF Scorecard: Contributors — project has 0 contributing companies or organizations -- score normalized to 0
Verwendete Eingangsdaten
bus_factor1
contributors_sampled1
top_contributor_share1
Wie die Bewertung erfolgt
35.1/46.8Issue-Lösungsquote — 75 % der Issues geschlossen
38.2/38.3PR-Annahme — 41/41 entschiedene PRs gemergt
0/15OpenSSF Scorecard: Code-Review — Found 0/14 approved changesets -- score normalized to 0
Verwendete Eingangsdaten
merged_prs41
open_issues1
closed_issues3
issue_closed_ratio0,75
closed_unmerged_prs0
Wie die Bewertung erfolgt
10/30Organisatorische Trägerschaft — persönliches (Nutzer-)Konto
0/20Verifizierte Domain — für Nutzerkonten nicht anwendbar
10.1/25Reichweite des Inhabers — 24 Follower von sanjay920
24.4/25Kontohistorie — 50 öffentliche Repos, Kontoalter ca. 12 Jahre
Verwendete Eingangsdaten
followers24
owner_typeUser
is_verified
owner_loginsanjay920
public_repos50
account_age_days4.560
Von der Bewertung ausgeschlossen (keine Daten oder nicht anwendbar): Verifizierte Domain. Die verbleibenden Gewichte wurden renormalisiert.

Paketpflege

100Exzellent
Wie die Bewertung erfolgt
25/25Veröffentlicht & auflösbar — 1 Paket(e) auf crates
35/35Veröffentlichungsaktualität — letzte Veröffentlichung vor 0 Tagen
20/20Versionshistorie — 32 veröffentlichte Versionen
20/20Nicht veraltet — aktiv, nicht veraltet oder zurückgezogen
Verwendete Eingangsdaten
packagesllmshim
ecosystemscrates
any_deprecatednein
min_days_since_publish0

Engineering-Qualität

Sind grundlegende Engineering- und Dokumentationspraktiken vorhanden?

65Mittel · 20 % des Gesamtindex
Wie die Bewertung erfolgt
24/24CI-Workflows — 2 Workflow(s)
24/24Tests vorhanden
0/16Linter-Konfiguration
0/9.6Pre-Commit-Hooks
0/6.4.editorconfig
0/20OpenSSF Scorecard: CI-Tests — 0 out of 13 merged PRs checked by a CI test -- score normalized to 0
Verwendete Eingangsdaten
has_cija
has_testsja
has_editorconfignein
has_linter_confignein
has_precommit_confignein

Dokumentation

90Exzellent
Wie die Bewertung erfolgt
30/30README
25/25Dokumentationsverzeichnis
15/15Dokumentations-/Homepage-Site — https://sanjay920.github.io/llmshim/
10/10Repository-Beschreibung
10/10Topics — 8 Topics
0/10Wiki
Verwendete Eingangsdaten
topicsanthropic, api-gateway, gemini, llm, llm-proxy, openai, rust, xai
has_wikinein
homepagehttps://sanjay920.github.io/llmshim/
has_readmeja
has_docs_dirja
has_descriptionja

Sicherheit

Sind die sichtbaren Sicherheits- und Lieferkettenpraktiken belastbar, ohne ungeklärte Exposition gegenüber Hochrisikojurisdiktionen?

38Gefährdet · 16 % des Gesamtindex

Sicherheitslage

38Gefährdet
Wie die Bewertung erfolgt
7.5/7.5Binary-Artifacts — no binaries found in the repo
0/7.5Branch-Protection — branch protection not enabled on development/release branches
0/2.5CI-Tests — 0 out of 13 merged PRs checked by a CI test -- score normalized to 0
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
0/7.5Code-Review — Found 0/14 approved changesets -- score normalized to 0
0/2.5Contributors — project has 0 contributing companies or organizations -- score normalized to 0
10/10Dangerous-Workflow — no dangerous workflow patterns detected
0/7.5Dependency-Update-Tool — no update tool detected
0/5Fuzzing — project is not fuzzed
2.5/2.5Lizenz — license file detected
7.5/7.5Maintained — 30 commit(s) and 3 issue activity found in the last 90 days -- score normalized to 10
5/5Packaging — packaging workflow detected
0/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
0/5SAST — SAST tool is not run on all commits -- score normalized to 0
5/5Security-Policy — security policy file detected
0/7.5Signed-Releases — Project has not signed or included provenance with any releases.
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
2.2/7.5Vulnerabilities — 7 existing vulnerabilities detected
Verwendete Eingangsdaten
sourceopenssf_scorecard
checks_evaluated18
scorecard_versionv5.5.0
checks_inconclusive0
scorecard_aggregate3,8

AI Readiness

Wie gut ist das Repository dafür ausgestattet, mit KI-Coding-Agenten entwickelt und gepflegt zu werden? Ein unabhängiges, experimentelles Badge — Gewicht 0,0, es wird eigenständig ausgewiesen und verändert den Gesamt-Gesundheitswert nicht.

78Gut · 0 % des Gesamtindex
Wie die Bewertung erfolgt
45/45Agentenanweisungen — CLAUDE.md
0/15Maschinenlesbare Doku (llms.txt)
38.4/40Lesbare Commit-Historie — 72 von 100 menschlichen Commits benennen ihre Absicht (strukturierter Betreff oder erläuternder Text)
Verwendete Eingangsdaten
has_llms_txtnein
legible_history_share0,72
agent_instruction_filesCLAUDE.md
agent_instruction_max_bytes20.920
Wie die Bewertung erfolgt
12.6/18Bootstrap mit einem Befehl — Cargo.toml, clients/go/go.mod (Toolchain-Konvention, kein Task-Runner)
22/22Automatisierte Tests
0/11Lint-/Format-Konfiguration
11/11Statische Typprüfung — clients/typescript/tsconfig.json
10/10Reproduzierbare Umgebung — Dockerfile, lockfile
10/10Belegte Agentenpraxis — 58 der letzten 100 Commits von Agenten verfasst oder ihnen zugeschrieben
0/8Automatisierte Wartung — keine automatisierten Abhängigkeits-Updates beobachtet
0/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
Verwendete Eingangsdaten
has_nixnein
has_testsja
lockfilesCargo.lock, package-lock.json
has_dockerfileja
typed_languageja
bootstrap_files
has_devcontainernein
has_linter_confignein
typecheck_configsclients/typescript/tsconfig.json
agent_commit_share0,58
toolchain_manifestsCargo.toml, clients/go/go.mod
dependency_bot_commit_share0
Wie die Bewertung erfolgt
45/45Typprüfbarer Code — Rust (statisch typisiert)
53.7/55Handhabbare Dateigrößen — 2/83 Quelldateien über 60 KB
Verwendete Eingangsdaten
primary_languageRust
largest_source_bytes2.667.011
source_files_sampled83
oversized_source_files2
Wie die Bewertung erfolgt
40/40API-Schema (OpenAPI/GraphQL/proto) — api/openapi.yaml
0/20MCP-Server
40/40Lauffähige Beispiele — examples
Verwendete Eingangsdaten
example_dirsexamples
has_mcp_signalnein
api_schema_filesapi/openapi.yaml

Eckdaten

2GitHub-Sterne
1Mitwirkende
185Commits, letzte 12 Monate
0Tage seit letztem Push
22Releases
1Bus-Faktor
1offene Issues
crates.ioPaket-Ökosysteme

Warnungen zur Datenerhebung

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
  • GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository

Weitere Details

OpenSSF Scorecard 3.8 / 10
3.8Gesamtwert

Unabhängige, werkzeugneutrale Sicherheitsbewertung durch das quelloffene OpenSSF Scorecard. Jede Prüfung honoriert eine Sicherheits-Praxis, nicht das Werkzeug eines bestimmten Anbieters. Prüfungen, die Scorecard nicht ermitteln konnte, sind mit k. A. markiert und vom Sicherheitswert ausgeschlossen (nie als null gezählt).Scorecard v5.5.0 · 2026-07-27 19:49 UTC

10Binary-Artifactsno binaries found in the repo
0Branch-Protectionbranch protection not enabled on development/release branches
0CI-Tests0 out of 13 merged PRs checked by a CI test -- score normalized to 0
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
0Code-ReviewFound 0/14 approved changesets -- score normalized to 0
0Contributorsproject has 0 contributing companies or organizations -- score normalized to 0
10Dangerous-Workflowno dangerous workflow patterns detected
0Dependency-Update-Toolno update tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 3 issue activity found in the last 90 days -- score normalized to 10
10Packagingpackaging workflow detected
0Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 0
0SASTSAST tool is not run on all commits -- score normalized to 0
10Security-Policysecurity policy file detected
0Signed-ReleasesProject has not signed or included provenance with any releases.
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
3Vulnerabilities7 existing vulnerabilities detected
Direkte Abhängigkeiten 19
RegistryPaketVersionsvorgabeManifest
crates.iotokio1Cargo.toml
crates.ioreqwest0.12Cargo.toml
crates.ioserde1Cargo.toml
crates.ioserde_json1Cargo.toml
crates.iofutures0.3Cargo.toml
crates.iothiserror2Cargo.toml
crates.iobytes1Cargo.toml
crates.iotokio-stream0.1Cargo.toml
crates.ioeventsource-stream0.2Cargo.toml
crates.iochrono0.4Cargo.toml
crates.iocrossterm0.28Cargo.toml
crates.iotoml0.8Cargo.toml
crates.iodirs6Cargo.toml
crates.ioaxum0.8Cargo.toml
crates.iotower0.5Cargo.toml
crates.iotower-http0.6Cargo.toml
crates.ioasync-stream0.3Cargo.toml
crates.ioasync-trait0.1Cargo.toml
crates.ioredis1Cargo.toml
Alle Abhängigkeiten nicht erhoben

Der aufgelöste Abhängigkeitssatz konnte für diesen Bericht nicht erhoben werden: GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository

JSON-Rohbericht maschinenlesbar
{
  "data": {
    "repo": {
      "topics": [
        "anthropic",
        "api-gateway",
        "gemini",
        "llm",
        "llm-proxy",
        "openai",
        "rust",
        "xai"
      ],
      "is_fork": false,
      "size_kb": 1557,
      "has_wiki": false,
      "homepage": "https://sanjay920.github.io/llmshim/",
      "languages": {
        "Go": 24858,
        "Ruby": 25948,
        "Rust": 740193,
        "Python": 44955,
        "Dockerfile": 664,
        "JavaScript": 10269,
        "TypeScript": 20632
      },
      "pushed_at": "2026-07-26T23:36:12Z",
      "created_at": "2026-03-08T11:03:28Z",
      "owner_type": "User",
      "updated_at": "2026-07-26T23:34:19Z",
      "description": "A pure-Rust LLM API translation layer — one OpenAI-shaped request, routed and translated to OpenAI, Anthropic, Gemini, and xAI.",
      "is_archived": false,
      "is_disabled": false,
      "license_spdx": "Apache-2.0",
      "default_branch": "main",
      "license_spdx_raw": "Apache-2.0",
      "primary_language": "Rust",
      "significant_languages": [
        "Rust"
      ]
    },
    "owner": {
      "blog": null,
      "name": "Sanjay Nadhavajhala",
      "type": "User",
      "login": "sanjay920",
      "company": null,
      "location": null,
      "followers": 24,
      "avatar_url": "https://avatars.githubusercontent.com/u/6551215?v=4",
      "created_at": "2014-01-31T06:07:11Z",
      "is_verified": null,
      "public_repos": 50,
      "account_age_days": 4560
    },
    "license": {
      "state": "standard",
      "spdx_id": "Apache-2.0",
      "raw_spdx": "Apache-2.0",
      "file_present": true,
      "scorecard_found": true,
      "profile_has_license": true
    },
    "activity": {
      "releases": [
        {
          "tag": "v0.3.1",
          "kind": "patch",
          "published_at": "2026-07-26T23:38:29Z"
        },
        {
          "tag": "v0.3.0",
          "kind": "minor",
          "published_at": "2026-07-26T00:53:08Z"
        },
        {
          "tag": "v0.2.3",
          "kind": "patch",
          "published_at": "2026-07-25T18:04:24Z"
        },
        {
          "tag": "v0.2.2",
          "kind": "patch",
          "published_at": "2026-07-18T01:03:16Z"
        },
        {
          "tag": "v0.2.1",
          "kind": "patch",
          "published_at": "2026-07-17T18:05:06Z"
        },
        {
          "tag": "v0.2.0",
          "kind": "minor",
          "published_at": "2026-07-16T19:52:55Z"
        },
        {
          "tag": "v0.1.26",
          "kind": "patch",
          "published_at": "2026-07-13T06:08:09Z"
        },
        {
          "tag": "v0.1.25",
          "kind": "patch",
          "published_at": "2026-07-13T05:24:43Z"
        },
        {
          "tag": "v0.1.23",
          "kind": "patch",
          "published_at": "2026-07-04T18:38:23Z"
        },
        {
          "tag": "v0.1.22",
          "kind": "patch",
          "published_at": "2026-07-03T22:13:27Z"
        },
        {
          "tag": "v0.1.21",
          "kind": "patch",
          "published_at": "2026-04-30T06:13:59Z"
        },
        {
          "tag": "v0.1.20",
          "kind": "patch",
          "published_at": "2026-04-25T17:17:32Z"
        },
        {
          "tag": "v0.1.18",
          "kind": "patch",
          "published_at": "2026-04-04T05:54:32Z"
        },
        {
          "tag": "v0.1.17",
          "kind": "patch",
          "published_at": "2026-04-04T05:53:58Z"
        },
        {
          "tag": "v0.1.16",
          "kind": "patch",
          "published_at": "2026-03-19T21:32:28Z"
        },
        {
          "tag": "v0.1.15",
          "kind": "patch",
          "published_at": "2026-03-19T00:54:27Z"
        },
        {
          "tag": "v0.1.14",
          "kind": "patch",
          "published_at": "2026-03-19T00:32:47Z"
        },
        {
          "tag": "v0.1.13",
          "kind": "patch",
          "published_at": "2026-03-18T05:23:28Z"
        },
        {
          "tag": "v0.1.12",
          "kind": "patch",
          "published_at": "2026-03-17T18:32:27Z"
        },
        {
          "tag": "v0.1.11",
          "kind": "patch",
          "published_at": "2026-03-17T02:43:58Z"
        },
        {
          "tag": "v0.1.10",
          "kind": "patch",
          "published_at": "2026-03-14T18:24:52Z"
        },
        {
          "tag": "v0.1.9",
          "kind": "patch",
          "published_at": "2026-03-13T02:39:21Z"
        }
      ],
      "recent_commits": [
        {
          "oid": "fff7717ae71b835218e885d719de80b1dbbbac93",
          "body": "Release v0.3.1",
          "is_bot": false,
          "headline": "Merge pull request #46 from sanjay920/release-0.3.1",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-26T23:34:14Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "ab92fa8a2b0368fb965baaad1f3c595eb363d8ef",
          "body": "Additive (patch): add vLLM and SGLang as self-hosted OpenAI-compatible\nproviders, configured by base URL (local or remote) with optional auth.\nLive-verified against a real SGLang server. Version lockstep across Cargo + TS\n+ Ruby clients.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>\nSigned-off-by: Sanjay Nadhavajhala <sanjay.nadhavajhala@gmail.com>",
          "is_bot": false,
          "headline": "Release v0.3.1",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-26T23:34:09Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "d6a5d1925ae2f9452ee24adfb92f481e9ad6da9e",
          "body": "Add vLLM and SGLang as self-hosted providers",
          "is_bot": false,
          "headline": "Merge pull request #45 from sanjay920/feat/vllm-sglang-providers",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-26T23:33:09Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "5cda213214b736278191f6a4b9914734a75cb98e",
          "body": "vLLM and SGLang are OpenAI Chat Completions-compatible inference servers, so\nthey're passthrough providers like OpenRouter — with one new twist: the base URL\nis configuration (local vs remote), and auth is optional.\n\n- src/providers/openai_compat.rs: one generic OpenAiCompatible provider backing\n  b\n[…]\nEADME, providers/request-fields/configuration/models reference.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>\nSigned-off-by: Sanjay Nadhavajhala <sanjay.nadhavajhala@gmail.com>",
          "is_bot": false,
          "headline": "Add vLLM and SGLang as self-hosted providers",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-26T22:42:32Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "ae5ea2161f8128e570224dc1ed2e35f80c0c8515",
          "body": "Release v0.3.0",
          "is_bot": false,
          "headline": "Merge pull request #44 from sanjay920/release-0.3.0",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-26T00:49:14Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "378e5185a4cd372437ac88e6bd653fd46a429b18",
          "body": "Minor: add OpenRouter as a provider (OpenAI Chat Completions-compatible\naggregator, addressed as openrouter/<vendor>/<model>). Live-verified. Includes\na new config::Keys.openrouter field. Version lockstep across Cargo + TS + Ruby\nclients.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>\nSigned-off-by: Sanjay Nadhavajhala <sanjay.nadhavajhala@gmail.com>",
          "is_bot": false,
          "headline": "Release v0.3.0",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-26T00:49:09Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "0521258dd8c3e3e74a42b7a6cb5fe998518cbf07",
          "body": "Add OpenRouter as a provider",
          "is_bot": false,
          "headline": "Merge pull request #43 from sanjay920/feat/openrouter-provider",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-26T00:48:06Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "592491c869e7a4852646c3c3ec4c31a160cf7fba",
          "body": "…state\n\nVerified end-to-end against the real API with poolside/laguna-s-2.1:free:\nbasic completion and reasoning (reasoning_effort -> reasoning:{effort}, with\nmessage.reasoning normalized to reasoning_content) both pass.\n\n- Default to a :free model (OR_TEST_MODEL to override) so the suite runs witho\n[…]\naces OpenRouter's 402 as a ProviderError with status + message.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>\nSigned-off-by: Sanjay Nadhavajhala <sanjay.nadhavajhala@gmail.com>",
          "is_bot": false,
          "headline": "test(openrouter): live-verified integration tests, robust to account …",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-25T23:39:13Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "b11e13c68cad61252b052f84de63b86f95856649",
          "body": "OpenRouter (openrouter.ai) is an OpenAI Chat Completions-compatible aggregator,\nso it becomes llmshim's first *passthrough* provider — every other provider\ntranslates the OpenAI-format input away to a native dialect; OpenRouter's\ntransforms are near-identity.\n\n- src/providers/openrouter.rs: transfor\n[…]\n/mdbook\ngreen. Live verification pending an OPENROUTER_API_KEY.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>\nSigned-off-by: Sanjay Nadhavajhala <sanjay.nadhavajhala@gmail.com>",
          "is_bot": false,
          "headline": "Add OpenRouter as a provider",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-25T23:32:04Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "1509cd839fd940352890d9e4078051bcbff97a34",
          "body": "Release v0.2.3",
          "is_bot": false,
          "headline": "Merge pull request #42 from sanjay920/release-0.2.3",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-25T18:00:38Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "7d21c413c6274647eade81bd96fe5b72621c0424",
          "body": "Additive (patch): register Anthropic Claude Opus 5 (claude-opus-5) — new\nadaptive family (native low..max effort), 1M context by default. Version\nlockstep across Cargo + TS + Ruby clients.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>\nSigned-off-by: Sanjay Nadhavajhala <sanjay.nadhavajhala@gmail.com>",
          "is_bot": false,
          "headline": "Release v0.2.3",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-25T18:00:32Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "3ee880536cea4d2fdae0183552f9c1fc574285a9",
          "body": "Add support for claude-opus-5",
          "is_bot": false,
          "headline": "Merge pull request #41 from sanjay920/feat/add-claude-opus-5",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-25T17:53:58Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "ac15f3a415430614b76ec791af18ae62de9bca61",
          "body": "Register Anthropic's Claude Opus 5 (released 2026-07-24). Verified live:\n- New adaptive family — adaptive thinking + native low..max effort (incl. xhigh,\n  not clamped); rejects the pre-4.6 enabled path (400). Added to\n  `is_new_adaptive_family`.\n- 1M-token context is the DEFAULT (no beta header nee\n[…]\nve end-to-end integration test\n  (passes against the real API).\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>\nSigned-off-by: Sanjay Nadhavajhala <sanjay.nadhavajhala@gmail.com>",
          "is_bot": false,
          "headline": "Add support for claude-opus-5",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-25T17:45:02Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "134ef8f7cca47b76bd0d6f1970199a6cac6e7bef",
          "body": null,
          "is_bot": false,
          "headline": "Delete LICENSE",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-21T20:21:10Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "a2fbf1b4d7335878c768941dfe3ebff89acbc68f",
          "body": "Add open-source project files (dual license, contributing, templates)",
          "is_bot": false,
          "headline": "Merge pull request #40 from sanjay920/chore/oss-project-files",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-21T20:20:26Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "81608fee05bac1b5c34ae0b6abc8ed00c307cdae",
          "body": "- Dual-license under MIT OR Apache-2.0 (LICENSE-MIT, LICENSE-APACHE, NOTICE)\n  and set the Cargo.toml license field to match.\n- CONTRIBUTING.md (dev setup, CI gates, public-API rules, DCO), plus\n  CODE_OF_CONDUCT.md and SECURITY.md (threat model for the auth-less proxy).\n- GitHub issue templates (bu\n[…]\n.\n\nCopyright: Sanjay Nadhavajhala and the llmshim contributors.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>\nSigned-off-by: Sanjay Nadhavajhala <sanjay.nadhavajhala@gmail.com>",
          "is_bot": false,
          "headline": "Add open-source project files: dual license, contributing, templates",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-21T15:42:48Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "8265de9a11610f0040babd91873c2dd43bb53a82",
          "body": "Release v0.2.2",
          "is_bot": false,
          "headline": "Merge pull request #39 from sanjay920/release-0.2.2",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-18T00:59:09Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "cc035761990057cf0bc41b1ebafd350f75489a9d",
          "body": "Additive (patch): Anthropic adaptive/enabled thinking now sets `display`\n(default \"summarized\") so newer models return reasoning text, plus the unified\n`reasoning_summary: auto|none` control (#37). Version lockstep across Cargo + TS\n+ Ruby clients.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Release v0.2.2",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-18T00:59:04Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "e041125d43de25ad57068c73ed7eee0efb68eb08",
          "body": "Anthropic thinking.display so Sonnet 5 / Opus 4.7-4.8 return reasoning text (#37)",
          "is_bot": false,
          "headline": "Merge pull request #38 from sanjay920/feat/reasoning-display",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-18T00:58:09Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "011ed8fa8746337bfd13323e8c3ddd98470b3f2c",
          "body": "…g text (#37)\n\nNewer adaptive models (Sonnet 5, Opus 4.7/4.8, ...) default thinking `display`\nto \"omitted\" — a signed but empty thinking block with no thinking_delta text —\nso clients requesting reasoning via reasoning_effort got zero reasoning text\neven though the model billed thinking tokens. Olde\n[…]\n+ reasoning_effort now returns thinking\nsummary text by default.\n\nAdditive → 0.2.2. Docs: reference/request-fields.md + CLAUDE.md.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "feat(anthropic): set thinking.display so newer models return reasonin…",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-18T00:27:10Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "19e2f6005bee8d5676d4d5b5d043e05912351820",
          "body": "Release v0.2.1",
          "is_bot": false,
          "headline": "Merge pull request #36 from sanjay920/release-0.2.1",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-17T18:01:13Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "9332137eba13212f378b78247aefa5bd9540a38b",
          "body": "Additive (patch): lossless reasoning round-trip for Anthropic — surface\n`reasoning_signature`/`redacted_reasoning_content` on responses (incl. streaming)\nand reconstruct the native thinking block from them on requests (#34). Version\nlockstep across Cargo + TS + Ruby clients.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Release v0.2.1",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-17T18:01:01Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "ddf670b9689d1637b94d6558bdfe2478408efc64",
          "body": "Lossless reasoning round-trip (signature passthrough) (#34)",
          "is_bot": false,
          "headline": "Merge pull request #35 from sanjay920/feat/reasoning-roundtrip",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-17T18:00:02Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "b2c87a3ebbe517750e9919139b7ffc0eb87256c4",
          "body": "…ugh (#34)\n\nMake standalone reasoning round-trip losslessly and symmetrically with the\ntool-call thought_signature convention.\n\nResponses (surface the signature):\n- Non-streaming: surface `reasoning_signature` alongside `reasoning_content`, and\n  `redacted_reasoning_content` for redacted_thinking bl\n[…]\n0, final answer produced).\n\nAdditive (Value-based API) → 0.2.1; no new required fields, non-reasoning\nproviders/models unaffected.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "feat(anthropic): lossless reasoning round-trip via signature passthro…",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-17T17:59:27Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "2cbc6d41e21c544ba0f9ce8209cb4f271d847dff",
          "body": "Release v0.2.0",
          "is_bot": false,
          "headline": "Merge pull request #33 from sanjay920/release-0.2.0",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-16T19:47:35Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "11afbd0573ff64280f14d39056e8bb063fda184f",
          "body": "Minor (breaking) bump: the model registry gained per-model spec metadata —\n`ModelInfo` is now `#[non_exhaustive]` with `context_window_tokens`,\n`max_output_tokens`, and a `ModelCapabilities` struct (#31). Also removed three\ndelisted/shut-down models. Version lockstep across Cargo + TS + Ruby clients.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Release v0.2.0",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-16T19:47:22Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "04c6708ecc9253965ceea0e0622e49bd66243178",
          "body": "Add per-model spec metadata to the registry (#31)",
          "is_bot": false,
          "headline": "Merge pull request #32 from sanjay920/feat/model-spec-metadata",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-16T19:44:09Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "104adf037162588fdb4d2025356bba680d1972d9",
          "body": "llmshim is a standalone public crate on crates.io; its docs, skills, and test\ncomments shouldn't couple to any specific downstream consumer. Replace every\n`ragents` reference with the generic reason (public crate / semver protection)\nor a generic \"streaming client\" in test comments. The semver-prote\n[…]\n valid.\n\nFiles: CLAUDE.md, .claude/skills/{release,add-model,add-provider,README}.md,\ntests/unit_gemini.rs (comment wording only).\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "docs: remove ragents references — llmshim stands on its own",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-16T19:40:28Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "8cad9a4fb04f62c289af1280e6f2009d6d2dd721",
          "body": "Research surfaced three models that are dead upstream, not just under-documented:\n- gemini-3.1-flash-lite-preview — shut down 2026-05-25 (per its own docs page)\n- grok-4-1-fast-reasoning / grok-4-1-fast-non-reasoning — doc pages delisted (404)\n\nRemove all three from the registry so discovery/specs d\n[…]\n, behavior-preserving); integration tests repointed to live models.\n\nPreflight green: fmt, clippy -D warnings, full suite, mdbook.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "feat(models): remove deprecated/delisted models (#31)",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-16T19:22:40Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "390ab43976642607c7ee063a9886f697d1a59906",
          "body": "Fill in context window, output ceiling, and capabilities for the registry,\nresearched from official provider docs (platform.claude.com,\ndevelopers.openai.com, ai.google.dev, docs.x.ai) as of 2026-07-16. Honesty rule\nheld throughout — unverified facts stay Unknown/None, never guessed.\n\nHighlights:\n- \n[…]\ns, documented exceptions, and still-Unknown honesty.\n- Docs: reference/models.md spec section updated with the snapshot + caveats.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "feat(models): populate spec metadata from provider docs (#31)",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-16T19:13:06Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "d33c0e4dedfb650d50d569fdb5f8efbe701f6fb8",
          "body": "Extend the model registry from an identity table into a spec source of truth so\nconsumers stop hand-maintaining parallel tables that drift.\n\n- Widen `ModelInfo` with `context_window_tokens`, `max_output_tokens`, and a\n  `ModelCapabilities` struct (tools, streaming, images, prompt_cache,\n  structured\n[…]\nng + non_exhaustive on a public struct -> 0.2.0, with a\ncoordinated ragents bump at release. Rationale + trimmed scope: issue #31.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "feat(models): add per-model spec metadata to the registry (#31)",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-16T19:01:52Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "274b912076eda6b15a6c8313e2d86813a205242c",
          "body": "An unpinned mdbook-mermaid resolved to a version incompatible with mdbook's\npreprocessor protocol, failing the build with \"Unable to parse the input\".\n0.16.2 is the version verified locally against mdbook 0.4.52.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "ci(pages): pin mdbook-mermaid to 0.16.2 to match mdbook 0.4.52",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-15T06:12:44Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "412a124baba9643110496ffb7ae7fc5e7863ef84",
          "body": "A 29-page mdBook documentation site (getting-started, core concepts, guides,\nproxy/operations, reference) built across four collaborative authoring waves,\neach verified against source. Plus: modernized example model ids across the\nsite and README to current flagships (feature gpt-5.6), reconciled the reasoning\ndoc to a single source of truth, and a GitHub Pages deploy workflow.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Merge docs/concepts-site: mdBook concepts site + model-id modernization",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-15T06:11:24Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "56384db650eb804e87816d6b6f23da6a0cccd649",
          "body": "Single source of truth for reasoning: the site guide docs/src/guides/reasoning.md\nis a complete superset (all effort tables incl. Anthropic pre-4.6 budget, mode\ntable, framing, mermaid), so remove the duplicated top-level docs/reasoning.md\nand repoint every reference:\n- README -> published guide URL\n[…]\nature branches and fires once this branch merges.\n\nPreflight green: mdbook build, cargo fmt, clippy (my changes), full unit suite.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "docs: reconcile reasoning doc + add gated GitHub Pages deploy",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-15T06:10:55Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "967c21d30b11a975bdc52a3f9c48590420a9ba98",
          "body": "Match the docs-site modernization: stale example ids -> current same-provider\nsuccessors (claude-sonnet-4-6 -> claude-sonnet-5, gpt-5.5 -> gpt-5.6-sol), so\nthe streaming quickstart, multi-model switch, and fallback chain now feature\ngpt-5.6 (shipped in v0.1.25).\n\nLeft untouched: the benchmark footnote (honest record of what was measured:\ngpt-5.4 / claude-sonnet-4-6) and the model catalog table (lists every real id).\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "docs(readme): modernize example model ids to current flagships",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-15T05:31:17Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "055dafbcc75305d83826d3fb9349de9b3f2f9e78",
          "body": "The reference catalog was correct, but narrative/getting-started pages leaned on\nstale example ids (claude-sonnet-4-6 everywhere, gpt-5.5 for OpenAI) so a new\nvisitor never saw gpt-5.6 — the flagship shipped in v0.1.25.\n\n- Lead getting-started + intro examples with openai/gpt-5.6-sol\n- Flagship-swit\n[…]\n6 now appears across intro, getting-started, guides, and reference.\nmdbook build green; all model ids valid against src/models.rs.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "docs: modernize example model ids to current flagships (feature gpt-5.6)",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-15T02:32:56Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "de8addf28e928c1c8c9e7e89b766a73a0d2737eb",
          "body": "Final authoring wave — canonical, table-forward reference backing the guides:\n- proxy/http-api: full endpoint + request/response + typed SSE StreamEvent reference\n- proxy/deployment: honest security posture (no built-in auth/TLS, permissive CORS; run behind a gateway)\n- proxy/scaling: shared pool, r\n[…]\n.reasoning_content to api/openapi.yaml.\n\nmdbook build green; all 26 model ids, error codes, and endpoints verified against source.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "docs: author Wave 4 reference + proxy/operations pages",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-15T02:15:04Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "8d278cbe92d2728c95c0e58ce84d52d89ab1e5ec",
          "body": "…backs, native controls)\n\nTask-first guides layered on the Wave-1 concept spine:\n- streaming: Rust normalized OpenAI-delta chunks vs proxy/client typed SSE events\n- tools: OpenAI Chat Completions tool format in, per-provider translation, app-runs-tools loop\n- images: cross-provider image translation\n[…]\nassthrough (no x-xai), precedence wins\n\nmdbook build green; top-level docs/reasoning.md left untouched for publish-time reconcile.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "docs: author Wave 3 guides (streaming, tools, images, reasoning, fall…",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-15T02:07:02Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "444b91976ac1abe1dabe76618efa95cd30a1b3cc",
          "body": "Authored the six Getting Started pages: choose-a-surface, configure,\nand Rust / CLI / proxy / language-client quickstarts. All snippets\nverified against the code (examples/*.rs compiled; client APIs checked\nper clients/*/README.md — Python/TS auto-start the bundled proxy, Go/Ruby\nconnect to a running one). Build green.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "docs: Wave 2 — Getting Started quickstarts",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-15T02:00:20Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "bf7b7780f079569a495baace2de63842d9ea5fcc",
          "body": "Greenfield mdBook docs site under docs/, co-designed with a gpt-5.6-sol\ndocs-architect agent. Wave 1 lands the scaffold, full navigation, and the\nsix \"spine\" pages that establish the mental model; remaining pages are\nstubs filled in later waves.\n\n- docs/book.toml + vendored mdbook-mermaid assets; do\n[…]\n.22 -> 0.1.26, documented the real 429/503 + Retry-After responses.\n\nNot merged; feature branch only, pending page-by-page review.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "docs: mdBook concepts site — Wave 1 (scaffold + mental-model spine)",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-14T07:02:13Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "563c0903c62c188a7a8ed819bee61c1bae90e445",
          "body": "Add xAI grok-4.5 (new flagship, 500K context) with a cannot-disable-\nreasoning clamp (effort none -> low, verified live). All client versions\nin lockstep.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Release v0.1.26",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-13T06:03:44Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "d649fcb5205f0342fff5483fd5bb5c2189fb4a5c",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/add-grok-4.5'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-13T05:40:34Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "29e601f2936836912591614364c63096b1e1ffbb",
          "body": "New xAI flagship (created 2026-06-28, 500K context), verified live via the\n/models + /responses APIs. Reasoning matrix: accepts low/medium/high/xhigh;\nrejects \"max\" (400, like grok-4.3) and — unlike grok-4.3 — rejects \"none\"\n(400 \"does not support value none\": grok-4.5 cannot disable reasoning).\n\n- \n[…]\nied end-to-end through the proxy (none/high/max+pro all accepted;\nnone would 400 without the clamp). 443 tests pass on rustc 1.97.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Add xAI grok-4.5 (cannot-disable-reasoning clamp)",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-13T05:40:29Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "351fe70e18b487c40ba167cf160b54c4700fd8c5",
          "body": "CI's dtolnay/rust-toolchain@stable moved to rustc 1.97, whose clippy\ntightened the question_mark lint and now flags the pre-existing\nelse-if-let/else-return-None block. Rewritten with `?`. (Caught by the\nrelease test gate; nothing was published.)\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Fix clippy 1.97 question_mark lint in translate_tool_choice",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-13T05:20:44Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "1427b5e2fc997fa56482c53d753af697c393d463",
          "body": "Unified fine-grained reasoning controls across all providers\n(reasoning_effort none..max + reasoning_mode standard|pro, per-model\nclamping verified live, docs/reasoning.md mapping reference), GPT-5.6\nmodels (sol/terra/luna), xAI reasoning fixed (nested object + summaries),\nand four latent provider bugs fixed. All client versions in lockstep.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Release v0.1.25",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-13T05:16:45Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "41b9ec49c9d71efdfe756433186fc4d0739b57cd",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/unified-reasoning'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-13T05:10:16Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "dd3eaa479bf0e22181c017e8170d95c5b78a896a",
          "body": "Adds two knobs that work identically everywhere — reasoning_effort\n(none|low|medium|high|xhigh|max) and reasoning_mode (standard|pro) — with\nper-provider translation and per-model clamping, every boundary verified\nagainst the live provider APIs (research by four provider-focused agents,\nthen confirm\n[…]\n (no clamp failures), \"none\" paths show zero reasoning\ntokens, and the adaptive no-thinking case matches raw-API behavior exactly.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Unified fine-grained reasoning controls across all providers",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-13T05:09:43Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "7fe4ebf68cefe77847cab5a2fdbb85c9a4f03a0a",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/add-gpt-5.6-models'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-13T04:16:04Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "59bbd04d2b439f467686d17a00393ddc1e9a60b2",
          "body": "New OpenAI generation (verified live via the /models + /responses APIs):\nthree named variants gpt-5.6-sol / -terra / -luna (not the usual\npro/mini/nano size suffixes). All work through the Responses API.\n\nReasoning-effort quirk: unlike regular models (accept all efforts) and pro\nmodels (only medium/\n[…]\nopenai; clients pass\nmodel strings). Verified end-to-end through the proxy against the live API,\nincluding the minimal-clamp path.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Add GPT-5.6 models (sol, terra, luna) with minimal-effort clamp",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-13T04:15:44Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "a63ba5e798fb63cb8450b57f0097a35b6332348c",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/docs-claude-md-update'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T04:43:14Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "0847e5bc35b4ae124d2b5ffe457bebe5d0b0d70b",
          "body": "…ine in CLAUDE.md\n\nCapture what was learned building out the multi-language clients and the\nmulti-registry release, so future maintainers don't rediscover it:\n\n- New \"Client libraries\" section: Python/TS bundle-and-auto-spawn the\n  binary (maturin / npm optionalDependencies), Go/Ruby are stdlib pure\n[…]\nxtension namespace (disable_1m_context,\n  extra_betas) and the control-key body-exclusion rule.\n- Fixed the stale unit-test count.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Document client libraries, provider extensions, and the release pipel…",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T04:43:09Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "320f1504b6f6554071a6f3f65101a67b556f5dd3",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/npm-idempotent-publish'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T04:19:00Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "ab7fef13e3eda7e292b9add248bf06e4d726d642",
          "body": "The npm binary jobs published all 5 platform packages @0.1.24 on one run,\nbut the root npm job failed separately — so a re-run to publish the root\nre-attempted the (now-published) binary packages and hit \"cannot publish\nover previously published versions,\" which cascaded to skip the root job\n(it `ne\n[…]\nis already on npm.\nMakes the release re-runnable and lets the root package publish even when\nthe platform packages are already up.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Make npm publish steps idempotent (skip if version already on registry)",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T04:18:56Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "4a2b28ed5ff6b0c55a57c01467ead5af3e7f2871",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/fix-root-npm-ruby-test'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T04:12:03Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "ef9a5964adb6e6731ced93bf68f14aeda106504a",
          "body": "Third round of real-CI fixes (all npm *binary* jobs now publish green;\nthese were the last two failures):\n\nroot npm: `npm ci` failed — the committed lockfile has empty versions for\nthe platform optionalDependencies (it was regenerated when the 0.1.24\nplatform packages didn't exist on npm yet), so ci\n[…]\n. Drop bundler for the test — install minitest +\nwebrick explicitly and run the test file directly. Deterministic on any\nRuby 3.x.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Fix root npm install and Ruby test in release pipeline",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T04:11:59Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "9615bb03fb49e600610629647df8944337e35aba",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/fix-npm-oidc-ruby-webrick'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T04:00:16Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "0bbba14c740e9f4e90742a39337bf8eade48f640",
          "body": "Second round of real-CI fixes for the multi-registry release (the mkdir +\nrubygems-action-pin round got further but exposed these):\n\nnpm: the binary packaged fine and provenance signed, but the registry PUT\nreturned a misleading E404 — the documented symptom of publishing via OIDC\ntrusted publishing\n[…]\n by Ruby 2.6, which still bundles it.)\nDeclare webrick as a dev dependency, enable bundler-cache, and run tests\nvia `bundle exec`.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Fix npm OIDC publish (npm >= 11.5.1) and Ruby webrick on 3.3",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T04:00:13Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "e9e5f30f57ea3c9492631092b7d67d7671fbddfc",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/fix-release-npm-rubygems-jobs'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T03:50:25Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "7d3c6a5fa923bc6523cb58b576a78e9d6c8fed3a",
          "body": "Two bugs surfaced on the v0.1.24 release (crates.io/PyPI/Homebrew/Go all\npublished fine; these five jobs failed):\n\n1. npm binary jobs: `cp ... bin/llmshim` failed with \"No such file or\n   directory\". Removing the bin/.gitignore files in a prior fix (to stop\n   them excluding the binary from the publ\n[…]\nase: upload --clobber if the release already exists.\n- go-tag: skip if the module tag already exists.\n- pypi: skip-existing: true.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Fix npm binary + rubygems release jobs, make pipeline re-runnable",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T03:50:07Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "141aabd46ce6e224fa5495dfa4d120a08315d370",
          "body": "The anthropic extra-betas feature (4def36f) already bumped Cargo.toml to\n0.1.24 but left Cargo.lock at 0.1.23 and didn't touch the language clients.\nBring everything in lockstep for the release:\n\n- Cargo.lock: llmshim 0.1.23 -> 0.1.24 (cargo publish requires the match).\n- clients/typescript/package.\n[…]\nag, so this is what\nlets the v0.1.24 release publish green across crates.io, PyPI, npm (root +\n5 platform packages), and RubyGems.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Release v0.1.24: sync Cargo.lock + all client versions",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T03:38:59Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "4b5cc36814281196dece810f84f8b919f3631550",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/scope-win32-npm-package'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T03:28:28Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "7967e127cb490b3cba473cf26d89c657c6dd840a",
          "body": "npm's spam detection returns 403 \"Package name triggered spam detection\"\nfor unscoped names matching `*-win32-<number>` (documented; the exact\nflagged example is `app-win32-x64`). The darwin/linux platform packages\npublish unscoped without issue, but `llmshim-win32-x64` is rejected every\ntime, inclu\n[…]\n skill updated.\n\nThe CI npm-windows-binary job already runs `npm publish --access public`\nwhich handles scoped packages correctly.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Scope the win32 npm package to dodge npm's spam filter",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T03:28:07Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "4def36f09c3a20899c3e0bfd0ec31f5ef96cc62c",
          "body": "The anthropic provider auto-manages beta headers (1M context, fast mode,\nextended cache TTL) but had no way for a caller to request an arbitrary\nadditional beta. Add an `x-anthropic.extra_betas` string-array passthrough:\nvalues are appended to the auto-managed anthropic-beta set (de-duplicated)\nand the key is excluded from the request body since it is a header control,\nnot an API body param.\n\nEnables Claude Code's `--betas` flag to reach the wire (rcode R-22b).\n\nBump 0.1.23 -> 0.1.24.",
          "is_bot": false,
          "headline": "feat(anthropic): pass through caller-supplied extra betas",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-08T03:11:40Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "73ec0edbf33e2382c9a5123a34f2dcf009b5c6e4",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/fix-npm-binary-gitignore-bug'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-05T16:47:51Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "c77bdeae05f2188ce1eb6e8b25b37c6ab24efa4d",
          "body": "npm's packing logic (npm pack/publish) still consults .gitignore rules\nfound within the package root being packed even when `files` explicitly\nallowlists that path -- a `bin/.gitignore` containing `*` / `!.gitignore`\n(added to keep locally-built test binaries out of git) also told npm to\nexclude the\n[…]\not gitignore\nlookup doesn't see, so it still keeps git from tracking locally-built\nbinaries without affecting what gets published.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Fix: nested bin/.gitignore silently excluded binaries from npm packages",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-05T16:47:28Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "beb7dcf67eca2deb7f8b1c9b54e9e46b09726d2a",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/npm-bundle-binary'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-05T16:26:17Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "8d46b9273d251e398fb67336cee364f6622ace9c",
          "body": "The TS client was deliberately scoped as pure-HTTP when it was first built,\nwhich meant Node users had to run `llmshim proxy` themselves while Python\nusers just got `pip install llmshim` and it worked. There's no technical\nreason npm can't match that UX -- esbuild/swc/Turborepo/Biome all bundle\nnati\n[…]\nits own one-time Trusted Publisher setup on npmjs.com -- see\nclients/typescript/README.md and the PR description for exact values.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Bundle a prebuilt binary in the npm package, auto-start like Python",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-05T16:25:47Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "69bb335d15c66f14776117c6f8afac424dfec24e",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/publish-language-clients'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-05T02:54:31Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "a69fdb61637395408fdf5395e3baf90616bcf974",
          "body": "Docs claimed `pip install llmshim` (true — already automated via maturin +\nPyPI trusted publishing) but the TS/Ruby/Go clients that were added earlier\nwere never actually published anywhere, despite their own READMEs showing\ninstall commands that didn't work.\n\n- Renamed the TS package `@llmshim/clie\n[…]\ny exist); RubyGems and PyPI support\npre-publish \"pending\" trusted publishers. See PR description for the exact\nmanual setup steps.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Publish TypeScript, Ruby, and Go clients (npm, RubyGems, go get)",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-05T02:53:59Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "33609874210a0fcbd57a3181fdfe307bb9218b54",
          "body": "Additive release since v0.1.22 (no breaking public-API changes):\n- Client libraries generated from api/openapi.yaml: TypeScript, Go, Ruby\n  (pure-HTTP, spec-faithful), plus a refreshed Python client with types.\n- Reactive retry upgrade (src/client.rs): honors Retry-After + provider\n  reset headers w\n[…]\nt harness (cargo run --features proxy --example loadtest) that\n  validates the shedding paths against a mock upstream at /bin/zsh.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Release v0.1.23",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T18:34:06Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "8eac233c7127dfc8dc42a9722415cf497226b96e",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/loadtest-harness'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T18:16:52Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "acb9a85f641b48bf09639efff02f5e388f010b81",
          "body": "A $0 shakeout (mock Anthropic upstream, no real provider calls) that drives\nthe real proxy under a concurrent burst and verifies the coordination layer\nend-to-end — the paths unit tests can't fully prove under load.\n\nRuns four scenarios and asserts seven path checks:\n- Uncoordinated baseline (shows \n[…]\nangs.\n\nRegistered as `cargo run --release --features proxy --example loadtest`\n(proxy-gated). README scaling section points to it.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Add load-test harness for proxy rate-limit coordination",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T18:16:24Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "d22c262638e6d7d428c69d95acfc9799d3bd1465",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/scale-coordination'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T18:07:35Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "3e23b1932f6fedf24448a11a6547c0ddfff2a085",
          "body": "Proactive load-shedding layer in front of the reactive retry in client.rs,\nso a fleet of proxy replicas doesn't collectively blow provider TPM/RPM limits.\n\n- `trait RateLimiter` (acquire/penalize) held as `Arc<dyn RateLimiter>` in\n  AppState. Pure `TokenBucket` math, unit-tested with tokio::time pau\n[…]\nst a pre-penalized limiter) — no real provider APIs, no\nexternal services required. The redis-coordination feature compile-checks.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Add horizontal-scale rate-limit coordination to the proxy",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T18:05:13Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "224917c6839827e87eb203f527d808bcfb3e024a",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/scale-reactive-retry'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T17:48:24Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "2b5628037bdab81ab1ee01650a98df9f0db5e27c",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/refresh-python-client'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T17:48:24Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "7a51f55eeb1c2940e5700fc8dc743e06dfe9a8b5",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/add-ruby-client'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T17:48:24Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "d53c864345c033643e7df488dd65ca6016631f54",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/add-go-client'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T17:48:24Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "5d5b0f39cded4db9b32764b080183b9ec02176f7",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/add-ts-client'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T17:48:24Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "d5dae52062165cb1143b0269ae434ab3e7f58ca4",
          "body": "Thin, standard-library-only Ruby HTTP client for a running llmshim proxy.\nImplements all four proxy endpoints per api/openapi.yaml:\n\n- chat  -> POST /v1/chat (non-streaming, returns ChatResponse)\n- stream -> POST /v1/chat/stream (SSE, yields typed StreamEvent objects)\n- models -> GET /v1/models\n- he\n[…]\nrick mock returning canned JSON and multi-event SSE;\nno real provider APIs and no running proxy required. 11 tests, 55 assertions.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Add Ruby client gem for the llmshim proxy",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T17:47:03Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "91ebf99b54638851f274404b3d4f364c4608b460",
          "body": "Upgrades ShimClient::send retry logic to be production-grade for a\nhorizontally-scaled proxy. Previously it retried the retryable statuses\nwith fixed exponential backoff (1s/2s/4s), no jitter, and ignored every\nserver-provided timing hint — a thundering-herd hazard at fleet scale.\n\nWhat changed:\n- H\n[…]\nbound, full_jitter). Tests are unit-only + mockito (new\ndev-dependency) against a local server — no provider API calls, $0 to run.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Make HTTP retry reactive: honor Retry-After, add jitter, env config",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T17:43:56Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "bd53e906295c77dc229e2dda249661114b846e2d",
          "body": "Audit the clients/python surface against api/openapi.yaml and close drift,\nwhile preserving the bundled-binary auto-spawn convenience.\n\nChanges:\n- Add spec-faithful TypedDicts in llmshim/types.py (ChatRequest, ChatResponse,\n  Config, Message, ToolCall, Usage, ResponseMessage, ModelsResponse,\n  Healt\n[…]\nock. Verifies request building, response parsing, SSE event\ntyping, and error handling. No real provider APIs, no keys, $0 to run.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Refresh Python client to match 0.1.22 API spec",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T17:43:49Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "75bd534fd26c9f09931e31e2d9f7517042ab4ab5",
          "body": "Thin, idiomatic, standard-library-only Go HTTP client in clients/go/.\nTalks to a running llmshim proxy over pure HTTP (default\nhttp://localhost:3000); does not spawn the Rust binary.\n\nImplements all four proxy endpoints with context.Context:\n- Chat    -> POST /v1/chat (non-streaming)\n- Stream  -> PO\n[…]\nnon-2xx responses. Tests use net/http/httptest with canned JSON and SSE\nonly, so `go test ./...` never touches real provider APIs.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Add Go client for the llmshim proxy",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T17:41:32Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "2d481d5877e3149d089dcbc432b18f8a058709b7",
          "body": "Adds clients/typescript/: a thin, pure-HTTP client implementing all four\nproxy endpoints from api/openapi.yaml (chat, chat/stream, models, health).\n\n- Zero runtime dependencies: global fetch + native ReadableStream (Node 18+),\n  ESM with shipped .d.ts declarations.\n- Pure HTTP against a running prox\n[…]\ns are fully mocked via an in-process http.createServer (node:test);\n  no real provider APIs, no running proxy required, $0 to run.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Add dependency-free TypeScript client for the llmshim proxy",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-04T17:40:04Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "dcedfcfeab42d44715be67555740100272cbccc3",
          "body": "Additive release since v0.1.21:\n- New models: Anthropic Opus 4.8/4.7 + Sonnet 5, Gemini 3.5 Flash,\n  xAI Grok 4.3, OpenAI gpt-5.5-pro/gpt-5.4-pro (15 -> 22 models).\n- Anthropic: route Opus 4.7/4.8 and Sonnet 5 through the adaptive\n  thinking path (the pre-4.6 enabled/budget path 400s on them).\n- Ope\n[…]\nchmarks and\n  restructured README around the Rust core + CLI + proxy surfaces.\n\nNo breaking changes to public API (additive only).\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Release v0.1.22",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T22:09:29Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "75aded2bc2e9e318c3f47ea2056f32a3a16d90fc",
          "body": null,
          "is_bot": false,
          "headline": "Merge branch 'clarify-readme'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T22:08:00Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "e663526512b07e9513dddb7d72be835fbce8bde0",
          "body": "The README described llmshim as \"pure Rust\" but showed almost exclusively\nPython examples, with no explanation of how the Python API relates to the\nRust engine — leaving readers unsure what language the project even is.\n\nRestructure around the three ways to use llmshim, with every code block\nlabeled\n[…]\nto a current model\n  (gemini-3.5-flash), and fix the unit-test count note (~326 -> ~370).\n\nNo behavior change; documentation only.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Restructure README around Rust core + CLI + proxy surfaces",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T22:07:42Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "a4571b430b0fe0df3c225a028fbb93e610e7627c",
          "body": null,
          "is_bot": false,
          "headline": "Merge branch 'refresh-benchmarks'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T21:59:57Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "4275852c2a1b6d75313ee43ca081e05cea5157c1",
          "body": "Rerun the Rust and Python benchmark suites (5 full runs each) and publish\nmedians rather than a single noisy sample.\n\n- Latency rows now reflect reality: llmshim ties the Python libs on\n  Anthropic p50 and wins OpenAI p50, but the differences are within\n  network noise (llmshim's own work is ~1.5µs)\n[…]\n and added the measured\n  transform-overhead row instead.\n- Binary size claims corrected 5MB/3.7MB -> ~6MB (same toolchain drift).\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Refresh benchmarks with honest median-of-5 numbers",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T21:59:33Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "acee03cc8000ecd69c508a020352e67950689f0a",
          "body": null,
          "is_bot": false,
          "headline": "Merge branch 'reorder-models-latest-first'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T19:04:18Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "3024506bc7bbf03fbcfe2f7f2c2e6cb6e013076b",
          "body": "New models were previously appended to the end of each provider's list,\nso e.g. GPT-5.5 Pro sorted after GPT-5.4 and Gemini 3.5 Flash appeared\nlast. Reorder OpenAI, Gemini, and xAI so the latest models lead, with\nversion families grouped (base model then its -pro/variants). Anthropic\nwas already new\n[…]\nodels by list position, so the newest now get the lowest\nselection numbers. No behavior change; ordering is not asserted by tests.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Order models newest-first within each provider",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T19:03:55Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "6106cd5b46bf7be027ceed62db70412f6c5a2de7",
          "body": null,
          "is_bot": false,
          "headline": "Merge branch 'add-maintainer-skills'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T18:51:19Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "256d4fb4ed8d606566430bce19fd7c15d1758e71",
          "body": "Reflects the model additions merged since the skills were authored.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Update preflight skill test count (~326 -> ~370)",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T18:51:13Z",
          "body_truncated": false,
          "is_coding_agent": true
        },
        {
          "oid": "50ff8a4915175c2b8d556c6e40a9d27debee1f9e",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/add-openai-pro-models'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T18:20:55Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "9d9b807823fb23b744cbbc4116d8ef28ee003112",
          "body": "Add two OpenAI \"pro\" tier models verified against the live Responses API:\n- gpt-5.5-pro (\"GPT-5.5 Pro\", openai/gpt-5.5-pro)\n- gpt-5.4-pro (\"GPT-5.4 Pro\", openai/gpt-5.4-pro)\n\nPro models only accept reasoning.effort of medium/high/xhigh and reject\nminimal/low/none with HTTP 400. Add is_pro_model() he\n[…]\nare unchanged.\n\nRegistry updated in both duplicated locations (src/models.rs and\nsrc/main.rs) plus docs and test count (20 -> 22).\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Add OpenAI pro-tier models with reasoning-effort clamp",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T18:19:52Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "aee27679c236fd0520eb39f6bf392826c75c581a",
          "body": "# Conflicts:\n#\tCLAUDE.md\n#\tREADME.md\n#\ttests/unit_models.rs",
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/add-xai-models'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T18:06:46Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "841e89ca41ffd1f93d593258e63f4227ce6e83d0",
          "body": "# Conflicts:\n#\tCLAUDE.md\n#\tREADME.md\n#\ttests/unit_models.rs",
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/add-gemini-models'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T18:06:03Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "c64b09def66f7456b1904e65357a1c0d4fda624c",
          "body": null,
          "is_bot": false,
          "headline": "Merge remote-tracking branch 'origin/add-anthropic-models'",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T18:05:04Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "189f043c3f931edf7cde3e80603d5c13f873ae91",
          "body": "Add three new Anthropic models to the registry: claude-opus-4-8\n(\"Claude Opus 4.8\"), claude-sonnet-5 (\"Claude Sonnet 5\"), and\nclaude-opus-4-7 (\"Claude Opus 4.7\").\n\nMandatory capability-flag change (verified against the live API):\nthe pre-4.6 thinking path (thinking:{type:\"enabled\", budget_tokens})\nr\n[…]\nder,\nand the registry count test bumped 15 -> 18. Docs updated in CLAUDE.md\nand README.md. Existing 4.6/4.5 behavior is unchanged.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Add Anthropic Opus 4.8/4.7 and Sonnet 5, fix adaptive thinking",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T17:26:24Z",
          "body_truncated": true,
          "is_coding_agent": true
        },
        {
          "oid": "10ac18d820d6ac4529f8bc4160aca00ae55d145a",
          "body": "Register gemini-3.5-flash (label \"Gemini 3.5 Flash\", id\ngemini/gemini-3.5-flash). Verified against the live Gemini API:\nsupports generateContent and returns HTTP 200.\n\nThe Gemini provider is a generic passthrough with no per-model\ncapability flags, so this change is purely additive with no provider\n\n[…]\nand\nsrc/main.rs), bumped the registry count test to 16, added a transform\nsmoke test, and updated the docs (CLAUDE.md, README.md).\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
          "is_bot": false,
          "headline": "Add Gemini 3.5 Flash model",
          "author_name": "Sanjay Nadhavajhala",
          "author_login": "sanjay920",
          "committed_at": "2026-07-03T17:25:33Z",
          "body_truncated": true,
          "is_coding_agent": true
        }
      ],
      "releases_count": 22,
      "commits_last_year": 185,
      "latest_release_at": "2026-07-26T23:38:29Z",
      "latest_release_tag": "v0.3.1",
      "releases_from_tags": false,
      "days_since_last_push": 0,
      "active_weeks_last_year": 13,
      "days_since_latest_release": 0,
      "mean_days_between_releases": 2.6
    },
    "community": {
      "has_readme": true,
      "has_license": true,
      "has_description": true,
      "has_contributing": true,
      "health_percentage": 100,
      "has_issue_template": false,
      "has_code_of_conduct": true,
      "has_pull_request_template": true
    },
    "ecosystem": {
      "packages": [
        {
          "name": "llmshim",
          "exists": true,
          "license": "MIT OR Apache-2.0",
          "keywords": [
            "ai",
            "anthropic",
            "gemini",
            "llm",
            "openai",
            "api-bindings",
            "web-programming"
          ],
          "ecosystem": "crates",
          "matches_repo": true,
          "registry_url": "https://crates.io/crates/llmshim",
          "is_deprecated": false,
          "latest_version": "0.3.1",
          "repository_url": "https://github.com/sanjay920/llmshim",
          "versions_count": 32,
          "total_downloads": 639,
          "dependents_count": null,
          "deprecation_note": null,
          "maintainers_count": null,
          "monthly_downloads": 121,
          "first_published_at": "2026-03-10T21:27:34.914506Z",
          "latest_published_at": "2026-07-26T23:36:30.535376Z",
          "latest_version_yanked": false,
          "days_since_latest_publish": 0
        }
      ]
    },
    "popularity": {
      "forks": 0,
      "stars": 2,
      "watchers": 0,
      "fork_history": {
        "days": [],
        "complete": true,
        "collected": 0,
        "total_forks": 0
      },
      "star_history": null,
      "open_issues_and_prs": 1
    },
    "ai_readiness": {
      "has_nix": false,
      "example_dirs": [
        "examples"
      ],
      "has_llms_txt": false,
      "has_dockerfile": true,
      "has_mcp_signal": false,
      "bootstrap_files": [],
      "api_schema_files": [
        "api/openapi.yaml"
      ],
      "has_devcontainer": false,
      "typecheck_configs": [
        "clients/typescript/tsconfig.json"
      ],
      "toolchain_manifests": [
        "Cargo.toml",
        "clients/go/go.mod"
      ],
      "largest_source_bytes": 2667011,
      "source_files_sampled": 83,
      "oversized_source_files": 2,
      "agent_instruction_files": [
        "CLAUDE.md"
      ],
      "agent_instruction_max_bytes": 20920
    },
    "dependencies": {
      "manifests": [
        "Cargo.toml"
      ],
      "advisories": {
        "error": null,
        "scope": null,
        "source": null,
        "findings": [],
        "collected": false,
        "malicious": [],
        "truncated": false,
        "by_severity": {},
        "advisory_count": 0,
        "affected_count": 0,
        "assessed_count": 0,
        "malicious_count": 0,
        "assessed_package": null,
        "unassessed_count": 0,
        "direct_affected_count": 0
      },
      "ecosystems": [
        "crates"
      ],
      "dependencies": [
        {
          "name": "tokio",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "1"
        },
        {
          "name": "reqwest",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "0.12"
        },
        {
          "name": "serde",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "1"
        },
        {
          "name": "serde_json",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "1"
        },
        {
          "name": "futures",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "0.3"
        },
        {
          "name": "thiserror",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "2"
        },
        {
          "name": "bytes",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "1"
        },
        {
          "name": "tokio-stream",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "0.1"
        },
        {
          "name": "eventsource-stream",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "0.2"
        },
        {
          "name": "chrono",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "0.4"
        },
        {
          "name": "crossterm",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "0.28"
        },
        {
          "name": "toml",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "0.8"
        },
        {
          "name": "dirs",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "6"
        },
        {
          "name": "axum",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "0.8"
        },
        {
          "name": "tower",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "0.5"
        },
        {
          "name": "tower-http",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "0.6"
        },
        {
          "name": "async-stream",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "0.3"
        },
        {
          "name": "async-trait",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "0.1"
        },
        {
          "name": "redis",
          "manifest": "Cargo.toml",
          "ecosystem": "crates",
          "version_constraint": "1"
        }
      ],
      "all_dependencies": {
        "error": "GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository",
        "source": null,
        "packages": [],
        "collected": false,
        "truncated": false,
        "total_count": null,
        "direct_count": null,
        "indirect_count": null
      }
    },
    "maintainership": {
      "issues": {
        "open_prs": 0,
        "merged_prs": 41,
        "open_issues": 1,
        "closed_ratio": 0.75,
        "closed_issues": 3,
        "closed_unmerged_prs": 0
      },
      "bus_factor": 1,
      "bot_contributors": 0,
      "top_contributors": [
        {
          "type": "User",
          "login": "sanjay920",
          "commits": 185,
          "avatar_url": "https://avatars.githubusercontent.com/u/6551215?v=4"
        }
      ],
      "contributors_sampled": 1,
      "top_contributor_share": 1
    },
    "quality_signals": {
      "has_ci": true,
      "has_tests": true,
      "ci_workflows": [
        "pages.yml",
        "release.yml"
      ],
      "has_docs_dir": true,
      "linter_configs": [],
      "has_editorconfig": false,
      "has_linter_config": false,
      "has_precommit_config": false
    },
    "security_signals": {
      "lockfiles": [
        "Cargo.lock",
        "package-lock.json"
      ],
      "scorecard": {
        "checks": [
          {
            "name": "Binary-Artifacts",
            "score": 10,
            "reason": "no binaries found in the repo",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#binary-artifacts"
          },
          {
            "name": "Branch-Protection",
            "score": 0,
            "reason": "branch protection not enabled on development/release branches",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
          },
          {
            "name": "CI-Tests",
            "score": 0,
            "reason": "0 out of 13 merged PRs checked by a CI test -- score normalized to 0",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#ci-tests"
          },
          {
            "name": "CII-Best-Practices",
            "score": 0,
            "reason": "no effort to earn an OpenSSF best practices badge detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#cii-best-practices"
          },
          {
            "name": "Code-Review",
            "score": 0,
            "reason": "Found 0/14 approved changesets -- score normalized to 0",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
          },
          {
            "name": "Contributors",
            "score": 0,
            "reason": "project has 0 contributing companies or organizations -- score normalized to 0",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#contributors"
          },
          {
            "name": "Dangerous-Workflow",
            "score": 10,
            "reason": "no dangerous workflow patterns detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dangerous-workflow"
          },
          {
            "name": "Dependency-Update-Tool",
            "score": 0,
            "reason": "no update tool detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dependency-update-tool"
          },
          {
            "name": "Fuzzing",
            "score": 0,
            "reason": "project is not fuzzed",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
          },
          {
            "name": "License",
            "score": 10,
            "reason": "license file detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
          },
          {
            "name": "Maintained",
            "score": 10,
            "reason": "30 commit(s) and 3 issue activity found in the last 90 days -- score normalized to 10",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#maintained"
          },
          {
            "name": "Packaging",
            "score": 10,
            "reason": "packaging workflow detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
          },
          {
            "name": "Pinned-Dependencies",
            "score": 0,
            "reason": "dependency not pinned by hash detected -- score normalized to 0",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#pinned-dependencies"
          },
          {
            "name": "SAST",
            "score": 0,
            "reason": "SAST tool is not run on all commits -- score normalized to 0",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#sast"
          },
          {
            "name": "Security-Policy",
            "score": 10,
            "reason": "security policy file detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#security-policy"
          },
          {
            "name": "Signed-Releases",
            "score": 0,
            "reason": "Project has not signed or included provenance with any releases.",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#signed-releases"
          },
          {
            "name": "Token-Permissions",
            "score": 0,
            "reason": "detected GitHub workflow tokens with excessive permissions",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
          },
          {
            "name": "Vulnerabilities",
            "score": 3,
            "reason": "7 existing vulnerabilities detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
          }
        ],
        "commit": "fff7717ae71b835218e885d719de80b1dbbbac93",
        "ran_at": "2026-07-27T19:49:03Z",
        "aggregate_score": 3.8,
        "scorecard_version": "v5.5.0"
      },
      "has_codeql_workflow": false,
      "has_security_policy": true,
      "has_dependabot_config": false
    },
    "contribution_flow": {
      "collected": true,
      "ci_last_run_at": "2026-07-26T23:39:45Z",
      "oldest_open_prs": [],
      "last_merged_pr_at": "2026-07-26T23:34:15Z",
      "ci_last_conclusion": "SUCCESS",
      "oldest_open_issues": [
        {
          "number": 1,
          "created_at": "2026-04-02T00:17:08Z",
          "last_comment_at": null,
          "last_comment_author": null
        }
      ]
    }
  },
  "config": {
    "disabled_metrics": [],
    "disabled_categories": [],
    "disabled_components": {}
  },
  "source": {
    "url": "https://github.com/sanjay920/llmshim",
    "host": "github.com",
    "name": "llmshim",
    "owner": "sanjay920"
  },
  "metrics": {
    "overall": {
      "key": "overall",
      "band": "moderate",
      "name": "Overall health",
      "note": null,
      "notes": [],
      "value": 57,
      "inputs": {
        "security": 38,
        "vitality": 80,
        "community": 41,
        "governance": 55,
        "engineering": 65
      },
      "components": []
    },
    "categories": [
      {
        "key": "vitality",
        "band": "good",
        "name": "Vitality",
        "value": 80,
        "weight": 0.22,
        "metrics": [
          {
            "key": "development_activity",
            "band": "good",
            "name": "Development activity",
            "note": null,
            "notes": [],
            "value": 73,
            "inputs": {
              "commits_last_year": 185,
              "human_commit_share": 1,
              "days_since_last_push": 0,
              "active_weeks_last_year": 13
            },
            "components": [
              {
                "key": "push_recency",
                "name": "Push recency",
                "detail": "last push 0 days ago",
                "points": 36,
                "status": "met",
                "details": [
                  {
                    "code": "push_recency",
                    "params": {
                      "days": 0
                    }
                  }
                ],
                "max_points": 36
              },
              {
                "key": "commit_cadence",
                "name": "Commit cadence",
                "detail": "13/52 weeks with commits",
                "points": 9,
                "status": "partial",
                "details": [
                  {
                    "code": "commit_cadence_weeks",
                    "params": {
                      "weeks": 13
                    }
                  }
                ],
                "max_points": 36
              },
              {
                "key": "commit_volume",
                "name": "Commit volume",
                "detail": "185 commits in the last year",
                "points": 18,
                "status": "met",
                "details": [
                  {
                    "code": "commits_last_year",
                    "params": {
                      "count": 185
                    }
                  }
                ],
                "max_points": 18
              },
              {
                "key": "openssf_scorecard_maintained",
                "name": "OpenSSF Scorecard: Maintained",
                "detail": "30 commit(s) and 3 issue activity found in the last 90 days -- score normalized to 10",
                "points": 10,
                "status": "met",
                "details": [],
                "max_points": 10
              }
            ]
          },
          {
            "key": "release_discipline",
            "band": "excellent",
            "name": "Release discipline",
            "note": null,
            "notes": [],
            "value": 90,
            "inputs": {
              "releases_count": 22,
              "latest_release_tag": "v0.3.1",
              "releases_from_tags": false,
              "days_since_latest_release": 0,
              "mean_days_between_releases": 2.6
            },
            "components": [
              {
                "key": "ships_releases",
                "name": "Ships releases",
                "detail": "22 releases published",
                "points": 27,
                "status": "met",
                "details": [
                  {
                    "code": "releases_published",
                    "params": {
                      "count": 22
                    }
                  }
                ],
                "max_points": 27
              },
              {
                "key": "release_recency",
                "name": "Release recency",
                "detail": "latest release 0 days ago",
                "points": 36,
                "status": "met",
                "details": [
                  {
                    "code": "release_recency",
                    "params": {
                      "days": 0
                    }
                  }
                ],
                "max_points": 36
              },
              {
                "key": "release_cadence",
                "name": "Release cadence",
                "detail": "a release every ~2.6 days",
                "points": 27,
                "status": "met",
                "details": [
                  {
                    "code": "release_cadence",
                    "params": {
                      "gap": 2.6
                    }
                  }
                ],
                "max_points": 27
              },
              {
                "key": "openssf_scorecard_signed_releases",
                "name": "OpenSSF Scorecard: Signed-Releases",
                "detail": "Project has not signed or included provenance with any releases.",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 10
              }
            ]
          },
          {
            "key": "abandonment",
            "band": "excellent",
            "name": "Abandonment",
            "note": null,
            "notes": [],
            "value": 100,
            "inputs": {
              "cap": null,
              "state": "unverified",
              "guards": [],
              "signals": [],
              "red_flag": false,
              "multiplier_pct": 100,
              "declared_reason": null,
              "unverified_reason": "repository_too_young",
              "unanswered_open_prs": null,
              "unanswered_open_issues": null,
              "days_since_last_merged_pr": null,
              "days_since_last_human_commit": null,
              "days_since_last_human_commit_is_floor": false
            },
            "components": [
              {
                "key": "project_is_still_maintained",
                "name": "Project is still maintained",
                "detail": "maintenance record not established from the collected data",
                "points": 100,
                "status": "met",
                "details": [
                  {
                    "code": "abandonment_unverified",
                    "params": {}
                  }
                ],
                "max_points": 100
              }
            ]
          }
        ],
        "description": "Is the project alive — is code being written and are releases shipping?"
      },
      {
        "key": "community",
        "band": "at_risk",
        "name": "Community & Adoption",
        "value": 41,
        "weight": 0.18,
        "metrics": [
          {
            "key": "popularity",
            "band": "critical",
            "name": "Popularity & adoption",
            "note": null,
            "notes": [],
            "value": 1,
            "inputs": {
              "forks": 0,
              "stars": 2,
              "watchers": 0,
              "growth_state": "unverified",
              "growth_factor_pct": 100,
              "growth_unverified_reason": "no_history"
            },
            "components": [
              {
                "key": "stars",
                "name": "Stars",
                "detail": "2 stars",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "stars",
                    "params": {
                      "count": 2
                    }
                  }
                ],
                "max_points": 60
              },
              {
                "key": "forks",
                "name": "Forks",
                "detail": "0 forks",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "forks",
                    "params": {
                      "count": 0
                    }
                  }
                ],
                "max_points": 25
              },
              {
                "key": "watchers",
                "name": "Watchers",
                "detail": "0 watchers",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "watchers",
                    "params": {
                      "count": 0
                    }
                  }
                ],
                "max_points": 15
              }
            ]
          },
          {
            "key": "community_health",
            "band": "excellent",
            "name": "Community health",
            "note": null,
            "notes": [],
            "value": 92,
            "inputs": {
              "has_readme": true,
              "has_license": true,
              "has_contributing": true,
              "has_issue_template": false,
              "has_code_of_conduct": true,
              "has_pull_request_template": true
            },
            "components": [
              {
                "key": "readme",
                "name": "README",
                "detail": null,
                "points": 22.5,
                "status": "met",
                "details": [],
                "max_points": 22.5
              },
              {
                "key": "license",
                "name": "License",
                "detail": "recognized license (Apache-2.0)",
                "points": 22.5,
                "status": "met",
                "details": [
                  {
                    "code": "license_standard",
                    "params": {}
                  },
                  {
                    "code": "license_spdx",
                    "params": {
                      "spdx": "Apache-2.0"
                    }
                  }
                ],
                "max_points": 22.5
              },
              {
                "key": "contributing_guide",
                "name": "CONTRIBUTING guide",
                "detail": null,
                "points": 18,
                "status": "met",
                "details": [],
                "max_points": 18
              },
              {
                "key": "code_of_conduct",
                "name": "Code of conduct",
                "detail": null,
                "points": 13.5,
                "status": "met",
                "details": [],
                "max_points": 13.5
              },
              {
                "key": "issue_template",
                "name": "Issue template",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.2
              },
              {
                "key": "pr_template",
                "name": "PR template",
                "detail": null,
                "points": 6.3,
                "status": "met",
                "details": [],
                "max_points": 6.3
              }
            ]
          },
          {
            "key": "ecosystem_adoption",
            "band": "at_risk",
            "name": "Ecosystem adoption (downloads)",
            "note": "Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.",
            "notes": [
              {
                "code": "excluded_no_data",
                "params": {
                  "components": [
                    "registry_dependents"
                  ]
                }
              },
              {
                "code": "weights_renormalized",
                "params": {}
              }
            ],
            "value": 35,
            "inputs": {
              "packages": [
                "llmshim"
              ],
              "dependents": null,
              "ecosystems": "crates",
              "total_downloads": 639,
              "monthly_downloads": 121
            },
            "components": [
              {
                "key": "monthly_downloads",
                "name": "Monthly downloads",
                "detail": "121 downloads/month across crates",
                "points": 27.8,
                "status": "partial",
                "details": [
                  {
                    "code": "downloads_monthly",
                    "params": {
                      "count": 121,
                      "ecosystems": "crates"
                    }
                  }
                ],
                "max_points": 80
              },
              {
                "key": "registry_dependents",
                "name": "Registry dependents",
                "detail": "not reported by this ecosystem",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "not_reported_by_this_ecosystem",
                    "params": {}
                  }
                ],
                "max_points": 20
              }
            ]
          }
        ],
        "description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
      },
      {
        "key": "governance",
        "band": "moderate",
        "name": "Sustainability & Governance",
        "value": 55,
        "weight": 0.24,
        "metrics": [
          {
            "key": "maintainer_resilience",
            "band": "critical",
            "name": "Maintainer resilience (bus factor)",
            "note": null,
            "notes": [],
            "value": 10,
            "inputs": {
              "bus_factor": 1,
              "contributors_sampled": 1,
              "top_contributor_share": 1
            },
            "components": [
              {
                "key": "bus_factor",
                "name": "Bus factor",
                "detail": "1 contributor(s) cover half of all commits",
                "points": 9,
                "status": "partial",
                "details": [
                  {
                    "code": "bus_factor",
                    "params": {
                      "count": 1
                    }
                  }
                ],
                "max_points": 54
              },
              {
                "key": "commit_distribution",
                "name": "Commit distribution",
                "detail": "top contributor authored 100% of commits",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "top_contributor_share",
                    "params": {
                      "share": 100
                    }
                  }
                ],
                "max_points": 22.5
              },
              {
                "key": "contributor_breadth",
                "name": "Contributor breadth",
                "detail": "1 contributors",
                "points": 1.4,
                "status": "partial",
                "details": [
                  {
                    "code": "contributors_sampled",
                    "params": {
                      "count": 1
                    }
                  }
                ],
                "max_points": 13.5
              },
              {
                "key": "openssf_scorecard_contributors",
                "name": "OpenSSF Scorecard: Contributors",
                "detail": "project has 0 contributing companies or organizations -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 10
              }
            ]
          },
          {
            "key": "responsiveness",
            "band": "good",
            "name": "Issue & PR responsiveness",
            "note": null,
            "notes": [],
            "value": 73,
            "inputs": {
              "merged_prs": 41,
              "open_issues": 1,
              "closed_issues": 3,
              "issue_closed_ratio": 0.75,
              "closed_unmerged_prs": 0
            },
            "components": [
              {
                "key": "issue_resolution",
                "name": "Issue resolution",
                "detail": "75% of issues closed",
                "points": 35.1,
                "status": "partial",
                "details": [
                  {
                    "code": "issues_closed_share",
                    "params": {
                      "share": 75
                    }
                  }
                ],
                "max_points": 46.75
              },
              {
                "key": "pr_acceptance",
                "name": "PR acceptance",
                "detail": "41/41 decided PRs merged",
                "points": 38.2,
                "status": "met",
                "details": [
                  {
                    "code": "decided_prs_merged",
                    "params": {
                      "merged": 41,
                      "decided": 41
                    }
                  }
                ],
                "max_points": 38.25
              },
              {
                "key": "openssf_scorecard_code_review",
                "name": "OpenSSF Scorecard: Code-Review",
                "detail": "Found 0/14 approved changesets -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 15
              }
            ]
          },
          {
            "key": "stewardship",
            "band": "moderate",
            "name": "Ownership & stewardship",
            "note": "Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.",
            "notes": [
              {
                "code": "excluded_no_data",
                "params": {
                  "components": [
                    "verified_domain"
                  ]
                }
              },
              {
                "code": "weights_renormalized",
                "params": {}
              }
            ],
            "value": 56,
            "inputs": {
              "followers": 24,
              "owner_type": "User",
              "is_verified": null,
              "owner_login": "sanjay920",
              "public_repos": 50,
              "account_age_days": 4560
            },
            "components": [
              {
                "key": "ownership_backing",
                "name": "Ownership backing",
                "detail": "personal (user) account",
                "points": 10,
                "status": "partial",
                "details": [
                  {
                    "code": "owner_personal",
                    "params": {}
                  }
                ],
                "max_points": 30
              },
              {
                "key": "verified_domain",
                "name": "Verified domain",
                "detail": "not applicable to user accounts",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "not_applicable_to_user_accounts",
                    "params": {}
                  }
                ],
                "max_points": 20
              },
              {
                "key": "owner_reach",
                "name": "Owner reach",
                "detail": "24 followers of sanjay920",
                "points": 10.1,
                "status": "partial",
                "details": [
                  {
                    "code": "owner_followers",
                    "params": {
                      "count": 24,
                      "login": "sanjay920"
                    }
                  }
                ],
                "max_points": 25
              },
              {
                "key": "track_record",
                "name": "Track record",
                "detail": "50 public repos, account ~12 yr old",
                "points": 24.4,
                "status": "partial",
                "details": [
                  {
                    "code": "public_repos",
                    "params": {
                      "count": 50
                    }
                  },
                  {
                    "code": "account_age_years",
                    "params": {
                      "years": 12
                    }
                  }
                ],
                "max_points": 25
              }
            ]
          },
          {
            "key": "package_maintenance",
            "band": "excellent",
            "name": "Package maintenance",
            "note": null,
            "notes": [],
            "value": 100,
            "inputs": {
              "packages": [
                "llmshim"
              ],
              "ecosystems": "crates",
              "any_deprecated": false,
              "min_days_since_publish": 0
            },
            "components": [
              {
                "key": "published_resolvable",
                "name": "Published & resolvable",
                "detail": "1 package(s) on crates",
                "points": 25,
                "status": "met",
                "details": [
                  {
                    "code": "packages_published",
                    "params": {
                      "count": 1,
                      "ecosystems": "crates"
                    }
                  }
                ],
                "max_points": 25
              },
              {
                "key": "publish_recency",
                "name": "Publish recency",
                "detail": "latest publish 0 days ago",
                "points": 35,
                "status": "met",
                "details": [
                  {
                    "code": "publish_recency",
                    "params": {
                      "days": 0
                    }
                  }
                ],
                "max_points": 35
              },
              {
                "key": "version_history",
                "name": "Version history",
                "detail": "32 published versions",
                "points": 20,
                "status": "met",
                "details": [
                  {
                    "code": "published_versions",
                    "params": {
                      "count": 32
                    }
                  }
                ],
                "max_points": 20
              },
              {
                "key": "not_deprecated",
                "name": "Not deprecated",
                "detail": "active, not deprecated or yanked",
                "points": 20,
                "status": "met",
                "details": [
                  {
                    "code": "package_not_deprecated",
                    "params": {}
                  }
                ],
                "max_points": 20
              }
            ]
          }
        ],
        "description": "Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?"
      },
      {
        "key": "engineering",
        "band": "moderate",
        "name": "Engineering Quality",
        "value": 65,
        "weight": 0.2,
        "metrics": [
          {
            "key": "engineering_practices",
            "band": "at_risk",
            "name": "Engineering practices",
            "note": null,
            "notes": [],
            "value": 48,
            "inputs": {
              "has_ci": true,
              "has_tests": true,
              "has_editorconfig": false,
              "has_linter_config": false,
              "has_precommit_config": false
            },
            "components": [
              {
                "key": "ci_workflows",
                "name": "CI workflows",
                "detail": "2 workflow(s)",
                "points": 24,
                "status": "met",
                "details": [
                  {
                    "code": "ci_workflows",
                    "params": {
                      "count": 2
                    }
                  }
                ],
                "max_points": 24
              },
              {
                "key": "tests_present",
                "name": "Tests present",
                "detail": null,
                "points": 24,
                "status": "met",
                "details": [],
                "max_points": 24
              },
              {
                "key": "linter_config",
                "name": "Linter config",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 16
              },
              {
                "key": "pre_commit_hooks",
                "name": "Pre-commit hooks",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 9.6
              },
              {
                "key": "editorconfig",
                "name": ".editorconfig",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 6.4
              },
              {
                "key": "openssf_scorecard_ci_tests",
                "name": "OpenSSF Scorecard: CI-Tests",
                "detail": "0 out of 13 merged PRs checked by a CI test -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 20
              }
            ]
          },
          {
            "key": "documentation",
            "band": "excellent",
            "name": "Documentation",
            "note": null,
            "notes": [],
            "value": 90,
            "inputs": {
              "topics": [
                "anthropic",
                "api-gateway",
                "gemini",
                "llm",
                "llm-proxy",
                "openai",
                "rust",
                "xai"
              ],
              "has_wiki": false,
              "homepage": "https://sanjay920.github.io/llmshim/",
              "has_readme": true,
              "has_docs_dir": true,
              "has_description": true
            },
            "components": [
              {
                "key": "readme",
                "name": "README",
                "detail": null,
                "points": 30,
                "status": "met",
                "details": [],
                "max_points": 30
              },
              {
                "key": "documentation_directory",
                "name": "Documentation directory",
                "detail": null,
                "points": 25,
                "status": "met",
                "details": [],
                "max_points": 25
              },
              {
                "key": "documentation_homepage_site",
                "name": "Documentation / homepage site",
                "detail": "https://sanjay920.github.io/llmshim/",
                "points": 15,
                "status": "met",
                "details": [],
                "max_points": 15
              },
              {
                "key": "repository_description",
                "name": "Repository description",
                "detail": null,
                "points": 10,
                "status": "met",
                "details": [],
                "max_points": 10
              },
              {
                "key": "topics",
                "name": "Topics",
                "detail": "8 topics",
                "points": 10,
                "status": "met",
                "details": [
                  {
                    "code": "topics_count",
                    "params": {
                      "count": 8
                    }
                  }
                ],
                "max_points": 10
              },
              {
                "key": "wiki",
                "name": "Wiki",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 10
              }
            ]
          }
        ],
        "description": "Are baseline engineering and documentation practices in place?"
      },
      {
        "key": "security",
        "band": "at_risk",
        "name": "Security",
        "value": 38,
        "weight": 0.16,
        "metrics": [
          {
            "key": "security_posture",
            "band": "at_risk",
            "name": "Security posture",
            "note": null,
            "notes": [],
            "value": 38,
            "inputs": {
              "source": "openssf_scorecard",
              "checks_evaluated": 18,
              "scorecard_version": "v5.5.0",
              "checks_inconclusive": 0,
              "scorecard_aggregate": 3.8
            },
            "components": [
              {
                "key": "binary_artifacts",
                "name": "Binary-Artifacts",
                "detail": "no binaries found in the repo",
                "points": 7.5,
                "status": "met",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "branch_protection",
                "name": "Branch-Protection",
                "detail": "branch protection not enabled on development/release branches",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "ci_tests",
                "name": "CI-Tests",
                "detail": "0 out of 13 merged PRs checked by a CI test -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 2.5
              },
              {
                "key": "cii_best_practices",
                "name": "CII-Best-Practices",
                "detail": "no effort to earn an OpenSSF best practices badge detected",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 2.5
              },
              {
                "key": "code_review",
                "name": "Code-Review",
                "detail": "Found 0/14 approved changesets -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "contributors",
                "name": "Contributors",
                "detail": "project has 0 contributing companies or organizations -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 2.5
              },
              {
                "key": "dangerous_workflow",
                "name": "Dangerous-Workflow",
                "detail": "no dangerous workflow patterns detected",
                "points": 10,
                "status": "met",
                "details": [],
                "max_points": 10
              },
              {
                "key": "dependency_update_tool",
                "name": "Dependency-Update-Tool",
                "detail": "no update tool detected",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "fuzzing",
                "name": "Fuzzing",
                "detail": "project is not fuzzed",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 5
              },
              {
                "key": "license",
                "name": "License",
                "detail": "license file detected",
                "points": 2.5,
                "status": "met",
                "details": [],
                "max_points": 2.5
              },
              {
                "key": "maintained",
                "name": "Maintained",
                "detail": "30 commit(s) and 3 issue activity found in the last 90 days -- score normalized to 10",
                "points": 7.5,
                "status": "met",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "packaging",
                "name": "Packaging",
                "detail": "packaging workflow detected",
                "points": 5,
                "status": "met",
                "details": [],
                "max_points": 5
              },
              {
                "key": "pinned_dependencies",
                "name": "Pinned-Dependencies",
                "detail": "dependency not pinned by hash detected -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 5
              },
              {
                "key": "sast",
                "name": "SAST",
                "detail": "SAST tool is not run on all commits -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 5
              },
              {
                "key": "security_policy",
                "name": "Security-Policy",
                "detail": "security policy file detected",
                "points": 5,
                "status": "met",
                "details": [],
                "max_points": 5
              },
              {
                "key": "signed_releases",
                "name": "Signed-Releases",
                "detail": "Project has not signed or included provenance with any releases.",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "token_permissions",
                "name": "Token-Permissions",
                "detail": "detected GitHub workflow tokens with excessive permissions",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "vulnerabilities",
                "name": "Vulnerabilities",
                "detail": "7 existing vulnerabilities detected",
                "points": 2.2,
                "status": "partial",
                "details": [],
                "max_points": 7.5
              }
            ]
          }
        ],
        "description": "Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure?"
      },
      {
        "key": "ai_readiness",
        "band": "good",
        "name": "AI Readiness",
        "value": 78,
        "weight": 0,
        "metrics": [
          {
            "key": "ai_agent_context",
            "band": "good",
            "name": "Agent context & guidance",
            "note": null,
            "notes": [],
            "value": 83,
            "inputs": {
              "has_llms_txt": false,
              "legible_history_share": 0.72,
              "agent_instruction_files": [
                "CLAUDE.md"
              ],
              "agent_instruction_max_bytes": 20920
            },
            "components": [
              {
                "key": "agent_instructions",
                "name": "Agent instructions",
                "detail": "CLAUDE.md",
                "points": 45,
                "status": "met",
                "details": [
                  {
                    "code": "file_list",
                    "params": {
                      "files": "CLAUDE.md"
                    }
                  }
                ],
                "max_points": 45
              },
              {
                "key": "machine_readable_docs_llms_txt",
                "name": "Machine-readable docs (llms.txt)",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 15
              },
              {
                "key": "legible_commit_history",
                "name": "Legible commit history",
                "detail": "72 of 100 human commits state their intent (structured subject or explanatory body)",
                "points": 38.4,
                "status": "partial",
                "details": [
                  {
                    "code": "legible_history",
                    "params": {
                      "legible": 72,
                      "sampled": 100
                    }
                  }
                ],
                "max_points": 40
              }
            ]
          },
          {
            "key": "ai_verify_loop",
            "band": "moderate",
            "name": "Verify loop (build / test / typecheck)",
            "note": null,
            "notes": [],
            "value": 66,
            "inputs": {
              "has_nix": false,
              "has_tests": true,
              "lockfiles": [
                "Cargo.lock",
                "package-lock.json"
              ],
              "has_dockerfile": true,
              "typed_language": true,
              "bootstrap_files": [],
              "has_devcontainer": false,
              "has_linter_config": false,
              "typecheck_configs": [
                "clients/typescript/tsconfig.json"
              ],
              "agent_commit_share": 0.58,
              "toolchain_manifests": [
                "Cargo.toml",
                "clients/go/go.mod"
              ],
              "dependency_bot_commit_share": 0
            },
            "components": [
              {
                "key": "one_command_bootstrap",
                "name": "One-command bootstrap",
                "detail": "Cargo.toml, clients/go/go.mod (toolchain convention, no task runner)",
                "points": 12.6,
                "status": "partial",
                "details": [
                  {
                    "code": "toolchain_convention",
                    "params": {
                      "files": "Cargo.toml, clients/go/go.mod"
                    }
                  }
                ],
                "max_points": 18
              },
              {
                "key": "automated_tests",
                "name": "Automated tests",
                "detail": null,
                "points": 22,
                "status": "met",
                "details": [],
                "max_points": 22
              },
              {
                "key": "lint_format_config",
                "name": "Lint / format config",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 11
              },
              {
                "key": "static_type_checking",
                "name": "Static type checking",
                "detail": "clients/typescript/tsconfig.json",
                "points": 11,
                "status": "met",
                "details": [
                  {
                    "code": "file_list",
                    "params": {
                      "files": "clients/typescript/tsconfig.json"
                    }
                  }
                ],
                "max_points": 11
              },
              {
                "key": "reproducible_environment",
                "name": "Reproducible environment",
                "detail": "Dockerfile, lockfile",
                "points": 10,
                "status": "met",
                "details": [
                  {
                    "code": "file_list",
                    "params": {
                      "files": "Dockerfile, lockfile"
                    }
                  }
                ],
                "max_points": 10
              },
              {
                "key": "demonstrated_agent_practice",
                "name": "Demonstrated agent practice",
                "detail": "58 of the last 100 commits agent-authored or agent-credited",
                "points": 10,
                "status": "met",
                "details": [
                  {
                    "code": "agent_authored_commits",
                    "params": {
                      "count": 58,
                      "sampled": 100
                    }
                  }
                ],
                "max_points": 10
              },
              {
                "key": "automated_maintenance",
                "name": "Automated maintenance",
                "detail": "no automated dependency updates observed",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "no_dependency_automation",
                    "params": {}
                  }
                ],
                "max_points": 8
              },
              {
                "key": "openssf_scorecard_pinned_dependencies",
                "name": "OpenSSF Scorecard: Pinned-Dependencies",
                "detail": "dependency not pinned by hash detected -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 10
              }
            ]
          },
          {
            "key": "ai_code_legibility",
            "band": "excellent",
            "name": "Code legibility for models",
            "note": null,
            "notes": [],
            "value": 99,
            "inputs": {
              "primary_language": "Rust",
              "largest_source_bytes": 2667011,
              "source_files_sampled": 83,
              "oversized_source_files": 2
            },
            "components": [
              {
                "key": "type_checkable_code",
                "name": "Type-checkable code",
                "detail": "Rust (statically typed)",
                "points": 45,
                "status": "met",
                "details": [
                  {
                    "code": "statically_typed_language",
                    "params": {
                      "language": "Rust"
                    }
                  }
                ],
                "max_points": 45
              },
              {
                "key": "manageable_file_sizes",
                "name": "Manageable file sizes",
                "detail": "2/83 source files over 60KB",
                "points": 53.7,
                "status": "partial",
                "details": [
                  {
                    "code": "oversized_source_files",
                    "params": {
                      "kb": 60,
                      "sampled": 83,
                      "oversized": 2
                    }
                  }
                ],
                "max_points": 55
              }
            ]
          },
          {
            "key": "ai_interfaces",
            "band": "good",
            "name": "Machine-readable interfaces",
            "note": null,
            "notes": [],
            "value": 80,
            "inputs": {
              "example_dirs": [
                "examples"
              ],
              "has_mcp_signal": false,
              "api_schema_files": [
                "api/openapi.yaml"
              ]
            },
            "components": [
              {
                "key": "api_schema_openapi_graphql_proto",
                "name": "API schema (OpenAPI/GraphQL/proto)",
                "detail": "api/openapi.yaml",
                "points": 40,
                "status": "met",
                "details": [
                  {
                    "code": "file_list",
                    "params": {
                      "files": "api/openapi.yaml"
                    }
                  }
                ],
                "max_points": 40
              },
              {
                "key": "mcp_server",
                "name": "MCP server",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 20
              },
              {
                "key": "runnable_examples",
                "name": "Runnable examples",
                "detail": "examples",
                "points": 40,
                "status": "met",
                "details": [
                  {
                    "code": "file_list",
                    "params": {
                      "files": "examples"
                    }
                  }
                ],
                "max_points": 40
              }
            ]
          }
        ],
        "description": "How well is the repo equipped to be developed and maintained with AI coding agents? An independent, experimental badge — weight 0.0, so it is surfaced on its own and does not affect the overall health score."
      }
    ],
    "metrics_version": "1.13.0"
  },
  "warnings": [
    "Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token",
    "GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository"
  ],
  "report_type": "repository",
  "generated_at": "2026-07-27T19:49:18.521443Z",
  "schema_version": "0.27.0",
  "badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/s/sanjay920/llmshim.svg",
  "full_name": "sanjay920/llmshim",
  "license_state": "standard",
  "license_spdx": "Apache-2.0"
}

Bewertungen sind Signale, keine Garantien. Sie spiegeln öffentlich sichtbare Praxis auf GitHub wider — kein Code-Audit und keine Sicherheitsgarantie.

Fehlende Daten werden ausgeschlossen und die Gewichte neu normiert, nie als null bewertet. Die Methodik ist versioniert und offen: Metriken v1.13.0, Schema v0.27.0 — vollständige Methodik · Metriken-Wiki.

Wie ein einzelnes Ergebnis im Gesamtregister steht: aggregierte Statistikencrates.io.