fundamental-research-labs/langdag erreicht einen Gesundheitsindex von 65 von 100 und liegt damit im Bereich Mittel. Am stärksten schneidet es bei Engineering Quality (81/100) ab, am schwächsten bei Security (48/100). Zuletzt vor 1 Tag aktualisiert. Ein einzelner Mitwirkender trägt den Großteil der jüngsten Arbeit.
65
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.
65
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)
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.
Dieses Repository wird von einer Organisation getragen — geteilte, rechenschaftspflichtige Trägerschaft, die jeden einzelnen Maintainer überdauern kann.
Liefert Releases aus — 28 Versions-Tags (keine GitHub-Releases)
36/36
Release-Aktualität — letztes Release vor 8 Tagen
27/27
Release-Rhythmus — ein Release etwa alle 12,7 Tage
0/10
OpenSSF Scorecard: Signed-Releases — keine Daten
Verwendete Eingangsdaten
releases_count
28
latest_release_tag
v0.10.0
releases_from_tags
ja
days_since_latest_release
8
mean_days_between_releases
12,7
Von der Bewertung ausgeschlossen (keine Daten oder nicht anwendbar): OpenSSF Scorecard: Signed-Releases. Die verbleibenden Gewichte wurden renormalisiert.
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.
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
Stern- und Fork-Verlauf 0 ★ / 4 ⇿
0Sterne
4Forks
13Releases
Wann jeder Stern und Fork hinzugefügt wurde, von GitHub erfasst und nach Tagen gruppiert. Das kumulierte Wachstum steht direkt über den täglichen Zugängen, aus denen es besteht, sodass beide gegeneinander lesbar sind: stetiger organischer Zuwachs sieht ganz anders aus als ein abrupter, kurzlebiger Ausschlag. Wo dieser Unterschied messbar ist, wird er als Wachstumsauthentizität ausgewiesen.
Major 0Minor 4Patch 9
OpenSSF Scorecard 4.8 / 10
4.8Gesamtwert
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 · 2026-07-24 12:32 UTC
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": [
"ai",
"cli",
"conversation",
"dag",
"langchain",
"langfuse",
"llm",
"prompt-engineering",
"prompt-management",
"self-hosted"
],
"is_fork": false,
"size_kb": 6214,
"has_wiki": true,
"homepage": "https://langdag.com",
"languages": {
"Go": 1357293,
"Shell": 10031,
"Python": 169695,
"Makefile": 847,
"Dockerfile": 741,
"TypeScript": 86475
},
"pushed_at": "2026-07-23T00:56:06Z",
"created_at": "2026-02-04T03:04:38Z",
"owner_type": "Organization",
"updated_at": "2026-07-21T19:17:28Z",
"description": "High-performance tool for managing LLM conversations and workflows as DAGs.",
"is_archived": false,
"is_disabled": false,
"license_spdx": "MIT",
"default_branch": "main",
"license_spdx_raw": "MIT",
"primary_language": "Go",
"significant_languages": [
"Go",
"Python"
]
},
"owner": {
"blog": "https://fundamentalresearchlabs.com/",
"name": "Fundamental Research Labs",
"type": "Organization",
"login": "fundamental-research-labs",
"company": null,
"location": null,
"followers": 8,
"avatar_url": "https://avatars.githubusercontent.com/u/271597406?v=4",
"created_at": "2026-03-27T18:05:03Z",
"is_verified": null,
"public_repos": 7,
"account_age_days": 118
},
"license": {
"state": "standard",
"spdx_id": "MIT",
"raw_spdx": "MIT",
"file_present": true,
"scorecard_found": true,
"profile_has_license": true
},
"activity": {
"releases": [
{
"tag": "v0.10.0",
"kind": "minor",
"published_at": "2026-07-16T07:35:45Z"
},
{
"tag": "v0.9.0",
"kind": "minor",
"published_at": "2026-05-21T17:49:59Z"
},
{
"tag": "v0.8.3",
"kind": "patch",
"published_at": "2026-04-13T00:44:19Z"
},
{
"tag": "v0.8.2",
"kind": "patch",
"published_at": "2026-04-12T17:51:14Z"
},
{
"tag": "v0.8.1",
"kind": "patch",
"published_at": "2026-04-10T19:08:53Z"
},
{
"tag": "v0.8.0",
"kind": "minor",
"published_at": "2026-04-02T05:20:21Z"
},
{
"tag": "v0.7.0",
"kind": "minor",
"published_at": "2026-03-28T01:39:16Z"
},
{
"tag": "v0.6.4",
"kind": "patch",
"published_at": "2026-03-24T19:47:48Z"
},
{
"tag": "v0.6.3",
"kind": "patch",
"published_at": "2026-03-23T23:47:09Z"
},
{
"tag": "v0.6.2",
"kind": "patch",
"published_at": "2026-03-23T22:01:03Z"
},
{
"tag": "v0.6.1",
"kind": "patch",
"published_at": "2026-03-21T18:41:05Z"
},
{
"tag": "v0.6.0",
"kind": "minor",
"published_at": "2026-03-21T00:57:14Z"
},
{
"tag": "v0.5.10",
"kind": "patch",
"published_at": "2026-03-21T00:57:14Z"
},
{
"tag": "v0.5.9",
"kind": "patch",
"published_at": "2026-03-21T00:47:22Z"
},
{
"tag": "v0.5.8",
"kind": "patch",
"published_at": "2026-03-17T21:57:50Z"
},
{
"tag": "v0.5.7",
"kind": "patch",
"published_at": "2026-03-16T17:15:45Z"
},
{
"tag": "v0.5.6",
"kind": "patch",
"published_at": "2026-03-16T16:14:28Z"
},
{
"tag": "v0.5.5",
"kind": "patch",
"published_at": "2026-03-13T19:23:11Z"
},
{
"tag": "v0.5.4",
"kind": "patch",
"published_at": "2026-03-12T22:36:33Z"
},
{
"tag": "v0.5.3",
"kind": "patch",
"published_at": "2026-03-11T18:12:08Z"
},
{
"tag": "v0.5.2",
"kind": "patch",
"published_at": "2026-03-11T16:36:39Z"
},
{
"tag": "v0.5.1",
"kind": "patch",
"published_at": "2026-03-10T16:42:41Z"
},
{
"tag": "v0.5.0",
"kind": "minor",
"published_at": "2026-03-10T01:51:32Z"
},
{
"tag": "v0.4.0",
"kind": "minor",
"published_at": "2026-03-09T23:09:36Z"
},
{
"tag": "v0.3.0",
"kind": "minor",
"published_at": "2026-03-09T21:25:36Z"
},
{
"tag": "v0.2.0",
"kind": "minor",
"published_at": "2026-03-09T18:15:42Z"
},
{
"tag": "v0.1.1",
"kind": "patch",
"published_at": "2026-03-05T19:23:19Z"
},
{
"tag": "v0.1.0",
"kind": "minor",
"published_at": "2026-03-05T18:22:03Z"
}
],
"recent_commits": [
{
"oid": "5c34041403f52d25ec6e8bce998d9c28ab34c061",
"body": null,
"is_bot": false,
"headline": "Sync embedded model catalog for release (#30)",
"author_name": "Gaetan de Villele",
"author_login": "gdevillele",
"committed_at": "2026-07-16T07:35:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "77130f41bac33fbadd1458cbd408f6988027140b",
"body": null,
"is_bot": false,
"headline": "Add OpenAI GPT-5.6 compatibility (#18)",
"author_name": "Gaetan de Villele",
"author_login": "gdevillele",
"committed_at": "2026-07-15T23:35:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d9d4047efee9dae14a04824c976dee7acddbde33",
"body": null,
"is_bot": false,
"headline": "Use Anthropic Models API for catalog refresh (#29)",
"author_name": "Adrian Duermael",
"author_login": "aduermael",
"committed_at": "2026-06-13T17:53:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "86cb48194cd228a08de62aadbebf0eea7dfff7f4",
"body": "* fm serve api doc\n\n* Add Apple Foundation Models provider\n\n* Normalize Apple tool schemas",
"is_bot": false,
"headline": "Add Apple Foundation Models provider (#28)",
"author_name": "Adrian Duermael",
"author_login": "aduermael",
"committed_at": "2026-06-09T23:58:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7e42e4112889608c8bd09c087edb086b70b955bd",
"body": null,
"is_bot": false,
"headline": "Stream completed tool calls from done response (#27)",
"author_name": "Adrian Duermael",
"author_login": "aduermael",
"committed_at": "2026-05-21T17:49:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "343fefbd87b422d5722602c0a7ccd501ffe48056",
"body": null,
"is_bot": false,
"headline": "fix OpenAI Responses assistant replay (#26)",
"author_name": "Adrian Duermael",
"author_login": "aduermael",
"committed_at": "2026-05-20T20:58:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "297b835d185a511bac8c65176de725404755d9b0",
"body": null,
"is_bot": false,
"headline": "support OpenAI Responses protocol routing (#25)",
"author_name": "Adrian Duermael",
"author_login": "aduermael",
"committed_at": "2026-05-20T18:12:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7c879345b32d6d667c54a83d58d20043272b9ebc",
"body": null,
"is_bot": false,
"headline": "Refresh model catalog generation (#24)",
"author_name": "Adrian Duermael",
"author_login": "aduermael",
"committed_at": "2026-05-19T21:59:04Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f0dba8ea8dbb38cf381f03e30577c1737cabbf0a",
"body": null,
"is_bot": false,
"headline": "Expose prompt tools and output groups (#23)",
"author_name": "Adrian Duermael",
"author_login": "aduermael",
"committed_at": "2026-05-19T04:48:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9090fb299f56b9e522d24087a72bc9d508d82422",
"body": "* 0: Lock langdag compatibility fixtures\n\n* 1: Define deployment-aware model contracts\n\n* 2: Make catalog deployment-aware\n\n* 3: Preserve usage pricing and served identity\n\n* 4: Bind deployments to model routing\n\n* 5: Publish refreshable model catalog\n\n* 8a-8c: Add deployment rollout tests and docs\n\n[…]\npre-commit hook\n\n* Make Pages version injection tag-aware\n\n* Integrate runtime catalog refresh with publishing model\n\n* Use published catalog as build-time source\n\n* Keep embedded catalog release-safe",
"is_bot": false,
"headline": "Add deployment-aware model catalog and runtime routing (#20)",
"author_name": "Adrian Duermael",
"author_login": "aduermael",
"committed_at": "2026-05-18T22:59:53Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "2edb26520786a1e8157cbcea99bfe0d45b1d2f91",
"body": null,
"is_bot": false,
"headline": "Use GitHub App token for catalog publishing (#22)",
"author_name": "Adrian Duermael",
"author_login": "aduermael",
"committed_at": "2026-05-18T19:11:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3e3e63d252ba3d1e59d46cddd15de23f5bb9ee02",
"body": null,
"is_bot": false,
"headline": "Add model catalog source-of-truth workflow (#21)",
"author_name": "Adrian Duermael",
"author_login": "aduermael",
"committed_at": "2026-05-18T18:05:44Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d5259a1bac774384031d31bbfb791a56781d2150",
"body": "* feat: add OpenRouter provider\n\n- Add OpenRouterProvider with dynamic model fetching from /models API\n with mutex-cached results and required HTTP-Referer + X-Title headers\n on every request (including model discovery)\n- Wire up in server.go providerRegistry after grok\n- Add OPENROUTER_API_KEY / \n[…]\n\n- Use strings.TrimSpace on error bodies for consistent formatting\n- Refactor TestOpenRouterRequiredHeaders to use Complete() instead of\n calling doRequest() directly for consistency with other tests",
"is_bot": false,
"headline": "feat: add OpenRouter provider (#5)",
"author_name": "Lakshman Patel",
"author_login": "Patel230",
"committed_at": "2026-05-02T17:28:05Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "456b5ed963d20188ccae63dd9b7c0016ce9b2cf4",
"body": "* fix Gemini SSE streaming: concat per-chunk text deltas\n\nThe parser assumed each chunk's parts[].text was a cumulative snapshot,\ntracking the longest seen and emitting only the suffix beyond it. The\nreal Gemini streamGenerateContent API sends incremental deltas per chunk:\nshort deltas were silently\n[…]\ner, mismatched garbled\nfragments) when run against the previous SSE parser.\n\nCo-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.7 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix Gemini SSE streaming: concat per-chunk text deltas (#17)",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-27T17:07:35Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "103a5b9f9113c5b3f016afd94ac4aa68f21ff0b4",
"body": "* gemini: gate model features via a per-model caps table\n\nThe Google AI Studio API rejects different combinations of fields per\nmodel with different error messages — Gemma 3 (1B/4B/12B/27B) rejects\nfunction calling, thinkingBudget, and the google_search server tool;\nGemma 4 (26B MoE / 31B) accepts f\n[…]\n let requests pass. The public\nsurface and the request path would disagree.\n\nCo-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.7 <noreply@anthropic.com>",
"is_bot": false,
"headline": "gemini: gate model features via a per-model caps table (#16)",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-27T17:03:33Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "733facaa108edc5e1ef1e9f0fc38fae21abcb545",
"body": "Adds gpt-5.5-2026-04-23 ($5/$30 per 1M) and gpt-5.5-pro-2026-04-23\n($30/$180 per 1M) with a 1,050,000-token context window and web_search\nserver tool. Pricing and spec data sourced from\ndevelopers.openai.com/api/docs/pricing and the per-model docs pages.\n\nReleased 2026-04-23, available in the API 2026-04-24.\n\nCo-authored-by: Claude Opus 4.7 <noreply@anthropic.com>",
"is_bot": false,
"headline": "Add GPT-5.5 to embedded catalog (#14)",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-24T23:18:55Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "4965a67c6343e4fa6853e047906a52e5fbcc96be",
"body": "Pricing, context window, and max output match the Anthropic docs page.\nFresh installs and offline fallbacks now see Opus 4.7 without waiting\nfor the runtime catalog fetch.",
"is_bot": false,
"headline": "add claude-opus-4-7 to embedded catalog (#13)",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-22T18:48:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "834469d20ad2e95a58c18f9df2e78dfaf90ed598",
"body": "Extend and harden transient error detection",
"is_bot": false,
"headline": "Merge pull request #12 from aduermael/extend-transient-error-detection",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-13T00:44:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "df24a4f67d150f07083e709cf2c43274e3b26258",
"body": "Connection refused, connection reset, timeout, temporary failure, and\nbroken pipe checks now use the lowercased message, consistent with the\nexisting rate limit and TLS handshake checks.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix isTransient: make all network/transport checks case-insensitive",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T21:44:05Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "a64a8bda956923cca924736d486806c9ef3be20a",
"body": "…add wrapped EOF tests\n\n- Add containsStatusCode helper that requires numeric codes to be bounded\n by non-digit characters, fixing false positives like \"50032\" matching \"500\"\n- Narrow \"overloaded\" check to suffix match + \"overloaded_error\" to avoid\n matching unrelated messages like \"circuit overloaded in module X\"\n- Add wrapped io.EOF/io.ErrUnexpectedEOF edge-case tests (errors.Is path)\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix isTransient: digit-bound status codes, tighten overloaded match, …",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T21:33:45Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "b5d20b0cf934e8c1874db2b6301d64066a529ed0",
"body": "…rop \"no such host\"\n\n- Replace broad \"EOF\" substring match with errors.Is(err, io.EOF/ErrUnexpectedEOF)\n- Make \"tls handshake\" detection case-insensitive, consistent with other checks\n- Remove \"no such host\" — DNS failures are typically permanent\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix isTransient: use errors.Is for EOF, case-insensitive TLS match, d…",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T21:21:23Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "47868ce7ded20098f86e9f50bd5784812b42df01",
"body": "Add detection for HTTP 529 (Anthropic overloaded), \"overloaded\" (case-\ninsensitive), \"EOF\", \"broken pipe\", \"TLS handshake\", and \"no such host\".\nMake \"rate limit\" matching case-insensitive. These patterns were previously\nhandled by herm's isRetryableError and are needed to maintain retry coverage\nwhen herm delegates retry logic to langdag.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "extend isTransient to cover additional transient error patterns",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T21:04:09Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "54a81a9b715a742105c361d14d055e05ac584279",
"body": "fix Gemini streaming: capture finishReason from SSE stream",
"is_bot": false,
"headline": "Merge pull request #11 from aduermael/fix/gemini-streaming-stop-reason",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T17:51:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "820e3c604dc55f464c2ffdfd78646cb12bd2339f",
"body": "parseSSEStream never read the candidate's finishReason, so the\nStopReason on the final CompletionResponse was always empty. This\nprevented the max_tokens continuation logic from detecting truncated\nresponses (e.g. Gemma returning only 12 output tokens).\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix Gemini streaming: capture finishReason from SSE stream",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T17:42:41Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "d14b3f47d05adb0ec0c4d777707efe5d64712037",
"body": "Gitignore entire .claude directory",
"is_bot": false,
"headline": "Merge pull request #10 from aduermael/merge-all-google-v2",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T17:04:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c04067d4f612b8988aeb908fc0971acd3c48468b",
"body": "Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "gitignore entire .claude directory",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T17:02:54Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "c43b62eb6dbb72dbe64dd8d3ffe5dc2c67fc7054",
"body": "Merge Gemma provider into Gemini",
"is_bot": false,
"headline": "Merge pull request #9 from aduermael/merge-all-google",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T16:51:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a380695689f46b3341c15792cdd824b993b94134",
"body": "…factory\n\n- Remove GEMMA_API_KEY and Gemma config field entirely; GEMINI_API_KEY is\n the only env var for Google AI Studio (matches Google's standard).\n- Extract shared newGeminiProvider helper in server.go to eliminate the\n duplicated \"gemini\"/\"gemma\" factory closures.\n- Port all 9 original Gemma\n[…]\nage: adds\n SimpleStream, ToolCall, ToolCallStream, MultiTurnToolUse,\n ConsecutiveToolCalls, and LargeContext alongside the 3 already present.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "standardize on GEMINI_API_KEY, add all Gemma live tests, deduplicate …",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T16:32:51Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "f0a0fc17ecf2b657fc6bb3904b6dd3a18eda2e7b",
"body": "Both providers share the same Google AI Studio endpoint and wire protocol.\nGemma's protocol.go was a strict subset of Gemini's (~85% identical code).\nThis eliminates ~1,020 lines of duplication by routing Gemma models through\nGemini's superset protocol, which handles the extra fields (function call\n\n[…]\nBackward compatibility preserved: \"gemma\" accepted as provider alias,\nGEMMA_API_KEY accepted as env var fallback, --provider gemma still works.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "merge Gemma provider into Gemini provider",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T15:40:00Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "41c456f9f009d450d601d1c3d55e7bb601e19cdc",
"body": "Gemini 3.x support, live test suites, and shutdown date filtering",
"is_bot": false,
"headline": "Merge pull request #8 from aduermael/gemma-live-tests",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T15:39:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "678f2c042ee8ff1fc6955f5d852ca7a656d86c83",
"body": "gemini-3-flash-preview can take 25-35s per call, causing 30s timeouts\nto fail on ToolCallStream and ConsecutiveToolCalls.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "increase timeouts for Gemini live tests that hit slow models",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T07:35:03Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "57e5f71048b6ee3eee93e0619d172ae59deb59a7",
"body": "FetchLatest now fetches the Gemini deprecations page concurrently\nand excludes any model that has an announced shutdown date.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "filter out Gemini models with announced shutdown dates",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T07:02:51Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "0fe2b4c2646e4385c31b20e79b26ce358d710b3d",
"body": null,
"is_bot": false,
"headline": "update catalog",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T07:00:55Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d28b417f925f1645b11aea50f2c6f0b1e785bc90",
"body": "Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "remove all Gemini 2.x model references, update to 3.x only",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T06:04:23Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "d8e0c149e6e3647b7bc94b57dc28d3a1db9dae31",
"body": "- Add RetryAfterError interface to retry.go; use max(serverDelay,\n computedBackoff) in both Complete and Stream retry loops so\n provider-reported Retry-After hints are respected\n- Add Thought field to Gemini part struct and filter thought parts\n in convertResponse and parseSSEStream, matching Gemma's behavior\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "honor server-suggested retry delays and filter Gemini thought parts",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T03:52:38Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "c4318b74cbc1cdfc16f671a92c294801d6602353",
"body": "…dd ToolConfig for server-side tools\n\n- Update model list from shutdown 2.0/2.5 to active Gemini 3.x models\n- Add structured apiError with RetryAfter() for retry delay support\n- Parse Google RetryInfo from 429 response bodies and Retry-After headers\n- Add ToolConfig with IncludeServerSideToolInvocations when server-side\n tools (e.g. google_search) are present alongside function declarations\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix Gemini provider: update models to 3.x, add retry-after parsing, a…",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T03:43:06Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "5fd02837291f90f93896c63f75caf6fc047ef4e0",
"body": "Gemini 3.x requires thought_signature to be echoed back on function\ncall parts in multi-turn tool use, and includes unique IDs on function\ncalls/responses. Without this, the API returns a 400 error.\n\nChanges:\n- Add ProviderData field to ContentBlock for opaque round-trip data\n- Capture thoughtSignat\n[…]\nni responses\n- Restore them when building requests via callNames ID→name map\n- Update live tests to target Gemini 3.x models and cover thinking\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "support Gemini 3.x thought signatures and function call IDs",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T03:42:35Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "39841de8d049ab04ebd7212982b857a1cafa242c",
"body": "Mirrors the Gemma live test suite with Gemini-specific adaptations:\nGEMINI_API_KEY env var, gemini-2.0-flash default model, explicit\nthinking test uses gemini-2.5-pro. All tests skip when key is unset.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "add live API test suite for Gemini provider",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T03:42:35Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "a94afad9bf8e1605a288c2011ee9c41b158031ce",
"body": "The model returns 400 when thinkingBudget is set, but does report\nthoughtsTokenCount in normal responses. Split into subtests that\nverify both behaviors.",
"is_bot": false,
"headline": "fix thinking tests: gemma-4-31b-it rejects explicit thinkingBudget",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T03:42:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9ca4deb07b8626bfbfe136e1fdb8b91ddfc4d0d7",
"body": "Tests require GEMMA_API_KEY env var; skip automatically when unset.\n\nCovers: basic complete/stream, tool calling (with and without text),\nmulti-turn tool use, thinking mode, large context sizes, and\nparallel tool call batching.",
"is_bot": false,
"headline": "add live API test suite for Gemma provider",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-12T03:42:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "99e3f9a1e9620b0e79b736203abfdb4f8dff5b3a",
"body": "Add retry callbacks and server-suggested retry delays for Gemma/Gemini",
"is_bot": false,
"headline": "Merge pull request #7 from aduermael/add-gemma-4-support",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-11T16:59:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d1f6bc27a19faa3b240e2657927b4fc303db0a54",
"body": "- Add RetryEvent, ContextWithRetryCallback for per-call retry notifications\n via context (allows callers like herm to show retry status in their UI)\n- Add RetryAfterError interface and retryDelay that uses server-suggested\n delays with jitter, falling back to exponential backoff\n- Add OnRetry call\n[…]\ne\n- Add apiError with RetryAfter() to Gemma and Gemini providers, parsing\n both Retry-After HTTP header and Google RetryInfo JSON body on 429s\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "add retry callback mechanism and server-suggested retry delays",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-11T05:52:31Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "48f85c7606c40032952e1d15c86f8895abce6da5",
"body": "add gemma provider",
"is_bot": false,
"headline": "Merge pull request #6 from aduermael/add-gemma-4-support",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-10T19:08:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0cbb2db997d99a90b7f7c56ab553d59d9db360d6",
"body": "Gemma 4 returns thinking/reasoning as response parts with thought=true.\nWithout filtering these, the chain-of-thought leaks into the displayed\nresponse instead of the actual answer.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: filter thinking parts from Gemma response",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-10T09:24:21Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "a78868b3fab3b78fb62c418507c788c269a0dd93",
"body": "The Google AI Studio API returns a 400 error when built-in tools like\ngoogle_search are mixed with function calling without setting\ntool_config.include_server_side_tool_invocations to true.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: enable server-side tool invocations in Gemma requests",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-10T09:21:17Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "6a5168fd131d259272c8e95c8470861ae3c921f8",
"body": "The embedded catalog.json and fetchGemmaModels had bare IDs like\n\"gemma-4\" which don't exist in Google AI Studio. Use the correct\ninstruction-tuned identifiers (e.g. gemma-4-31b-it) and add the\ngemma-4-26b-a4b-it MoE variant.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix Gemma model IDs in catalog and fetch logic",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-10T09:17:56Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "d85263f6a7c1ca59dca8f4bc86f0a33fc7ea99b0",
"body": "Use correct instruction-tuned model identifiers (e.g. gemma-4-31b-it\ninstead of gemma-4). Add gemma-4-26b-a4b-it (MoE variant). Fix Gemma 4\ncontext window from 1M to 256K per the model card.\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix Gemma model IDs to match Google AI Studio API",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-10T09:11:12Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "cd9e21790b74c2aabbd68c4b40fd1e467ad56a6c",
"body": "Mirror the gemini provider package as gemma, sharing the Google AI\nStudio endpoint. Wire the new provider through langdag.go config,\ninternal/api/server, internal/config, internal/cli/models, and the\nembedded model catalog (gemma-3 family + gemma-4).\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "add gemma provider",
"author_name": "Gaëtan de Villèle",
"author_login": "gdevillele",
"committed_at": "2026-04-10T07:56:23Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "4348ff99dd372ea33e2624d3d3cd8571f5f8ad7d",
"body": "Document intentional divergences for malformed delta JSON and unknown\nevent types in SSE_FORMAT.md. Add explicit tests in each SDK verifying\nits specific behavior: Go forwards unknown events and emits malformed\ndeltas with empty content, Python wraps malformed JSON and skips\nunknown events, TypeScript throws SSEParseError for both.",
"is_bot": false,
"headline": "12d: document and test cross-SDK divergences",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-02T05:20:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "fe1fa6954c012ad4089a691bbfda733979193948",
"body": "Add error_message and error_after_chunks to mock config (env vars\nLANGDAG_MOCK_ERROR_MESSAGE, LANGDAG_MOCK_ERROR_AFTER_CHUNKS). Add E2E\ntests for immediate error and mid-stream error modes in Go, Python,\nand TypeScript SDKs. New test-e2e-errors.sh starts 3 servers (echo,\nerror, stream_error) and runs all SDK E2E tests against them.",
"is_bot": false,
"headline": "12c: add E2E streaming error tests across all 3 SDKs",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-02T05:15:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ca7fb86923a05f787313315b60b1d6f354fbfe83",
"body": "Define degradation contract: all SDKs must complete iteration, preserve\ncontent, and signal abnormal state when stream ends without done event.\nTests cover no-done, error-termination, empty-response, and I/O error.",
"is_bot": false,
"headline": "12b: add graceful degradation contract and cross-SDK tests",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-02T05:00:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "805d55fa13c5fd564369b272c1c263a44a0c9e56",
"body": "Document exact SSE wire format in sdks/SSE_FORMAT.md. Add identical\nfixture strings (normal, error-mid-stream, multi-line-error, error-only)\ntested in all 3 SDKs to verify parsing consistency.",
"is_bot": false,
"headline": "12a: add SSE format contract and cross-SDK consistency tests",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-02T04:57:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "37147a51b2479546ea9fee29836c6e170c65e963",
"body": "Verified existing test, added descriptive message check,\nstreaming continuation path (node.promptStream), and\nundefined body edge case. All guarded by requestStream().",
"is_bot": false,
"headline": "11e: extend Response.body null tests in TypeScript SDK",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-02T04:39:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ddc51698650a7d781e1226b86cc6c00538e8a1a5",
"body": "Parser-level: reader error mid-stream and on first read both\npropagate through async generator. Stream-level: events()\nthrows, node() rejects, content preserved via stream.content.\nErrors are raw Error (not NetworkError) — matches Go SDK.",
"is_bot": false,
"headline": "11d: test fetch failure during streaming in TypeScript SDK",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-02T04:39:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "45bc57a621dacc35954c01ac020e23f6bfe76978",
"body": "Six split scenarios: mid-\\n\\n, mid-data:, mid-event:,\nmid-UTF8 multibyte char, single-byte-at-a-time, and\nmid-JSON. TextDecoder stream mode handles partial UTF-8;\nbuffer accumulation handles all other boundary splits.",
"is_bot": false,
"headline": "11c: test chunked SSE delivery edge cases in TypeScript SDK",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-02T01:46:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d7171202154eadaff787d03bb0f587bcfb004b95",
"body": "Tests verify error event yielded, content preserved via\nstream.content, node() throws when no done follows error.\nAlso tests error-after-done edge case (node() still works).",
"is_bot": false,
"headline": "11b: test provider error mid-stream in TypeScript SDK",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-02T00:37:46Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "80f2a3cd51cbce1f5c2334ee2c4d7b4792888b0f",
"body": "Added public `content` getter to Stream class — previously\ncollectedContent was private and inaccessible after failed\nstreams (same gap as Go SDK Phase 9). Tests verify node()\nthrows SSEParseError while content remains accessible.",
"is_bot": false,
"headline": "11a: add Stream.content getter, test SSE stream without done event",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-02T00:36:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5a6f958b0f457d5bf66ef2e9efe6f512b2e3628c",
"body": "Both clients complete iteration without hanging when stream ends\nwithout a done event. Content from deltas remains accessible.\nParser-level tests verify the same behavior.",
"is_bot": false,
"headline": "10a: test SSE stream without done event — sync and async",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-02T00:02:02Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1e56e59f3b3c29c3fe1ce34f8306fc425723e646",
"body": "5 concurrent PromptStream requests with unique content per stream.\nVerified: each stream gets its own events, no content mixing, no\nduplicate content, no races (passes -race). No bugs found.",
"is_bot": false,
"headline": "9e: test concurrent streaming — no shared state corruption",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T23:50:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8ab548ac1a22794171c344765a9ac56999e83bf0",
"body": "Mock HTTP server hijacks and closes connection after partial SSE.\nBoth mid-stream (between events) and mid-event (mid-line) drops\ndetected without hang. Content preserved, Node() returns error.",
"is_bot": false,
"headline": "9d: test connection drop mid-stream and mid-event",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T23:27:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d795f0743b4762d771a5c30d3295c955d350c0a4",
"body": "HTTP 500 before streaming → *APIError (status 500, server message).\nHTTP 200 with SSE error event → *StreamError (event message).\nBoth produce correct typed errors. No bugs found.",
"is_bot": false,
"headline": "9c: test HTTP 5xx vs SSE error differentiation",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T22:47:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1b1c3e4e51a211bd5c06b7cec9e249640ee29e21",
"body": "Malformed delta JSON is silently ignored (Content stays empty) — valid\ndeltas still accumulate correctly. Verified as intentional: no stream\nerror for per-event parse failures, only for connection/protocol errors.",
"is_bot": false,
"headline": "9b: test malformed JSON among valid deltas, verify Err() method",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T22:09:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3ec280a9784a36b13c86c72fea985fddabc4f2e0",
"body": "Added content accumulation in Stream.read() and Content()/Err() methods.\nTests verify: no-done returns StreamError with content preserved,\nabrupt close doesn't hang, content accessible after incomplete stream.",
"is_bot": false,
"headline": "9a: add Content() and Err() to Stream, test stream-without-done",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T22:08:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5e9290abaa925cdf042a886f763da8b6165d7826",
"body": "Bug: error messages containing newlines broke SSE format — raw\nnewlines split the data field, causing the SSE parser to see only\nthe first line. Fix: writeSSEError helper writes each line with its\nown \"data:\" prefix per the SSE spec. Also added nil-check for\nStreamEventError.Error to prevent panic on malformed events.",
"is_bot": false,
"headline": "8f: fix SSE error events truncating multi-line error messages",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T22:02:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9ce4f0090a5a8793089b17511b69ad925996a3ec",
"body": "Tests: empty X-API-Key header, malformed Bearer tokens (trailing\nspace, no space, Basic scheme, wrong key), health endpoint bypasses\nauth with wrong credentials, no-config means all endpoints open.",
"is_bot": false,
"headline": "8e: add auth edge case tests",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T22:01:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "12b64597dbfbd422753d5897b0b7a32903d0773f",
"body": "Tests: empty body (nil), missing message field, 1MB+ message (no\nserver limit), streaming request with empty body. All return\nappropriate 400 status with descriptive error messages.",
"is_bot": false,
"headline": "8d: add invalid request validation tests",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T21:54:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9b084e35214534d4ec0f0d642a2d2636185583de",
"body": "Two tests: (1) Stream() returns error → HTTP 500 JSON with original\nerror context, (2) mid-stream StreamEventError → collectEvents\nreturns error → HTTP 500 JSON with error message.",
"is_bot": false,
"headline": "8c: add non-streaming error response tests",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T21:52:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "318dbb9979108b3a6253d25c80c825a0255dfeae",
"body": "Verifies that when Stream() returns error, API sends SSE error event\n(not JSON 500) since Content-Type: text/event-stream is already set.\nNo start or done events emitted.",
"is_bot": false,
"headline": "8b: add provider failure during streaming test",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T21:50:29Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f30a764b72cd34bb9e9a952835d7ccab7356b823",
"body": "Test verifies SSE stream with mock stream_error mode: start event,\n3 delta chunks, error event with provider message, then done event\nwith saved partial content node.",
"is_bot": false,
"headline": "8a: add streaming error mid-response test for API server",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T21:38:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "16df94be2c616117998c7b240d95adfb5cf513ea",
"body": null,
"is_bot": false,
"headline": "4c: add filter tests for unknown model, empty model ID, and stream path",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T07:10:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "07c9436df2ae8e5e916e006f1f6365085dba47d0",
"body": "Tests context cancellation during backoff sleep (exits fast),\nMaxRetries=1 semantics (2 total attempts), deep error wrapping\n(3+ levels), and isTransient() edge cases including false\npositives from substring matching.",
"is_bot": false,
"headline": "4b: add retry edge case tests",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T04:47:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "60ae7188611a74ecdea8a1b599f699a163d2bbe2",
"body": "Tests Router.Complete() and Stream() under concurrent load (50\ngoroutines) with -race. Verifies fallback behavior difference\nbetween context cancellation (fast fail) and transient error\n(fallback succeeds).",
"is_bot": false,
"headline": "4a: add router concurrent access and context cancellation tests",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T04:35:00Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "92ad99cedf3ffd17d558512a400412b65ffc85da",
"body": "Test multiple orphans on different nodes, duplicate tool_use IDs,\ncross-branch tool_result (only ancestor-path results should count),\nand synthetic injection on multiple nodes. All edge cases handled\ncorrectly — no panics or DB corruption.",
"is_bot": false,
"headline": "3e: test orphaned tool_use edge cases",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T04:16:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9756d67d450b3cf0373b122f0e9dc37e0ef94682",
"body": "Test exact budget boundary (cumulative == budget stops), one-below\nboundary, default budget multiplier (4x), provider failure during\ncontinuation (graceful fallback to last saved node), and max_tokens\nwith empty content (both with and without prior saved continuation).",
"is_bot": false,
"headline": "3d: test output group budget boundary conditions",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T04:15:00Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "98391bf285e1849dc6d69cead5e69878cf03927e",
"body": "Test buildMessages() with plain text, unknown block types, empty/null\ncontent, large content (>1MB), broken JSON arrays, and special chars.\n\nBug found: contentToRawMessage used fmt.Sprintf(\"%q\") which produces\nGo-style escapes (\\x00) instead of JSON-valid escapes (\\u0000).\nFixed by using json.Marshal for string encoding.",
"is_bot": false,
"headline": "3c: test malformed content in buildMessages, fix null byte bug",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T04:09:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "03807bde4cae914b6e249163ac1c5758fdd509ab",
"body": "Test CreateNode failure during continuation (second assistant node\nfails after first saves) and first-call failure. Verify error events\nemitted, no hangs, no spurious NodeSaved events.",
"is_bot": false,
"headline": "3b: test database failure mid-stream during continuation",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T03:54:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f2e2d8f943306d4eda454ba87c6b827b6ed98c86",
"body": "Test that provider-level errors (Stream() returning error) propagate\ncorrectly through Prompt() and PromptFrom(). Also test mid-stream\nStreamEventError forwarding and channel cleanup.",
"is_bot": false,
"headline": "3a: test Provider.Stream() error propagation in conversation",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T03:52:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0a235fc295712ca5cbcbf803d40ecdd892f9803f",
"body": "Test convertResponsesMessages with malformed JSON, empty arrays, unknown\nblocks, ContentJSON priority. Test convertResponsesResult with empty\noutput, unknown types, nil usage, empty text, no-argument function calls.\nTest parseResponsesSSEStream with malformed JSON, empty stream, missing\ncompleted event, args delta without prior item, read errors, [DONE]\nsentinel, nil response in completed, non-data lines.",
"is_bot": false,
"headline": "2d: add Grok/Responses API error branch tests",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T03:39:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "96170e0d6f6bc81c25b0c01b895fb16d1f5fb78b",
"body": "Test convertMessages with malformed JSON, empty arrays, unknown blocks,\nnil function args, non-JSON function responses, missing image data.\nTest convertResponse with no candidates, empty content, safety filter,\nnil usage, nil function args.\nTest parseSSEStream with malformed JSON, no candidates, empty stream,\nempty content, read errors, non-data lines.",
"is_bot": false,
"headline": "2c: add Gemini protocol error branch tests",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T03:33:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8a468f97b7ccc4bd46966f63c9207e0200f99996",
"body": "Test convertMessages with malformed JSON, empty arrays, unknown blocks,\nempty function names, image/document edge cases.\nTest convertResponse with empty choices, nil usage, nil content.\nTest parseSSEStream with malformed JSON, non-data lines, [DONE]\nmid-stream, empty deltas, no choices, read errors, empty streams,\nmissing [DONE] sentinel.",
"is_bot": false,
"headline": "2b: add OpenAI protocol error branch tests",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T03:29:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b1d5d9d8c4436fbe0dcfff881593aacbf681ddf2",
"body": "Test convertMessages with malformed JSON, empty arrays, unknown block\ntypes, string/null tool_use input, mixed known/unknown blocks.\nTest processStreamEvents with mid-close, unknown block types, stream\nerrors, partial content errors, and missing message_start.",
"is_bot": false,
"headline": "2a: add Anthropic protocol error branch tests",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T03:09:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9c052633e3c1621e8856cd40884ffcde508fc975",
"body": "…mate message",
"is_bot": false,
"headline": "add conversation-level prompt caching via cache breakpoint on penulti…",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T03:02:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c69b28ed79db9c516fa639cc7a271c0fb626dd2c",
"body": "…ailUntilCall",
"is_bot": false,
"headline": "1e: add tests for error, stream_error, partial_max_tokens modes and F…",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T02:49:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7a1f495a4a10b125faa9dda8684af3dcd9d55c57",
"body": "…ting to mock provider",
"is_bot": false,
"headline": "1a-d: add error, stream_error, partial_max_tokens modes and call-coun…",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-04-01T02:48:47Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e29af58e75e680371fbd23159ad36550007bf7c0",
"body": null,
"is_bot": false,
"headline": "7e: add tests for output group continuation, budget, and deduplication",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-03-28T01:39:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0364d073a1f8bc4e079ad7c11c0091ba8a79fd26",
"body": null,
"is_bot": false,
"headline": "7c: deduplicate output group nodes in buildMessages",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-03-28T01:35:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2cd362ecbb8ed996b944ebef7070ae20ebf4317d",
"body": null,
"is_bot": false,
"headline": "7b: implement max_tokens continuation loop in streamResponse",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-03-28T01:34:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d1c9b525d9ac314abf8c38217a152248a61671d3",
"body": null,
"is_bot": false,
"headline": "7a: add OutputGroupID to Node and WithMaxOutputGroupTokens option",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-03-28T01:26:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4469ae7c32646cfc6e81dbd91ac8ad0f13d65768",
"body": "TestMaxTokensCrashChain_NoCorruption exercises the full scenario:\nnormal response → max_tokens empty (no node saved) → recovery from\nfirst assistant node succeeds.",
"is_bot": false,
"headline": "6a: integration test reproducing the max_tokens crash chain",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-03-28T01:18:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "62043f98680e4bfd61cd1b54df29a83d43712197",
"body": "toContentBlockArray returns empty slice for empty strings instead of\nproducing {\"type\":\"text\",\"text\":\"\"} which the Anthropic API rejects.\nconvertMessages skips empty text blocks and empty-string assistant messages.",
"is_bot": false,
"headline": "3a+3b: filter empty text blocks in message construction",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-03-28T00:58:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bb1dc0c7ed861f9ecbb2f67bf992fcba6f56f57c",
"body": "conversation.Manager.Prompt/PromptFrom now accept maxTokens and pass\nit to streamResponse instead of hardcoding 4096. langdag.Client\nforwards o.maxTokens from the option. Falls back to 4096 when 0.",
"is_bot": false,
"headline": "1a+1b+1c+1d: wire WithMaxTokens through to provider",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-03-28T00:47:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "497b39245602daf871ea7d7e492eef32be86514f",
"body": "OpenAI/Ollama: pass think field in request JSON (omitted when nil).\nAnthropic: enable extended thinking with 10240 budget, bump max_tokens,\nskip temperature. Gemini: set thinkingConfig budget (8192 for true,\n0 for false, omitted for nil). Tests for all three.",
"is_bot": false,
"headline": "2a+2b+2c: Wire Think into OpenAI, Anthropic, and Gemini providers",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-03-24T19:47:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9c8f793c722fc6f08d94f3d85d1a77baa8246ad0",
"body": "Add tri-state Think field (nil/true/false) to CompletionRequest, thread\nit through conversation manager, and add WithThink() option with tests.",
"is_bot": false,
"headline": "1a+1b: Add Think *bool to CompletionRequest and WithThink prompt option",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-03-24T19:36:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "16eb214d4b47ad6c2856466d5ec5ec3c8df54004",
"body": null,
"is_bot": false,
"headline": "fix: downgrade deploy-pages action to v4 (v5 does not exist)",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-03-24T05:12:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2949c86a9c709a705b9c1135015ac6ac71dd14a7",
"body": "Graceful server tool handling + capability metadata",
"is_bot": false,
"headline": "Merge pull request #4 from aduermael/feat/server-tool-capabilities",
"author_name": "Adrian Duermael",
"author_login": "aduermael",
"committed_at": "2026-03-23T22:01:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "67d97925014f327d51844dce2c8a50b75385a69c",
"body": "…talog\n\nCloses #3. Clients can now always declare server tools (e.g. web_search)\nand langdag silently strips unsupported ones per-model before they reach\nthe provider. ModelInfo and ModelPricing expose a ServerTools field so\nclients can make informed decisions (e.g. system prompt optimization, UI).\n\n[…]\nlter into both server and library provider creation chains\n- Change Anthropic convertTools to skip (not error) on unknown server tools\n- Annotate catalog.json and FetchLatest with server tool metadata",
"is_bot": false,
"headline": "feat: graceful server tool handling + capability metadata in model ca…",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-03-23T21:46:38Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "2e39877a0cfb5e5434feffbf831eb98d13c5855a",
"body": "Adds a release workflow that triggers on version tags and notifies\nproxy.golang.org so the module is immediately available via go get.\n\nCo-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "ci: auto-index new versions on Go module proxy",
"author_name": "aduermael",
"author_login": "aduermael",
"committed_at": "2026-03-21T18:41:05Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "f8286de1cae0ef7347f8e3845492c42967020cee",
"body": "feat: add Ollama provider support",
"is_bot": false,
"headline": "Merge pull request #1 from Patel230/feature/ollama-provider",
"author_name": "Adrian Duermael",
"author_login": "aduermael",
"committed_at": "2026-03-21T18:17:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4df6d3ffcc4a59fae9864aae31cb2e4aa04b8ee6",
"body": "…ama factory",
"is_bot": false,
"headline": "fix: add doc comments, thread ctx into getContextWindow, simplify oll…",
"author_name": "Patel230",
"author_login": "Patel230",
"committed_at": "2026-03-21T04:06:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9137c7fe654ce6144058173da6f66b392a94bbed",
"body": null,
"is_bot": false,
"headline": "test: match project style, full Ollama coverage — 29 tests all passing",
"author_name": "Patel230",
"author_login": "Patel230",
"committed_at": "2026-03-21T03:56:20Z",
"body_truncated": false,
"is_coding_agent": false
}
],
"releases_count": 28,
"commits_last_year": 257,
"latest_release_at": "2026-07-16T07:35:45Z",
"latest_release_tag": "v0.10.0",
"releases_from_tags": true,
"days_since_last_push": 1,
"active_weeks_last_year": 16,
"days_since_latest_release": 8,
"mean_days_between_releases": 12.7
},
"community": {
"has_readme": true,
"has_license": true,
"has_description": true,
"has_contributing": true,
"health_percentage": 50,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"ecosystem": {
"packages": [
{
"name": "langdag.com/langdag",
"exists": true,
"license": null,
"keywords": [],
"ecosystem": "go",
"matches_repo": null,
"registry_url": "https://pkg.go.dev/langdag.com/langdag",
"is_deprecated": false,
"latest_version": "v0.10.0",
"repository_url": null,
"versions_count": 28,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": null,
"monthly_downloads": null,
"first_published_at": null,
"latest_published_at": "2026-07-16T07:35:45Z",
"latest_version_yanked": null,
"days_since_latest_publish": 8
}
]
},
"popularity": {
"forks": 4,
"stars": 31,
"watchers": 1,
"fork_history": {
"days": [
{
"date": "2026-03-19",
"count": 2
},
{
"date": "2026-06-12",
"count": 1
},
{
"date": "2026-06-19",
"count": 1
}
],
"complete": true,
"collected": 4,
"total_forks": 4
},
"star_history": null,
"open_issues_and_prs": 0
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [
"examples"
],
"has_llms_txt": true,
"has_dockerfile": true,
"has_mcp_signal": false,
"bootstrap_files": [
"Makefile"
],
"api_schema_files": [
"api/openapi.yaml"
],
"has_devcontainer": false,
"typecheck_configs": [
"examples/typescript/tsconfig.json",
"sdks/typescript/tsconfig.json"
],
"toolchain_manifests": [
"examples/go/go.mod",
"go.mod",
"sdks/go/go.mod",
"tools/mockllm/go.mod"
],
"largest_source_bytes": 83947,
"source_files_sampled": 141,
"oversized_source_files": 3,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"dependencies": {
"manifests": [
"go.mod"
],
"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": [
"go"
],
"dependencies": [
{
"name": "github.com/anthropics/anthropic-sdk-go",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v1.20.0"
},
{
"name": "github.com/google/uuid",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v1.6.0"
},
{
"name": "github.com/olekukonko/tablewriter",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v0.0.5"
},
{
"name": "github.com/spf13/cobra",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v1.8.1"
},
{
"name": "github.com/spf13/viper",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v1.19.0"
},
{
"name": "gopkg.in/yaml.v3",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v3.0.1"
},
{
"name": "modernc.org/sqlite",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v1.34.4"
}
],
"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": 27,
"open_issues": 0,
"closed_ratio": 1,
"closed_issues": 1,
"closed_unmerged_prs": 2
},
"bus_factor": 1,
"bot_contributors": 0,
"top_contributors": [
{
"type": "User",
"login": "aduermael",
"commits": 201,
"avatar_url": "https://avatars.githubusercontent.com/u/6775074?v=4"
},
{
"type": "User",
"login": "gdevillele",
"commits": 37,
"avatar_url": "https://avatars.githubusercontent.com/u/939999?v=4"
},
{
"type": "User",
"login": "Patel230",
"commits": 14,
"avatar_url": "https://avatars.githubusercontent.com/u/17196758?v=4"
},
{
"type": "User",
"login": "imadcat",
"commits": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/1559729?v=4"
}
],
"contributors_sampled": 4,
"top_contributor_share": 0.794
},
"quality_signals": {
"has_ci": true,
"has_tests": true,
"ci_workflows": [
"model-catalog.yml",
"pages.yml",
"release.yml",
"test-go.yml",
"test-python.yml",
"test-typescript.yml",
"test.yml"
],
"has_docs_dir": true,
"linter_configs": [],
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [
"go.sum",
"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": 5,
"reason": "branch protection is not maximal on development and all release branches",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
},
{
"name": "CI-Tests",
"score": 10,
"reason": "22 out of 22 merged PRs checked by a CI test -- score normalized to 10",
"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": 7,
"reason": "Found 17/22 approved changesets -- score normalized to 7",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 10,
"reason": "project has 4 contributing companies or organizations",
"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": "15 commit(s) and 0 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": null,
"reason": "packaging workflow not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
},
{
"name": "Pinned-Dependencies",
"score": 6,
"reason": "dependency not pinned by hash detected -- score normalized to 6",
"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": 0,
"reason": "security policy file not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#security-policy"
},
{
"name": "Signed-Releases",
"score": null,
"reason": "no releases found",
"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": 0,
"reason": "44 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "5c34041403f52d25ec6e8bce998d9c28ab34c061",
"ran_at": "2026-07-24T12:32:18Z",
"aggregate_score": 4.8,
"scorecard_version": "v5.5.0"
},
"has_codeql_workflow": false,
"has_security_policy": false,
"has_dependabot_config": false
},
"contribution_flow": {
"collected": true,
"ci_last_run_at": "2026-07-24T11:54:08Z",
"oldest_open_prs": [],
"last_merged_pr_at": "2026-07-16T07:35:46Z",
"ci_last_conclusion": "SUCCESS",
"oldest_open_issues": []
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/fundamental-research-labs/langdag",
"host": "github.com",
"name": "langdag",
"owner": "fundamental-research-labs"
},
"metrics": {
"overall": {
"key": "overall",
"band": "moderate",
"name": "Overall health",
"note": null,
"notes": [],
"value": 65,
"inputs": {
"security": 48,
"vitality": 80,
"community": 48,
"governance": 63,
"engineering": 81
},
"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": 75,
"inputs": {
"commits_last_year": 257,
"human_commit_share": 1,
"days_since_last_push": 1,
"active_weeks_last_year": 16
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 1 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 1
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "16/52 weeks with commits",
"points": 11.1,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 16
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "257 commits in the last year",
"points": 18,
"status": "met",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 257
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "15 commit(s) and 0 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": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"openssf_scorecard_signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 88,
"inputs": {
"releases_count": 28,
"latest_release_tag": "v0.10.0",
"releases_from_tags": true,
"days_since_latest_release": 8,
"mean_days_between_releases": 12.7
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "28 version tags (no GitHub releases)",
"points": 16.2,
"status": "partial",
"details": [
{
"code": "version_tags_no_releases",
"params": {
"count": 28
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 8 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 8
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~12.7 days",
"points": 27,
"status": "met",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 12.7
}
}
],
"max_points": 27
},
{
"key": "openssf_scorecard_signed_releases",
"name": "OpenSSF Scorecard: Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"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": 48,
"weight": 0.18,
"metrics": [
{
"key": "popularity",
"band": "critical",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 28,
"inputs": {
"forks": 4,
"stars": 31,
"watchers": 1,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "31 stars",
"points": 24,
"status": "partial",
"details": [
{
"code": "stars",
"params": {
"count": 31
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "4 forks",
"points": 4,
"status": "partial",
"details": [
{
"code": "forks",
"params": {
"count": 4
}
}
],
"max_points": 25
},
{
"key": "watchers",
"name": "Watchers",
"detail": "1 watchers",
"points": 0,
"status": "missed",
"details": [
{
"code": "watchers",
"params": {
"count": 1
}
}
],
"max_points": 15
}
]
},
{
"key": "community_health",
"band": "good",
"name": "Community health",
"note": null,
"notes": [],
"value": 70,
"inputs": {
"has_readme": true,
"has_license": true,
"has_contributing": true,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 22.5,
"status": "met",
"details": [],
"max_points": 22.5
},
{
"key": "license",
"name": "License",
"detail": "recognized license (MIT)",
"points": 22.5,
"status": "met",
"details": [
{
"code": "license_standard",
"params": {}
},
{
"code": "license_spdx",
"params": {
"spdx": "MIT"
}
}
],
"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": 0,
"status": "missed",
"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": 0,
"status": "missed",
"details": [],
"max_points": 6.3
}
]
}
],
"description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
},
{
"key": "governance",
"band": "moderate",
"name": "Sustainability & Governance",
"value": 63,
"weight": 0.24,
"metrics": [
{
"key": "maintainer_resilience",
"band": "critical",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 29,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 4,
"top_contributor_share": 0.794
},
"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 79% of commits",
"points": 4.6,
"status": "partial",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 79
}
}
],
"max_points": 22.5
},
{
"key": "contributor_breadth",
"name": "Contributor breadth",
"detail": "4 contributors",
"points": 5.4,
"status": "partial",
"details": [
{
"code": "contributors_sampled",
"params": {
"count": 4
}
}
],
"max_points": 13.5
},
{
"key": "openssf_scorecard_contributors",
"name": "OpenSSF Scorecard: Contributors",
"detail": "project has 4 contributing companies or organizations",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
},
{
"key": "responsiveness",
"band": "excellent",
"name": "Issue & PR responsiveness",
"note": null,
"notes": [],
"value": 93,
"inputs": {
"merged_prs": 27,
"open_issues": 0,
"closed_issues": 1,
"issue_closed_ratio": 1,
"closed_unmerged_prs": 2
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "100% of issues closed",
"points": 46.8,
"status": "met",
"details": [
{
"code": "issues_closed_share",
"params": {
"share": 100
}
}
],
"max_points": 46.75
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "27/29 decided PRs merged",
"points": 35.6,
"status": "partial",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 27,
"decided": 29
}
}
],
"max_points": 38.25
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 17/22 approved changesets -- score normalized to 7",
"points": 10.5,
"status": "partial",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "at_risk",
"name": "Ownership & stewardship",
"note": null,
"notes": [],
"value": 44,
"inputs": {
"followers": 8,
"owner_type": "Organization",
"is_verified": null,
"owner_login": "fundamental-research-labs",
"public_repos": 7,
"account_age_days": 118
},
"components": [
{
"key": "ownership_backing",
"name": "Ownership backing",
"detail": "organization-owned",
"points": 30,
"status": "met",
"details": [
{
"code": "owner_organization",
"params": {}
}
],
"max_points": 30
},
{
"key": "verified_domain",
"name": "Verified domain",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 20
},
{
"key": "owner_reach",
"name": "Owner reach",
"detail": "8 followers of fundamental-research-labs",
"points": 6.9,
"status": "partial",
"details": [
{
"code": "owner_followers",
"params": {
"count": 8,
"login": "fundamental-research-labs"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "7 public repos, account ~0 yr old",
"points": 7.2,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 7
}
},
{
"code": "account_age_years",
"params": {
"years": 0
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "excellent",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"langdag.com/langdag"
],
"ecosystems": "go",
"any_deprecated": false,
"min_days_since_publish": 8
},
"components": [
{
"key": "published_resolvable",
"name": "Published & resolvable",
"detail": "1 package(s) on go",
"points": 25,
"status": "met",
"details": [
{
"code": "packages_published",
"params": {
"count": 1,
"ecosystems": "go"
}
}
],
"max_points": 25
},
{
"key": "publish_recency",
"name": "Publish recency",
"detail": "latest publish 8 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 8
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "28 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 28
}
}
],
"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": "good",
"name": "Engineering Quality",
"value": 81,
"weight": 0.2,
"metrics": [
{
"key": "engineering_practices",
"band": "moderate",
"name": "Engineering practices",
"note": null,
"notes": [],
"value": 68,
"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": "7 workflow(s)",
"points": 24,
"status": "met",
"details": [
{
"code": "ci_workflows",
"params": {
"count": 7
}
}
],
"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": "22 out of 22 merged PRs checked by a CI test -- score normalized to 10",
"points": 20,
"status": "met",
"details": [],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "excellent",
"name": "Documentation",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"topics": [
"ai",
"cli",
"conversation",
"dag",
"langchain",
"langfuse",
"llm",
"prompt-engineering",
"prompt-management",
"self-hosted"
],
"has_wiki": true,
"homepage": "https://langdag.com",
"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://langdag.com",
"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": "10 topics",
"points": 10,
"status": "met",
"details": [
{
"code": "topics_count",
"params": {
"count": 10
}
}
],
"max_points": 10
},
{
"key": "wiki",
"name": "Wiki",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
}
],
"description": "Are baseline engineering and documentation practices in place?"
},
{
"key": "security",
"band": "at_risk",
"name": "Security",
"value": 48,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "at_risk",
"name": "Security posture",
"note": "Excluded from scoring (no data or not applicable): Packaging, Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"packaging",
"signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 48,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 16,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 2,
"scorecard_aggregate": 4.8
},
"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 is not maximal on development and all release branches",
"points": 3.8,
"status": "partial",
"details": [],
"max_points": 7.5
},
{
"key": "ci_tests",
"name": "CI-Tests",
"detail": "22 out of 22 merged PRs checked by a CI test -- score normalized to 10",
"points": 2.5,
"status": "met",
"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 17/22 approved changesets -- score normalized to 7",
"points": 5.2,
"status": "partial",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 4 contributing companies or organizations",
"points": 2.5,
"status": "met",
"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": "15 commit(s) and 0 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 not detected",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 5
},
{
"key": "pinned_dependencies",
"name": "Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 6",
"points": 3,
"status": "partial",
"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 not detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "signed_releases",
"name": "Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"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": "44 existing vulnerabilities detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
}
]
},
{
"key": "high_risk_jurisdiction_exposure",
"band": "excellent",
"name": "High-Risk Jurisdiction Exposure",
"note": "Only high-confidence self-published location evidence affects this multiplier. Ambiguous matches are review-only; country evidence is not proof of nationality, citizenship, legal registration, malicious intent, or sanctions status.",
"notes": [
{
"code": "jurisdiction_evidence_limits",
"params": {}
}
],
"value": 100,
"inputs": {
"meaning": "self-published location evidence; not nationality or citizenship",
"red_flag": false,
"exposures": [],
"policy_countries": [
"Russia",
"Iran",
"North Korea"
],
"review_only_matches": 0,
"assessed_self_published_locations": 4
},
"components": [
{
"key": "policy_exposure_multiplier",
"name": "Policy exposure multiplier",
"detail": "no confirmed policy-scope location match",
"points": 100,
"status": "met",
"details": [
{
"code": "jurisdiction_no_match",
"params": {}
}
],
"max_points": 100
}
]
}
],
"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": 74,
"weight": 0,
"metrics": [
{
"key": "ai_agent_context",
"band": "moderate",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 55,
"inputs": {
"has_llms_txt": true,
"legible_history_share": 0.89,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "no CLAUDE.md / AGENTS.md / editor rules",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_agent_instructions",
"params": {}
}
],
"max_points": 45
},
{
"key": "machine_readable_docs_llms_txt",
"name": "Machine-readable docs (llms.txt)",
"detail": "llms.txt present",
"points": 15,
"status": "met",
"details": [
{
"code": "llms_txt_present",
"params": {}
}
],
"max_points": 15
},
{
"key": "legible_commit_history",
"name": "Legible commit history",
"detail": "89 of 100 human commits state their intent (structured subject or explanatory body)",
"points": 40,
"status": "met",
"details": [
{
"code": "legible_history",
"params": {
"legible": 89,
"sampled": 100
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "good",
"name": "Verify loop (build / test / typecheck)",
"note": null,
"notes": [],
"value": 77,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [
"go.sum",
"package-lock.json"
],
"has_dockerfile": true,
"typed_language": true,
"bootstrap_files": [
"Makefile"
],
"has_devcontainer": false,
"has_linter_config": false,
"typecheck_configs": [
"examples/typescript/tsconfig.json",
"sdks/typescript/tsconfig.json"
],
"agent_commit_share": 0.25,
"toolchain_manifests": [
"examples/go/go.mod",
"go.mod",
"sdks/go/go.mod",
"tools/mockllm/go.mod"
],
"dependency_bot_commit_share": 0
},
"components": [
{
"key": "one_command_bootstrap",
"name": "One-command bootstrap",
"detail": "Makefile",
"points": 18,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "Makefile"
}
}
],
"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": "examples/typescript/tsconfig.json, sdks/typescript/tsconfig.json",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "examples/typescript/tsconfig.json, sdks/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": "25 of the last 100 commits agent-authored or agent-credited",
"points": 10,
"status": "met",
"details": [
{
"code": "agent_authored_commits",
"params": {
"count": 25,
"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 6",
"points": 6,
"status": "partial",
"details": [],
"max_points": 10
}
]
},
{
"key": "ai_code_legibility",
"band": "excellent",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 99,
"inputs": {
"primary_language": "Go",
"largest_source_bytes": 83947,
"source_files_sampled": 141,
"oversized_source_files": 3
},
"components": [
{
"key": "type_checkable_code",
"name": "Type-checkable code",
"detail": "Go (statically typed)",
"points": 45,
"status": "met",
"details": [
{
"code": "statically_typed_language",
"params": {
"language": "Go"
}
}
],
"max_points": 45
},
{
"key": "manageable_file_sizes",
"name": "Manageable file sizes",
"detail": "3/141 source files over 60KB",
"points": 53.8,
"status": "partial",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 141,
"oversized": 3
}
}
],
"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": "2026-07-24T12:32:35.300822Z",
"schema_version": "0.27.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/f/fundamental-research-labs/langdag.svg",
"full_name": "fundamental-research-labs/langdag",
"license_state": "standard",
"license_spdx": "MIT"
}
Verwandte Einträge
Geprüfte Repositories, die Katalog-Tags oder Ökosysteme mit fundamental-research-labs/langdag teilen. Nebeneinander lesen →
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.
