Öffentliches RegisterMittel
Software-GesundheitsberichtSchema 0.27.0 · Metriken 1.13.0 · 2026-07-24 20:44 UTC
hung12ct / gopheragent
Go/Golang multi-agent LLM framework — ReAct loops, parallel tool calls, streaming, sub-agents, and pluggable Anthropic / OpenAI / Gemini providers.
hung12ct/gopheragent erreicht einen Gesundheitsindex von 57 von 100 und liegt damit im Bereich Mittel. Am stärksten schneidet es bei Engineering Quality (80/100) ab, am schwächsten bei Community & Adoption (27/100). Zuletzt heute aktualisiert. Ein einzelner Mitwirkender trägt den Großteil der jüngsten Arbeit.
57
gesamt / 100Software-Gesundheitsindex
Metriken werden auf einer Skala von 1–100 in gewichtete Kategorien gruppiert. Der Gesamtwert beginnt als ihr Mittel; sobald öffentliche Evidenz die Richtlinie für Hochrisikojurisdiktionen auslöst, wird die Bewertung angepasst und erhält die Obergrenze 49 (Gefährdet). AI Readiness liegt außerhalb.
57
Exzellent85-100Vorbildlich; erfüllt im Wesentlichen alle geprüften Kriterien
Gut70-84Gesund; geringfügige Lücken
Mittel50-69Akzeptabel mit deutlichen Lücken; Überprüfung empfohlen
Gefährdet30-49Erhebliche Schwächen; eine Übernahme erfordert Vorsicht
Kritisch1-29Schwerwiegende Probleme (aufgegeben, nur ein Maintainer, keine Hygiene)
Bewertungsprofil
Jede Achse ist eine Kategorie. Die Form zählt mehr als der Durchschnitt — ein gesundes Projekt füllt die gesamte Fläche, während ein Profil aus Spitzen und Kratern bedeutet, dass Stärke in einer Dimension Risiken in einer anderen verdeckt.
Eigentümerschaft
hung12ctPersönliches Konto
1 Follower9 öffentliche Reposseit März 2019
Dieses Repository gehört einem persönlichen Konto. Ein Projekt mit nur einem Eigentümer trägt ein höheres Kontinuitätsrisiko als ein organisationsgetragenes.
Paket-Ökosysteme
| Registry | Paket | Version | Downloads / Monat | Versionen | Zuletzt veröffentlicht |
|---|---|---|---|---|---|
| Go | github.com/hung12ct/gopheragent | v0.34.0 | - | 54 | vor 0 Tagen |
Metriken nach Kategorie
Vitalität
Lebt das Projekt — wird Code geschrieben und werden Releases ausgeliefert?
78
Wie die Bewertung erfolgt
| 36/36 | Push-Aktualität — letzter Push vor 0 Tagen |
| 7.6/36 | Commit-Rhythmus — 11/52 Wochen mit Commits |
| 18/18 | Commit-Volumen — 339 Commits im letzten Jahr |
| 10/10 | OpenSSF Scorecard: Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
Verwendete Eingangsdaten
| commits_last_year | 339 |
| human_commit_share | 1 |
| days_since_last_push | 0 |
| active_weeks_last_year | 11 |
Release-Disziplin
88Exzellent
Wie die Bewertung erfolgt
| 16.2/27 | Liefert Releases aus — 54 Versions-Tags (keine GitHub-Releases) |
| 36/36 | Release-Aktualität — letztes Release vor 0 Tagen |
| 27/27 | Release-Rhythmus — ein Release etwa alle 7,3 Tage |
| 0/10 | OpenSSF Scorecard: Signed-Releases — keine Daten |
Verwendete Eingangsdaten
| releases_count | 54 |
| latest_release_tag | v0.34.0 |
| releases_from_tags | ja |
| days_since_latest_release | 0 |
| mean_days_between_releases | 7,3 |
Von der Bewertung ausgeschlossen (keine Daten oder nicht anwendbar): OpenSSF Scorecard: Signed-Releases. Die verbleibenden Gewichte wurden renormalisiert.
Community & Verbreitung
Hat das Projekt Nutzer, Downloads, Aufmerksamkeit und ein einladendes Umfeld für Beitragende?
27
Popularität & Verbreitung
1Kritisch
Wie die Bewertung erfolgt
| 0/60 | Stars — 2 Stars |
| 0/25 | Forks — 0 Forks |
| 0/15 | Watcher — 0 Watcher |
Verwendete Eingangsdaten
| forks | 0 |
| stars | 2 |
| watchers | 0 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
Community-Gesundheit
57Mittel
Wie die Bewertung erfolgt
| 22.5/22.5 | README |
| 22.5/22.5 | Lizenz — anerkannte Lizenz (Apache-2.0) |
| 0/18 | CONTRIBUTING-Leitfaden |
| 0/13.5 | Verhaltenskodex |
| 0/7.2 | Issue-Vorlage |
| 6.3/6.3 | PR-Vorlage |
Verwendete Eingangsdaten
| has_readme | ja |
| has_license | ja |
| has_contributing | nein |
| has_issue_template | nein |
| has_code_of_conduct | nein |
| has_pull_request_template | ja |
Nachhaltigkeit & Governance
Überdauert das Projekt die Menschen, die es tragen — Bus-Faktor, Reaktionsfähigkeit, Trägerschaft und Paketpflege?
50
Maintainer-Resilienz (Bus-Faktor)
10Kritisch
Wie die Bewertung erfolgt
| 9/54 | Bus-Faktor — 1 Beitragende decken die Hälfte aller Commits ab |
| 0/22.5 | Commit-Verteilung — wichtigste beitragende Person verfasste 100 % der Commits |
| 1.4/13.5 | Breite der Beitragenden — 1 Beitragende |
| 0/10 | OpenSSF Scorecard: Contributors — project has 0 contributing companies or organizations -- score normalized to 0 |
Verwendete Eingangsdaten
| bus_factor | 1 |
| contributors_sampled | 1 |
| top_contributor_share | 1 |
Wie die Bewertung erfolgt
| 0/46.8 | Issue-Lösungsquote — keine Issues oder keine Daten |
| 38/38.3 | PR-Annahme — 132/133 entschiedene PRs gemergt |
| 0/15 | OpenSSF Scorecard: Code-Review — Found 0/8 approved changesets -- score normalized to 0 |
Verwendete Eingangsdaten
| merged_prs | 132 |
| open_issues | 0 |
| closed_issues | 0 |
| issue_closed_ratio | — |
| closed_unmerged_prs | 1 |
Von der Bewertung ausgeschlossen (keine Daten oder nicht anwendbar): Issue-Lösungsquote. Die verbleibenden Gewichte wurden renormalisiert.
Eigentümerschaft & Trägerschaft
39Gefährdet
Wie die Bewertung erfolgt
| 10/30 | Organisatorische Trägerschaft — persönliches (Nutzer-)Konto |
| 0/20 | Verifizierte Domain — für Nutzerkonten nicht anwendbar |
| 2.2/25 | Reichweite des Inhabers — 1 Follower von hung12ct |
| 19.3/25 | Kontohistorie — 9 öffentliche Repos, Kontoalter ca. 7 Jahre |
Verwendete Eingangsdaten
| followers | 1 |
| owner_type | User |
| is_verified | — |
| owner_login | hung12ct |
| public_repos | 9 |
| account_age_days | 2.692 |
Von der Bewertung ausgeschlossen (keine Daten oder nicht anwendbar): Verifizierte Domain. Die verbleibenden Gewichte wurden renormalisiert.
Paketpflege
100Exzellent
Wie die Bewertung erfolgt
| 25/25 | Veröffentlicht & auflösbar — 1 Paket(e) auf go |
| 35/35 | Veröffentlichungsaktualität — letzte Veröffentlichung vor 0 Tagen |
| 20/20 | Versionshistorie — 54 veröffentlichte Versionen |
| 20/20 | Nicht veraltet — aktiv, nicht veraltet oder zurückgezogen |
Verwendete Eingangsdaten
| packages | github.com/hung12ct/gopheragent |
| ecosystems | go |
| any_deprecated | nein |
| min_days_since_publish | 0 |
Engineering-Qualität
Sind grundlegende Engineering- und Dokumentationspraktiken vorhanden?
80
Wie die Bewertung erfolgt
| 24/24 | CI-Workflows — 1 Workflow(s) |
| 24/24 | Tests vorhanden |
| 16/16 | Linter-Konfiguration — .golangci.yml |
| 0/9.6 | Pre-Commit-Hooks |
| 0/6.4 | .editorconfig |
| 20/20 | OpenSSF Scorecard: CI-Tests — 6 out of 6 merged PRs checked by a CI test -- score normalized to 10 |
Verwendete Eingangsdaten
| has_ci | ja |
| has_tests | ja |
| has_editorconfig | nein |
| has_linter_config | ja |
| has_precommit_config | nein |
Dokumentation
75Gut
Wie die Bewertung erfolgt
| 30/30 | README |
| 0/25 | Dokumentationsverzeichnis |
| 15/15 | Dokumentations-/Homepage-Site — https://pkg.go.dev/github.com/hung12ct/gopheragent |
| 10/10 | Repository-Beschreibung |
| 10/10 | Topics — 19 Topics |
| 10/10 | Wiki |
Verwendete Eingangsdaten
| topics | agent, ai-agent, anthropic, framework, gemini, go, golang, llm, multi-agent, openai, chatbot, agent-framework, agentic, agents, ai-agents, function-calling, llm-framework, multiagent, tool-use |
| has_wiki | ja |
| homepage | https://pkg.go.dev/github.com/hung12ct/gopheragent |
| has_readme | ja |
| has_docs_dir | nein |
| has_description | ja |
Sicherheit
Sind die sichtbaren Sicherheits- und Lieferkettenpraktiken belastbar, ohne ungeklärte Exposition gegenüber Hochrisikojurisdiktionen?
45
Sicherheitslage
45Gefährdet
Wie die Bewertung erfolgt
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 3.8/7.5 | Branch-Protection — branch protection is not maximal on development and all release branches |
| 2.5/2.5 | CI-Tests — 6 out of 6 merged PRs checked by a CI test -- score normalized to 10 |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 0/7.5 | Code-Review — Found 0/8 approved changesets -- score normalized to 0 |
| 0/2.5 | Contributors — project has 0 contributing companies or organizations -- score normalized to 0 |
| 10/10 | Dangerous-Workflow — no dangerous workflow patterns detected |
| 0/7.5 | Dependency-Update-Tool — no update tool detected |
| 0/5 | Fuzzing — project is not fuzzed |
| 2.5/2.5 | Lizenz — license file detected |
| 7.5/7.5 | Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| 0/5 | Packaging — keine Daten |
| 0/5 | Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
| 0/5 | SAST — SAST tool is not run on all commits -- score normalized to 0 |
| 0/5 | Security-Policy — security policy file not detected |
| 0/7.5 | Signed-Releases — keine Daten |
| 7.5/7.5 | Token-Permissions — GitHub workflow tokens follow principle of least privilege |
| 0/7.5 | Vulnerabilities — 32 existing vulnerabilities detected |
Verwendete Eingangsdaten
| source | openssf_scorecard |
| checks_evaluated | 16 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 2 |
| scorecard_aggregate | 4,5 |
Von der Bewertung ausgeschlossen (keine Daten oder nicht anwendbar): packaging, signed_releases. Die verbleibenden Gewichte wurden renormalisiert.
AI Readiness
Wie gut ist das Repository dafür ausgestattet, mit KI-Coding-Agenten entwickelt und gepflegt zu werden? Ein unabhängiges, experimentelles Badge — Gewicht 0,0, es wird eigenständig ausgewiesen und verändert den Gesamt-Gesundheitswert nicht.
62
AI-Agentenkontext & Leitlinien
40Gefährdet
Wie die Bewertung erfolgt
| 0/45 | Agentenanweisungen — keine CLAUDE.md / AGENTS.md / Editor-Regeln |
| 0/15 | Maschinenlesbare Doku (llms.txt) |
| 40/40 | Lesbare Commit-Historie — 99 von 100 menschlichen Commits benennen ihre Absicht (strukturierter Betreff oder erläuternder Text) |
Verwendete Eingangsdaten
| has_llms_txt | nein |
| legible_history_share | 0,99 |
| agent_instruction_files | — |
| agent_instruction_max_bytes | — |
Wie die Bewertung erfolgt
| 18/18 | Bootstrap mit einem Befehl — Makefile |
| 22/22 | Automatisierte Tests |
| 11/11 | Lint-/Format-Konfiguration — .golangci.yml |
| 11/11 | Statische Typprüfung — Go (statisch typisiert) |
| 10/10 | Reproduzierbare Umgebung — lockfile |
| 0/10 | Belegte Agentenpraxis — keine von Agenten verfassten Commits unter den letzten 100 |
| 0/8 | Automatisierte Wartung — keine automatisierten Abhängigkeits-Updates beobachtet |
| 0/10 | OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
Verwendete Eingangsdaten
| has_nix | nein |
| has_tests | ja |
| lockfiles | go.sum |
| has_dockerfile | nein |
| typed_language | ja |
| bootstrap_files | Makefile |
| has_devcontainer | nein |
| has_linter_config | ja |
| typecheck_configs | — |
| agent_commit_share | 0 |
| toolchain_manifests | go.mod |
| dependency_bot_commit_share | 0 |
AI-Code-Lesbarkeit für Modelle
100Exzellent
Wie die Bewertung erfolgt
| 45/45 | Typprüfbarer Code — Go (statisch typisiert) |
| 55/55 | Handhabbare Dateigrößen — 0/243 Quelldateien über 60 KB |
Verwendete Eingangsdaten
| primary_language | Go |
| largest_source_bytes | 44.792 |
| source_files_sampled | 243 |
| oversized_source_files | 0 |
Maschinenlesbare AI-Schnittstellen
40Gefährdet
Wie die Bewertung erfolgt
| 0/40 | API-Schema (OpenAPI/GraphQL/proto) |
| 0/20 | MCP-Server |
| 40/40 | Lauffähige Beispiele — examples |
Verwendete Eingangsdaten
| example_dirs | examples |
| has_mcp_signal | nein |
| api_schema_files | — |
Eckdaten
2GitHub-Sterne
1Mitwirkende
339Commits, letzte 12 Monate
0Tage seit letztem Push
54Releases
1Bus-Faktor
0offene Issues
GoPaket-Ökosysteme
Warnungen zur Datenerhebung
- Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
- GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
Weitere Details
OpenSSF Scorecard 4.5 / 10
4.5Gesamtwert
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).
| 10 | Binary-Artifacts | no binaries found in the repo |
| 5 | Branch-Protection | branch protection is not maximal on development and all release branches |
| 10 | CI-Tests | 6 out of 6 merged PRs checked by a CI test -- score normalized to 10 |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 0 | Code-Review | Found 0/8 approved changesets -- score normalized to 0 |
| 0 | Contributors | project has 0 contributing companies or organizations -- score normalized to 0 |
| 10 | Dangerous-Workflow | no dangerous workflow patterns detected |
| 0 | Dependency-Update-Tool | no update tool detected |
| 0 | Fuzzing | project is not fuzzed |
| 10 | License | license file detected |
| 10 | Maintained | 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| k. A. | Packaging | packaging workflow not detected |
| 0 | Pinned-Dependencies | dependency not pinned by hash detected -- score normalized to 0 |
| 0 | SAST | SAST tool is not run on all commits -- score normalized to 0 |
| 0 | Security-Policy | security policy file not detected |
| k. A. | Signed-Releases | no releases found |
| 10 | Token-Permissions | GitHub workflow tokens follow principle of least privilege |
| 0 | Vulnerabilities | 32 existing vulnerabilities detected |
Direkte Abhängigkeiten 8
| Registry | Paket | Versionsvorgabe | Manifest |
|---|---|---|---|
| Go | github.com/anthropics/anthropic-sdk-go | v1.27.1 | go.mod |
| Go | github.com/go-sql-driver/mysql | v1.9.3 | go.mod |
| Go | github.com/joho/godotenv | v1.5.1 | go.mod |
| Go | github.com/sashabaranov/go-openai | v1.41.2 | go.mod |
| Go | go.opentelemetry.io/otel | v1.29.0 | go.mod |
| Go | go.opentelemetry.io/otel/trace | v1.29.0 | go.mod |
| Go | google.golang.org/genai | v1.52.1 | go.mod |
| Go | gopkg.in/yaml.v3 | v3.0.1 | go.mod |
Alle Abhängigkeiten nicht erhoben
Der aufgelöste Abhängigkeitssatz konnte für diesen Bericht nicht erhoben werden: GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
JSON-Rohbericht maschinenlesbar
{
"data": {
"repo": {
"topics": [
"agent",
"ai-agent",
"anthropic",
"framework",
"gemini",
"go",
"golang",
"llm",
"multi-agent",
"openai",
"chatbot",
"agent-framework",
"agentic",
"agents",
"ai-agents",
"function-calling",
"llm-framework",
"multiagent",
"tool-use"
],
"is_fork": false,
"size_kb": 1324,
"has_wiki": true,
"homepage": "https://pkg.go.dev/github.com/hung12ct/gopheragent",
"languages": {
"Go": 1299139,
"Makefile": 5099
},
"pushed_at": "2026-07-24T16:09:30Z",
"created_at": "2026-04-01T08:02:54Z",
"owner_type": "User",
"updated_at": "2026-07-24T16:09:30Z",
"description": "Go/Golang multi-agent LLM framework — ReAct loops, parallel tool calls, streaming, sub-agents, and pluggable Anthropic / OpenAI / Gemini providers.",
"is_archived": false,
"is_disabled": false,
"license_spdx": "Apache-2.0",
"default_branch": "main",
"license_spdx_raw": "Apache-2.0",
"primary_language": "Go",
"significant_languages": [
"Go"
]
},
"owner": {
"blog": null,
"name": null,
"type": "User",
"login": "hung12ct",
"company": null,
"location": null,
"followers": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/48434938?v=4",
"created_at": "2019-03-11T09:24:28Z",
"is_verified": null,
"public_repos": 9,
"account_age_days": 2692
},
"license": {
"state": "standard",
"spdx_id": "Apache-2.0",
"raw_spdx": "Apache-2.0",
"file_present": true,
"scorecard_found": true,
"profile_has_license": true
},
"activity": {
"releases": [
{
"tag": "v0.34.0",
"kind": "minor",
"published_at": "2026-07-24T15:13:01Z"
},
{
"tag": "v0.33.0",
"kind": "minor",
"published_at": "2026-07-18T18:37:46Z"
},
{
"tag": "v0.32.1",
"kind": "patch",
"published_at": "2026-06-29T07:49:06Z"
},
{
"tag": "v0.32.0",
"kind": "minor",
"published_at": "2026-06-06T16:55:44Z"
},
{
"tag": "v0.31.5",
"kind": "patch",
"published_at": "2026-06-06T01:22:45Z"
},
{
"tag": "v0.31.4",
"kind": "patch",
"published_at": "2026-05-31T14:15:21Z"
},
{
"tag": "v0.31.3",
"kind": "patch",
"published_at": "2026-05-31T10:45:37Z"
},
{
"tag": "v0.31.2",
"kind": "patch",
"published_at": "2026-05-31T10:18:26Z"
},
{
"tag": "v0.31.1",
"kind": "patch",
"published_at": "2026-05-31T08:51:36Z"
},
{
"tag": "v0.31.0",
"kind": "minor",
"published_at": "2026-05-20T08:54:46Z"
},
{
"tag": "v0.30.0",
"kind": "minor",
"published_at": "2026-05-20T08:15:06Z"
},
{
"tag": "v0.29.0",
"kind": "minor",
"published_at": "2026-05-20T06:28:24Z"
},
{
"tag": "v0.28.0",
"kind": "minor",
"published_at": "2026-05-20T06:01:36Z"
},
{
"tag": "v0.27.0",
"kind": "minor",
"published_at": "2026-05-20T04:51:38Z"
},
{
"tag": "v0.26.3",
"kind": "patch",
"published_at": "2026-05-18T15:07:50Z"
},
{
"tag": "v0.26.2",
"kind": "patch",
"published_at": "2026-05-18T09:46:01Z"
},
{
"tag": "v0.26.1",
"kind": "patch",
"published_at": "2026-05-17T16:01:09Z"
},
{
"tag": "v0.26.0",
"kind": "minor",
"published_at": "2026-05-17T10:45:21Z"
},
{
"tag": "v0.25.0",
"kind": "minor",
"published_at": "2026-05-17T09:02:48Z"
},
{
"tag": "v0.24.0",
"kind": "minor",
"published_at": "2026-05-17T05:22:01Z"
},
{
"tag": "v0.23.0",
"kind": "minor",
"published_at": "2026-05-14T17:44:12Z"
},
{
"tag": "v0.22.0",
"kind": "minor",
"published_at": "2026-05-14T06:20:27Z"
},
{
"tag": "v0.21.0",
"kind": "minor",
"published_at": "2026-05-13T16:30:11Z"
},
{
"tag": "v0.20.2",
"kind": "patch",
"published_at": "2026-05-13T09:25:55Z"
},
{
"tag": "v0.20.1",
"kind": "patch",
"published_at": "2026-05-13T08:55:43Z"
},
{
"tag": "v0.20.0",
"kind": "minor",
"published_at": "2026-05-13T08:11:14Z"
},
{
"tag": "v0.19.0",
"kind": "minor",
"published_at": "2026-05-04T17:36:44Z"
},
{
"tag": "v0.18.1",
"kind": "patch",
"published_at": "2026-05-04T14:43:32Z"
},
{
"tag": "v0.18.0",
"kind": "minor",
"published_at": "2026-05-04T11:12:25Z"
},
{
"tag": "v0.17.0",
"kind": "minor",
"published_at": "2026-05-04T09:39:51Z"
},
{
"tag": "v0.16.0",
"kind": "minor",
"published_at": "2026-05-04T06:01:23Z"
},
{
"tag": "v0.15.0",
"kind": "minor",
"published_at": "2026-05-04T03:01:50Z"
},
{
"tag": "v0.14.2",
"kind": "patch",
"published_at": "2026-05-03T04:24:31Z"
},
{
"tag": "v0.14.1",
"kind": "patch",
"published_at": "2026-05-02T17:31:23Z"
},
{
"tag": "v0.14.0",
"kind": "minor",
"published_at": "2026-05-02T08:33:24Z"
},
{
"tag": "v0.13.0",
"kind": "minor",
"published_at": "2026-05-02T03:43:37Z"
},
{
"tag": "v0.12.0",
"kind": "minor",
"published_at": "2026-05-01T08:37:03Z"
},
{
"tag": "v0.11.1",
"kind": "patch",
"published_at": "2026-04-30T18:35:30Z"
},
{
"tag": "v0.11.0",
"kind": "minor",
"published_at": "2026-04-26T19:08:13Z"
},
{
"tag": "v0.10.0",
"kind": "minor",
"published_at": "2026-04-22T08:00:58Z"
},
{
"tag": "v0.9.2",
"kind": "patch",
"published_at": "2026-04-22T07:15:18Z"
},
{
"tag": "v0.9.0",
"kind": "minor",
"published_at": "2026-04-22T01:31:01Z"
},
{
"tag": "v0.8.1",
"kind": "patch",
"published_at": "2026-04-21T17:33:10Z"
},
{
"tag": "v0.8.0",
"kind": "minor",
"published_at": "2026-04-21T17:15:20Z"
},
{
"tag": "v0.7.0",
"kind": "minor",
"published_at": "2026-04-20T19:14:48Z"
},
{
"tag": "v0.6.0",
"kind": "minor",
"published_at": "2026-04-18T07:10:49Z"
},
{
"tag": "v0.5.0",
"kind": "minor",
"published_at": "2026-04-17T18:55:03Z"
},
{
"tag": "v0.4.0",
"kind": "minor",
"published_at": "2026-04-17T13:52:17Z"
},
{
"tag": "v0.3.0",
"kind": "minor",
"published_at": "2026-04-17T08:58:45Z"
},
{
"tag": "v0.2.3",
"kind": "patch",
"published_at": "2026-04-12T10:30:45Z"
},
{
"tag": "v0.2.2",
"kind": "patch",
"published_at": "2026-04-12T10:07:42Z"
},
{
"tag": "v0.2.1",
"kind": "patch",
"published_at": "2026-04-12T09:18:39Z"
},
{
"tag": "v0.2.0",
"kind": "minor",
"published_at": "2026-04-01T14:07:28Z"
},
{
"tag": "v0.1.0",
"kind": "minor",
"published_at": "2026-04-01T08:01:56Z"
}
],
"recent_commits": [
{
"oid": "5d75cd2d166a6de430531f1630851550a9165dad",
"body": "chore(ci): enforce golangci-lint in CI; add PR and issue templates",
"is_bot": false,
"headline": "Merge pull request #133 from hung12ct/chore/ci-lint-and-templates",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-07-24T16:09:24Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6086be968e2bf3524587ccec3d4de6e28a5dad79",
"body": "Adds a lint job (golangci-lint v2.5.0) alongside the existing vet/build/race\ntest, plus PR and bug/feature issue templates keyed to the project gates.",
"is_bot": false,
"headline": "chore(ci): enforce golangci-lint in CI; add PR and issue templates",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T16:05:43Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c543b30005f3d2857e1f8a208f2f2c0f831885d6",
"body": "feat(eval): agent evaluation harness (pkg/eval + gopherevals CLI)",
"is_bot": false,
"headline": "Merge pull request #132 from hung12ct/feat/eval-harness",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-07-24T15:13:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2041b89b85f2ad570afcd203ddeb9259205848de",
"body": null,
"is_bot": false,
"headline": "docs(changelog): add v0.34.0 — agent evaluation harness",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T15:11:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f83b07a27ef2583c1dd82831ab5edb0f5d7a0e23",
"body": "Feat/eval harness",
"is_bot": false,
"headline": "Merge pull request #131 from hung12ct/feat/eval-harness",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-07-24T11:13:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "efe279f004ae9ea99c08cba68e5877ee620ec903",
"body": null,
"is_bot": false,
"headline": "fix(eval): validate args_regex.key is non-empty",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T11:07:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c777d87f1887ad4467cdf743e2f6d92b64974b2d",
"body": "Strip XML-1.0-invalid control bytes from JUnit failure text so strict CI\nparsers accept the file, and render judge-inconclusive tasks as SKIP in\nMarkdown to match the JUnit <skipped> classification.",
"is_bot": false,
"headline": "fix(eval): sanitize JUnit control chars; align Markdown skip label",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T11:07:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5869213542da246beaba3e25352031b3693e23de",
"body": "A trial deadline expiring on a run that already hit max_iters reclassified\nthe cause as ctx; now the more specific terminal cause survives.",
"is_bot": false,
"headline": "fix(eval): keep max_iters/limit termination over ctx expiry",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T11:07:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "13a27dac4956391461dcf8706417ebae90cef8e9",
"body": "A schema-compliant judge returning verdict:pass but omitting score yielded\nscore=0, which could fail a PassPolicy.MinScore gate despite passing.",
"is_bot": false,
"headline": "fix(eval): require score in judge verdict schema",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T11:07:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5d859e5d37ee7f17122c6e588ad15977ce75c65a",
"body": "Greedy first-fit false-negatived when heterogeneous arg matchers shared a\ntool name (AnyArgs consuming the call a stricter matcher needed). Kuhn's\nmaximum bipartite matching finds a valid assignment when one exists.",
"is_bot": false,
"headline": "fix(eval): use bipartite matching for unordered/subset trajectories",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T11:07:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3cabf09e445ed8d033df5bbfdefee54803bd85bb",
"body": "buildProvider silently downgraded to the mock when LLM_PROVIDER was set\nbut construction failed (missing key), letting CI pass a real suite —\nincluding LLM judges — against a stub. Now it errors instead.",
"is_bot": false,
"headline": "fix(eval): fail when a named provider cannot be built",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T11:07:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d93b6587d9428c338994b9c557265791d8005323",
"body": "Capture ActionRequired/HITLDenied/HITLTimedOut events into the transcript\nas HITLRecords, with HITLTriggered/NoHITL graders and a yaml hitl block.\nRecords serialize, so gate assertions survive two-phase re-grade.",
"is_bot": false,
"headline": "feat(eval): assert human-in-the-loop approval gates",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T10:47:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "981b6405e693b7d774fa40d989f026f3462be824",
"body": null,
"is_bot": false,
"headline": "docs(readme): add evaluation harness section and example",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T10:38:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "824a19ab65d506de4084b79b6c05ddf6d329020d",
"body": "cmd/gopherevals runs a YAML suite against a builder agent (provider from\nenv, doubling as judge), writes JSON/JUnit/Markdown, and exits non-zero\nbelow threshold; -save-transcripts/-from-transcripts give a two-phase\nrun-then-regrade flow. Adds Runner.OnTranscript, examples/agent_eval\n(deterministic go-test + suite/agent YAML + CI recipe), and\ntest-eval/eval-example make targets.",
"is_bot": false,
"headline": "feat(eval): gopherevals CLI, example suite, and Makefile targets",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T10:37:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "02835d7b4df82c448a21ba31f7432df5b8838540",
"body": "LoadSuite/ParseSuiteBytes compile a declarative suite (multi-turn plus\nsingle-turn shorthand) into graders; the judge provider is injected in Go,\nnever named in YAML. SuiteValidationError reports every problem at once.",
"is_bot": false,
"headline": "feat(eval): YAML suite loader with aggregated validation",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T10:31:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ecfb66ec13fff7c56cdd925acac12129b3a4e404",
"body": "WriteTranscripts/ReadTranscripts (streaming JSONL), GradeRecorded re-runs\ngraders over stored transcripts without re-running the agent, and\nTaskFromHistory scaffolds a golden Task from a recorded session.",
"is_bot": false,
"headline": "feat(eval): transcript persistence, re-grade, and session capture",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T10:29:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1373cadfca70c471e33a9f525e0df9af2fc2025f",
"body": "WriteJSON (programmatic), WriteJUnit (one testcase per task; failure body\ncarries grade reasons, judge-inconclusive tasks emit <skipped>), and\nWriteMarkdown (PR-comment table + collapsible failure details).",
"is_bot": false,
"headline": "feat(eval): JSON, JUnit XML, and Markdown report writers",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T10:27:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d3cb6e8229da7df0b471dbbd3d705fb52992a9f4",
"body": "Judge grades a transcript against a rubric via agent.GenerateJSONInto,\nsampling N times and majority-voting (ties->fail, all-unknown->Unknown\nescape hatch, malformed samples dropped). IncludeTrajectory switches on\nevidence discipline; prompt trajectory is middle-truncated.",
"is_bot": false,
"headline": "feat(eval): LLM-as-judge grader with N-sample majority vote",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T10:25:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c73215d2e2837db37af2eda401af39500e461bb4",
"body": "Runner.RunSuite executes tasks/trials with a channel-semaphore pool into\npre-indexed slots (no result mutex), computes pass@k/pass^k, applies\nPassPolicy, and recovers grader panics. RunT drives a suite as go subtests.\nAdds report structs (SuiteReport/TaskReport/TrialReport/TurnReport).",
"is_bot": false,
"headline": "feat(eval): suite runner with bounded concurrency and RunT adapter",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T10:23:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ce89d9c0afab5d85e8e8ab32eab7310c5d8aa22c",
"body": "Trajectory() over tool-call records: strict, in_order (subsequence),\nunordered, subset, superset. Arg matchers ArgsExact/ArgsSubset/ArgsRegex/\nAnyArgs; partial-credit scoring and positional diffs.",
"is_bot": false,
"headline": "feat(eval): trajectory grader with five match modes",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T10:20:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9bac8da780895e93b28e134273f056a2b10710d5",
"body": "New pkg/eval: Task/Turn/Suite/PassPolicy, Target + WrapLoop adapter,\nCapture (stream->Transcript with tool-result join), and code graders\n(Contains/Regexp/Exact/NoError/All/Any).",
"is_bot": false,
"headline": "feat(eval): transcript capture and core grader types",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-24T10:18:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "14e1d53de48b726dd6ee26721bd9485c3940a21a",
"body": "GitHub/Google tokenize \"multi-agent\" and \"multiagent\" differently; the README\nonly used the hyphenated form, so the common no-hyphen query missed it. Add the\nvariant once in the opening sentence.\n\nClaude-Session: https://claude.ai/code/session_01N8KU1eBMd5ECQhoxqZr2wk",
"is_bot": false,
"headline": "docs: add \"multiagent\" spelling for search discoverability",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-21T05:06:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a089050691053ee00db89a7f39a50d5e66689a61",
"body": "The LICENSE body had been paraphrased (§4 and §9 wording changed), so GitHub\nreported the license as NOASSERTION — no badge, excluded from license-filtered\nsearch, and legally a modified (non-standard) license. Restore the verbatim\nApache-2.0 text from apache.org so it detects correctly and is a valid Apache\nlicense again. Only the appendix copyright line carries the project's name.\n\nClaude-Session: https://claude.ai/code/session_01N8KU1eBMd5ECQhoxqZr2wk",
"is_bot": false,
"headline": "chore: restore canonical Apache-2.0 LICENSE text",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-21T05:06:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "85d34bf1eae35f54d1656815276ffc87158ff24d",
"body": "refactor(llm)!: split providers into per-vendor subpackages + sampling controls",
"is_bot": false,
"headline": "Merge pull request #130 from hung12ct/refactor/llm-provider-subpackages",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-07-18T18:37:46Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bcd3dfe24fbac868a7f56492233dba17ccf76197",
"body": "…) + sampling controls",
"is_bot": false,
"headline": "docs(changelog): v0.33.0 — pkg/llm per-provider subpackages (breaking…",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-18T18:36:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "30a780c156b013ef017fc09122c0e191f8075893",
"body": "…import alias",
"is_bot": false,
"headline": "docs(llm): fix stale NewOpenAICompatProvider ref; drop redundant SDK …",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-18T18:33:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ab860ae75e5bfd9f300ac3a8b60fa1b145a5b4cb",
"body": "pkg/llm/anthropic, pkg/llm/openai, pkg/llm/gemini — importing one vendor no\nlonger links the other two SDKs. Adds WithTemperature/WithTopP (+ WithSeed on\nOpenAI/Gemini) sampling options. Breaking: import paths and constructor names.",
"is_bot": false,
"headline": "refactor(llm)!: split providers into per-vendor subpackages",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-07-18T18:20:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "37765a6607b72fd858daa1e40d2b05d047621455",
"body": "feat(builder): OKF frontmatter parsing and type/tag filtering for kno…",
"is_bot": false,
"headline": "Merge pull request #129 from hung12ct/feat/okf-knowledge-base-filtering",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-06-30T15:10:55Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "177fa1268d9ff588d5c3ed6d4e6aa0b9ef3cd875",
"body": "…wledge base\n\nStrip YAML frontmatter from injected docs, surface type/title/tags as\n<file> attributes, and add KBFilter to load only matching concepts.\nZero filter preserves existing load-all behavior.",
"is_bot": false,
"headline": "feat(builder): OKF frontmatter parsing and type/tag filtering for kno…",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-06-30T15:08:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6c245a4ae6cd7334d3c4432777f476e3ec5bf9d7",
"body": "…nt-result\n\nfix(agent): anti-loop counts same-args streak regardless of result",
"is_bot": false,
"headline": "Merge pull request #128 from hung12ct/fix/anti-loop-same-args-differe…",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-06-29T07:49:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "876d2ffcdb18c3659fcb8041709cc6dea13f8ea8",
"body": "Sub-agent tools wrap their own LLM, so identical args yield a different\nresult hash each run; the same-args counter no longer requires a matching\nresult, so such loops now warn and hard-stop instead of running to MaxIters.",
"is_bot": false,
"headline": "fix(agent): anti-loop counts same-args streak regardless of result",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-06-29T07:47:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3027fc6278d6922ee4e35b957729e339612672bd",
"body": "… redactor",
"is_bot": false,
"headline": "docs(changelog): v0.32.0 — PlanProposal payload (breaking) + SQL cell…",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-06-06T16:55:44Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bc81b1fe4ca853db5e5b7570715148e301e22c0c",
"body": "feat(sql-agent): WithCellRedactor to mask result values before the LLM",
"is_bot": false,
"headline": "Merge pull request #127 from hung12ct/feat/sql-agent-cell-redactor",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-06-06T16:54:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "47c1bdde40e836f1cb427c02b8c469a3a5e9fb86",
"body": "Adds an opt-in per-cell redactor applied to the model-facing preview only.\nIt deep-copies the redacted rows, so OnSQL, tools.Result.Structured, and the\nhost grid keep full-fidelity values while the model sees masked ones. nil\n(default) is a zero-allocation no-op.",
"is_bot": false,
"headline": "feat(sql-agent): WithCellRedactor to mask result values before the LLM",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-06-06T16:50:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "079db5d909bdbcf9be9f235cbe6f3a830c241296",
"body": "feat(agent)!: structured plan payload via PlanProposal",
"is_bot": false,
"headline": "Merge pull request #126 from hung12ct/feat/structured-plan-payload",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-06-06T05:35:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f68fee2d0c96ffda1b663024f0a0a0d28b4e719d",
"body": "ConfirmPlanFunc now takes PlanProposal{Plan, RawArgs} instead of a plain\nstring, so a host registering a structured exit_plan_mode tool can\nunmarshal typed steps from RawArgs without parsing markdown. Plan still\ncarries the built-in tool's markdown for the common case.\n\nBREAKING: ConfirmPlanFunc signature changed.",
"is_bot": false,
"headline": "feat(agent)!: structured plan payload via PlanProposal",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-06-06T05:33:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "828ca578928d4e1b38ce969d2fae943ebf45a3e2",
"body": "…m cancel classification",
"is_bot": false,
"headline": "docs(changelog): v0.31.5 — anti-loop cross-turn hard-stop + mid-strea…",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-06-06T01:22:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "41d2b736163439ccff22656d87e80b57e9bfe2e7",
"body": "…fication\n\nfix(agent): classify mid-stream cancel as ErrContextCancelled",
"is_bot": false,
"headline": "Merge pull request #124 from hung12ct/fix/ctx-cancel-midstream-classi…",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-06-06T01:20:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f51a171c289a8312d2cae6964cf7c68c0f2cf606",
"body": "…eseed\n\nrefactor(agent): derive anti-loop warning marker from shared prefix",
"is_bot": false,
"headline": "Merge pull request #125 from hung12ct/fix/anti-loop-warning-poisons-r…",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-06-06T01:20:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e7036cbbd8b751d71fcb2e65582de3c120a4427a",
"body": "The strip marker and the two Detect warning format strings now share\nloopWarnPrefix, so rewording the warning can't silently break the\ncross-turn strip. Add a guard test driven by real Detect output.",
"is_bot": false,
"headline": "refactor(agent): derive anti-loop warning marker from shared prefix",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-06-06T01:16:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "de5fe487a7216a774c1d977e4dcb2f1562b52c01",
"body": "A cancel landing while the provider stream is in flight returned a\nprovider error wrapped as LLMFailureError, so errors.Is(err,\nErrContextCancelled) missed it and a user Stop rendered as a model error.\nReclassify it before the wrap, mirroring the pre-call cancel path.",
"is_bot": false,
"headline": "fix(agent): classify mid-stream cancel as ErrContextCancelled",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-06-06T01:09:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ab87ae98b96bdb757614a0297bef85f03c870ce3",
"body": "…eseed\n\nfix(agent): strip anti-loop warning before cross-turn re-seed hash",
"is_bot": false,
"headline": "Merge pull request #123 from hung12ct/fix/anti-loop-warning-poisons-r…",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-06-06T01:08:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f09ea8c85dfe7ce9dd4c8a0319c7dd871ee8def3",
"body": "The injected [SYSTEM WARNING] embeds a consecutive-call count, so persisted\ntool results hashed differently when loopDetectorFromHistory re-seeded across\nturns, making the kill threshold unreachable. Strip the suffix on re-seed to\nrestore byte-identity with the live AddCall path.",
"is_bot": false,
"headline": "fix(agent): strip anti-loop warning before cross-turn re-seed hash",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-06-06T01:05:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "30ab1e9a064df2e5d8f0643d08213e13f381e288",
"body": null,
"is_bot": false,
"headline": "docs(changelog): v0.31.4 — WithLLMPreviewRows",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T14:15:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "515c3d147519608783e35f09acd7fbfaf44ea184",
"body": "Feat/sql agent llm preview rows",
"is_bot": false,
"headline": "Merge pull request #122 from hung12ct/feat/sql-agent-llm-preview-rows",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-31T14:14:00Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b41bb4440ec9aff81981d9939826a86e89f8cd40",
"body": "style: gofmt router_test.go comment alignment",
"is_bot": false,
"headline": "Merge pull request #121 from hung12ct/style/router-test-gofmt",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-31T14:13:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7af6f332cbbeb05366ab29cbfa58d6dc9f7479d3",
"body": "Pre-existing staticcheck finding surfaced when the package cache was\ninvalidated; no behavior change.",
"is_bot": false,
"headline": "refactor(builtin): fmt.Fprintf over WriteString(fmt.Sprintf) (QF1012)",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T14:10:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9124dfb09de20b0f9eee384f71c4b1d894d1f19f",
"body": "…eads\n\nDecouples LLM-visible rows from the full set emitted to the OnSQL hook and\ntools.Result.Structured. Opt-in (n<=0 = no-op, no behavior change); when\nset, only the first n rows are marshaled into the model context with the\ntrue RowCount and Truncated set so it knows it saw a sample.",
"is_bot": false,
"headline": "feat(builtin): add WithLLMPreviewRows to cap rows the sub-agent LLM r…",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T14:10:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b386c72e0290d0d40582afaa1ea5c5ec2a4c0223",
"body": "Trailing-comment realignment left over from the S1025 fix in #120\n(make lint does not run gofmt, so it slipped through).",
"is_bot": false,
"headline": "style: gofmt router_test.go comment alignment",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T12:05:55Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4a728ccf66f078a61ccbcd3c6b587e6fde234e39",
"body": "Style/gofmt cleanup",
"is_bot": false,
"headline": "Merge pull request #120 from hung12ct/style/gofmt-cleanup",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-31T12:00:44Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3a5ada37c087e2efef1966c7fe4b3e7b9ea797be",
"body": "Remove dead fields/const/func (unused) and apply staticcheck quickfixes\n(De Morgan, tagged switch, merged assignment, string conversion). No\nbehavior change; full suite green.",
"is_bot": false,
"headline": "refactor: clear unused and staticcheck lint findings",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T11:54:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9bcc9589a1ae8c7a2d140b95f8fe07dd4b8f9435",
"body": "errcheck excludes conventional no-action calls (Close, fmt.Fprint*,\nos.Remove cleanup, deferred SDK stream Close) and skips test setup;\nissue caps lifted so repeats are not silently hidden.",
"is_bot": false,
"headline": "build: add golangci-lint v2 config",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T11:53:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "cae7716233ea64b0efecce53943b49c8bea427fe",
"body": "The comment documented SQL's '' and backtick-doubling escapes literally;\ngofmt's TeX-style quote substitution would rewrite those pairs into curly\nquotes and corrupt the meaning. Reword to describe the escape without the\ntrigger pairs, keeping the file gofmt-clean.",
"is_bot": false,
"headline": "docs(builtin): reword scanQuoted comment to be gofmt-stable",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T11:39:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ff53f197e44b2169c9c85c9795f76a26cddde2e1",
"body": "Formatting only (alignment, line-grouping, blank lines) — no logic\nchange; full suite green. Excludes sql_validate.go, handled separately.",
"is_bot": false,
"headline": "style: gofmt remaining tracked files",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T11:38:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1fe6fc6fdecd2c4352170ce14a0d011ee28d4bf5",
"body": "Whitespace-only: struct-field realignment and trailing-newline trim on\nthe two files touched this session. No logic change.",
"is_bot": false,
"headline": "style(agent,builtin): gofmt sql_agent.go and memory_test.go",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T11:20:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6d8404c0312b1953e8d171e5fc639fd4f9bfe583",
"body": null,
"is_bot": false,
"headline": "docs(changelog): v0.31.3 — SQL-agent result contract + RowCount",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T10:45:37Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f91900313a9a9dc5b173fce2aa56278f0cb8f79d",
"body": "Fix/sql agent result contract",
"is_bot": false,
"headline": "Merge pull request #119 from hung12ct/fix/sql-agent-result-contract",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-31T10:44:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b0e31aa9ce36602cfe38e06413afc49b05c7f1d9",
"body": "…tured rows\n\nThe tool described itself as returning structured data but returned only\nthe sub-agent's prose answer, so a parent agent looped trying to extract\nverbatim rows for export. Describe it honestly (written answer, not raw\nrows) and attach the captured SQLResult on tools.Result.Structured for\nhost integrations.",
"is_bot": false,
"headline": "fix(builtin): honest call_sql_agent contract — written answer + struc…",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T10:41:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e7d305131267b34e814c5197a34aad402356240e",
"body": "The OnSQL hook fired without row-count or execution time even though\nSQLResult already carried both. Add RowCount + ExecutionMs to\nSQLQueryEvent and populate them at the makeEmitFunc chokepoint.",
"is_bot": false,
"headline": "feat(builtin): surface RowCount and ExecutionMs on SQLQueryEvent",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T10:41:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "256db12780932db942774676cbfab6dbfc4e1c2d",
"body": null,
"is_bot": false,
"headline": "docs(changelog): v0.31.2 — tool-call CorrelationID",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T10:18:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a2f35e79e5b7e3fd774f90924f4b0571d54aa1fe",
"body": "fix(agent): persist tool-call CorrelationID for reload-stable rendering",
"is_bot": false,
"headline": "Merge pull request #118 from hung12ct/fix/tool-call-correlation-id",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-31T10:16:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b5cb06f59cbd58be720c171a40e66e7f023e40d8",
"body": "Live events expose the opaque per-dispatch callID while the persisted\ntool row carried only the provider tCall.ID — disjoint namespaces, so\nconsumer-rendered artifact cards could not re-match after reload. Add\nhistory.Message.CorrelationID stamped with callID; ToolCallID stays the\nprovider ID for tool_use/tool_result adjacency.",
"is_bot": false,
"headline": "fix(agent): persist tool-call CorrelationID for reload-stable rendering",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T10:12:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8fc45da8247cfc5ac97b48bcfdfa2f901f5c3457",
"body": null,
"is_bot": false,
"headline": "docs(changelog): v0.31.1 — consolidator strict-schema fix",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T08:51:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d17a408c89968210dab6cb05e389d16b6583ee0a",
"body": "…required\n\nfix(agent): add tags to consolidator schema required array",
"is_bot": false,
"headline": "Merge pull request #117 from hung12ct/fix/consolidator-schema-strict-…",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-31T08:50:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a0c649bb021f98aec135c84cc620b751512f8c34",
"body": "OpenAI strict structured-outputs requires every declared property in\nrequired; tags was missing, silently no-oping memory consolidation on\nOpenAI. Add regression test asserting the invariant recursively.",
"is_bot": false,
"headline": "fix(agent): add tags to consolidator schema required array",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-31T08:49:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "770fb148aa4d92d2fa995b76eb678764959a892f",
"body": "…-func\n\nRefactor/builtin tools register func",
"is_bot": false,
"headline": "Merge pull request #116 from hung12ct/refactor/builtin-tools-register…",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-20T08:54:46Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "33a2b4a26ace3977c953afe6914abcc122171719",
"body": null,
"is_bot": false,
"headline": "refactor(builtin): rename file_read shadowed 'cap' to 'limit'",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-20T08:42:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "97e5feaf4eb2d92b93250029924ab1347c9f9bd9",
"body": "exit_plan_mode, show_media, read_url, file_read, web_search shed\ntheir struct + Descriptor + Execute boilerplate. tools.Registerer\ninterface lets RegisterFunc target both *tools.Registry and\n*builder.GlobalCatalog. Breaking: NewFooTool constructors removed.\nYAML configs unaffected (lookup by name).",
"is_bot": false,
"headline": "refactor(builtin)!: migrate 5 tools to tools.RegisterFunc (v0.31.0)",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-20T08:38:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3e647b695b4c479714316df05a8719791dbb985c",
"body": "Feat/v030 ergonomics ops",
"is_bot": false,
"headline": "Merge pull request #115 from hung12ct/feat/v030-ergonomics-ops",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-20T08:15:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c162ba5ddf6c3a1d5bc8abb278348e3b72202266",
"body": "Move emit to deferred cleanup in runLogicLoop AND continueLogicLoop\nvia installRunCostAccumulator helper. Drops the inline emit from\nhandleFinalAnswer so MaxIters / MaxToolCallsPerSession / fatal LLM\nerrors / Continue / Regenerate all surface cost too.",
"is_bot": false,
"headline": "fix(cost): emit RunCostEvent on all terminal paths",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-20T08:00:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "71ebf4d05a79410dba73c2bf85b9383e2c726230",
"body": "Five additive primitives: llmfake.ScriptedProvider, tools.RegisterFunc,\nBudgetTracker.Rewind, AgentLoop.Shutdown, PriceTable + RunCostEvent.\nAll opt-in, zero hot-path cost when unused. No breaking changes beyond\nEventVisitor (same v0.22 convention).",
"is_bot": false,
"headline": "feat: ergonomics + ops bundle (v0.30.0)",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-20T07:46:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "874969304fbc1ea404512191047e67bfa6a0d6c5",
"body": "New Consolidator.FirePolicy{Disabled, NTurns, MinInterval} with\nper-scope state. DefaultFirePolicy = {MinInterval: 10m} so adopters\nwho wire WithMemoryConsolidator don't accidentally pay one LLM call\nper turn. MinTranscriptMessages default raised 3 -> 6.\nBreaking default change.",
"is_bot": false,
"headline": "feat(memory)!: throttled Consolidator auto-fire (v0.29.0)",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-20T06:28:24Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "44bf91d37c781e8dc252945c7d5f5720220b9acf",
"body": "feat(memory): fail-closed empty scope + audit events (v0.28.0)",
"is_bot": false,
"headline": "Merge pull request #114 from hung12ct/feat/memory-scope-and-audit",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-20T06:01:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f0e34aa5a4968c1b504e0fd7cedeaa2f8a05834a",
"body": "MemoryScopeFunc returning \"\" now disables memory for that Run —\nloader skips, Consolidator skips, no audit event fires. Zero new\nAPI; the empty-string return is the contract. New typed events\nMemoryLoadedEvent (per-Run, includes Scope/NoteCount/EstimatedTokens)\nand MemoryConsolidatedEvent (post-Run, includes Scope/Before/After/\nError) ride the existing EventHandler chain.",
"is_bot": false,
"headline": "feat(memory): fail-closed empty scope + audit events (v0.28.0)",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-20T05:39:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e0f5ae18a4d37b2f00fbc49fd9bdc6f253cfc6a4",
"body": "feat(memory)!: bounded growth + merge-aware Consolidator (v0.28.0)",
"is_bot": false,
"headline": "Merge pull request #113 from hung12ct/feat/memory-bounded-and-merging",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-20T05:28:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c178a73e2dd4b2d29892a2828af98d2fd5163f61",
"body": "Closes the unbounded-growth + variable-key drift failure modes in\nv0.27.0. Store.List gains ListOpts (Limit/Tags/UpdatedAfter); new\nReplaceAll enables atomic merge. InMemStore now bounded by default\n(WithMaxNotesPerScope, DefaultMaxNotesPerScope=100). Consolidator\nreads existing notes + transcript, returns curated full set, atomic\nReplaceAll. Loader gains MemoryConfig{TokenBudget,MaxNotes}.\nBreaking: List/WithMemory/Consolidate signatures changed.",
"is_bot": false,
"headline": "feat(memory)!: bounded growth + merge-aware Consolidator (v0.28.0)",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-20T05:25:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "96a2d7222872e7d438a54492c30759ed3ce35fcd",
"body": null,
"is_bot": false,
"headline": "docs(changelog): add v0.27.0 — cross-session memory",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-20T04:51:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "07b99cfb69737a9a1e352c714f9a96b0453a99ff",
"body": "feat(memory): cross-session memory with Loader + Consolidator",
"is_bot": false,
"headline": "Merge pull request #112 from hung12ct/feat/pkg-memory-cross-session",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-20T04:50:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9860cabde4c68fdf640686d4bbbdc21c6361c411",
"body": "New pkg/memory (Note, Store, InMemStore) plus pkg/agent wiring:\nloader injects scoped notes into every Run's system prompt, optional\nConsolidator distills closed transcripts into notes via structured\noutput. Three opt-in options keep the disabled path zero-cost.",
"is_bot": false,
"headline": "feat(memory): cross-session memory with Loader + Consolidator",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-20T04:48:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c54c4577a23d4471b2f3a0165d1ecb85dca0dad3",
"body": "docs(changelog): add v0.26.3 + drop adopter-product names from entries",
"is_bot": false,
"headline": "Merge pull request #111 from hung12ct/docs/changelog-no-adopter-refs",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-18T15:38:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ff27b5d8702767e32aef93f8d459db634369c84c",
"body": "Library shipping artifacts describe failure modes on their own merits;\nthe adopter who reported each bug belongs in private notes only.",
"is_bot": false,
"headline": "docs(changelog): add v0.26.3 + drop adopter-product names from entries",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-18T15:33:39Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "abd741b7a803771a3fc929c8dcaf6dded1b009bf",
"body": "…tion\n\nfix(agent): seed loopDetector from history to catch cross-turn loops",
"is_bot": false,
"headline": "Merge pull request #110 from hung12ct/fix/agent-cross-turn-loop-detec…",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-18T15:07:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9bba728d59043a109e066e1c13413fabf5ad9b23",
"body": "iterateMessages now calls loopDetectorFromHistory(msgs) so prior\ntool_call/tool_result pairs feed the ring before the new turn runs.",
"is_bot": false,
"headline": "fix(agent): seed loopDetector from history to catch cross-turn loops",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-18T15:02:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c94501995033d784681f34e22582347f4825fd4d",
"body": null,
"is_bot": false,
"headline": "Merge branch 'fix/anthropic-accumulate-soft-truncation'",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-18T09:46:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5443962fa61d8b15429138ecb188953ae636d055",
"body": "Emit LimitExhaustedEvent with new Reason=incomplete_tool_use instead of\nkilling the turn, ship intact content, skip partial tool_use blocks.",
"is_bot": false,
"headline": "fix(llm/anthropic): recover from accumulate error on truncated tool_use",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-18T09:44:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6fb1aa84999caef736b4f59e4bea41ac6a119a07",
"body": "fix(llm/openai): stamp non-empty content on every role",
"is_bot": false,
"headline": "Merge pull request #109 from hung12ct/fix/openai-null-content-sweep",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-17T16:01:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7e01cd879b756d0d290a751155a68c4b946918ef",
"body": "v0.25.0 only stamped a space on assistant+tool-calls messages, leaving\ntool-result rows and empty-stream assistant rows exposed. gpt-4.1 and\ngpt-5 reject both with \"expected a string, got null.\" Move the stamp to\na single chokepoint pre-append; multimodal user messages stay untouched.",
"is_bot": false,
"headline": "fix(llm/openai): stamp non-empty content on every role",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-17T15:59:46Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6f178c62519554b13a4a3da768e152b9d85639a5",
"body": "docs(changelog): record v0.26.0",
"is_bot": false,
"headline": "Merge pull request #108 from hung12ct/docs/changelog-v0.26.0",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-17T10:45:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9a4f4f98b61763db032892d9e406c60ddd9a82e0",
"body": null,
"is_bot": false,
"headline": "docs(changelog): record v0.26.0",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-17T10:42:22Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "340168f341c2ed0b9b6a9a6f5e49221130c9b1b0",
"body": "feat(tools/builtin): harden SQL sub-agent against Gemini drift",
"is_bot": false,
"headline": "Merge pull request #107 from hung12ct/feat/sql-agent-gemini-hardening",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-17T09:52:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a2c7d81c552838ad65147783387ef1d41efe1470",
"body": "Imperative-negative safety contract + tightened HITL_BLOCKED prose so\nweakly-grounding models stop hallucinating destructive follow-ups and\nrespect denial. Adds WithProviderHint for adopter-specific addendums\nand a server-side bare \"SELECT *\" guard (WithAllowSelectStar to opt out).",
"is_bot": false,
"headline": "feat(tools/builtin): harden SQL sub-agent against Gemini drift",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-17T09:44:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bccc9d37995c468d7683d50a4f93a35415e0fd2f",
"body": "Refactor/tool interface collapse",
"is_bot": false,
"headline": "Merge pull request #106 from hung12ct/refactor/tool-interface-collapse",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-17T09:03:43Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "513c1aac224f65b0c24bcd6809a989bdc4aeef48",
"body": "Five integration-driven items on top of v0.24.0 — WithAllowDDL,\nSessionTitler, PatchDanglingToolCalls export + Anthropic sanitization,\nOpenAI GPT-5 content stamp, SQL sub-agent task-adherence directives.\nNo breaking changes.",
"is_bot": false,
"headline": "docs(changelog): record v0.25.0",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-17T09:02:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5e661b6b0b6cedd59abe97a5557478acc7b66309",
"body": "SessionMeta gains an optional Title field surfaced on every Query\nresult. The new optional capability agent.SessionTitler{ SetTitle(ctx,\nkey, title) error } is implemented by InMem, File, MySQL, and the\nhistoryfake backends. MySQL adds an idempotent ALTER TABLE migration\nso existing tables upgrade in place. Empty title clears any\npreviously-recorded label. Pairs with builtin.GenerateTitle for\nsidebar / picker UIs.",
"is_bot": false,
"headline": "feat(history,agent): SessionMeta.Title + SessionTitler capability",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-17T09:02:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9b94812351f7256b46cda5b7e7eb6a9d9425608f",
"body": "…applies it\n\nAdopters slicing session history for ad-hoc LLM calls (titling,\nsummarisation, classification) produced shapes that Anthropic rejected\nwith \"tool_use ids were found without tool_result blocks immediately\nafter.\" The internal sanitizer is now public, and the Anthropic\nconverter runs it on incoming memory so the converter is robust\nregardless of how the input slice was assembled. Zero behaviour change\nfor in-loop calls (the helper short-circuits when nothing is dangling).",
"is_bot": false,
"headline": "feat(agent,llm): export PatchDanglingToolCalls + Anthropic converter …",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-17T09:02:29Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "917d23d797512d9637a965f8849bbe13c92bf9f2",
"body": "The Go SDK tags ChatCompletionMessage.Content with omitempty, dropping\nempty strings from JSON entirely. GPT-5's stricter validator then 400s\nwith \"expected a string, got null\" on every intermediate tool-only turn.\nA single space passes omitempty and is a semantic no-op for the model.",
"is_bot": false,
"headline": "fix(llm/openai): stamp non-empty content on tool-call assistant messages",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-17T09:02:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ee7a21b3873fbe0b59332146af4652084e12fbad",
"body": "…ompt directives\n\nClassifySQL gains SQLKindDDL; CallSQLAgentTool.WithAllowDDL(bool) gates\nthe executor dispatch. Default false — orthogonal to WithAllowMutations.\nSystem prompt picks up two tail directives that pull weak instruction-\nfollowing models back onto the literal request and stop them echoing\npolicy text.",
"is_bot": false,
"headline": "feat(tools/builtin): opt-in DDL on SQL sub-agents + task-adherence pr…",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-17T09:02:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ed2d1f9b1f1dcfb80c7e20815e3f5a909d061726",
"body": null,
"is_bot": false,
"headline": "docs(changelog): record v0.24.0 — Tool interface collapse",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-17T05:22:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4ca8bdcf998a6c04288464ec8e4866e003067670",
"body": "refactor(tools): collapse Tool interface to Descriptor + Result",
"is_bot": false,
"headline": "Merge pull request #105 from hung12ct/refactor/tool-interface-collapse",
"author_name": "hung12ct",
"author_login": "hung12ct",
"committed_at": "2026-05-17T05:17:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a8abcfb29475507c6d5f3a80ef5a46a230147527",
"body": "The 6-method Tool interface plus 3 opt-in method-set interfaces\n(Cacheable, InlineRenderer, StructuredResult) silently dropped\ncapability flags whenever a tool was wrapped. Replaced with one\nDescriptor() ToolDescriptor accessor and one Execute() (Result, error)\nmethod — flags live as fields on the descriptor; structured payloads\nlive on Result.Structured. Wrappers now preserve every capability for\nfree. Registry.GetAll renamed to All to match the Get-prefix-drop in\nB.5.",
"is_bot": false,
"headline": "refactor(tools): collapse Tool interface to Descriptor + Result",
"author_name": "Hung Nguyen",
"author_login": "hung12ct",
"committed_at": "2026-05-17T05:07:13Z",
"body_truncated": false,
"is_coding_agent": false
}
],
"releases_count": 54,
"commits_last_year": 339,
"latest_release_at": "2026-07-24T15:13:01Z",
"latest_release_tag": "v0.34.0",
"releases_from_tags": true,
"days_since_last_push": 0,
"active_weeks_last_year": 11,
"days_since_latest_release": 0,
"mean_days_between_releases": 7.3
},
"community": {
"has_readme": true,
"has_license": true,
"has_description": true,
"has_contributing": false,
"health_percentage": 57,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": true
},
"ecosystem": {
"packages": [
{
"name": "github.com/hung12ct/gopheragent",
"exists": true,
"license": null,
"keywords": [],
"ecosystem": "go",
"matches_repo": true,
"registry_url": "https://pkg.go.dev/github.com/hung12ct/gopheragent",
"is_deprecated": false,
"latest_version": "v0.34.0",
"repository_url": "https://github.com/hung12ct/gopheragent",
"versions_count": 54,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": null,
"monthly_downloads": null,
"first_published_at": null,
"latest_published_at": "2026-07-24T15:13:01Z",
"latest_version_yanked": null,
"days_since_latest_publish": 0
}
]
},
"popularity": {
"forks": 0,
"stars": 2,
"watchers": 0,
"fork_history": {
"days": [],
"complete": true,
"collected": 0,
"total_forks": 0
},
"star_history": null,
"open_issues_and_prs": 0
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [
"examples"
],
"has_llms_txt": false,
"has_dockerfile": false,
"has_mcp_signal": false,
"bootstrap_files": [
"Makefile"
],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [],
"toolchain_manifests": [
"go.mod"
],
"largest_source_bytes": 44792,
"source_files_sampled": 243,
"oversized_source_files": 0,
"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": "v1.27.1"
},
{
"name": "github.com/go-sql-driver/mysql",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v1.9.3"
},
{
"name": "github.com/joho/godotenv",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v1.5.1"
},
{
"name": "github.com/sashabaranov/go-openai",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v1.41.2"
},
{
"name": "go.opentelemetry.io/otel",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v1.29.0"
},
{
"name": "go.opentelemetry.io/otel/trace",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v1.29.0"
},
{
"name": "google.golang.org/genai",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v1.52.1"
},
{
"name": "gopkg.in/yaml.v3",
"manifest": "go.mod",
"ecosystem": "go",
"version_constraint": "v3.0.1"
}
],
"all_dependencies": {
"error": "GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository",
"source": null,
"packages": [],
"collected": false,
"truncated": false,
"total_count": null,
"direct_count": null,
"indirect_count": null
}
},
"maintainership": {
"issues": {
"open_prs": 0,
"merged_prs": 132,
"open_issues": 0,
"closed_ratio": null,
"closed_issues": 0,
"closed_unmerged_prs": 1
},
"bus_factor": 1,
"bot_contributors": 0,
"top_contributors": [
{
"type": "User",
"login": "hung12ct",
"commits": 360,
"avatar_url": "https://avatars.githubusercontent.com/u/48434938?v=4"
}
],
"contributors_sampled": 1,
"top_contributor_share": 1
},
"quality_signals": {
"has_ci": true,
"has_tests": true,
"ci_workflows": [
"ci.yml"
],
"has_docs_dir": false,
"linter_configs": [
".golangci.yml"
],
"has_editorconfig": false,
"has_linter_config": true,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [
"go.sum"
],
"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": "6 out of 6 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": 0,
"reason": "Found 0/8 approved changesets -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 0,
"reason": "project has 0 contributing companies or organizations -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#contributors"
},
{
"name": "Dangerous-Workflow",
"score": 10,
"reason": "no dangerous workflow patterns detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dangerous-workflow"
},
{
"name": "Dependency-Update-Tool",
"score": 0,
"reason": "no update tool detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dependency-update-tool"
},
{
"name": "Fuzzing",
"score": 0,
"reason": "project is not fuzzed",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
},
{
"name": "License",
"score": 10,
"reason": "license file detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
},
{
"name": "Maintained",
"score": 10,
"reason": "30 commit(s) and 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": 0,
"reason": "dependency not pinned by hash detected -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#pinned-dependencies"
},
{
"name": "SAST",
"score": 0,
"reason": "SAST tool is not run on all commits -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#sast"
},
{
"name": "Security-Policy",
"score": 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": 10,
"reason": "GitHub workflow tokens follow principle of least privilege",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
},
{
"name": "Vulnerabilities",
"score": 0,
"reason": "32 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "5d75cd2d166a6de430531f1630851550a9165dad",
"ran_at": "2026-07-24T20:44:31Z",
"aggregate_score": 4.5,
"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": "2026-07-24T16:10:52Z",
"oldest_open_prs": [],
"last_merged_pr_at": "2026-07-24T16:09:26Z",
"ci_last_conclusion": "SUCCESS",
"oldest_open_issues": []
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/hung12ct/gopheragent",
"host": "github.com",
"name": "gopheragent",
"owner": "hung12ct"
},
"metrics": {
"overall": {
"key": "overall",
"band": "moderate",
"name": "Overall health",
"note": null,
"notes": [],
"value": 57,
"inputs": {
"security": 45,
"vitality": 78,
"community": 27,
"governance": 50,
"engineering": 80
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "good",
"name": "Vitality",
"value": 78,
"weight": 0.22,
"metrics": [
{
"key": "development_activity",
"band": "good",
"name": "Development activity",
"note": null,
"notes": [],
"value": 72,
"inputs": {
"commits_last_year": 339,
"human_commit_share": 1,
"days_since_last_push": 0,
"active_weeks_last_year": 11
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 0 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 0
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "11/52 weeks with commits",
"points": 7.6,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 11
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "339 commits in the last year",
"points": 18,
"status": "met",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 339
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "30 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": 54,
"latest_release_tag": "v0.34.0",
"releases_from_tags": true,
"days_since_latest_release": 0,
"mean_days_between_releases": 7.3
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "54 version tags (no GitHub releases)",
"points": 16.2,
"status": "partial",
"details": [
{
"code": "version_tags_no_releases",
"params": {
"count": 54
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 0 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 0
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~7.3 days",
"points": 27,
"status": "met",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 7.3
}
}
],
"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": "critical",
"name": "Community & Adoption",
"value": 27,
"weight": 0.18,
"metrics": [
{
"key": "popularity",
"band": "critical",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 1,
"inputs": {
"forks": 0,
"stars": 2,
"watchers": 0,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "2 stars",
"points": 0,
"status": "missed",
"details": [
{
"code": "stars",
"params": {
"count": 2
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "0 forks",
"points": 0,
"status": "missed",
"details": [
{
"code": "forks",
"params": {
"count": 0
}
}
],
"max_points": 25
},
{
"key": "watchers",
"name": "Watchers",
"detail": "0 watchers",
"points": 0,
"status": "missed",
"details": [
{
"code": "watchers",
"params": {
"count": 0
}
}
],
"max_points": 15
}
]
},
{
"key": "community_health",
"band": "moderate",
"name": "Community health",
"note": null,
"notes": [],
"value": 57,
"inputs": {
"has_readme": true,
"has_license": true,
"has_contributing": false,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": true
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 22.5,
"status": "met",
"details": [],
"max_points": 22.5
},
{
"key": "license",
"name": "License",
"detail": "recognized license (Apache-2.0)",
"points": 22.5,
"status": "met",
"details": [
{
"code": "license_standard",
"params": {}
},
{
"code": "license_spdx",
"params": {
"spdx": "Apache-2.0"
}
}
],
"max_points": 22.5
},
{
"key": "contributing_guide",
"name": "CONTRIBUTING guide",
"detail": null,
"points": 0,
"status": "missed",
"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": 6.3,
"status": "met",
"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": 50,
"weight": 0.24,
"metrics": [
{
"key": "maintainer_resilience",
"band": "critical",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 10,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 1,
"top_contributor_share": 1
},
"components": [
{
"key": "bus_factor",
"name": "Bus factor",
"detail": "1 contributor(s) cover half of all commits",
"points": 9,
"status": "partial",
"details": [
{
"code": "bus_factor",
"params": {
"count": 1
}
}
],
"max_points": 54
},
{
"key": "commit_distribution",
"name": "Commit distribution",
"detail": "top contributor authored 100% of commits",
"points": 0,
"status": "missed",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 100
}
}
],
"max_points": 22.5
},
{
"key": "contributor_breadth",
"name": "Contributor breadth",
"detail": "1 contributors",
"points": 1.4,
"status": "partial",
"details": [
{
"code": "contributors_sampled",
"params": {
"count": 1
}
}
],
"max_points": 13.5
},
{
"key": "openssf_scorecard_contributors",
"name": "OpenSSF Scorecard: Contributors",
"detail": "project has 0 contributing companies or organizations -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "responsiveness",
"band": "good",
"name": "Issue & PR responsiveness",
"note": "Excluded from scoring (no data or not applicable): Issue resolution. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"issue_resolution"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 71,
"inputs": {
"merged_prs": 132,
"open_issues": 0,
"closed_issues": 0,
"issue_closed_ratio": null,
"closed_unmerged_prs": 1
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "no issues or no data",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_issues_or_data",
"params": {}
}
],
"max_points": 46.75
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "132/133 decided PRs merged",
"points": 38,
"status": "partial",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 132,
"decided": 133
}
}
],
"max_points": 38.25
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 0/8 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "at_risk",
"name": "Ownership & stewardship",
"note": "Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"verified_domain"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 39,
"inputs": {
"followers": 1,
"owner_type": "User",
"is_verified": null,
"owner_login": "hung12ct",
"public_repos": 9,
"account_age_days": 2692
},
"components": [
{
"key": "ownership_backing",
"name": "Ownership backing",
"detail": "personal (user) account",
"points": 10,
"status": "partial",
"details": [
{
"code": "owner_personal",
"params": {}
}
],
"max_points": 30
},
{
"key": "verified_domain",
"name": "Verified domain",
"detail": "not applicable to user accounts",
"points": 0,
"status": "excluded",
"details": [
{
"code": "not_applicable_to_user_accounts",
"params": {}
}
],
"max_points": 20
},
{
"key": "owner_reach",
"name": "Owner reach",
"detail": "1 followers of hung12ct",
"points": 2.2,
"status": "partial",
"details": [
{
"code": "owner_followers",
"params": {
"count": 1,
"login": "hung12ct"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "9 public repos, account ~7 yr old",
"points": 19.3,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 9
}
},
{
"code": "account_age_years",
"params": {
"years": 7
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "excellent",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"github.com/hung12ct/gopheragent"
],
"ecosystems": "go",
"any_deprecated": false,
"min_days_since_publish": 0
},
"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 0 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 0
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "54 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 54
}
}
],
"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": 80,
"weight": 0.2,
"metrics": [
{
"key": "engineering_practices",
"band": "good",
"name": "Engineering practices",
"note": null,
"notes": [],
"value": 84,
"inputs": {
"has_ci": true,
"has_tests": true,
"has_editorconfig": false,
"has_linter_config": true,
"has_precommit_config": false
},
"components": [
{
"key": "ci_workflows",
"name": "CI workflows",
"detail": "1 workflow(s)",
"points": 24,
"status": "met",
"details": [
{
"code": "ci_workflows",
"params": {
"count": 1
}
}
],
"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": ".golangci.yml",
"points": 16,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": ".golangci.yml"
}
}
],
"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": "6 out of 6 merged PRs checked by a CI test -- score normalized to 10",
"points": 20,
"status": "met",
"details": [],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "good",
"name": "Documentation",
"note": null,
"notes": [],
"value": 75,
"inputs": {
"topics": [
"agent",
"ai-agent",
"anthropic",
"framework",
"gemini",
"go",
"golang",
"llm",
"multi-agent",
"openai",
"chatbot",
"agent-framework",
"agentic",
"agents",
"ai-agents",
"function-calling",
"llm-framework",
"multiagent",
"tool-use"
],
"has_wiki": true,
"homepage": "https://pkg.go.dev/github.com/hung12ct/gopheragent",
"has_readme": true,
"has_docs_dir": false,
"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": 0,
"status": "missed",
"details": [],
"max_points": 25
},
{
"key": "documentation_homepage_site",
"name": "Documentation / homepage site",
"detail": "https://pkg.go.dev/github.com/hung12ct/gopheragent",
"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": "19 topics",
"points": 10,
"status": "met",
"details": [
{
"code": "topics_count",
"params": {
"count": 19
}
}
],
"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": 45,
"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": 45,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 16,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 2,
"scorecard_aggregate": 4.5
},
"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": "6 out of 6 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 0/8 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 0 contributing companies or organizations -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "dangerous_workflow",
"name": "Dangerous-Workflow",
"detail": "no dangerous workflow patterns detected",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
},
{
"key": "dependency_update_tool",
"name": "Dependency-Update-Tool",
"detail": "no update tool detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "fuzzing",
"name": "Fuzzing",
"detail": "project is not fuzzed",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "license",
"name": "License",
"detail": "license file detected",
"points": 2.5,
"status": "met",
"details": [],
"max_points": 2.5
},
{
"key": "maintained",
"name": "Maintained",
"detail": "30 commit(s) and 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 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "sast",
"name": "SAST",
"detail": "SAST tool is not run on all commits -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "security_policy",
"name": "Security-Policy",
"detail": "security policy file 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": "GitHub workflow tokens follow principle of least privilege",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "vulnerabilities",
"name": "Vulnerabilities",
"detail": "32 existing vulnerabilities detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
}
]
}
],
"description": "Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure?"
},
{
"key": "ai_readiness",
"band": "moderate",
"name": "AI Readiness",
"value": 62,
"weight": 0,
"metrics": [
{
"key": "ai_agent_context",
"band": "at_risk",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 40,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 0.99,
"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": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
},
{
"key": "legible_commit_history",
"name": "Legible commit history",
"detail": "99 of 100 human commits state their intent (structured subject or explanatory body)",
"points": 40,
"status": "met",
"details": [
{
"code": "legible_history",
"params": {
"legible": 99,
"sampled": 100
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "good",
"name": "Verify loop (build / test / typecheck)",
"note": null,
"notes": [],
"value": 72,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [
"go.sum"
],
"has_dockerfile": false,
"typed_language": true,
"bootstrap_files": [
"Makefile"
],
"has_devcontainer": false,
"has_linter_config": true,
"typecheck_configs": [],
"agent_commit_share": 0,
"toolchain_manifests": [
"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": ".golangci.yml",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": ".golangci.yml"
}
}
],
"max_points": 11
},
{
"key": "static_type_checking",
"name": "Static type checking",
"detail": "Go (statically typed)",
"points": 11,
"status": "met",
"details": [
{
"code": "statically_typed_language",
"params": {
"language": "Go"
}
}
],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": "lockfile",
"points": 10,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "lockfile"
}
}
],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "no agent-authored commits among the last 100",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_agent_authored_commits",
"params": {
"sampled": 100
}
}
],
"max_points": 10
},
{
"key": "automated_maintenance",
"name": "Automated maintenance",
"detail": "no automated dependency updates observed",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_dependency_automation",
"params": {}
}
],
"max_points": 8
},
{
"key": "openssf_scorecard_pinned_dependencies",
"name": "OpenSSF Scorecard: Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "ai_code_legibility",
"band": "excellent",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"primary_language": "Go",
"largest_source_bytes": 44792,
"source_files_sampled": 243,
"oversized_source_files": 0
},
"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": "0/243 source files over 60KB",
"points": 55,
"status": "met",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 243,
"oversized": 0
}
}
],
"max_points": 55
}
]
},
{
"key": "ai_interfaces",
"band": "at_risk",
"name": "Machine-readable interfaces",
"note": null,
"notes": [],
"value": 40,
"inputs": {
"example_dirs": [
"examples"
],
"has_mcp_signal": false,
"api_schema_files": []
},
"components": [
{
"key": "api_schema_openapi_graphql_proto",
"name": "API schema (OpenAPI/GraphQL/proto)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"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": "2026-07-24T20:44:44.325349Z",
"schema_version": "0.27.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/h/hung12ct/gopheragent.svg",
"full_name": "hung12ct/gopheragent",
"license_state": "standard",
"license_spdx": "Apache-2.0"
}Bewertungen sind Signale, keine Garantien. Sie spiegeln öffentlich sichtbare Praxis auf GitHub wider — kein Code-Audit und keine Sicherheitsgarantie.
Fehlende Daten werden ausgeschlossen und die Gewichte neu normiert, nie als null bewertet. Die Methodik ist versioniert und offen: Metriken v1.13.0, Schema v0.27.0 — vollständige Methodik · Metriken-Wiki.
Wie ein einzelnes Ergebnis im Gesamtregister steht: aggregierte Statistiken — Go.