Public recordModerate
Software health reportschema 0.27.0 · metrics 1.13.0 · 2026-07-24 13:25 UTC
gumieri / nenya
A lightweight, highly secure AI API Gateway/Proxy written in Go. Acts as transparent middleware between local AI coding clients (OpenCode/Pi/Cursor) and upstream LLM providers (Gemini, DeepSeek, Zhipu z.ai).
gumieri/nenya holds a health index of 64 out of 100, placing it in the Moderate band. It scores highest on Vitality (84/100) and lowest on Community & Adoption (35/100). It was last updated 2 days ago. A single contributor accounts for most of its recent work.
64
overall / 100Software health index
Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At risk ceiling of 49. AI Readiness sits outside the overall score.
64
Excellent85-100Exemplary; meets essentially all checked criteria
Good70-84Healthy; minor gaps
Moderate50-69Acceptable with notable gaps; review recommended
At risk30-49Significant weaknesses; adoption warrants caution
Critical1-29Severe problems (abandoned, single-maintainer, no hygiene)
Score profile
Each axis is a category. The shape matters more than the average — a healthy subject fills the whole shape, while a spike-and-crater profile means strength in one dimension is masking risk in another.
Ownership
Rafael GumieriPersonal account
70 followers38 public repossince Feb 2011@Geekie @arcotech-services
This repository is owned by a personal account. A single-owner project carries more continuity risk than an organization-backed one.
Metrics by category
Vitality
Is the project alive — is code being written and are releases shipping?
84
Development activity
74Good
How it's scored
| 36/36 | Push recency — last push 2 days ago |
| 10.4/36 | Commit cadence — 15/52 weeks with commits |
| 18/18 | Commit volume — 485 commits in the last year |
| 10/10 | OpenSSF Scorecard: Maintained — 30 commit(s) and 3 issue activity found in the last 90 days -- score normalized to 10 |
Inputs used
| commits_last_year | 485 |
| human_commit_share | 1 |
| days_since_last_push | 2 |
| active_weeks_last_year | 15 |
Release discipline
98Excellent
How it's scored
| 27/27 | Ships releases — 21 releases published |
| 36/36 | Release recency — latest release 6 days ago |
| 27/27 | Release cadence — a release every ~3.1 days |
| 8/10 | OpenSSF Scorecard: Signed-Releases — 5 out of the last 5 releases have a total of 5 signed artifacts. |
Inputs used
| releases_count | 21 |
| latest_release_tag | v0.8.6 |
| releases_from_tags | no |
| days_since_latest_release | 6 |
| mean_days_between_releases | 3.1 |
Community & Adoption
Does the project have users, downloads, attention, and a welcoming setup for contributors?
35
Popularity & adoption
22Critical
How it's scored
| 22.4/60 | Stars — 25 stars |
| 0/25 | Forks — 0 forks |
| 0/15 | Watchers — 0 watchers |
Inputs used
| forks | 0 |
| stars | 25 |
| watchers | 0 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
Community health
50Moderate
How it's scored
| 22.5/22.5 | README |
| 22.5/22.5 | License — recognized license (Apache-2.0) |
| 0/18 | CONTRIBUTING guide |
| 0/13.5 | Code of conduct |
| 0/7.2 | Issue template |
| 0/6.3 | PR template |
Inputs used
| has_readme | yes |
| has_license | yes |
| has_contributing | no |
| has_issue_template | no |
| has_code_of_conduct | no |
| has_pull_request_template | no |
Sustainability & Governance
Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?
48
Maintainer resilience (bus factor)
16Critical
How it's scored
| 9/54 | Bus factor — 1 contributor(s) cover half of all commits |
| 0/22.5 | Commit distribution — top contributor authored 100% of commits |
| 1.4/13.5 | Contributor breadth — 1 contributors |
| 6/10 | OpenSSF Scorecard: Contributors — project has 2 contributing companies or organizations -- score normalized to 6 |
Inputs used
| bus_factor | 1 |
| contributors_sampled | 1 |
| top_contributor_share | 1 |
How it's scored
| 46.8/46.8 | Issue resolution — 100% of issues closed |
| 28/38.3 | PR acceptance — 11/15 decided PRs merged |
| 0/15 | OpenSSF Scorecard: Code-Review — Found 0/30 approved changesets -- score normalized to 0 |
Inputs used
| merged_prs | 11 |
| open_issues | 0 |
| closed_issues | 3 |
| issue_closed_ratio | 1 |
| closed_unmerged_prs | 4 |
Ownership & stewardship
59Moderate
How it's scored
| 10/30 | Ownership backing — personal (user) account |
| 0/20 | Verified domain — not applicable to user accounts |
| 13.3/25 | Owner reach — 70 followers of gumieri |
| 23.6/25 | Track record — 38 public repos, account ~15 yr old |
Inputs used
| followers | 70 |
| owner_type | User |
| is_verified | — |
| owner_login | gumieri |
| public_repos | 38 |
| account_age_days | 5,650 |
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.
Engineering Quality
Are baseline engineering and documentation practices in place?
82
Engineering practices
80Good
How it's scored
| 24/24 | CI workflows — 3 workflow(s) |
| 24/24 | Tests present |
| 16/16 | Linter config — .golangci.yml |
| 0/9.6 | Pre-commit hooks |
| 0/6.4 | .editorconfig |
| 0/20 | OpenSSF Scorecard: CI-Tests — no data |
Inputs used
| has_ci | yes |
| has_tests | yes |
| has_editorconfig | no |
| has_linter_config | yes |
| has_precommit_config | no |
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: CI-Tests. Remaining weights renormalized.
Documentation
85Excellent
How it's scored
| 30/30 | README |
| 25/25 | Documentation directory |
| 0/15 | Documentation / homepage site |
| 10/10 | Repository description |
| 10/10 | Topics — 20 topics |
| 10/10 | Wiki |
Inputs used
| topics | ai, ai-governance, ai-safety, ai-security, ai-tools, ai-gateway, ai-proxy, anthropic, litellm-alternative, llm, llm-gateway, observability, ollama, openai, openai-compatible-api, proxy, deepseek, opencode-zen, zhipu-ai, openai-proxy |
| has_wiki | yes |
| homepage | — |
| has_readme | yes |
| has_docs_dir | yes |
| has_description | yes |
Security
Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?
68
Security posture
68Moderate
How it's scored
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 0/7.5 | Branch-Protection — branch protection not enabled on development/release branches |
| 0/2.5 | CI-Tests — no data |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 0/7.5 | Code-Review — Found 0/30 approved changesets -- score normalized to 0 |
| 1.5/2.5 | Contributors — project has 2 contributing companies or organizations -- score normalized to 6 |
| 10/10 | Dangerous-Workflow — no dangerous workflow patterns detected |
| 7.5/7.5 | Dependency-Update-Tool — update tool detected |
| 5/5 | Fuzzing — project is fuzzed |
| 2.5/2.5 | License — license file detected |
| 7.5/7.5 | Maintained — 30 commit(s) and 3 issue activity found in the last 90 days -- score normalized to 10 |
| 5/5 | Packaging — packaging workflow detected |
| 0/5 | Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
| 5/5 | SAST — SAST tool detected: CodeQL |
| 5/5 | Security-Policy — security policy file detected |
| 6/7.5 | Signed-Releases — 5 out of the last 5 releases have a total of 5 signed artifacts. |
| 0/7.5 | Token-Permissions — detected GitHub workflow tokens with excessive permissions |
| 7.5/7.5 | Vulnerabilities — 0 existing vulnerabilities detected |
Inputs used
| source | openssf_scorecard |
| checks_evaluated | 17 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 1 |
| scorecard_aggregate | 6.8 |
Excluded from scoring (no data or not applicable): ci_tests. Remaining weights renormalized.
AI Readiness
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.
76
Agent context & guidance
82Good
How it's scored
| 45/45 | Agent instructions — AGENTS.md |
| 0/15 | Machine-readable docs (llms.txt) |
| 36.8/40 | Legible commit history — 69 of 100 human commits state their intent (structured subject or explanatory body) |
Inputs used
| has_llms_txt | no |
| legible_history_share | 0.69 |
| agent_instruction_files | AGENTS.md |
| agent_instruction_max_bytes | 28,024 |
How it's scored
| 18/18 | One-command bootstrap — mise.toml |
| 22/22 | Automated tests |
| 11/11 | Lint / format config — .golangci.yml |
| 11/11 | Static type checking — Go (statically typed) |
| 10/10 | Reproducible environment — Dockerfile, lockfile |
| 0/10 | Demonstrated agent practice — no agent-authored commits among the last 100 |
| 5/8 | Automated maintenance — dependency automation configured, none observed in the sampled commits |
| 0/10 | OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
Inputs used
| has_nix | no |
| has_tests | yes |
| lockfiles | go.sum |
| has_dockerfile | yes |
| typed_language | yes |
| bootstrap_files | mise.toml |
| has_devcontainer | no |
| has_linter_config | yes |
| typecheck_configs | — |
| agent_commit_share | 0 |
| toolchain_manifests | go.mod |
| dependency_bot_commit_share | 0 |
Code legibility for models
100Excellent
How it's scored
| 45/45 | Type-checkable code — Go (statically typed) |
| 54.8/55 | Manageable file sizes — 1/278 source files over 60KB |
Inputs used
| primary_language | Go |
| largest_source_bytes | 75,201 |
| source_files_sampled | 278 |
| oversized_source_files | 1 |
Machine-readable interfaces
40At risk
How it's scored
| 0/40 | API schema (OpenAPI/GraphQL/proto) |
| 0/20 | MCP server |
| 40/40 | Runnable examples — examples |
Inputs used
| example_dirs | examples |
| has_mcp_signal | no |
| api_schema_files | — |
Key facts
25GitHub stars
1contributors
485commits, last 12 months
2days since last push
21releases
1bus factor
0open issues
Gopackage ecosystems
Data collection warnings
- Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
- Could not fetch go package 'github.com/nenya' from its registry
More detail
OpenSSF Scorecard 6.8 / 10
6.8aggregate
Independent, tool-agnostic security assessment from the open-source OpenSSF Scorecard. Each check rewards a security practice, not a specific vendor's tool. Checks Scorecard could not determine are marked n/a and excluded from the security score (never counted as zero).
| 10 | Binary-Artifacts | no binaries found in the repo |
| 0 | Branch-Protection | branch protection not enabled on development/release branches |
| n/a | CI-Tests | no pull request found |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 0 | Code-Review | Found 0/30 approved changesets -- score normalized to 0 |
| 6 | Contributors | project has 2 contributing companies or organizations -- score normalized to 6 |
| 10 | Dangerous-Workflow | no dangerous workflow patterns detected |
| 10 | Dependency-Update-Tool | update tool detected |
| 10 | Fuzzing | project is fuzzed |
| 10 | License | license file detected |
| 10 | Maintained | 30 commit(s) and 3 issue activity found in the last 90 days -- score normalized to 10 |
| 10 | Packaging | packaging workflow detected |
| 0 | Pinned-Dependencies | dependency not pinned by hash detected -- score normalized to 0 |
| 10 | SAST | SAST tool detected: CodeQL |
| 10 | Security-Policy | security policy file detected |
| 8 | Signed-Releases | 5 out of the last 5 releases have a total of 5 signed artifacts. |
| 0 | Token-Permissions | detected GitHub workflow tokens with excessive permissions |
| 10 | Vulnerabilities | 0 existing vulnerabilities detected |
All dependencies 0
Full resolved dependency set from the GitHub dependency graph: 0 direct and 0 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.
| Registry | Package | Version | Relation |
|---|
Dependency advisories not assessed
Advisory matching could not run for this report: No resolved dependencies to assess
Raw JSON report machine-readable
{
"data": {
"repo": {
"topics": [
"ai",
"ai-governance",
"ai-safety",
"ai-security",
"ai-tools",
"ai-gateway",
"ai-proxy",
"anthropic",
"litellm-alternative",
"llm",
"llm-gateway",
"observability",
"ollama",
"openai",
"openai-compatible-api",
"proxy",
"deepseek",
"opencode-zen",
"zhipu-ai",
"openai-proxy"
],
"is_fork": false,
"size_kb": 3098,
"has_wiki": true,
"homepage": null,
"languages": {
"Go": 2070947,
"Shell": 9474,
"Dockerfile": 1138
},
"pushed_at": "2026-07-21T17:24:16Z",
"created_at": "2026-03-28T21:23:38Z",
"owner_type": "User",
"updated_at": "2026-07-18T00:20:53Z",
"description": "A lightweight, highly secure AI API Gateway/Proxy written in Go. Acts as transparent middleware between local AI coding clients (OpenCode/Pi/Cursor) and upstream LLM providers (Gemini, DeepSeek, Zhipu z.ai).",
"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": "gumieri.com",
"name": "Rafael Gumieri",
"type": "User",
"login": "gumieri",
"company": "@Geekie @arcotech-services ",
"location": "Maringá, Paraná - Brazil",
"followers": 70,
"avatar_url": "https://avatars.githubusercontent.com/u/596856?v=4",
"created_at": "2011-02-02T14:28:11Z",
"is_verified": null,
"public_repos": 38,
"account_age_days": 5650
},
"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": "v0.8.6",
"kind": "patch",
"published_at": "2026-07-17T19:16:59Z"
},
{
"tag": "v0.8.5",
"kind": "patch",
"published_at": "2026-07-16T18:19:47Z"
},
{
"tag": "v0.8.4",
"kind": "patch",
"published_at": "2026-07-16T13:23:41Z"
},
{
"tag": "v0.8.3",
"kind": "patch",
"published_at": "2026-07-15T17:08:37Z"
},
{
"tag": "v0.8.2",
"kind": "patch",
"published_at": "2026-07-14T18:38:59Z"
},
{
"tag": "v0.8.1",
"kind": "patch",
"published_at": "2026-07-14T03:05:56Z"
},
{
"tag": "v0.8.0",
"kind": "minor",
"published_at": "2026-07-13T18:44:24Z"
},
{
"tag": "v0.7.1",
"kind": "patch",
"published_at": "2026-07-10T23:59:14Z"
},
{
"tag": "v0.7.0",
"kind": "minor",
"published_at": "2026-07-03T01:53:55Z"
},
{
"tag": "v0.6.3",
"kind": "patch",
"published_at": "2026-06-19T13:42:11Z"
},
{
"tag": "v0.6.2",
"kind": "patch",
"published_at": "2026-06-17T17:30:07Z"
},
{
"tag": "v0.6.1",
"kind": "patch",
"published_at": "2026-06-09T22:12:08Z"
},
{
"tag": "v0.6.0",
"kind": "minor",
"published_at": "2026-06-05T07:09:33Z"
},
{
"tag": "v0.5.2",
"kind": "patch",
"published_at": "2026-06-03T03:32:42Z"
},
{
"tag": "v0.5.1",
"kind": "patch",
"published_at": "2026-06-01T17:37:32Z"
},
{
"tag": "v0.5.0",
"kind": "minor",
"published_at": "2026-05-28T15:59:24Z"
},
{
"tag": "v0.4.0",
"kind": "minor",
"published_at": "2026-05-24T04:30:38Z"
},
{
"tag": "v0.3.0",
"kind": "minor",
"published_at": "2026-05-20T15:28:14Z"
},
{
"tag": "v0.2.0",
"kind": "minor",
"published_at": "2026-05-11T15:54:05Z"
},
{
"tag": "v0.1.1",
"kind": "patch",
"published_at": "2026-05-09T21:53:03Z"
},
{
"tag": "v0.1.0",
"kind": "minor",
"published_at": "2026-05-05T19:36:13Z"
}
],
"recent_commits": [
{
"oid": "2723ff6948b62ab28a74a5f6f5074b492c76c79c",
"body": "- Delete config/types_test.go (duplicated validation logic from validate.go)\n- Remove internal/proxy/empty_stream_integration_test.go (unused)\n- Fix test struct field alignment across all test files (gofmt)\n- Fix missing final newlines in test files",
"is_bot": false,
"headline": "test: remove duplicate test file and fix test formatting",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-17T18:58:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "fe503f3212c802bb3370defa797a0df8accd560f",
"body": "- Add StreamIdleTimeoutSeconds to ProviderConfig and Provider structs\n- Raise EffectiveStreamIdleTimeout default from 120s to 300s\n- Add EffectiveThinkingStreamIdleTimeout with 600s default\n- Implement SetThinkingActive on stallReader for dynamic timeout extension\n- Add ExtractThinkingSignal to dete\n[…]\nsolution\n- Add tests for thinking-aware timeout, ExtractThinkingSignal, and activeTimeout\n- Update CONFIGURATION.md and ARCHITECTURE.md with new fields and defaults\n\nPhase 1-4 of stream-stall-thinking",
"is_bot": false,
"headline": "feat(stream): add thinking-aware stall timeout extension",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-17T18:55:19Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "de9568cd921a1683409cebe5197442e0d7271041",
"body": "…lerts\n\n- Replace raw targets slice in chat.go logger with []string of\n provider/model pairs — Credential field never enters the log call\n- Use fmt.Sprintf for safe formatting, rename variable to targetStrings\n- Change log key from \"upstreams\" to \"targets\" for consistency\n- Remove header value logg\n[…]\nlacements verifying\n header_count logging and no header value leaks\n- Keep UpstreamTarget.LogValue() as defense-in-depth against future\n accidental logging of targets directly\n\nCloses #13\nCloses #15",
"is_bot": false,
"headline": "fix(security): break data flow to satisfy CodeQL clear-text logging a…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-16T17:43:44Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "8a97ff7543c0e681ae4de8d1d866c243daedf37b",
"body": "- Add LogValue() to UpstreamTarget omitting Credential field to\n prevent API key leakage via slog formatting\n- Switch logRequestIfDebug from deny-list to allow-list via\n logSafeHeaders to prevent header leakage\n- Add ReasoningEffort to LogValue() for complete non-sensitive\n field coverage\n- Log \"all-redacted\" when all request headers are sensitive\n- Add comprehensive tests for both fixes (nil, empty, multi-valued,\n redaction, field presence)\n\nCloses #13\nCloses #14",
"is_bot": false,
"headline": "fix(security): redact credentials and sensitive HTTP headers from logs",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-16T14:59:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4b5b9a9d86326a7bcc69369613d3ea97e1f8911e",
"body": "…int cleanup\n\nStream idle timeout:\n- Replace hardcoded 60s streamIdleTimeout with configurable\n governance.stream_idle_timeout_seconds (default 120s, 0=disabled)\n- Fix stallReader race condition: discard partial data when stall\n timer fires concurrently with data arrival\n- Emit proper gateway_erro\n[…]\n) and imports (stream, config)\n- Use modern octal literals (0o644 instead of 0644)\n- Remove dead writeSSEDONE function and unreachable overflow guard\n- Fix wasted assignments in trim.go and handler.go",
"is_bot": false,
"headline": "fix(proxy): resolve GLM-4.7 SSE stream truncation and comprehensive l…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-16T12:25:35Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "be72c1931f6bd5a8b80daa197090dad805a02fe9",
"body": "- Add governance.upstream_timeout_seconds config field (*int, default 300s)\n- Replace hardcoded 120s secureClient timeout with configurable value\n- Set to 0 for unlimited (rely on streamIdleTimeout 60s stall detection)\n- Cap at 86400s (24h) with additional MaxInt64 nanosecond overflow guard\n- Add de\n[…]\nnance section\n- Clarify refusal cache comment: false positives unlikely because\n refusal/content_filter are technical field values, not conversational\n content; worst case is conservative cache miss",
"is_bot": false,
"headline": "feat(governance): add configurable upstream client timeout",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-15T15:50:38Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "ee71cea3f5185b014043872ad020f0531696a9cb",
"body": "…nses\n\n- Map Anthropic refusal stop_reason to OpenAI content_filter in both\n mapStopReason (stream transformer) and processStopReason (adapter)\n- Skip response cache storage when captured buffer contains refusal or\n content_filter indicators\n- Add test coverage for refusal mapping and cache skip logic\n\nFixes: Unknown Anthropic stop_reason debug log for refusal responses\nFixes: Refusal responses being cached and replayed to subsequent requests",
"is_bot": false,
"headline": "fix(proxy): handle refusal stop_reason and skip caching refusal respo…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-15T04:00:29Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "73730d47d690704f627a5010963c2cafb905c44a",
"body": null,
"is_bot": false,
"headline": "Merge phase-004-provider-name-fix: provider name fix",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-14T14:22:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9ff60f3e51fd507a77e228a030f181d34bad321d",
"body": "- Try zai-coding-plan first, then zai as fallback\n- Extract provider slice to package-level constant\n- Add comprehensive test coverage for precedence and disable blocking\n- Update GoDoc to explain provider precedence logic\n\nPhase 4 of zai-optimization",
"is_bot": false,
"headline": "fix(providers): check both provider names in thinking injection",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-14T14:18:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2abe59bfdcd8e8b8c03b1f81cd7b052a0d0d06ca",
"body": null,
"is_bot": false,
"headline": "Merge phase-003-thinking-config: GLM Thinking config",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-14T14:05:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7b025eb3f8425fd6d2a0d7b4981a8a9cb8e420f7",
"body": "…utput limits\n\n- Add Thinking config to GLM-5.x, GLM-4.7, GLM-4.6, GLM-4.5 series\n- Correct GLM-4.6v: MaxContext 200000→128000, MaxOutput 32000→32768\n- Correct GLM-4.5v: MaxContext 128000→64000, MaxOutput 16000→16384\n- Validated against Z.AI docs and models.dev.json ground truth\n\nPhase 3 of zai-optimization",
"is_bot": false,
"headline": "feat(config): add Thinking config to GLM models and correct context/o…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-14T13:51:24Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "fb9f8073476fcf089cf7c3df4eeea2a01d52c4d5",
"body": null,
"is_bot": false,
"headline": "Merge phase-002-message-sanitization: sanitization wiring fix",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-14T13:48:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "000b0e090a2a41e9df31458553dca8cf82b91ef2",
"body": "…iltering\n\n- Move hasTools check after orphan filtering in ZaiSanitizeAdapterOnly\n- When tools present: filter orphaned messages but skip merge/bridge\n- Wire zaiSanitize (A+B) into both zaiSpec and zaiCodingPlanSpec\n- Update test to verify orphaned tools are filtered even with tools present\n\nPhase 2 of zai-optimization",
"is_bot": false,
"headline": "fix(routing): wire zaiSanitize into specs and fix tools-skip orphan f…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-14T13:48:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3d3e4b65b49bef9cfadfda72f0c9b0309d0e4294",
"body": null,
"is_bot": false,
"headline": "Merge phase-001-cached-tokens: Z.AI cached_tokens tracking",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-14T13:28:02Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "95354dcb963cf884049b207393e091b94a3b7394",
"body": "- Extract cached_tokens from usage.prompt_tokens_details when flat\n prompt_cache_hit_tokens is zero\n- Add two test cases for the nested format and precedence behavior\n- Flat prompt_cache_hit_tokens takes precedence over nested format\n\nPhase 1 of zai-optimization",
"is_bot": false,
"headline": "feat(stream): support nested cached_tokens for Z.AI",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-14T13:27:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0ea544e0f948bf99c20006130c0b0cabc294cbcc",
"body": null,
"is_bot": false,
"headline": "Merge phase-017: configurable SSE transformed output size",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-14T02:58:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f71935b5bcc6d2ccac4070cba74d9b12eabd428f",
"body": "…ault\n\n- Add governance.max_transformed_sse_bytes config field (default 50MB, cap 1GB)\n- Replace hardcoded 256KB maxTransformedEventBytes with configurable limit\n- Add EffectiveMaxTransformedSSEBytes() with named constants for clarity\n- Add SetMaxTransformedBytes() to SSETransformingReader\n- Change \n[…]\netMaxTransformedBytes, add warnedAtThreshold reset check\n- Add tests: SetMaxTransformedBytes, EffectiveMaxTransformedSSEBytes default/custom/1GB cap, token too long\n\nPhase 017 of configurable-sse-size",
"is_bot": false,
"headline": "fix(stream): make max transformed SSE size configurable with 50MB def…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-14T02:42:04Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "a04575834836da6fcfd7c14e16d89eb4227aad63",
"body": "Phase 010 (b87c69f) accidentally removed these patterns:\n- max_context_length\n- prompt too long\n- this model's maximum context length\n- too many_tokens\n\nTests still expected these patterns to be detected. Restored to fix\nTestIsContextLengthError and TestClassifyHTTPErrorWithContextLimit failures.",
"is_bot": false,
"headline": "fix(resilience): restore missing context-limit error patterns",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T15:03:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f3a636f39a788f81d0fdb17c5770303fdca0ebb4",
"body": null,
"is_bot": false,
"headline": "fix(format): align constant declarations with gofmt",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:28:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4e3093b74aae63137e293c68b7f04ba3285fd0a5",
"body": "- Add TokenDirectionReasoning const for reasoning token classification\n- Add ReasoningTokens field to UsageTracker with atomic counters\n- Update makeUsageCallback to capture reasoning tokens from stream usage\n- Fix stallReader readLoop pool bug: wrap io.Reader to prevent pool reuse\n- Add clampDelta helper and extractUsageFromMap for SSE parsing\n- Fix entropy filter nil-ctx guard and add decrease test\n- Comprehensive test coverage for reasoning token tracking",
"is_bot": false,
"headline": "Merge phase-016: Reasoning token usage tracking",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:23:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "584e84679807c23f581c58cf0861b2197e7d9a44",
"body": "Critical fixes:\n- Fix reasoning decrease dropping all other token deltas (moved to clampDelta)\n- Fix entropy filter not applying redactions (added ReplaceDeltaContentMap call)\n- Fix unreachable dead code in makeUsageCallback (removed nested reasoning < 0)\n\nMedium fixes:\n- Fixed 32KB stack allocation\n[…]\n misleading test comment (delta vs final value)\n\nAdded test:\n- TestSSETransformingReader_UsageCallbackReasoningDecrease validates clampDelta\n\nPhase 016 final: clean review loop, all findings addressed",
"is_bot": false,
"headline": "fix(metrics): address reasoning token tracking bugs found in review",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:22:45Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "59802cffd57a152c375d186337fe5c81d5aea436",
"body": "- Add ReasoningTokens field to modelStats in stats.go\n- Add RecordReasoning method to UsageTracker\n- Update UsageCallback signature to include reasoningTokens\n- Add lastReasoningTokens field to SSETransformingReader\n- Extract reasoning_tokens from streaming usage chunks\n- Wire reasoning token record\n[…]\ntest callbacks to match new signature\n\nPhase 016 partial: non-streaming nested usage and Gemini usageMetadata handling remain\n- Cyclomatic complexity warning in extractUsageFromMap (16 > 15 threshold)",
"is_bot": false,
"headline": "feat(metrics): add reasoning token tracking to streaming path",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:22:45Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "bb5b9f2933d511d32c698531118b90214e0c4557",
"body": null,
"is_bot": false,
"headline": "Merge phase-015: Prompt cache key injection",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:22:02Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "811288c494da6a86c1820f4dce0e851299312df2",
"body": "Consistency fix: TestInjectPromptCacheKey_InjectsForOpenAI now validates\nthe cache key is valid hex, matching the xAI test assertion.",
"is_bot": false,
"headline": "fix(review): add hex validation for OpenAI cache key test",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:22:02Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "776c93933697dcb70d510a9b524b944cc1fc8719",
"body": "- Add injectPromptCacheKey to TransformRequestForUpstream pipeline\n- Inject SHA-256(agent:model) truncated to 16 hex chars as cache key\n- Only inject for 'xai' and 'openai' providers when prefix_cache.enabled\n- Skip if prompt_cache_key already exists or agent name is empty\n- Add AgentName to TransformDeps and set in proxy retry loop\n- Add hex format validation and empty agent name test\n- Document 16-char truncation rationale in GoDoc\n\nPhase 015 of provider-hardening-opencode-sync",
"is_bot": false,
"headline": "feat(cache): inject prompt_cache_key for xai/openai providers",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:22:02Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "57370ab4587389754af8be798e34f276534b5b52",
"body": null,
"is_bot": false,
"headline": "Merge phase-014: Strip bare reasoning field",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:21:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "21a50ff62dc6c5277bd3e98db7eca1d4f9abe3b6",
"body": "- Add GoDoc for SanitizePayload and stripBareReasoningField\n- Remove redundant map assignment in flattenContentArrays\n- Rename hasEffort to hasReasoningEffort for clarity\n- Add TestStripBareReasoningField_NilPayload, _EmptyPayload, _NonMapReasoning, _NoSideEffects\n- Add final newline to test file",
"is_bot": false,
"headline": "fix(review): address Phase 014 review findings",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:21:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "371f22b1b57a943329a63be5bfcc842ed919d591",
"body": "- Add stripBareReasoningField to remove 'reasoning': {} from payloads\n- Strip when reasoning_effort is present (redundant) or model non-reasoning\n- Wire into SanitizePayload between stripToolChoice and processMessages\n- Fix unsafe repeated type assertion in flattenContentArrays\n- Add comprehensive tests covering all stripping scenarios\n\nPhase 014 of provider-hardening-opencode-sync",
"is_bot": false,
"headline": "feat(routing): strip non-standard bare reasoning field",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:21:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a34ed2df1acafd68dd5082b32f0a5e7bb7c8f075",
"body": null,
"is_bot": false,
"headline": "Merge phase-013: xAI reasoning_effort injection",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:21:04Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "dec422534c868aafacde667ca681753b051ae7d1",
"body": "- Improve XaiSanitize GoDoc with reasoning_effort valid values\n- Rename test TestXAI_NoReasoningWithoutSupportsReasoning to TestXAI_NoReasoningWhenSupportsReasoningNil\n- Replace mock model names with real registry models (grok-4.3, grok-4)",
"is_bot": false,
"headline": "fix(review): address Phase 013 review findings",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:17:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "535873f4b68446721aed08568b98ca4c294ef7eb",
"body": "- Add XaiSanitize function to inject reasoning_effort: 'medium'\n- Wire SanitizeRequest hook in xaiSpec()\n- Add comprehensive tests covering reasoning/non-reasoning models\n- Respect client-provided reasoning_effort values\n- Skip injection when SupportsReasoning is nil or model missing/empty\n\nPhase 013 of provider-hardening-opencode-sync",
"is_bot": false,
"headline": "feat(xai): inject reasoning_effort for reasoning-capable Grok models",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:17:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1d125415d5440b5293feb623d1d0f572429e9126",
"body": "- Add Adaptive flag to ModelThinkingConfig (requires Max > 0)\n- Inject display:\"summarized\" for adaptive models (Opus 4.7+, Sonnet 5, Fable 5)\n- Extract constants thinkingTypeEnabled/thinkingDisplaySummarized\n- Eliminate code duplication in injectReasoningEffort\n- Add comprehensive test coverage for adaptive vs legacy paths",
"is_bot": false,
"headline": "Merge phase-012: Adaptive thinking for Anthropic",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T14:16:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a212b5de5189891b109f2ff5c8a6f06b7ffa5584",
"body": "- Add Adaptive field GoDoc to ModelThinkingConfig\n- Add validation: Adaptive requires Max > 0\n- Extract constants thinkingTypeEnabled/thinkingDisplaySummarized\n- Eliminate code duplication in injectReasoningEffort (unified budget calc)\n- Add expectedDisplay field to test struct for display verification\n- Add adaptive model test case (display:summarized)\n- Add legacy model test case (no display field)\n- Add Validate test cases for Adaptive with/without Max",
"is_bot": false,
"headline": "fix(review): address Phase 012 review findings",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-13T11:51:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e6988517969d51fd75b033e17200453671ffe856",
"body": "…dels\n\n- Add Adaptive field to ModelThinkingConfig in config/entry.go\n- Mark claude-opus-4-7, opus-4-8, fable-5, sonnet-5 with Adaptive: true in registry\n- Update injectReasoningEffort to check entry.Thinking.Adaptive flag\n- When adaptive: use thinking with display:'summarized' override\n- Wire format preserved: type:'enabled' with budget_tokens + display:'summarized'\n- Legacy non-adaptive models unchanged\n\nPhase 012 of provider-hardening-opencode-sync",
"is_bot": false,
"headline": "feat(anthropic): add adaptive thinking support for newer Anthropic mo…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T23:36:24Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6de207a3d24d120716f50a22c0ccebeb4455c38c",
"body": null,
"is_bot": false,
"headline": "Merge phase-011: Model version detection utility",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T22:24:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bed99620c8d307d1314faf545dbfb46e940ad226",
"body": "- Add AnthropicVersion function extracting family/major/minor from model IDs\n- Handle standard (claude-opus-4-7), Vertex (@default suffix), SAP inverted (4.7-opus)\n- Add IsAnthropicAtLeast helper for version comparison\n- Add IsAnthropicOpus47OrLater gate for adaptive thinking\n- Add IsAnthropicSonnet5OrLater gate for adaptive thinking\n- Comprehensive table-driven tests covering all naming conventions\n\nPhase 011 of provider-hardening-opencode-sync",
"is_bot": false,
"headline": "feat(util): add Anthropic model version detection utility",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T22:23:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c29e77b99a243e2ac6554f627ecee6ef433adb77",
"body": null,
"is_bot": false,
"headline": "Merge phase-010: Context-overflow patterns + HTTP 529 retry",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T22:13:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b87c69ff5f1c3d865e93f2bae1c53c5c63166fa4",
"body": "- Add 13 new context-overflow error patterns to IsContextLengthError (Z.AI, MLflow, generic)\n- Add 5 new patterns to inferErrorKind containsAny check\n- Add HTTP 529 to defaultRetryableStatusCodes (Provider Overloaded, non-standard)\n- Classify HTTP 529 as ErrorKindRateLimited alongside 429\n- Cross-check HTTP 413 body for context-overflow before PayloadTooLarge\n- Extract and log error_code from SSE error events for better classification\n\nPhase 010 of provider-hardening-opencode-sync",
"is_bot": false,
"headline": "fix(proxy): expand context-overflow patterns and add HTTP 529 retry",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T22:12:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "914e36d0badf9b76f06e95572aa384e9a63d8035",
"body": "- Extract Anthropic format conversion logic into helper function\n- Reduces cyclomatic complexity of TransformRequestForUpstream from 19 to 14\n- Fixes golangci-lint gocyclo finding (threshold: 15)",
"is_bot": false,
"headline": "refactor(routing): extract convertToAnthropicFormat to reduce complexity",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T21:45:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e343930c8c2703aa04dea8661c60f7d8798df21e",
"body": "- Restore buffer length in putStreamBuffer before returning to pool\n Prevents shared streamingBufPool pollution when readLoop reslices to [:n]\n Fixes TestStreamingBufPool_ReturnsCorrectSize and TestStreamingBufPool_ConcurrentSafe\n\n- Fix DrainPending behavioral regression\n Rewritten from drain-all\n[…]\n GoDoc comments for streamingBufPool and putStreamBuffer\n\n- Change localBuf size from [32 * 1024]byte{} to [streamBufferSize]byte{} for consistency\n\nPhase 014 regression fix - 3 test failures resolved",
"is_bot": false,
"headline": "fix(stream): prevent pool pollution and fix drain timeout",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T21:00:12Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "8b14ec7b41006651b63a59e26d119475614a03a1",
"body": "- Add readResult.poolBufPtr field for pooled buffer lifecycle tracking\n- Integrate streamingBufPool into readLoop to reduce per-read allocations\n- Fix remainBuf aliasing by copying data instead of slicing\n- Add nil-safety checks to putStreamBuffer and putStreamBuffer\n- Fix DrainPending leak by drain\n[…]\ndBufSize constant to prevent pool memory bloat\n- Extract getTransformedLine helper with pooling integration\n- Add fallback allocation for lines exceeding maxPooledBufSize\n\nPhase 014 of resilience-plan",
"is_bot": false,
"headline": "feat(stream): add pooling to reduce streaming allocations",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T19:23:38Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "d45441730509f94cebe6faf620df71f75a5bdd93",
"body": null,
"is_bot": false,
"headline": "Merge phase-013-mcp-scanner-fix: MCP scanner buffer fix",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T17:21:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "eb121e52c237b31ef6d66fd0feb3b07f316dfbcd",
"body": "- Add scanner.Buffer() with 64KB initial / 1MiB max (matches main SSE path)\n- Handle bufio.ErrTooLong with descriptive error message\n- Fix latent nil-logger panics in sseAccumulator.result() and buildToolCalls()\n- Add 3 tests: large line (100KB), normal lines, over-limit line (>1MiB)\n\nPhase 013 of gomodel-resilience",
"is_bot": false,
"headline": "fix(proxy): fix MCP bufferStreamResponse scanner limit",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T17:20:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c54264d441057601ca12b76ff2cec250a46fd22b",
"body": "… guard",
"is_bot": false,
"headline": "Merge phase-012-sse-backpressure: SSE transformed-output backpressure…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T16:58:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8a47ba5ae1701b920e5d212df0f1e5b1793e0d63",
"body": "- Add maxTransformedEventBytes (256KB) guard in SSETransformingReader\n- Accumulate transformed output size; when exceeding limit, discard\n subsequent events and return ErrTransformedSizeExceeded\n- Allow [DONE] through even when discarding for clean stream end\n- Inject gateway_error + [DONE] via injectErrorBuffer on limit breach\n- Add ResetCounters() for future reader-pooling implementations\n- 3 new tests covering size limit, normal stream, and reset\n\nPhase 012 of gomodel-resilience",
"is_bot": false,
"headline": "feat(stream): add SSE transformed-output backpressure guard",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T16:56:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "dfd79e0574219df7891ef6be161e91662928aedf",
"body": "…client disconnect",
"is_bot": false,
"headline": "Merge phase-011-cb-inflight-leak: prevent half-open inflight leak on …",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T15:48:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "70a53bd248c1a6e9c6091911ed24679bd2875294",
"body": "- Add ReleaseHalfOpen(key) method to CircuitBreaker that decrements\n halfOpenInflight without state transition\n- Wire ReleaseHalfOpen into recordNetworkError client-disconnect path\n to free the probe slot when request is canceled before dispatch\n- No-op safe: returns silently if circuit doesn't exist, is not\n HalfOpen, or has no inflight slots\n- Add 4 tests: decrement, noop on closed, noop on non-existent,\n abandoned probe guard\n\nPhase 011 of gomodel-resilience",
"is_bot": false,
"headline": "fix(resilience): prevent half-open inflight leak on client disconnect",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T15:47:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2edba97219fea0bd9c971d6c8e3a6b9ba06850c4",
"body": "…isconnect during failover",
"is_bot": false,
"headline": "Merge phase-010-failover-ctx-cancel: prevent CB pollution on client d…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T15:28:24Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2aa6ea658a37862688c0ad4ec7f032c04fe698ec",
"body": "…lover\n\n- Add context-cancellation guard in RetryLoop.Run that bails out\n before CB interaction when client disconnects\n- Add recordNetworkError helper to distinguish client disconnect\n from provider timeout via parent context health check\n- Add IsContextCanceled helper detecting Canceled or\n Dea\n[…]\nping\n- Client disconnect (parent terminated) skips RecordFailure\n- Provider timeout (child context only) records failure correctly\n- 5 new tests covering all scenarios\n\nPhase 010 of gomodel-resilience",
"is_bot": false,
"headline": "fix(resilience): prevent CB pollution on client disconnect during fai…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-10T15:22:39Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "ce09a707fac5e88f1e37294bc1bf6be096b8a9df",
"body": "- Remove RecordRequest from streaming callback to prevent double-counting\n- Add cacheCreationTokens and cacheReadTokens reset in Reset()\n- Add TTL validation rejecting non-\"ephemeral\" at config load time\n- Add cache_creation_tokens to Anthropic transformer OpenAI usage output\n- Fix unguarded type as\n[…]\n- Add GoDoc for UsageCallback documenting all 6 parameters\n- Add tests: cache_control injection (7 cases), cache stats (3 cases),\n usage callback with cache fields (2 cases), TTL validation (4 cases)",
"is_bot": false,
"headline": "fix(cache): harden anthropic cache_control for production readiness",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-02T21:23:53Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "778ce32308535ab4c3839840dadf2937edc6ffc5",
"body": null,
"is_bot": false,
"headline": "feat(cache): track anthropic cache creation tokens in usage stats",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-02T17:23:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2c4e10f3aa038fe68f20dc727ddb0e930a42f79e",
"body": null,
"is_bot": false,
"headline": "feat(cache): add anthropic prompt caching - system + tools + messages",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-02T16:58:43Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "03900190e5b28428c726bff136b716952dabafa8",
"body": "- Add ReasoningEffort field to AgentModel and UpstreamTarget\n- Propagate through all target expansion functions\n- Implement last-entry-wins dedup for dynamic models\n- Inject reasoning_effort into payload before sanitization\n- Map reasoning_effort levels to Anthropic thinking.budget_tokens\n- Add table-driven tests for budget calculation and injection",
"is_bot": false,
"headline": "feat(routing): add per-model reasoning_effort configuration",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-02T14:05:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e189c2f45e881c75f418f0419a7c65ebc7369674",
"body": "…ference\n\n- claude-opus-4-6: remove spurious 'xhigh' level (copy-paste from opus-4-7).\n Reference (routerforme L68-73): [low, medium, high, max]\n- grok-4.3: restore ZeroAllowed: true removed by over-aggressive cleanup.\n Reference (routerforme L2126): zero_allowed: true\n\nPhase 013 of update-model-registry",
"is_bot": false,
"headline": "fix(registry): align opus-4-6 levels and grok-4.3 ZeroAllowed with re…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-01T17:31:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e31f70241941667fd6c8d2a5c2487b39fd70e9ab",
"body": null,
"is_bot": false,
"headline": "Merge phase-012: cleanup trailing zero and redundant fields",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-01T17:06:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f5625a9eb0b962edb1e0d796fa2f41e8581cbab5",
"body": "- gpt-5.4-nano pricing: 1.10 -> 1.1 (trailing zero)\n- kimi-k2.7-code: remove redundant ZeroAllowed: false\n- grok-4.3: remove redundant ZeroAllowed: true (covered by \"none\" in Levels)\n\nPhase 012 of update-model-registry",
"is_bot": false,
"headline": "style(registry): cleanup trailing zero, redundant ZeroAllowed fields",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-01T17:06:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a43b748b8890fc6e58c04258e3e214d74132e33d",
"body": null,
"is_bot": false,
"headline": "Merge phase-011: correct GLM pricing",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-01T15:34:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "de33ebc2b41eb05903d8b81e1856fa9e42697994",
"body": "- Update 18 GLM pricing entries to Z.AI official published rates\n- glm-4.7-flash, glm-4.5-flash, glm-4.6v-flash: set to Free (omit PricingOverride)\n- glm-4.5-x: 0.50/2.00 → 2.20/8.90 (highest correction, ~4x)\n- glm-4-32b-0414-128k: 0.50/2.00 → 0.10/0.10 (decrease)\n- All remaining GLM models get modest corrections (0.60/2.20 avg)\n\nPhase 011 of update-model-registry",
"is_bot": false,
"headline": "fix(registry): correct all GLM pricing to match Z.AI official rates",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-01T15:31:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b271473a304176b01e8fa274d0b2a336c72b0118",
"body": null,
"is_bot": false,
"headline": "Merge phase-010: add 16 new models",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-01T15:10:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9aeb5ad32cd269ef1e397a778bd509bfc2ed035a",
"body": "…levels\n\n- Add claude-opus-4-8, claude-fable-5, claude-sonnet-5 (anthropic)\n- Add glm-5.2 (zai)\n- Add grok-4.3, grok-build-0.1, grok-4.20-0309-* (5 xai models)\n- Add kimi-k2.7-code, kimi-k2.7-code-highspeed (moonshot)\n- Add gemini-3-pro-preview, gemini-3.1-flash-image-preview, gemini-3-pro-image-pre\n[…]\nt-5.5-pro (openai)\n- Fix claude-sonnet-4-6: add \"max\" to thinking levels\n- Fix trailing zeros: 2.50 → 2.5\n- Remove explicit zero PricingOverride from kimi-k2.7-code\n\nPhase 010 of update-model-registry",
"is_bot": false,
"headline": "feat(registry): add 16 new models and fix claude-sonnet-4-6 thinking …",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-01T15:10:28Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "9b7df8c130ae58937c6e7d198d95d312fb399124",
"body": "- TestResolveWindowMaxOutput_WithModels and _AgentNotFound\n- TestResolveWindowMaxOutput_AgentLevelOverride (agent override MAX)\n- TestResolveAgentCapabilities_Intersection (4 table-driven cases)\n- TestResolveAgentCapabilities_UnresolvableMetadata (early-return)\n- TestResolveAgentPricing_Average (4 table-driven cases)\n- TestServeHTTP_Models_AgentMetadata (handler integration test)\n- TestServeHTTP_Models_AgentDescription (handler description test)\n\nPhase 013 of agent-models-metadata",
"is_bot": false,
"headline": "test(proxy): add tests for agent metadata aggregation",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-01T13:49:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "659bb739a841ac911664cf25c3163a619e61546c",
"body": null,
"is_bot": false,
"headline": "Merge phase-012: Add description field to AgentConfig",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-01T01:28:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7dd698c0b0240f5c52466c15b5dbe1c3a1443f59",
"body": "- Add Description string with omitempty to AgentConfig\n- Populate description in buildAgentModelEntry for /v1/models response\n\nPhase 012 of agent-models-metadata",
"is_bot": false,
"headline": "feat(config): add description field to AgentConfig",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-01T01:27:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0e39bf8882e73a00cd3561ac654935f7f6f6e61c",
"body": null,
"is_bot": false,
"headline": "Merge phase-011: Enrich /v1/models agent entries",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-01T01:17:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "cfc6122ade955d8ecbf3814898509f4c44ae80c7",
"body": "- Add RoutingStrategy and Description fields to modelEntry struct\n- Add buildAgentModelEntry helper with gw nil guard\n- Add applyModelFields helper for catalog model entries\n- Replace addModel closure with direct loops (fixes gocyclo)\n- Agent entries now surface context_window, max_tokens, capabilities,\n pricing (AVG), and routing_strategy\n\nPhase 011 of agent-models-metadata",
"is_bot": false,
"headline": "feat(proxy): enrich /v1/models agent entries with aggregate metadata",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-07-01T01:16:32Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3fc552b1f13e287ddddc9e151c8bc9aca23d3c1a",
"body": null,
"is_bot": false,
"headline": "Merge phase-010: Add agent metadata aggregation helpers",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-30T21:55:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f922e15cc57a8c1025ef0059d516862f0ee990b7",
"body": "- Add ResolveWindowMaxOutput (mirror of ResolveWindowMaxContext)\n- Add AgentCapabilities struct + ResolveAgentCapabilities (intersection)\n- Add AgentPricing struct + ResolveAgentPricing (average)\n- Add resolveModelMetadata (catalog lookup → InferCapabilities fallback)\n- Add resolveModelPricing (catalog → registry fallback with copy)\n- All functions document static-only model limitation\n\nPhase 010 of agent-models-metadata",
"is_bot": false,
"headline": "feat(routing): add agent metadata aggregation helpers",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-30T21:53:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "feeb224ef8524be7a42c601c56badc7b2cc53728",
"body": "…mestampMs\n\n- Split parseQuotaExhaustion into smaller functions (parseZaiQuota1308,\n parseZaiQuota1310, parseGenericQuotaPatterns) to reduce cyclomatic\n complexity from 16 to <15\n- Extracted parseDigitsToTimestamp helper to reduce nesting in\n extractUnixTimestampMs (nestif complexity from 5 to <4)\n- Fix gofmt alignment in Proxy and retryLoop structs\n- All linters pass: gocyclo, nestif, gofmt",
"is_bot": false,
"headline": "refactor: reduce complexity in parseQuotaExhaustion and extractUnixTi…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-18T15:29:43Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "49e714a1aaa35032c0c4dc38c7e0766843d725ed",
"body": "- Phase 010: ALL parseQuotaExhaustion call sites updated with slog.Default()\n- Phase 011: handleAdapterRetryableError now returns (retryable, isQuota) and\n propagates to p.lastQuotaExhausted; GoDoc added to Retryable, ShouldFailover,\n ErrorType, GatewayError, OpenAIErrorEnvelope, OpenAIErrorObject\n[…]\nth exported sanitize functions; docs reference updated\n- Phase 013: MutateRequest deprecation doc corrected for execution order,\n ZaiSanitizeAdapterOnly references removed, references section updated",
"is_bot": false,
"headline": "fix: code review fixes for phases 010-013",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-18T12:57:23Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "0d0ba6a6229f2df4598edd3192f9cd5797809fc7",
"body": "Add docs/MUTATEREQUEST-DEPRECATION.md documenting that the MutateRequest\ninterface method is vestigial (not dead code) and explaining the architectural\nevolution from MutateRequest-only to the current two-layer approach:\n\n- Spec-level (SanitizeRequest): Cross-cutting concerns (thinking injection,\n \n[…]\ns usage patterns, when to use each layer, and why\nboth layers are needed. No code changes are required - the current architecture\nis by design and sound.\n\nFiles changed: 1\nDocumentation: comprehensive",
"is_bot": false,
"headline": "Phase 013: Add comprehensive MutateRequest deprecation documentation",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-17T21:46:02Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "2611c23f3a9190785731ad5812707f6c32a12ae9",
"body": "Split zaiSanitize() into two distinct functions for proper separation of concerns:\n\n- ZaiSanitizeSpecOnly (Category A): Spec-level sanitization that runs before\n adapter transformation (thinking injection, temperature defaults)\n- zaiSanitizeAdapterOnly (Category B): Adapter-level message cleanup\n \n[…]\nnly, keep zaiSanitize() as wrapper for backward\n compatibility\n- internal/providers/defaults.go: Add SanitizeRequest: ZaiSanitizeSpecOnly\n to zaiCodingPlanSpec()\n\nFiles changed: 2\nVerification: PASS",
"is_bot": false,
"headline": "Phase 012: Split zaiSanitize into spec-level and adapter-level functions",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-17T21:37:51Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "286286ca56106b4b85a666ad50fa8ef8a8d7a390",
"body": null,
"is_bot": false,
"headline": "Phase 011: Fix test comparison for ErrorType vs string alias type",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-17T21:15:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "10ed335a0357c1d37dc9c50e2747aef28a6904b0",
"body": "Add ErrorKindQuotaExhausted with corresponding ErrorTypeQuotaExhausted,\nmapped through mapErrorKind to emit error_kind=quota_exhausted in responses\nwhen all upstream targets are exhausted due to quota limits.\n\nChanges:\n- internal/infra/errors.go: Add ErrorKindQuotaExhausted constant, update Retryabl\n[…]\nssage with ErrorTypeQuotaExhausted\n- internal/proxy/handler.go: Add lastQuotaExhausted atomic.Bool to Proxy for\n tracking quota state across retry loop iterations\n\nFiles changed: 6\nVerification: PASS",
"is_bot": false,
"headline": "Phase 011: Add ErrorKindQuotaExhausted for Better Client Diagnostics",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-17T21:14:58Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "407b93729e64943a70287dc5cb24bc96a9b01b6d",
"body": "…caps at 410244479903999)",
"is_bot": false,
"headline": "Phase 010: Fix — remove overflow check for valid range (maxTimestamp …",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-17T20:34:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "15b44716e55a752608d9ecd7afdfc00d7a0720ea",
"body": "Add ZAI error code 1308 (5-hour prompt limit) and 1310 (weekly limit)\nrecognition to parseQuotaExhaustion. This fixes the cooldown mismatch that\ncaused \"All upstream targets exhausted\" for zai-coding-plan provider.\n\nChanges:\n- Extend parseQuotaExhaustion to parse ZAI error JSON format and return\n p\n[…]\nth.MaxInt/10 with proper digit check\n- Add comprehensive test coverage for ZAI error codes, timestamps,\n overflow scenarios, and edge cases\n\nFiles changed: 2\nReviewer iterations: 2\nVerification: PASS",
"is_bot": false,
"headline": "Phase 010: Extend parseQuotaExhaustion for ZAI Coding Plan Error Codes",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-17T20:14:59Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "1a672ef0806726c67fe040e5cf49c4f068529f86",
"body": "Update go.mod module path and all import statements across 123 files.\nAlso update repository URLs in .gitignore and CHANGELOG.md.",
"is_bot": false,
"headline": "chore: migrate module path from git.0ur.uk/nenya to github.com/nenya",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-15T15:43:32Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d055dc962c7ba070404e2e48060706f2a54510fe",
"body": "Update go.mod module path and all import statements across 123 files.\nAlso update repository URLs in .gitignore and CHANGELOG.md.",
"is_bot": false,
"headline": "chore: migrate module path from git.0ur.uk/nenya to github.com/nenya",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-15T15:43:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "651aba7cbcec57145cbc012eaceadb127f6faa44",
"body": "…plan docs\n\nCONFIGURATION.md:\n- Fix claude model providers: zen → anthropic (opus-4-7, opus-4-6, sonnet-4-6)\n- Fix claude-sonnet-4-6 context: 1,000,000 → 200,000 (matches registry)\n- Fix kimi-k2 pricing: $0.10/M → — (registry has no Pricing field)\n- Remove 3 duplicate rows: nemotron-3-super (wrong p\n[…]\non\" sub-section explaining 3-tier model\n\nPROVIDERS.md:\n- Add z.ai Coding Plan to Tier 1, provider reference table, auth styles\n- Update z.ai Special Behaviors with variant table and diff documentation",
"is_bot": false,
"headline": "docs: fix model table, adapter registration accuracy, add zai-coding-…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-14T11:39:32Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "07c56c563d33829c10e009e993a4481fbd4eced4",
"body": "…VIDERS)",
"is_bot": false,
"headline": "Merge phase-015: Remaining docs fixes (ARCHITECTURE, PASSTHROUGH, PRO…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-14T02:12:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "02c4d4b8cd9db5ae6e92b327d01bbb2d8817013b",
"body": "Fix remaining documentation inaccuracies found during audit:\n- ARCHITECTURE.md: correct package paths (internal/config/ → config/), add missing packages (billing, auth, security, version), fix metric name backoff_level_total → backoff_increments_total\n- PASSTHROUGH_PROXY.md: remove reference to non-\n[…]\n codebase. Provider count verified as 24 built-in providers (zai + zai-coding-plan counted as one, 24 raw entries for 24 unique providers).\n\nReviewer iterations: 0 (trivial docs changes, all verified)",
"is_bot": false,
"headline": "Phase 015: Remaining docs fixes (ARCHITECTURE, PASSTHROUGH, PROVIDERS)",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-14T02:11:45Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "09aa1a1c7e232f646c16189f0a9f6798f1bf868b",
"body": "…es, update model table",
"is_bot": false,
"headline": "Merge phase-014: Merge CONFIG.md into CONFIGURATION.md, fix field nam…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-13T20:53:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "75d1b8659e45e6e2e557c71caaab8fbf8d32d4bd",
"body": "…date model table\n\nComprehensive documentation audit fix for CONFIGURATION.md:\n- Merge unique content from orphaned CONFIG.md (mcp_servers section, migration guides, validation docs)\n- Delete CONFIG.md (zero inbound links, all content merged)\n- Fix bouncer field names: patterns→redact_patterns, outp\n[…]\n76/65,536\n- Update Claude model values: 3-7-sonnet 200K→128K context, 3-5-sonnet 8K→64K output\n- Update Kimi model values: k2.6 to 262K/65K, k2.5 to 131K/32K\n- Add 13 missing models to reference table",
"is_bot": false,
"headline": "Phase 014: Merge CONFIG.md into CONFIGURATION.md, fix field names, up…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-13T20:53:43Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "679a2033920e023c02d0798396172401798d68a0",
"body": null,
"is_bot": false,
"headline": "Merge phase-013: README accuracy fixes",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-13T11:34:55Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4ab7f005b962b55dc3297acc07f8d25de03dab75",
"body": "Fix all README inaccuracies found during docs audit:\n- Flow diagram: /v1/messages + x-api-key → /v1/messages + Bearer token\n- Reliability: 5s grace period → 30s grace period\n- Endpoint table: /v1/files method GET → GET/POST/DELETE\n- Endpoint table: /v1/batches method POST/GET",
"is_bot": false,
"headline": "Phase 013: README accuracy fixes",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-13T11:32:22Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "40464101acc6a5106d4c7979b7621a75040205ef",
"body": "Add explicit syscall filtering via SystemCallFilter directives:\n- Allow @system-service (covers all syscalls a Go HTTP server needs)\n- Deny @mount, @privileged, @raw-io, @reboot, @swap (dangerous groups)\n\nThis makes the README's \"Seccomp + no-new-privileges\" claim fully backed\nby explicit configuration, not just container runtime defaults.\n\nAlso adds explicit K8s seccompProfile: RuntimeDefault (already present in\nvalues.yaml).",
"is_bot": false,
"headline": "Phase 012: Add seccomp SystemCallFilter to systemd unit",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-13T03:16:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8f6e9bd7f36e931e65ebd973df12166753264076",
"body": null,
"is_bot": false,
"headline": "Merge phase-011: Standardize binary path to /usr/bin",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-13T03:15:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bc05f0bbdcbc2e620c0be67d819efc07439d2eb3",
"body": "Fix the mismatch where install.sh installs to /usr/local/bin but systemd units expect /usr/bin.\n- install.sh: change INSTALL_DIR=\"/usr/local/bin\" to \"/usr/bin\" (lines 10, 225, and help text)\n- docs/DEPLOY_BAREMETAL.md: change ExecStart=/usr/local/bin to /usr/bin (lines 154, 229)\n\nNow all installs (deb/rpm/arch/arch via goreleaser, install.sh script) agree on /usr/bin/nenya.\n\nReviewer iterations: 0 (trivial docs change)",
"is_bot": false,
"headline": "Phase 011: Standardize binary path to /usr/bin",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-13T03:15:04Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3f4f745b943749cee99f3da99618359b5e8376c3",
"body": "… + moonshot",
"is_bot": false,
"headline": "Merge phase-010: Fix pprof + statsz/metrics auth + method enforcement…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-13T03:06:18Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9b410f4ca74005f7321c920476fb5835ae36c5be",
"body": "…nshot\n\nFix code bugs found during docs audit:\n- Add _ net/http/pprof blank import and fix route prefix=true for sub-path matching\n- Make /statsz and /metrics publicly accessible (no auth required)\n- Enforce HTTP methods on key endpoints (POST for chat/embeddings, GET for metrics)\n- Add moonshot adapter and ProviderSpec for consistency\n- Add registerOpenAI helper to reduce boilerplate in adapter registry\n\nReviewer iterations: 4",
"is_bot": false,
"headline": "Phase 010: Fix pprof + statsz/metrics auth + method enforcement + moo…",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-13T03:02:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "73a55b5afca03bb6406c302e1c38fb93f8117747",
"body": "Added forwardFunctionCallIDs to both internal/providers/gemini.go and\ninternal/adapter/gemini.go to forward tool call IDs from assistant\nmessages to tool messages. Gemini 3.5+ requires echoing unique id\nfields from functionCalls into functionResponses.\n\nAlso added isGemini35OrNewer helper to detect models requiring this\nbehavior. Duplication is intentional to avoid circular dependencies\nand follows the existing pattern.\n\nFiles changed: 2\nReviewer iterations: 3",
"is_bot": false,
"headline": "Phase 014: Add function call ID forwarding for Gemini 3.5+",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-05T20:13:37Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "adb7b026b15bbc1d9a736da13f5e873f97b02a2c",
"body": null,
"is_bot": false,
"headline": "Merge phase-013-gemini-temperature-default",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-05T19:32:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "29133aa76395f01592baaafe6ef62ea5170bc2ee",
"body": "Added injectTemperatureDefaultsForGemini to set temperature=1.0 as default for Gemini 3+ models. Google recommends temperature=1.0 to prevent looping behavior on reasoning tasks. Respects existing client-specified temperature values.\n\nFiles changed: 1\nReviewer iterations: 3",
"is_bot": false,
"headline": "Phase 013: Add temperature default for Gemini 3",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-05T19:28:43Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2c6c94cb909a80af59347983adc2661d8c44ea9c",
"body": null,
"is_bot": false,
"headline": "Merge phase-012-gemini-thinking-mapping",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-05T19:14:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2a817f982f94256177fe98c63d7a70db177a2158",
"body": "Added mapping from client reasoning_effort parameter to Gemini's thinking config:\n- Gemini 3+: maps to thinkingLevel (minimal/low/medium/high)\n- Gemini 2.5: maps to thinkingBudget (0/1024/8192/24576)\n- Invalid values log warning and default to medium/8192\n- Non-string reasoning_effort logs warning and is skipped\n- reasoning_effort removed from payload after mapping\n\nFiles changed: 1\nReviewer iterations: 3",
"is_bot": false,
"headline": "Phase 012: Add thinking config mapping for Gemini",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-05T19:14:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "66bbcbe875670f95b3a7c271d0622bc3255f664f",
"body": null,
"is_bot": false,
"headline": "Merge phase-011-gemini-3-capability-rule",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-05T18:06:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f92b62f7b9b8035ed7fbbab22be285f1e4a4f94d",
"body": "Added capability inference rule for gemini-3 prefix with full capabilities (vision, tool_calls, reasoning, content_arrays, auto_tool_choice). Rule placed before gemini-2 to ensure correct prefix matching order. Added test cases for gemini-3-flash, gemini-3.1-pro, gemini-3.5-flash.\n\nFiles changed: 2\nReviewer iterations: 2",
"is_bot": false,
"headline": "Phase 011: Add gemini-3 capability rule",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-05T18:06:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "53d9f6ef0267156e53fd68276cb49697b5f75e7a",
"body": null,
"is_bot": false,
"headline": "Merge phase-010-gemini-model-registry",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-05T17:51:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c7c9cd1b921322f020b5b25959bc0d17aec14088",
"body": "Removed dead model gemini-3-pro-preview from all 3 locations (registry and both model maps). Added new gemini-3.5-flash model to all 3 locations. Updated test case that referenced removed model. Both GeminiModelMap copies remain identical and in sync.\n\nFiles changed: 4\nReviewer iterations: 2",
"is_bot": false,
"headline": "Phase 010: Update model registry and maps",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-05T17:50:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8b76e20913e2e659ca8a30dec6fe5f98489cb969",
"body": null,
"is_bot": false,
"headline": "chore: remove phase-runner skill and opencode.json",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-05T15:29:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "73ad57e20444b850ac026b497c19302385b255df",
"body": "Line 237 was 'if stillExists { return nil }' which returned early\nwhen the model still existed (wrong). Fixed to 'if !stillExists { return nil }'\nwhich returns early when model was re-added during HTTP call (correct).",
"is_bot": false,
"headline": "fix: correct UnloadModel TOCTOU logic (inverted condition)",
"author_name": "Rafael Gumieri",
"author_login": "gumieri",
"committed_at": "2026-06-05T06:50:28Z",
"body_truncated": false,
"is_coding_agent": false
}
],
"releases_count": 21,
"commits_last_year": 485,
"latest_release_at": "2026-07-17T19:16:59Z",
"latest_release_tag": "v0.8.6",
"releases_from_tags": false,
"days_since_last_push": 2,
"active_weeks_last_year": 15,
"days_since_latest_release": 6,
"mean_days_between_releases": 3.1
},
"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": false
},
"ecosystem": {
"packages": []
},
"popularity": {
"forks": 0,
"stars": 25,
"watchers": 0,
"fork_history": {
"days": [],
"complete": true,
"collected": 0,
"total_forks": 0
},
"star_history": null,
"open_issues_and_prs": 5
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [
"examples"
],
"has_llms_txt": false,
"has_dockerfile": true,
"has_mcp_signal": false,
"bootstrap_files": [
"mise.toml"
],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [],
"toolchain_manifests": [
"go.mod"
],
"largest_source_bytes": 75201,
"source_files_sampled": 278,
"oversized_source_files": 1,
"agent_instruction_files": [
"AGENTS.md"
],
"agent_instruction_max_bytes": 28024
},
"dependencies": {
"manifests": [
"go.mod"
],
"advisories": {
"error": "No resolved dependencies to assess",
"scope": "repository_graph",
"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": [],
"all_dependencies": {
"error": null,
"source": "github-sbom",
"packages": [],
"collected": true,
"truncated": false,
"total_count": 0,
"direct_count": 0,
"indirect_count": 0
}
},
"maintainership": {
"issues": {
"open_prs": 5,
"merged_prs": 11,
"open_issues": 0,
"closed_ratio": 1,
"closed_issues": 3,
"closed_unmerged_prs": 4
},
"bus_factor": 1,
"bot_contributors": 1,
"top_contributors": [
{
"type": "User",
"login": "gumieri",
"commits": 472,
"avatar_url": "https://avatars.githubusercontent.com/u/596856?v=4"
}
],
"contributors_sampled": 1,
"top_contributor_share": 1
},
"quality_signals": {
"has_ci": true,
"has_tests": true,
"ci_workflows": [
"ci.yml",
"codeql.yml",
"release.yml"
],
"has_docs_dir": true,
"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": 0,
"reason": "branch protection not enabled on development/release branches",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
},
{
"name": "CI-Tests",
"score": null,
"reason": "no pull request found",
"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 0/30 approved changesets -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 6,
"reason": "project has 2 contributing companies or organizations -- score normalized to 6",
"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": 10,
"reason": "update tool detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dependency-update-tool"
},
{
"name": "Fuzzing",
"score": 10,
"reason": "project is fuzzed",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
},
{
"name": "License",
"score": 10,
"reason": "license file detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
},
{
"name": "Maintained",
"score": 10,
"reason": "30 commit(s) and 3 issue activity found in the last 90 days -- score normalized to 10",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#maintained"
},
{
"name": "Packaging",
"score": 10,
"reason": "packaging workflow detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
},
{
"name": "Pinned-Dependencies",
"score": 0,
"reason": "dependency not pinned by hash detected -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#pinned-dependencies"
},
{
"name": "SAST",
"score": 10,
"reason": "SAST tool detected: CodeQL",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#sast"
},
{
"name": "Security-Policy",
"score": 10,
"reason": "security policy file detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#security-policy"
},
{
"name": "Signed-Releases",
"score": 8,
"reason": "5 out of the last 5 releases have a total of 5 signed artifacts.",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#signed-releases"
},
{
"name": "Token-Permissions",
"score": 0,
"reason": "detected GitHub workflow tokens with excessive permissions",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
},
{
"name": "Vulnerabilities",
"score": 10,
"reason": "0 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "2723ff6948b62ab28a74a5f6f5074b492c76c79c",
"ran_at": "2026-07-24T13:25:11Z",
"aggregate_score": 6.8,
"scorecard_version": "v5.5.0"
},
"has_codeql_workflow": true,
"has_security_policy": true,
"has_dependabot_config": true
},
"contribution_flow": {
"collected": true,
"ci_last_run_at": "2026-07-21T17:24:14Z",
"oldest_open_prs": [
{
"number": 16,
"created_at": "2026-05-12T22:19:06Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 20,
"created_at": "2026-07-21T17:23:45Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 21,
"created_at": "2026-07-21T17:23:48Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 22,
"created_at": "2026-07-21T17:23:52Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 23,
"created_at": "2026-07-21T17:24:12Z",
"last_comment_at": null,
"last_comment_author": null
}
],
"last_merged_pr_at": "2026-05-05T20:02:47Z",
"ci_last_conclusion": "SUCCESS",
"oldest_open_issues": []
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/gumieri/nenya",
"host": "github.com",
"name": "nenya",
"owner": "gumieri"
},
"metrics": {
"overall": {
"key": "overall",
"band": "moderate",
"name": "Overall health",
"note": null,
"notes": [],
"value": 64,
"inputs": {
"security": 68,
"vitality": 84,
"community": 35,
"governance": 48,
"engineering": 82
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "good",
"name": "Vitality",
"value": 84,
"weight": 0.22,
"metrics": [
{
"key": "development_activity",
"band": "good",
"name": "Development activity",
"note": null,
"notes": [],
"value": 74,
"inputs": {
"commits_last_year": 485,
"human_commit_share": 1,
"days_since_last_push": 2,
"active_weeks_last_year": 15
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 2 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 2
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "15/52 weeks with commits",
"points": 10.4,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 15
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "485 commits in the last year",
"points": 18,
"status": "met",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 485
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "30 commit(s) and 3 issue activity found in the last 90 days -- score normalized to 10",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
},
{
"key": "release_discipline",
"band": "excellent",
"name": "Release discipline",
"note": null,
"notes": [],
"value": 98,
"inputs": {
"releases_count": 21,
"latest_release_tag": "v0.8.6",
"releases_from_tags": false,
"days_since_latest_release": 6,
"mean_days_between_releases": 3.1
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "21 releases published",
"points": 27,
"status": "met",
"details": [
{
"code": "releases_published",
"params": {
"count": 21
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 6 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 6
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~3.1 days",
"points": 27,
"status": "met",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 3.1
}
}
],
"max_points": 27
},
{
"key": "openssf_scorecard_signed_releases",
"name": "OpenSSF Scorecard: Signed-Releases",
"detail": "5 out of the last 5 releases have a total of 5 signed artifacts.",
"points": 8,
"status": "partial",
"details": [],
"max_points": 10
}
]
},
{
"key": "abandonment",
"band": "excellent",
"name": "Abandonment",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"cap": null,
"state": "unverified",
"guards": [],
"signals": [],
"red_flag": false,
"multiplier_pct": 100,
"declared_reason": null,
"unverified_reason": "repository_too_young",
"unanswered_open_prs": null,
"unanswered_open_issues": null,
"days_since_last_merged_pr": null,
"days_since_last_human_commit": null,
"days_since_last_human_commit_is_floor": false
},
"components": [
{
"key": "project_is_still_maintained",
"name": "Project is still maintained",
"detail": "maintenance record not established from the collected data",
"points": 100,
"status": "met",
"details": [
{
"code": "abandonment_unverified",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Is the project alive — is code being written and are releases shipping?"
},
{
"key": "community",
"band": "at_risk",
"name": "Community & Adoption",
"value": 35,
"weight": 0.18,
"metrics": [
{
"key": "popularity",
"band": "critical",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 22,
"inputs": {
"forks": 0,
"stars": 25,
"watchers": 0,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "25 stars",
"points": 22.4,
"status": "partial",
"details": [
{
"code": "stars",
"params": {
"count": 25
}
}
],
"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": 50,
"inputs": {
"has_readme": true,
"has_license": true,
"has_contributing": false,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 22.5,
"status": "met",
"details": [],
"max_points": 22.5
},
{
"key": "license",
"name": "License",
"detail": "recognized license (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": 0,
"status": "missed",
"details": [],
"max_points": 6.3
}
]
}
],
"description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
},
{
"key": "governance",
"band": "at_risk",
"name": "Sustainability & Governance",
"value": 48,
"weight": 0.24,
"metrics": [
{
"key": "maintainer_resilience",
"band": "critical",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 16,
"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 2 contributing companies or organizations -- score normalized to 6",
"points": 6,
"status": "partial",
"details": [],
"max_points": 10
}
]
},
{
"key": "responsiveness",
"band": "good",
"name": "Issue & PR responsiveness",
"note": null,
"notes": [],
"value": 75,
"inputs": {
"merged_prs": 11,
"open_issues": 0,
"closed_issues": 3,
"issue_closed_ratio": 1,
"closed_unmerged_prs": 4
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "100% of issues closed",
"points": 46.8,
"status": "met",
"details": [
{
"code": "issues_closed_share",
"params": {
"share": 100
}
}
],
"max_points": 46.75
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "11/15 decided PRs merged",
"points": 28,
"status": "partial",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 11,
"decided": 15
}
}
],
"max_points": 38.25
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 0/30 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "moderate",
"name": "Ownership & stewardship",
"note": "Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"verified_domain"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 59,
"inputs": {
"followers": 70,
"owner_type": "User",
"is_verified": null,
"owner_login": "gumieri",
"public_repos": 38,
"account_age_days": 5650
},
"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": "70 followers of gumieri",
"points": 13.3,
"status": "partial",
"details": [
{
"code": "owner_followers",
"params": {
"count": 70,
"login": "gumieri"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "38 public repos, account ~15 yr old",
"points": 23.6,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 38
}
},
{
"code": "account_age_years",
"params": {
"years": 15
}
}
],
"max_points": 25
}
]
}
],
"description": "Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?"
},
{
"key": "engineering",
"band": "good",
"name": "Engineering Quality",
"value": 82,
"weight": 0.2,
"metrics": [
{
"key": "engineering_practices",
"band": "good",
"name": "Engineering practices",
"note": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: CI-Tests. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"openssf_scorecard_ci_tests"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 80,
"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": "3 workflow(s)",
"points": 24,
"status": "met",
"details": [
{
"code": "ci_workflows",
"params": {
"count": 3
}
}
],
"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": "no pull request found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "excellent",
"name": "Documentation",
"note": null,
"notes": [],
"value": 85,
"inputs": {
"topics": [
"ai",
"ai-governance",
"ai-safety",
"ai-security",
"ai-tools",
"ai-gateway",
"ai-proxy",
"anthropic",
"litellm-alternative",
"llm",
"llm-gateway",
"observability",
"ollama",
"openai",
"openai-compatible-api",
"proxy",
"deepseek",
"opencode-zen",
"zhipu-ai",
"openai-proxy"
],
"has_wiki": true,
"homepage": null,
"has_readme": true,
"has_docs_dir": true,
"has_description": true
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 30,
"status": "met",
"details": [],
"max_points": 30
},
{
"key": "documentation_directory",
"name": "Documentation directory",
"detail": null,
"points": 25,
"status": "met",
"details": [],
"max_points": 25
},
{
"key": "documentation_homepage_site",
"name": "Documentation / homepage site",
"detail": null,
"points": 0,
"status": "missed",
"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": "20 topics",
"points": 10,
"status": "met",
"details": [
{
"code": "topics_count",
"params": {
"count": 20
}
}
],
"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": "moderate",
"name": "Security",
"value": 68,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "moderate",
"name": "Security posture",
"note": "Excluded from scoring (no data or not applicable): CI-Tests. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"ci_tests"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 68,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 17,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 1,
"scorecard_aggregate": 6.8
},
"components": [
{
"key": "binary_artifacts",
"name": "Binary-Artifacts",
"detail": "no binaries found in the repo",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "branch_protection",
"name": "Branch-Protection",
"detail": "branch protection not enabled on development/release branches",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "ci_tests",
"name": "CI-Tests",
"detail": "no pull request found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"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 0/30 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 2 contributing companies or organizations -- score normalized to 6",
"points": 1.5,
"status": "partial",
"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": "update tool detected",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "fuzzing",
"name": "Fuzzing",
"detail": "project is fuzzed",
"points": 5,
"status": "met",
"details": [],
"max_points": 5
},
{
"key": "license",
"name": "License",
"detail": "license file detected",
"points": 2.5,
"status": "met",
"details": [],
"max_points": 2.5
},
{
"key": "maintained",
"name": "Maintained",
"detail": "30 commit(s) and 3 issue activity found in the last 90 days -- score normalized to 10",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "packaging",
"name": "Packaging",
"detail": "packaging workflow detected",
"points": 5,
"status": "met",
"details": [],
"max_points": 5
},
{
"key": "pinned_dependencies",
"name": "Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "sast",
"name": "SAST",
"detail": "SAST tool detected: CodeQL",
"points": 5,
"status": "met",
"details": [],
"max_points": 5
},
{
"key": "security_policy",
"name": "Security-Policy",
"detail": "security policy file detected",
"points": 5,
"status": "met",
"details": [],
"max_points": 5
},
{
"key": "signed_releases",
"name": "Signed-Releases",
"detail": "5 out of the last 5 releases have a total of 5 signed artifacts.",
"points": 6,
"status": "partial",
"details": [],
"max_points": 7.5
},
{
"key": "token_permissions",
"name": "Token-Permissions",
"detail": "detected GitHub workflow tokens with excessive permissions",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "vulnerabilities",
"name": "Vulnerabilities",
"detail": "0 existing vulnerabilities detected",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
}
]
},
{
"key": "high_risk_jurisdiction_exposure",
"band": "excellent",
"name": "High-Risk Jurisdiction Exposure",
"note": "Only high-confidence self-published location evidence affects this multiplier. Ambiguous matches are review-only; country evidence is not proof of nationality, citizenship, legal registration, malicious intent, or sanctions status.",
"notes": [
{
"code": "jurisdiction_evidence_limits",
"params": {}
}
],
"value": 100,
"inputs": {
"meaning": "self-published location evidence; not nationality or citizenship",
"red_flag": false,
"exposures": [],
"policy_countries": [
"Russia",
"Iran",
"North Korea"
],
"review_only_matches": 0,
"assessed_self_published_locations": 2
},
"components": [
{
"key": "policy_exposure_multiplier",
"name": "Policy exposure multiplier",
"detail": "no confirmed policy-scope location match",
"points": 100,
"status": "met",
"details": [
{
"code": "jurisdiction_no_match",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure?"
},
{
"key": "ai_readiness",
"band": "good",
"name": "AI Readiness",
"value": 76,
"weight": 0,
"metrics": [
{
"key": "ai_agent_context",
"band": "good",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 82,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 0.69,
"agent_instruction_files": [
"AGENTS.md"
],
"agent_instruction_max_bytes": 28024
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "AGENTS.md",
"points": 45,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "AGENTS.md"
}
}
],
"max_points": 45
},
{
"key": "machine_readable_docs_llms_txt",
"name": "Machine-readable docs (llms.txt)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
},
{
"key": "legible_commit_history",
"name": "Legible commit history",
"detail": "69 of 100 human commits state their intent (structured subject or explanatory body)",
"points": 36.8,
"status": "partial",
"details": [
{
"code": "legible_history",
"params": {
"legible": 69,
"sampled": 100
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "good",
"name": "Verify loop (build / test / typecheck)",
"note": null,
"notes": [],
"value": 77,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [
"go.sum"
],
"has_dockerfile": true,
"typed_language": true,
"bootstrap_files": [
"mise.toml"
],
"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": "mise.toml",
"points": 18,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "mise.toml"
}
}
],
"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": "Dockerfile, lockfile",
"points": 10,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "Dockerfile, lockfile"
}
}
],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "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": "dependency automation configured, none observed in the sampled commits",
"points": 5,
"status": "partial",
"details": [
{
"code": "dependency_bot_config_only",
"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": 75201,
"source_files_sampled": 278,
"oversized_source_files": 1
},
"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": "1/278 source files over 60KB",
"points": 54.8,
"status": "partial",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 278,
"oversized": 1
}
}
],
"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",
"Could not fetch go package 'github.com/nenya' from its registry"
],
"report_type": "repository",
"generated_at": "2026-07-24T13:25:17.994758Z",
"schema_version": "0.27.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/g/gumieri/nenya.svg",
"full_name": "gumieri/nenya",
"license_state": "standard",
"license_spdx": "Apache-2.0"
}Scores are signals, not warranties. They reflect publicly visible practices on GitHub — not a code audit, and not a security guarantee.
Missing data is excluded and weights renormalized, never scored as zero. Methodology is versioned and open: metrics v1.13.0, schema v0.27.0 — full methodology · metrics wiki.
How one result sits in the wider record: aggregate statistics.