Public record
Software health reportschema 0.27.0 · metrics 2.3.1 · 2026-07-31 16:51 UTC

baabakk / llm-ports

TypeScript LLM Abstraction Layer for Multi-Provider AI Systems. Multi-provider routing, fallback chains, USD cost gating, capability factories, tool-use security.

TypeScriptMIT★ 2 stars⑂ 0 forkssince May 2026View on GitHub ↗

baabakk/llm-ports holds a health index of 65 out of 100, placing it in the Good band. It scores highest on Engineering Quality (88/100) and lowest on Security (42/100). It was last updated 9 days ago. A single contributor accounts for most of its recent work.

65
overall / 100
Good

Software health index

Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean, calibrated against the distribution of the public record so bands carry percentile meaning; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At Risk ceiling of 34.

65
Exceptional93-100The record's top tier (≈ top 5%); essentially all checked criteria met
Excellent80-92Strong across the board; minor gaps
Good65-79Healthy; gaps are limited and manageable
Moderate50-64Acceptable with notable gaps; review recommended
Weak35-49Material weaknesses across several areas
At Risk20-34Significant weaknesses; adoption warrants caution
Critical1-19Severe problems (abandoned, single-maintainer, no hygiene)
VitalityCommunity &AdoptionSustainability &GovernanceEngineeringQualitySecurityAI Readiness

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.

The weighted overall 60 is calibrated to 65 on the published index scale (record calibration 2026-08-02).

Ownership

BabakPersonal account
2 followers32 public repossince Mar 2015

This repository is owned by a personal account. A single-owner project carries more continuity risk than an organization-backed one.

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publishTags
npm@llm-ports/core0.1.0-alpha.281,825249 days agollmaitypescriptopenaianthropicollamaai-sdkgenerative-aillm-routingllm-fallbackllm-abstractionmulti-providermulti-provider-llmports-and-adaptershexagonal-architecturecost-controlcost-gatingvendor-lock-inprovider-routerai-architectureproduction-llm
npm@llm-ports/migrate0.1.0-alpha.20.138145 days agollm-portsmigratecodemodalpha
npm@llm-ports/capabilities0.1.0-alpha.281,387259 days agollmaitypescriptgenerative-aillm-portsllm-capabilitiescapabilitiesclassifyscoredraftsummarizeextractplananalyzestructured-outputzodjson-modefactory-patternreusable-promptsproduction-llm
npm@llm-ports/adapter-aider0.1.0-alpha.286519 days agollm-portsaideradaptersubprocessagent
npm@llm-ports/adapter-codex0.1.0-alpha.286319 days agollmaicodexopenaiagentsubprocessllm-portsadapter
npm@llm-ports/adapter-google0.1.0-alpha.281,076239 days agollmaitypescriptgooglegeminigoogle-genaivisionmultimodalports-and-adaptersllm-portsproduction-llm
npm@llm-ports/adapter-ollama0.1.0-alpha.281,086269 days agollmaitypescriptollamalocal-llmself-hostedllamallama3mistralphiqwengemmaai-sdkgenerative-aillm-portsllm-adapterllm-routingembeddingsmodel-managementlocal-to-cloudtool-usevisionmulti-provideroffline-llmprivacy
npm@llm-ports/adapter-openai0.1.0-alpha.282,023309 days agollmaitypescriptopenaiopenai-compatiblegptgpt-4gpt-4ogpt-5azure-openaigroqtogether-aifireworksdeepinfraperplexitycerebraslitellmai-sdkgenerative-aillm-portsllm-adapterllm-routingllm-fallbackembeddingstool-usefunction-callingstructured-outputvisionmulti-providercost-controlreasoning-models

Metrics by category

Vitality

Is the project alive — is code being written and are releases shipping?

73Good · 21% of overall
How it's scored
28.8/36Push recency — last push 9 days ago
8.3/36Commit cadence — 12/52 weeks with commits
18/18Commit volume — 165 commits in the last year
0/10OpenSSF Scorecard: Maintained — project was created within the last 90 days. Please review its contents carefully
Inputs used
commits_last_year165
human_commit_share1
days_since_last_push9
active_weeks_last_year12

Release discipline

100Exceptional
How it's scored
27/27Ships releases — 82 releases published
36/36Release recency — latest release 13 days ago
27/27Release cadence — a release every ~3.8 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count82
latest_release_tag@llm-ports/core@0.1.0-alpha.27
releases_from_tagsno
days_since_latest_release13
mean_days_between_releases3.8
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.

Community & Adoption

Does the project have users, downloads, attention, and a welcoming setup for contributors?

49Weak · 17% of overall
How it's scored
0/60Stars — 2 stars
0/25Forks — 0 forks
0/15Watchers — 1 watchers
Inputs used
forks0
stars2
watchers1
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

92Excellent
How it's scored
22.5/22.5README
22.5/22.5License — recognized license (MIT)
18/18CONTRIBUTING guide
13.5/13.5Code of conduct
0/7.2Issue template
6.3/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges
has_contributingyes
has_issue_templateno
has_code_of_conductyes
readme_badge_services
has_pull_request_templateyes
How it's scored
51.7/80Monthly downloads — 7,563 downloads/month across npm
0/20Registry dependents — not reported by this ecosystem
Inputs used
packages@llm-ports/core, @llm-ports/migrate, @llm-ports/capabilities, @llm-ports/adapter-aider, @llm-ports/adapter-codex, @llm-ports/adapter-google, @llm-ports/adapter-ollama, @llm-ports/adapter-openai
dependents
ecosystemsnpm
total_downloads
monthly_downloads7,563
Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.

Sustainability & Governance

Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?

46Weak · 23% of overall
How it's scored
9/54Bus factor — 1 contributor(s) cover half of all commits
0/22.5Commit distribution — top contributor authored 100% of commits
1.4/13.5Contributor breadth — 1 contributors
0/10OpenSSF Scorecard: Contributors — project has 0 contributing companies or organizations -- score normalized to 0
Inputs used
bus_factor1
contributors_sampled1
top_contributor_share1
How it's scored
26.8/42Issue resolution — 64% of issues closed
0/30PR acceptance — no decided pull requests or no data
0/13Newcomer PR acceptance — no first-time contributor's PR decided in 30d
0/15OpenSSF Scorecard: Code-Review — Found 0/30 approved changesets -- score normalized to 0
Inputs used
merged_prs0
open_issues13
closed_issues23
prs_merged_7d
prs_decided_7d
prs_merged_30d
prs_decided_30d
issue_closed_ratio0.639
closed_unmerged_prs0
first_time_authors_30d
first_time_prs_merged_30d
first_time_prs_decided_30d
Excluded from scoring (no data or not applicable): PR acceptance, newcomer_pr_acceptance. Remaining weights renormalized.
How it's scored
10/30Ownership backing — personal (user) account
0/20Verified domain — not applicable to user accounts
3.4/25Owner reach — 2 followers of baabakk
23.1/25Track record — 32 public repos, account ~11 yr old
Inputs used
followers2
owner_typeUser
is_verified
owner_loginbaabakk
public_repos32
account_age_days4,163
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 8 package(s) on npm
35/35Publish recency — latest publish 9 days ago
20/20Version history — 30 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packages@llm-ports/core, @llm-ports/migrate, @llm-ports/capabilities, @llm-ports/adapter-aider, @llm-ports/adapter-codex, @llm-ports/adapter-google, @llm-ports/adapter-ollama, @llm-ports/adapter-openai
ecosystemsnpm
any_deprecatedno
min_days_since_publish9

Engineering Quality

Are baseline engineering and documentation practices in place?

88Excellent · 19% of overall
How it's scored
24/24CI workflows — 2 workflow(s)
24/24Tests present
16/16Linter config — .eslintrc.cjs
0/9.6Pre-commit hooks
0/6.4.editorconfig
0/20OpenSSF Scorecard: CI-Tests — no data
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configno
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: CI-Tests. Remaining weights renormalized.

Documentation

100Exceptional
How it's scored
30/30README
25/25Documentation directory
15/15Documentation / homepage site — https://baabakk.github.io/llm-ports/
10/10Repository description
10/10Topics — 16 topics
10/10Wiki
Inputs used
topicsai, ai-architecture, anthropic, cost-control, generative-ai, llm, llm-abstraction, llm-fallback, llm-routing, multi-provider, ollama, openai, software-architecture, typescript, vendor-lock-in, multi-provider-ai-support
has_wikiyes
homepagehttps://baabakk.github.io/llm-ports/
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?

42Weak · 16% of overall
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
0/7.5Branch-Protection — branch protection not enabled on development/release branches
0/2.5CI-Tests — no data
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
0/7.5Code-Review — Found 0/30 approved changesets -- score normalized to 0
0/2.5Contributors — project has 0 contributing companies or organizations -- score normalized to 0
10/10Dangerous-Workflow — no dangerous workflow patterns detected
0/7.5Dependency-Update-Tool — no update tool detected
0/5Fuzzing — project is not fuzzed
2.5/2.5License — license file detected
0/7.5Maintained — project was created within the last 90 days. Please review its contents carefully
0/5Packaging — no data
0/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
0/5SAST — no SAST tool detected
5/5Security-Policy — security policy file detected
0/7.5Signed-Releases — no data
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
0/7.5Vulnerabilities — 22 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated15
scorecard_versionv5.5.0
checks_inconclusive3
scorecard_aggregate2.8
Excluded from scoring (no data or not applicable): ci_tests, packaging, signed_releases. Remaining weights renormalized.

Dependency advisories

100Exceptional
How it's scored
35/35Direct dependencies free of known advisories — no direct dependency carries a known advisory
25/25Indirect dependencies free of known advisories — no indirect dependency carries a known advisory
0/40No advisories left outstanding — no advisory carries a publication date
Inputs used
sourceosv
advisories0
affected_packages0
assessed_packages1
unassessed_packages0
affected_by_severitynone
direct_affected_packages0
Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the npm:@llm-ports/core@0.1.0-alpha.28 runtime dependency closure — what installing the published package pulls in — 1 packages. Reachability is not analyzed.

AI Readiness

How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight (4%): agent tooling is a real maintenance signal, but a repository with none can still reach 100/100.

55Moderate · 4% of overall
How it's scored
0/45Agent instructions — no CLAUDE.md / AGENTS.md / editor rules
0/15Machine-readable docs (llms.txt)
40/40Legible commit history — 99 of 100 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtno
legible_history_share0.99
agent_instruction_files
agent_instruction_max_bytes
How it's scored
0/18One-command bootstrap
22/22Automated tests
11/11Lint / format config — .eslintrc.cjs
11/11Static type checking — examples/agent-with-approval/tsconfig.json, examples/basic/tsconfig.json, examples/email-triage/tsconfig.json, examples/extract-from-pdf/tsconfig.json, examples/local-with-ollama/tsconfig.json, examples/migrate-from-vercel-ai/tsconfig.json, examples/multi-provider/tsconfig.json, examples/streaming-chat/tsconfig.json, examples/with-onretry/tsconfig.json, packages/adapter-aider/tsconfig.json, packages/adapter-anthropic/tsconfig.json, packages/adapter-codex/tsconfig.json, packages/adapter-contract-tests/tsconfig.json, packages/adapter-google/tsconfig.json, packages/adapter-ollama/tsconfig.json, packages/adapter-openai/tsconfig.json, packages/adapter-vercel/tsconfig.json, packages/benchmarks/tsconfig.json, packages/capabilities/tsconfig.json, packages/consumer-type-check/tsconfig.json, packages/core/tsconfig.json, packages/migrate/tsconfig.json, packages/observability-contract/tsconfig.json
10/10Reproducible environment — lockfile
0/10Demonstrated agent practice — no agent-authored commits among the last 100
0/8Automated maintenance — no automated dependency updates observed
0/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
Inputs used
has_nixno
has_testsyes
lockfilespnpm-lock.yaml
has_dockerfileno
typed_languageyes
bootstrap_files
has_devcontainerno
has_linter_configyes
typecheck_configsexamples/agent-with-approval/tsconfig.json, examples/basic/tsconfig.json, examples/email-triage/tsconfig.json, examples/extract-from-pdf/tsconfig.json, examples/local-with-ollama/tsconfig.json, examples/migrate-from-vercel-ai/tsconfig.json, examples/multi-provider/tsconfig.json, examples/streaming-chat/tsconfig.json, examples/with-onretry/tsconfig.json, packages/adapter-aider/tsconfig.json, packages/adapter-anthropic/tsconfig.json, packages/adapter-codex/tsconfig.json, packages/adapter-contract-tests/tsconfig.json, packages/adapter-google/tsconfig.json, packages/adapter-ollama/tsconfig.json, packages/adapter-openai/tsconfig.json, packages/adapter-vercel/tsconfig.json, packages/benchmarks/tsconfig.json, packages/capabilities/tsconfig.json, packages/consumer-type-check/tsconfig.json, packages/core/tsconfig.json, packages/migrate/tsconfig.json, packages/observability-contract/tsconfig.json
agent_commit_share0
toolchain_manifests
dependency_bot_commit_share0
How it's scored
45/45Type-checkable code — TypeScript (statically typed)
54.8/55Manageable file sizes — 1/262 source files over 60KB
Inputs used
primary_languageTypeScript
largest_source_bytes82,975
source_files_sampled262
oversized_source_files1
How it's scored
0/40API schema (OpenAPI/GraphQL/proto)
0/20MCP server
40/40Runnable examples — examples
Inputs used
example_dirsexamples
has_mcp_signalno
api_schema_files

Key facts

2GitHub stars
1contributors
165commits, last 12 months
9days since last push
82releases
1bus factor
13open issues
npmpackage ecosystems

Data collection warnings

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

More detail

OpenSSF Scorecard 2.8 / 10
2.8aggregate

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).Scorecard v5.5.0 · 2026-07-31 16:51 UTC

10Binary-Artifactsno binaries found in the repo
0Branch-Protectionbranch protection not enabled on development/release branches
n/aCI-Testsno pull request found
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
0Code-ReviewFound 0/30 approved changesets -- score normalized to 0
0Contributorsproject has 0 contributing companies or organizations -- score normalized to 0
10Dangerous-Workflowno dangerous workflow patterns detected
0Dependency-Update-Toolno update tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
0Maintainedproject was created within the last 90 days. Please review its contents carefully
n/aPackagingpackaging workflow not detected
0Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 0
0SASTno SAST tool detected
10Security-Policysecurity policy file detected
n/aSigned-Releasesno releases found
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities22 existing vulnerabilities detected
Direct dependencies 21
RegistryPackageVersion constraintManifest
npm@anthropic-ai/sdk^0.32.1packages/adapter-anthropic/package.json
npm@llm-ports/coreworkspace:*packages/adapter-anthropic/package.json
npmzod-to-json-schema^3.24.1packages/adapter-anthropic/package.json
npm@llm-ports/coreworkspace:*packages/adapter-contract-tests/package.json
npmvitest^2.1.4packages/adapter-contract-tests/package.json
npmzod^3.23.0packages/adapter-contract-tests/package.json
npm@llm-ports/coreworkspace:*packages/adapter-google/package.json
npmzod-to-json-schema^3.23.5packages/adapter-google/package.json
npm@llm-ports/coreworkspace:*packages/adapter-ollama/package.json
npmollama^0.5.10packages/adapter-ollama/package.json
npm@llm-ports/coreworkspace:*packages/adapter-openai/package.json
npmopenai^4.73.0packages/adapter-openai/package.json
npmzod-to-json-schema^3.24.1packages/adapter-openai/package.json
npm@llm-ports/coreworkspace:*packages/adapter-vercel/package.json
npmai^4.3.19packages/adapter-vercel/package.json
npm@llm-ports/coreworkspace:*packages/capabilities/package.json
npm@llm-ports/coreworkspace:*packages/consumer-type-check/package.json
npm@llm-ports/capabilitiesworkspace:*packages/consumer-type-check/package.json
npmzod^3.25.76packages/consumer-type-check/package.json
npmjsonrepair^3.14.0packages/core/package.json
npmnanoid^5.0.9packages/observability-contract/package.json
All dependencies not collected

The resolved dependency set could not be collected for this report: GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository

Dependency advisories 0

Installing npm:@llm-ports/core@0.1.0-alpha.28 pulls in 1 packages, direct and transitive: 0 carry known advisories, of which 0 are direct dependencies.

No known advisories affect the assessed dependencies.

An advisory means the version recorded in the dependency graph falls inside an advisory’s affected range. Reachability is not analysed, and the graph includes development and test pins — a finding may concern tooling rather than shipped software.

Raw JSON report machine-readable
{
  "data": {
    "repo": {
      "topics": [
        "ai",
        "ai-architecture",
        "anthropic",
        "cost-control",
        "generative-ai",
        "llm",
        "llm-abstraction",
        "llm-fallback",
        "llm-routing",
        "multi-provider",
        "ollama",
        "openai",
        "software-architecture",
        "typescript",
        "vendor-lock-in",
        "multi-provider-ai-support"
      ],
      "is_fork": false,
      "size_kb": 4580,
      "has_wiki": true,
      "homepage": "https://baabakk.github.io/llm-ports/",
      "languages": {
        "JavaScript": 14014,
        "TypeScript": 1664309
      },
      "pushed_at": "2026-07-22T12:53:03Z",
      "created_at": "2026-05-06T00:38:41Z",
      "owner_type": "User",
      "updated_at": "2026-07-22T12:51:03Z",
      "description": "TypeScript LLM Abstraction Layer for Multi-Provider AI Systems. Multi-provider routing, fallback chains, USD cost gating, capability factories, tool-use security.",
      "is_archived": false,
      "is_disabled": false,
      "license_spdx": "MIT",
      "default_branch": "main",
      "license_spdx_raw": "MIT",
      "primary_language": "TypeScript",
      "significant_languages": [
        "TypeScript"
      ]
    },
    "owner": {
      "blog": null,
      "name": "Babak",
      "type": "User",
      "login": "baabakk",
      "company": null,
      "location": null,
      "followers": 2,
      "avatar_url": "https://avatars.githubusercontent.com/u/11369431?v=4",
      "created_at": "2015-03-07T22:22:52Z",
      "is_verified": null,
      "public_repos": 32,
      "account_age_days": 4163
    },
    "license": {
      "state": "standard",
      "spdx_id": "MIT",
      "raw_spdx": "MIT",
      "file_present": true,
      "scorecard_found": true,
      "profile_has_license": true
    },
    "activity": {
      "releases": [
        {
          "tag": "@llm-ports/core@0.1.0-alpha.27",
          "kind": "other",
          "published_at": "2026-07-17T23:55:25Z"
        },
        {
          "tag": "@llm-ports/capabilities@0.1.0-alpha.26.1",
          "kind": "other",
          "published_at": "2026-07-03T07:57:15Z"
        },
        {
          "tag": "v0.1.0-alpha.26",
          "kind": "prerelease",
          "published_at": "2026-07-02T23:18:53Z"
        },
        {
          "tag": "v0.1.0-alpha.25",
          "kind": "prerelease",
          "published_at": "2026-07-02T22:45:56Z"
        },
        {
          "tag": "v0.1.0-alpha.24",
          "kind": "prerelease",
          "published_at": "2026-06-25T01:58:21Z"
        },
        {
          "tag": "v0.1.0-alpha.23",
          "kind": "prerelease",
          "published_at": "2026-06-25T01:12:11Z"
        },
        {
          "tag": "v0.1.0-alpha.22",
          "kind": "prerelease",
          "published_at": "2026-06-19T15:58:14Z"
        },
        {
          "tag": "v0.1.0-alpha.21",
          "kind": "prerelease",
          "published_at": "2026-06-19T04:52:32Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.20.1",
          "kind": "other",
          "published_at": "2026-06-15T23:26:22Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.20",
          "kind": "other",
          "published_at": "2026-06-13T20:39:54Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.19.1",
          "kind": "other",
          "published_at": "2026-06-12T22:59:14Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.19",
          "kind": "other",
          "published_at": "2026-06-12T19:24:01Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.18",
          "kind": "other",
          "published_at": "2026-06-05T09:14:05Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.17",
          "kind": "other",
          "published_at": "2026-06-05T07:18:43Z"
        },
        {
          "tag": "@llm-ports/adapter-openai@0.1.0-alpha.16",
          "kind": "other",
          "published_at": "2026-05-30T20:38:02Z"
        },
        {
          "tag": "@llm-ports/adapter-openai@0.1.0-alpha.15",
          "kind": "other",
          "published_at": "2026-05-27T08:15:35Z"
        },
        {
          "tag": "@llm-ports/adapter-openai@0.1.0-alpha.14",
          "kind": "other",
          "published_at": "2026-05-27T04:17:21Z"
        },
        {
          "tag": "@llm-ports/adapter-vercel@0.1.0-alpha.13",
          "kind": "other",
          "published_at": "2026-05-27T03:13:47Z"
        },
        {
          "tag": "@llm-ports/adapter-ollama@0.1.0-alpha.13",
          "kind": "other",
          "published_at": "2026-05-27T03:13:46Z"
        },
        {
          "tag": "@llm-ports/adapter-google@0.1.0-alpha.13",
          "kind": "other",
          "published_at": "2026-05-27T03:13:45Z"
        },
        {
          "tag": "@llm-ports/adapter-anthropic@0.1.0-alpha.13",
          "kind": "other",
          "published_at": "2026-05-27T03:13:43Z"
        },
        {
          "tag": "@llm-ports/adapter-openai@0.1.0-alpha.13",
          "kind": "other",
          "published_at": "2026-05-27T03:13:41Z"
        },
        {
          "tag": "@llm-ports/capabilities@0.1.0-alpha.13",
          "kind": "other",
          "published_at": "2026-05-27T03:13:39Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.13",
          "kind": "other",
          "published_at": "2026-05-27T03:13:38Z"
        },
        {
          "tag": "@llm-ports/adapter-vercel@0.1.0-alpha.12",
          "kind": "other",
          "published_at": "2026-05-27T02:04:39Z"
        },
        {
          "tag": "@llm-ports/adapter-openai@0.1.0-alpha.12",
          "kind": "other",
          "published_at": "2026-05-27T02:04:34Z"
        },
        {
          "tag": "@llm-ports/capabilities@0.1.0-alpha.12",
          "kind": "other",
          "published_at": "2026-05-27T02:04:32Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.12",
          "kind": "other",
          "published_at": "2026-05-27T02:04:31Z"
        },
        {
          "tag": "@llm-ports/adapter-ollama@0.1.0-alpha.12",
          "kind": "other",
          "published_at": "2026-05-27T02:04:38Z"
        },
        {
          "tag": "@llm-ports/adapter-google@0.1.0-alpha.12",
          "kind": "other",
          "published_at": "2026-05-27T02:04:36Z"
        },
        {
          "tag": "@llm-ports/adapter-anthropic@0.1.0-alpha.12",
          "kind": "other",
          "published_at": "2026-05-27T02:04:35Z"
        },
        {
          "tag": "@llm-ports/adapter-vercel@0.1.0-alpha.11",
          "kind": "other",
          "published_at": "2026-05-26T11:27:47Z"
        },
        {
          "tag": "@llm-ports/adapter-openai@0.1.0-alpha.11",
          "kind": "other",
          "published_at": "2026-05-26T11:27:43Z"
        },
        {
          "tag": "@llm-ports/adapter-ollama@0.1.0-alpha.11",
          "kind": "other",
          "published_at": "2026-05-26T11:27:46Z"
        },
        {
          "tag": "@llm-ports/adapter-google@0.1.0-alpha.11",
          "kind": "other",
          "published_at": "2026-05-26T11:27:44Z"
        },
        {
          "tag": "@llm-ports/adapter-anthropic@0.1.0-alpha.11",
          "kind": "other",
          "published_at": "2026-05-26T11:27:42Z"
        },
        {
          "tag": "@llm-ports/adapter-anthropic@0.1.0-alpha.10",
          "kind": "other",
          "published_at": "2026-05-26T10:54:44Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.9",
          "kind": "other",
          "published_at": "2026-05-26T10:31:49Z"
        },
        {
          "tag": "@llm-ports/adapter-vercel@0.1.0-alpha.9",
          "kind": "other",
          "published_at": "2026-05-26T10:31:59Z"
        },
        {
          "tag": "@llm-ports/adapter-ollama@0.1.0-alpha.9",
          "kind": "other",
          "published_at": "2026-05-26T10:31:57Z"
        },
        {
          "tag": "@llm-ports/adapter-google@0.1.0-alpha.9",
          "kind": "other",
          "published_at": "2026-05-26T10:31:56Z"
        },
        {
          "tag": "@llm-ports/adapter-anthropic@0.1.0-alpha.9",
          "kind": "other",
          "published_at": "2026-05-26T10:31:54Z"
        },
        {
          "tag": "@llm-ports/adapter-openai@0.1.0-alpha.9",
          "kind": "other",
          "published_at": "2026-05-26T10:31:52Z"
        },
        {
          "tag": "@llm-ports/capabilities@0.1.0-alpha.9",
          "kind": "other",
          "published_at": "2026-05-26T10:31:51Z"
        },
        {
          "tag": "@llm-ports/adapter-openai@0.1.0-alpha.8",
          "kind": "other",
          "published_at": "2026-05-26T06:45:58Z"
        },
        {
          "tag": "@llm-ports/adapter-anthropic@0.1.0-alpha.8",
          "kind": "other",
          "published_at": "2026-05-26T06:45:56Z"
        },
        {
          "tag": "@llm-ports/adapter-vercel@0.1.0-alpha.8",
          "kind": "other",
          "published_at": "2026-05-26T06:45:59Z"
        },
        {
          "tag": "@llm-ports/adapter-google@0.1.0-alpha.8",
          "kind": "other",
          "published_at": "2026-05-26T06:46:01Z"
        },
        {
          "tag": "@llm-ports/adapter-ollama@0.1.0-alpha.8",
          "kind": "other",
          "published_at": "2026-05-26T06:46:00Z"
        },
        {
          "tag": "@llm-ports/adapter-google@0.1.0-alpha.7",
          "kind": "other",
          "published_at": "2026-05-23T22:48:33Z"
        },
        {
          "tag": "@llm-ports/adapter-ollama@0.1.0-alpha.7",
          "kind": "other",
          "published_at": "2026-05-23T22:48:32Z"
        },
        {
          "tag": "@llm-ports/adapter-vercel@0.1.0-alpha.7",
          "kind": "other",
          "published_at": "2026-05-23T22:48:31Z"
        },
        {
          "tag": "@llm-ports/adapter-openai@0.1.0-alpha.7",
          "kind": "other",
          "published_at": "2026-05-23T22:48:30Z"
        },
        {
          "tag": "@llm-ports/adapter-anthropic@0.1.0-alpha.7",
          "kind": "other",
          "published_at": "2026-05-23T22:48:29Z"
        },
        {
          "tag": "@llm-ports/capabilities@0.1.0-alpha.7",
          "kind": "other",
          "published_at": "2026-05-23T22:48:28Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.7",
          "kind": "other",
          "published_at": "2026-05-23T22:48:27Z"
        },
        {
          "tag": "@llm-ports/adapter-ollama@0.1.0-alpha.6",
          "kind": "other",
          "published_at": "2026-05-23T11:14:26Z"
        },
        {
          "tag": "@llm-ports/adapter-vercel@0.1.0-alpha.6",
          "kind": "other",
          "published_at": "2026-05-23T11:14:25Z"
        },
        {
          "tag": "@llm-ports/adapter-openai@0.1.0-alpha.6",
          "kind": "other",
          "published_at": "2026-05-23T11:14:24Z"
        },
        {
          "tag": "@llm-ports/capabilities@0.1.0-alpha.6",
          "kind": "other",
          "published_at": "2026-05-23T11:14:21Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.6",
          "kind": "other",
          "published_at": "2026-05-23T11:14:20Z"
        },
        {
          "tag": "@llm-ports/adapter-google@0.1.0-alpha.6",
          "kind": "other",
          "published_at": "2026-05-23T11:14:28Z"
        },
        {
          "tag": "@llm-ports/adapter-anthropic@0.1.0-alpha.6",
          "kind": "other",
          "published_at": "2026-05-23T11:14:22Z"
        },
        {
          "tag": "@llm-ports/adapter-google@0.1.0-alpha.5",
          "kind": "other",
          "published_at": "2026-05-21T04:26:13Z"
        },
        {
          "tag": "@llm-ports/adapter-ollama@0.1.0-alpha.5",
          "kind": "other",
          "published_at": "2026-05-21T04:26:12Z"
        },
        {
          "tag": "@llm-ports/adapter-vercel@0.1.0-alpha.5",
          "kind": "other",
          "published_at": "2026-05-21T04:26:10Z"
        },
        {
          "tag": "@llm-ports/adapter-openai@0.1.0-alpha.5",
          "kind": "other",
          "published_at": "2026-05-21T04:26:09Z"
        },
        {
          "tag": "@llm-ports/adapter-anthropic@0.1.0-alpha.5",
          "kind": "other",
          "published_at": "2026-05-21T04:26:08Z"
        },
        {
          "tag": "@llm-ports/capabilities@0.1.0-alpha.5",
          "kind": "other",
          "published_at": "2026-05-21T04:26:07Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.5",
          "kind": "other",
          "published_at": "2026-05-21T04:26:06Z"
        },
        {
          "tag": "@llm-ports/adapter-ollama@0.1.0-alpha.4",
          "kind": "other",
          "published_at": "2026-05-21T02:51:52Z"
        },
        {
          "tag": "@llm-ports/adapter-vercel@0.1.0-alpha.4",
          "kind": "other",
          "published_at": "2026-05-21T02:51:51Z"
        },
        {
          "tag": "@llm-ports/adapter-openai@0.1.0-alpha.4",
          "kind": "other",
          "published_at": "2026-05-21T02:51:50Z"
        },
        {
          "tag": "@llm-ports/adapter-anthropic@0.1.0-alpha.4",
          "kind": "other",
          "published_at": "2026-05-21T02:51:49Z"
        },
        {
          "tag": "@llm-ports/capabilities@0.1.0-alpha.4",
          "kind": "other",
          "published_at": "2026-05-21T02:51:48Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.4",
          "kind": "other",
          "published_at": "2026-05-21T02:51:47Z"
        },
        {
          "tag": "@llm-ports/adapter-ollama@0.1.0-alpha.3",
          "kind": "other",
          "published_at": "2026-05-21T01:15:58Z"
        },
        {
          "tag": "@llm-ports/adapter-vercel@0.1.0-alpha.3",
          "kind": "other",
          "published_at": "2026-05-21T01:15:57Z"
        },
        {
          "tag": "@llm-ports/adapter-openai@0.1.0-alpha.3",
          "kind": "other",
          "published_at": "2026-05-21T01:15:56Z"
        },
        {
          "tag": "@llm-ports/adapter-anthropic@0.1.0-alpha.3",
          "kind": "other",
          "published_at": "2026-05-21T01:15:54Z"
        },
        {
          "tag": "@llm-ports/capabilities@0.1.0-alpha.3",
          "kind": "other",
          "published_at": "2026-05-21T01:15:53Z"
        },
        {
          "tag": "@llm-ports/core@0.1.0-alpha.3",
          "kind": "other",
          "published_at": "2026-05-21T01:15:52Z"
        }
      ],
      "recent_commits": [
        {
          "oid": "d1ed31b72bd6c237f280eeac049113d385a61a79",
          "body": "Runs `pnpm changeset version` against the alpha-28\nchangeset entry. All non-ignored @llm-ports/* packages\nbumped from alpha.27 → alpha.28 uniformly per the\n`linked` config. @llm-ports/migrate stays at alpha.20.1\nvia a new addition to the changesets `ignore` list\n(migrate is on an independent release\n[…]\n8 §5.1).\n\nVerification: `pnpm -r --workspace-concurrency=1 build`\ngreen; full test suite green (~1400 tests across\nadapter-aider 26/26, adapter-codex 41/41, and every\nother package's suite unchanged).",
          "is_bot": false,
          "headline": "chore(release): version @llm-ports/* to 0.1.0-alpha.28",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T12:48:15Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "592f79b2f5f939bf306a8f05e0b9d79095375b19",
          "body": "…dapter-aider\n\nThe initial adapter.test.ts suites covered LLMPort shape, error paths,\noptions passthrough, and observability *started*-event emission — but\nthe CLI arg construction and codex's --json parse path were untested.\nIf codex ever renamed a flag or changed its --json event shape (or\naider i\n[…]\ne shape as codex.\n\nCombined results:\n- adapter-codex: 41/41 passing (12 shape + 29 internals).\n- adapter-aider: 26/26 passing (12 shape + 14 internals).\n\nBoth packages rebuild clean (ESM + CJS + DTS).",
          "is_bot": false,
          "headline": "test(alpha.28-prep): unit-test internal helpers for adapter-codex + a…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T12:28:08Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "29ad0be72c6484e304bf12844b5ce1a3a0686c80",
          "body": "…er adapter (Shape A passthrough)\n\nAdds @llm-ports/adapter-aider@0.1.0-alpha.28. Wraps the aider CLI's\n`aider --no-stream --yes-always --message \"<prompt>\"` invocation as\nan in-process LLMPort.runAgent implementation.\n\nShape A (passthrough governance): the operator supplies aider with\nits own provid\n[…]\n —\nconstructor, unsupported-method errors, missing-workingDirectory\nerror, empty-messages error, smoke runAgent through node-as-mock-cli,\nobservability-event emission, and adapter options passthrough.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): @llm-ports/adapter-aider — subprocess-driven aid…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T11:49:36Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "bce1d5475cd2ebbaf5acc84f37711c77718d6b49",
          "body": "…ex adapter (Shape A passthrough)\n\nAdds @llm-ports/adapter-codex@0.1.0-alpha.28. Wraps codex-cli's\n`codex exec --json` as an in-process LLMPort.runAgent implementation.\n\nShape A (passthrough governance): the operator supplies codex with its\nown OpenAI credentials via env vars or ~/.codex/auth.toml. \n[…]\nructor shape, unsupported-method\nerrors, missing-workingDirectory error, empty-messages error, smoke\nrunAgent through node-as-mock-codex, observability-event emission,\nand adapter options passthrough.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): @llm-ports/adapter-codex — subprocess-driven cod…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T11:44:57Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "8eed89a6a03c58c51df99d95759e50f371affc98",
          "body": "…@llm-ports/core (§4.2)\n\nThe caller-provided context ingress mechanism. Consumers who want to\nattach correlation, W3C Trace Context, Baggage, attributes, or an\nHMAC fingerprint key to every call flowing through a port wrap it\nonce at the workflow root:\n\n  const scoped = withObservabilityContext(port\n[…]\nions.\n\nProvenance: Cross-consumer review pass 2026-07-21. Plan 58 v0.4 §4.2.\nThis is the last step of the observability-contract deliverables.\nAdapter-aider and adapter-codex (steps 5k + 5l) are next.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): withObservabilityContext scoped-port wrapper in …",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T11:35:22Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "c4ac431a0fd5fb9ef0de74238b85e9e2bf8a78e0",
          "body": "…ort callers (§4.13)\n\nThe convenience API that non-port callers (subprocess-driven agent\nruntimes, custom orchestrators, framework middleware) use to emit\nconformant observability events without pulling in @llm-ports/core.\n\nPublic exports:\n\n- EmitterConfig: static setup { source, sink, spec_version?\n[…]\nnew). All pass.\n\nProvenance: Cross-consumer review pass 2026-07-21. Plan 58 v0.4 §4.13.\nThis commit is what closes the \"non-port caller can emit conformant\nevents\" property to a runtime demonstration.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): observability-contract emitter helpers for non-p…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T11:31:37Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "a73e405b2a004149b3b6aa12b9d540dfc965538f",
          "body": "…r every type\n\nRuntime validators for every type in the contract. Downstream sinks\n(ClickHouse ingestion, OTel adapter, consumer-supplied storage) call\n.parse() on incoming events to reject malformed payloads at the sink\nboundary.\n\nSchemas mirror their TypeScript types:\n\nFoundation:\n- eventSourceSch\n[…]\n; +49 new). All pass.\n\nProvenance: Cross-consumer review pass 2026-07-21. Plan 58 v0.4 §7.1\nrequired schema validation as part of the contract-conformance\nsuccess criteria; this commit satisfies that.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): observability-contract Zod validation schemas fo…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T11:28:48Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "93e66161ded673372cc714c8ce3cff4316af4de1",
          "body": "…cy contract\n\nThe formal privacy contract. Every emitter reads a CapturePolicy at\nconstruction time and decides how much of each event's payload lands\non the wire. Sinks may LOWER capture (drop fields the policy allowed)\nbut MUST NOT RAISE it. Defense-in-depth.\n\nCapturePolicy shape:\n- content: \"none\n[…]\nservability-contract tests: 225 (was 192; +33 new). All pass.\n\nProvenance: Cross-consumer review pass 2026-07-21. Plan 58 v0.4 §4.10.\nOutsider critique §10 informed the formal privacy-contract design.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): observability-contract §4.10 CapturePolicy priva…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T11:24:05Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "22b7d4f2c41b4084a7d0629bf24a69483ab2d5b1",
          "body": "…uationTarget union + score union\n\nThe write surface for post-hoc scores that consumers attach to\nobservability data. Evaluations arrive LATE: an LLM-judge score runs\noffline; a human annotator labels an interaction hours later; a\ndataset replay produces retrospective scores days after the original\n\n[…]\nt tests: 192 (was 169; +23 new). All pass.\n\nProvenance: Cross-consumer review pass 2026-07-21. Plan 58 v0.4 §4.9.\nOutsider critique §7 informed the target-union + score-union + dedup\ndesign decisions.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): observability-contract §4.9 EvaluationRef + Eval…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T11:21:27Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "8b963517c6140b6d3740af43c59cc9d847441e09",
          "body": "… golden vectors\n\nSecond half of the RequestFingerprint deliverable. Assembles the\ncanonicalization + hash primitives from the previous commit into the\npublic API, and ships golden vectors that pin the exact byte outputs\nfor cross-implementation validation.\n\nRequestFingerprint shape:\n- message_hash:\n[…]\n +35\n  new). All pass.\n\nProvenance: Cross-consumer review pass 2026-07-21. Plan 58 v0.4 §4.6.\nOutsider critique §7.1 asked for golden vectors; §6 asked for the\ntwo-hash + canonicalization spec design.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): observability-contract §4.6 RequestFingerprint +…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T11:18:46Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "e482f0fae9a55f14aff52f9727560dba8298a6fb",
          "body": "…ash primitives\n\nFirst half of the RequestFingerprint deliverable. Adds the normative\ncanonicalization spec (v1) plus the hash primitives that produce the\ntwo fingerprint hashes.\n\nCanonicalization spec v1 rules (canonicalize.ts):\n\n1. Key ordering: JSON object keys sorted lexicographically at every\n \n[…]\nimitives into the RequestFingerprint\ntype + computeRequestFingerprint helper + golden vectors JSON pinning\nthe exact byte output.\n\nProvenance: Cross-consumer review pass 2026-07-21. Plan 58 v0.4 §4.6.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): observability-contract §4.6 canonicalization + h…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T11:13:34Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "1922b97dbdad995bedf4e08feb5a9bd25e6970b1",
          "body": "Replaces the CacheStatsPlaceholder from the lifecycle commit with the\nfull nested shape:\n\n- provider_cache?: ProviderCacheStats\n- semantic_cache?: SemanticCacheStats\n\nProviderCacheStats:\n- status: \"hit\" | \"miss\" | \"partial\" | \"ineligible\" | \"unknown\"\n- read_input_tokens? (Anthropic cache_read, OpenA\n[…]\n Total observability-contract tests: 84 (was 58; +26 new). All pass.\n\nProvenance: Cross-consumer review pass 2026-07-21. Plan 58 v0.4 §4.5.\nOutsider critique §8 informed the nested-with-status design.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): observability-contract §4.5 CacheStats nested shape",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T11:09:26Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "e2efa68f6f7c3b41e1dc4ec383b0686aeaee63b4",
          "body": "…useCategory rollup\n\nReplaces the ErrorInfoPlaceholder from the lifecycle commit with the\nfull shape:\n\n- error_type: string form of the typed error class\n- message?: human-readable, redactable per CapturePolicy\n- retryable: boolean (same-provider retry may succeed)\n- fallback_worthy: boolean (walk t\n[…]\n completeness of the\n  ERROR_TYPE_TO_CATEGORY static table.\n- Total observability-contract tests: 58 (was 40; +18 new). All pass.\n\nProvenance: Cross-consumer review pass 2026-07-21. Plan 58 v0.4 §4.4.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): observability-contract §4.4 ErrorInfo shape + Ca…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T11:06:33Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "bc29c4379e8faf5d871e6eb1e05c30bf38cb16d4",
          "body": "…4.7 agent-step events\n\nAdds thirteen event types covering the complete operation lifecycle:\n\nNine core lifecycle events per Plan 58 v0.4 §4.3:\n- llm.operation.started\n- llm.attempt.started\n- llm.attempt.retry_scheduled\n- llm.fallback.selected\n- llm.attempt.failed\n- llm.attempt.completed\n- llm.opera\n[…]\n ending with an OPERATION_TERMINATOR_TYPES\n    event\n- Total observability-contract tests: 40 (was 21; +19 new). All pass.\n\nProvenance: Cross-consumer review pass 2026-07-21. Plan 58 v0.4 §4.3 + §4.7.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): observability-contract §4.3 lifecycle events + §…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T11:03:22Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "eef5de19928300d648c37e3c70dc3f204bdaafa5",
          "body": "…1.0-alpha.28 — foundation types (envelope, correlation, sink, IDs)\n\nFirst landmark commit for Plan 58 v0.4 §5.1 alpha.28 contract foundation.\nBootstraps the standalone data contract package that non-port callers\n(ADW's ClaudeCodeDriver subprocess path, custom agent runtimes, etc.)\nimport to emit co\n[…]\n total workspace tests: 934 (was 913 pre-commit; +21 new).\n\nProvenance: Cross-consumer review pass 2026-07-21. Plan 58 v0.4 approved\n2026-07-21T18:45:46 -07:00, §5.1 alpha.28 contract foundation only.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): new package @llm-ports/observability-contract@0.…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T05:20:13Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "e2934f72e68ba09581a804043de7321f9574f882",
          "body": "…es on invalid_enum_value before retry\n\nModel-emitted Unicode confusables of ASCII delimiter characters (U+2010..U+2015\nhyphens, U+2018/U+2019 curly single quotes, U+201C/U+201D curly double quotes,\nU+00A0 non-breaking space and other Unicode spaces, U+FF0D fullwidth\nhyphen-minus) silently broke Zod\n[…]\nepair-validation tests pass (was 33; +13 new).\n\nConsumer-side origin: ADW TD-LLM-20 + BEPA\nTD-LLMPORTS-EXTRACTJSON-UNICODE-CONFUSABLE-NORMALIZATION.\n\nProvenance: Cross-consumer review pass 2026-07-21.",
          "is_bot": false,
          "headline": "fix(TD-LLMP-18): attemptValidationRepair normalizes Unicode confusabl…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T05:13:18Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "24194b775db008d7eb34adee376040dfdd5a196f",
          "body": "… isolates local JS runtime errors as AdapterInternalError\n\nTwo-part fix for the ADW-reported bug: runAgent throws raw TypeError\nwhen tools omitted, and local TypeErrors get misclassified as\nServiceUnavailableError triggering futile chain-wide failover.\n\nPart 1: defensive tools normalization (fixes \n[…]\nelopment_TechDebt.md:1125-1141)\nplus BEPA TD-LLMPORTS-TYPEERROR-MISCLASSIFIED-AS-SERVICE-UNAVAILABLE\n(BEPA-side sibling tracking the same exposure).\n\nProvenance: Cross-consumer review pass 2026-07-21.",
          "is_bot": false,
          "headline": "fix(TD-LLMP-17): runAgent tools defensive default + wrapProviderError…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T05:10:35Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "9647f043e47098b255dcb98fbb133fd911dc3bfd",
          "body": "…ouldFallback (TD-LLMP-19)\n\nCanonical walk-table policy from the 2026-07-21 cross-consumer review pass,\nexported as a single-function predicate consumers can wire into\nruntimeFallback config. Codifies the outcome of the review; supersedes\nhand-rolled per-consumer classifiers.\n\nWalk-worthy (returns t\n[…]\nrMatchers.default policy\n(with two exceptions: ImageTooLargeError and ContentBlockUnsupportedError\nnow walk correctly, closing a small ambient bug).\n\nProvenance: Cross-consumer review pass 2026-07-21.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): publish canonical walk-table policy as defaultSh…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T05:07:22Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "c1f0841dc1da9aba17c342e574880bb5ffbed136",
          "body": "…Error, ProviderMalformed400Error, AdapterInternalError\n\nFoundational building block for alpha.28 (Plan 58 §4.4 ErrorInfo shape +\nwalk-table policy). All three classes are prerequisites for:\n\n- TD-LLMP-17 (runAgent tools guard + local-throw isolation): adapter code\n  wraps only the provider-call blo\n[…]\npty-body 400 detection\npath already outlined in the DeepInfra + Cerebras production reports. Those\nchanges ship in subsequent alpha.28-prep commits.\n\nProvenance: Cross-consumer review pass 2026-07-21.",
          "is_bot": false,
          "headline": "feat(alpha.28-prep): add 3 new typed error classes — CreditExhaustion…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T05:04:12Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "993db1bf4a886402e035ecadfae800a54324ffeb",
          "body": "…textWindowExceededError and ContentPolicyViolationError\n\nThe alpha.28 pre-work batch starts with TD-LLMP-16 (from the cross-consumer\nreview pass 2026-07-21). Previously, wrapProviderError construct the two\nmodel-scoped BadRequest subclasses with a hardcoded \"(unknown)\" placeholder\neven when the ada\n[…]\n-side origin: BEPA TD-LLMPORTS-DEEPINFRA-CONTEXT-EXCEEDED-MODEL-UNKNOWN-AND-SILENT-HANG-ON-RETRY Bug 1 (filed 2026-07-21T03:06:38 in BEPA's TD log).\n\nProvenance: Cross-consumer review pass 2026-07-21.",
          "is_bot": false,
          "headline": "fix(TD-LLMP-16): propagate modelId through wrapProviderError into Con…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-22T02:16:56Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "f0147f65cabc9a0da63fe50796747ff534cf9567",
          "body": "…sk requirements + provider capabilities + boot-time chain resolution)\n\nFiled after BEPA's 2026-07-21T09:35 UTC selector-compile incident: task\ntype had no explicit LLM_TASK_ROUTE_SELECTOR_COMPILE, fell through to\ndefault chain including deepseek-4flash-deepinfra (32K context), which\ncorrectly rejec\n[…]\nract; runtime wiring via\nnew capabilityChain option on createRegistryFromEnv in core.\n\nTarget release: alpha.29 or alpha.30 pending scope decisions.\n\nProvenance: Cross-consumer review pass 2026-07-21.",
          "is_bot": false,
          "headline": "docs(tech-debt): TD-LLMP-20 — capability-based router (declarative ta…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-21T23:09:19Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "f35f963f484ac7b2f87f3ae07c9eb1d4cb97187a",
          "body": "TD-LLMP-16: adapter-openai ContextWindowExceededError reports model\n\"(unknown)\" even when the model name is at request-construction time.\nReported by BEPA.\n\nTD-LLMP-17: runAgent throws raw TypeError when tools omitted; local\nTypeErrors then get misclassified as ServiceUnavailableError, triggering\nfu\n[…]\nk-table\nmisalignment) and ADW (audit finding TD-LLM-18 + policy question in\nTD-LLM-21).\n\nTarget: alpha.28 pre-work window. Each TD names its consumer-side\norigin TD so the ecosystem trail is walkable.",
          "is_bot": false,
          "headline": "docs(tech-debt): batch of 4 TDs from 2026-07-21 cross-consumer review",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-21T22:46:39Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "bac6ecb49ec58637d76e8f431d03225dfc7fa9df",
          "body": "7 publishable packages ship at 0.1.0-alpha.27:\n- @llm-ports/core (BREAKING: instructions/prompt removed; messages required)\n- @llm-ports/adapter-openai\n- @llm-ports/adapter-anthropic (new NonContiguousSystemError guard)\n- @llm-ports/adapter-google (new NonContiguousSystemError guard)\n- @llm-ports/ad\n[…]\npha-26-to-alpha-27.md\nDeprecation infra generalized: warnDeprecatedLegacyInput -> warnDeprecated(state, {what, where, removalVersion?, migrationUrl?})\n\n886 tests pass workspace-wide. Zero regressions.",
          "is_bot": false,
          "headline": "chore(release): v0.1.0-alpha.27",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-17T23:51:09Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "d3b8ad1b189cef47738a8bbceb2a3daa55e393fb",
          "body": "…es required\n\nCommits D + E bundled: the legacy fields are removed from the type\ninterfaces AND the examples migrate to the canonical messages shape.\n\nChanges in packages/core/src/ports/llm-port.ts:\n- Deleted 'instructions?: string' from GenerateTextOptions,\n  GenerateStructuredOptions, StreamTextOp\n[…]\n: 24\n\nZero regressions across the workspace.\n\nBlocker 1 + Blocker 2 + Blocker 3 all complete. Ship-ready subject to\nCommit F (migration guide + release notes + version bumps + publish\n+ BEPA Dev Log).",
          "is_bot": false,
          "headline": "feat(alpha.27): remove instructions/prompt from options + make messag…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-17T23:42:26Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "3d50f72d54a33b89c3490aad961a9edb416de062",
          "body": "…e migration\n\nRenames warnDeprecatedLegacyInput to warnDeprecated with a generalized\nDeprecationDetails signature. Preserves the useful primitive (WarningState +\ndedup + suppression + handler routing) for any future deprecation cycle\nwithout rebuilding it. Removes the field-specific glue that alpha.\n[…]\na.27 execution sequence. Next: Commit D (remove\nthe instructions?/prompt? fields from the four options interfaces +\nmake messages required). The rename is documented in the migration\nguide (Commit F).",
          "is_bot": false,
          "headline": "refactor(alpha.27): generalize deprecation infrastructure + test suit…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-17T23:21:22Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "ca0e5ba2abb4bbd665458788781dcb208ab07f12",
          "body": "Deletes populateLegacyFieldsFromMessages and simplifies the four\nRegistryPort methods (generateText, generateStructured, streamText,\nstreamStructured) to use { ...options, messages } directly, dropping\nthe legacy-field spread that alpha.26 introduced as a bridge for\nadapters that hadn't yet been upd\n[…]\n.\nThe Registry no longer touches the deprecated fields at all beyond\nthe normalizeMessagesOnOptions entry point (Commit C generalizes the\ndeprecation infra; Commit D removes the type fields entirely).",
          "is_bot": false,
          "headline": "refactor(alpha.27-prep): delete Registry dual-population code",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-17T23:12:23Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "89d2f98602295a4386687e5625d92bb740563b28",
          "body": "Migrates adapter-google to consume options.messages natively. Google's\nGemini API splits systemInstruction (top-level) from contents (the\nmessages array), matching Anthropic's shape. Reuses the\nNonContiguousSystemError class added in Commit A3.\n\nChanges in adapter-google/src/adapter.ts:\n- New helper\n[…]\nni)\n\nBlocker 1 complete. Next: Blocker 2 (Commit B) — delete Registry\ndual-population code (populateLegacyFieldsFromMessages + four spread\nsites). Safe now that all adapters consume messages natively.",
          "is_bot": false,
          "headline": "feat(alpha.27-prep): adapter-google native messages consumption",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-17T23:09:45Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "dafd979ef236624f36516a7d67b25f761b511a31",
          "body": "…sSystemError\n\nMigrates adapter-anthropic to consume options.messages natively AND\nintroduces the NonContiguousSystemError class in @llm-ports/core that\nAnthropic (and later Google) uses to reject mid-conversation system\nmessages at the adapter boundary.\n\nChanges in @llm-ports/core:\n- New NonContigu\n[…]\nlso\nlands here (rather than in a separate commit) because adapter-anthropic\nis the first user of the error class. Adapter-google (A4) reuses it.\n\nNext: A4 (adapter-google), then Commits B, C, D, E, F.",
          "is_bot": false,
          "headline": "feat(alpha.27-prep): adapter-anthropic native messages + NonContiguou…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-17T21:47:38Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "2fa32f0622cba17318b662e358b1f8368e833a41",
          "body": "Migrates adapter-vercel to consume options.messages natively. Vercel's\nunderlying SDK (@ai-sdk) accepts a top-level 'system' string plus a\nCoreMessage[] array; this migration extracts leading system messages\ninto the 'system' field (concatenated with \\n\\n) and passes the\nremainder as messages.\n\nChan\n[…]\nThe non-null-assertion options.messages! is intentional; becomes\nredundant in Commit D.\n\nNext: A3 (adapter-anthropic + NonContiguousSystemError class), A4\n(adapter-google), then Commits B, C, D, E, F.",
          "is_bot": false,
          "headline": "feat(alpha.27-prep): adapter-vercel native messages consumption",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-17T21:40:18Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "aeac34338257463933d385e0fae7aa108970701a",
          "body": "…red contract suite migration\n\nMigrates adapter-ollama to consume options.messages natively instead of\nreading options.prompt via non-null assertion (the alpha.26 shipping\nexpedient). Ollama's chat API accepts mid-conversation system messages\ninline, so the migration is the simplest of the four adap\n[…]\nevel; the ! becomes redundant but not incorrect.\n\nNext: A2 (adapter-vercel), A3 (adapter-anthropic + NonContiguousSystemError),\nA4 (adapter-google), then Blocker 2 (Registry dual-population deletion).",
          "is_bot": false,
          "headline": "feat(alpha.27-prep): adapter-ollama native messages consumption + sha…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-17T21:35:50Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "348c115b101bc745e1a74f2135afe9b09439f7d3",
          "body": "…al messages shape\n\nThe alpha.26 ship marked {instructions, prompt} deprecated on the port\ninterface but left @llm-ports/capabilities calling the port with the\ndeprecated shape internally. That worked at runtime (Registry dual-\npopulation synthesized messages from the legacy fields) but would have\nf\n[…]\nly the internal port call shape\nchanged.\n\nVersion: @llm-ports/capabilities@0.1.0-alpha.26.1 (hotfix; other\npackages stay on alpha.26; alpha.27 stays reserved for the coordinated\nlegacy-field removal).",
          "is_bot": false,
          "headline": "fix(alpha.26.1): migrate @llm-ports/capabilities factories to canonic…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-03T07:56:25Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "79cafd5e044b306cc89268ff39224131c119c18c",
          "body": "… + one-cycle deprecation\n\nBREAKING in alpha.27. This release adds the canonical shape alongside the\ndeprecated fields; alpha.27 removes the deprecated fields.\n\nThe four generation methods (generateText, generateStructured, streamText,\nstreamStructured) now accept `messages: LLMMessage[]` as the can\n[…]\n26 messages input tests; zero regressions).\n\nDocs: alpha-25-to-alpha-26 migration guide, top-level README banner\nupdated, VitePress sidebar entry.\n\nAll 7 publishable packages bumped to 0.1.0-alpha.26.",
          "is_bot": false,
          "headline": "feat(alpha.26): canonical messages input + toMessages/sys/usr helpers…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-02T23:16:45Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "a7498fa20f6751f9be940b2b265f5dbe8fe2a590",
          "body": "…st surfacing\n\nThree additive features under an \"Observability surface + reliability\nhardening\" theme. Zero breaking changes.\n\n**#53 refs field.** `refs?: Record<string, ArtifactRef>` on all five\ncall-options interfaces, threaded verbatim to all five observability\nevents (onCost, onTokenUsage, onFal\n[…]\nput around a\ncanonical messages: LLMMessage[] field, deprecating {instructions, prompt}\nwith a one-cycle window and a toMessages() migration shim.\n\nAll 7 publishable packages bumped to 0.1.0-alpha.25.",
          "is_bot": false,
          "headline": "feat(alpha.25): refs field + aggressive fallback preset + streamed co…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-07-02T22:42:11Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "3c33140f856f19c9036cb72fa2897f6df51220d3",
          "body": "…ree-tier architecture\n\nSame per-adapter README update pattern I missed in alpha.23's initial ship\nand had to follow up on. Catching it inline this time.\n\nAdds 'Capability detection — three-tier architecture (alpha.24+)' section\nabove the existing 'Known reasoning models' subsection. Cross-links to\nthe new docs/concepts/capability-detection.md concept page for the full\narchitectural design.\n\nIncludes the fingerprintCache option example + bundled backends overview.",
          "is_bot": false,
          "headline": "docs(alpha.24): adapter-openai README — surface fingerprintCache + th…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-25T02:06:57Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "8f6aa00997b0fdf9df064d2ef99a5f806a4cadea",
          "body": "…lper + Cerebras pricing\n\nThe catalog architectural redesign Babak called for across the alpha.22\n→ alpha.23 transition, plus the alpha.21-deferred onValidationRetry\nRegistry-level emission, plus Cerebras pricing entries from the 2026-06-24\nempirical reasoning-model survey.\n\n## Catalog architectural\n[…]\nache uses it)\n- parseHarmonyToolCalls (promoted from internal — alpha.23 was unexported)\n- type FingerprintCacheBackend, type ModelFingerprint\n\n@llm-ports/core:\n- deriveValidationRetryFromAdapterRetry",
          "is_bot": false,
          "headline": "feat(alpha.24): catalog architectural redesign + onValidationRetry he…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-25T01:56:32Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "f5d37faa6833935db0e759d6ac022eae6d6303d7",
          "body": "… telemetry tags + per-attempt timeout\n\nBeyond the migration page committed in 10fca25, four additional surfaces\nneeded alpha.23 updates that weren't in that commit:\n\npackages/adapter-openai/README.md\n  - \"Known limitation: DeepInfra gpt-oss harmony tool-use (alpha.22)\"\n    section gets an \"Update f\n[…]\nnator table mapping every reason to when-it-fires +\n    recovery-action\n  - Worked filter examples for harmony-tool-call-extracted and\n    zero-tool-call-prose-retry\n\nVerified `pnpm docs:build` clean.",
          "is_bot": false,
          "headline": "docs(alpha.23): update per-package + concept docs for ASK 1 + ASK 2 +…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-25T01:24:39Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "10fca258d780a94a115bc6d75ab8c69a31f47661",
          "body": "Adds docs/migration/alpha-22-to-alpha-23.md (additive-only migration note)\nand registers it in the VitePress sidebar. Covers:\n\n- Harmony tool-call extraction (automatic; closes DeepInfra gpt-oss gap)\n- Zero-tool-call corrective rescue (automatic; mimo prose case)\n- Telemetry tags via existing onRetr\n[…]\nptions.perAttemptTimeoutMs)\n- Explicit \"what's NOT fixed\" note on Case B under-production\n- Routing recommendation for orchestration-layer guards\n\nVerified with `pnpm docs:build` (clean, no warnings).",
          "is_bot": false,
          "headline": "docs(alpha.23): migration guide + sidebar entry",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-25T01:14:01Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "e44513ae6038ae2cbce6020f895aacbfa6769975",
          "body": "…+ per-attempt timeout\n\nFour additions, all empirically grounded in ADW's 2026-06-19 multi-team\nagentic-build-loop diagnostic + production wedge incident.\n\n## ASK 1 — Harmony tool-call extraction (adapter-openai)\n\nparseHarmonyToolCalls() extracts tool calls from harmony-formatted\nmessage.reasoning_c\n[…]\ns are additive. Existing callers see no API surface\nchanges. Two existing tests updated to accommodate ASK 2's rescue\nretry (test intent preserved; mockResolvedValue instead of\nmockResolvedValueOnce).",
          "is_bot": false,
          "headline": "feat(alpha.23): harmony tool-call extraction + zero-tool-call rescue …",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-25T01:10:27Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "2e4a03b4541137aa63d69f6927b2fcbc48aaa611",
          "body": "…ME + docs/adapters/openai.md\n\nBoth surfaces still showed the pre-alpha.22 framing — gpt-oss-* → Cerebras\nonly — and didn't surface what alpha.22 actually changed. Updated to\nreflect:\n\n- Three reasoning signals (added reasoning_content for DeepInfra harmony)\n- Starvation discriminator accepts finish\n[…]\nation is\nunambiguous, and includes ADW's 2026-06-19 empirical observation (Cerebras\ngpt-oss writes 5 files; DeepInfra gpt-oss writes 0 in the multi-turn\nbuild loop).\n\nVerified `pnpm docs:build` clean.",
          "is_bot": false,
          "headline": "docs(alpha.22): update reasoning-model framing in adapter-openai READ…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-19T16:14:50Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "89a384b33c293dde8bb6448d97ea5aff55040afc",
          "body": "Adds docs/migration/alpha-21-to-alpha-22.md (additive-only migration note)\nand registers it in the VitePress sidebar. Covers:\n\n- Model-ID normalization improvement (automatic; no caller change)\n- Runtime detection broadening for reasoning_content + finish=stop\n- Xiaomi MiMo catalog entry\n- adapter-g\n[…]\nple)\n- Explicit note on what's NOT fixed (DeepInfra gpt-oss harmony tool-use)\n- Routing recommendation: use Cerebras for gpt-oss tool-use\n\nVerified with `pnpm docs:build` (no dead links, no warnings).",
          "is_bot": false,
          "headline": "docs(alpha.22): migration guide + sidebar entry",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-19T16:00:37Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "41f305ec10b7beb44b4e8c76492ed4a4a44dfe5b",
          "body": "Pre-seed `MiMo-V\\d+` family as a reasoning model. Empirically driven by\nADW production incident 2026-06-19T15:40 UTC: mimo-parasail\n(XiaomiMiMo/MiMo-V2.5) starved on a structured-output decompose call.\n\nPre-this-commit, runtime detection caught the starvation (reasoning_field\nor reasoning_tokens pop\n[…]\nrefixed and canonical forms)\n- MiniMax-M2.7 still matches its own pattern (no regression)\n- Mimosa-V1 does NOT match either (negative guard)\n\n763 tests pass total (was 761 with 0a63479; +2 from MiMo).",
          "is_bot": false,
          "headline": "feat(adapter-openai): add Xiaomi MiMo to KNOWN_REASONING_MODELS catalog",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-19T15:54:52Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "0a634795310376c07e58f19577d07aab196c38d2",
          "body": "… httpOptions\n\nTwo themes shipped together, both empirically motivated by ADW + Dramma\nfindings on 2026-06-19.\n\n## adapter-openai: reasoning-model architecture (2 changes)\n\n### Model-ID normalization\n\nAdds normalizeModelId helper: strips a `<owner>/` namespace prefix and\nreturns the canonical name. \n[…]\n.\n\nEmpirical sources: ADW Development_Logs.md commit b1eeee2 (DeepInfra\ntool-loop root cause), Dramma 08-cloud-llm-backend-proxy-plan.md §7 Q1\n(httpOptions gap), 2026-06-19 raw 2-turn DeepInfra probe.",
          "is_bot": false,
          "headline": "feat(alpha.22): reasoning-model architecture cleanup + adapter-google…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-19T15:44:45Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "46285c70284fe0dd8b4278e9da6c2436fd2e1b35",
          "body": "…i adapter updates + alpha.20-to-21 migration\n\nCompanion to 094cc4d (feat(alpha.21)). The npm packages shipped without\nthe in-repo VitePress docs; this commit closes that gap.\n\nAdded:\n- docs/concepts/observability.md — full concept page for the 5 OTel-aligned\n  Registry-level hooks (onCost, onTokenU\n[…]\n — sidebar entries for the new Observability\n  concept page and the alpha.20→alpha.21 migration note.\n\nVerified: `pnpm docs:build` clean (no dead links, no warnings, all 5 new\n+ updated pages render).",
          "is_bot": false,
          "headline": "docs(alpha.21): observability hooks concept + per-call strict + opena…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-19T06:21:25Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "094cc4deb9d19cfbcbff61ff0bab605f550f002b",
          "body": "…ing + OTel observability hooks\n\nThree empirically-driven structured-output reliability changes plus the planned\nOTel-aligned observability hook surface.\n\n## 1. Per-call `strict?: boolean` (closes section 2 of #46)\n\n`GenerateStructuredOptions` and `StreamStructuredOptions` gain `strict?: boolean`.\nP\n[…]\n + adapter-google + adapter-ollama + adapter-vercel pass.\n\nFiled upstream: #46 (per-call strict + adapter-openai isJsonModeRejection rescue\nalready in main as 9cb9a82), #47 (allowlist), #48 (pricing).",
          "is_bot": false,
          "headline": "feat(alpha.21): per-call strict + DeepInfra/Parasail allowlist + pric…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-19T04:48:48Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "9cb9a82ae750afabe30a2719ec314acfc77542ea",
          "body": "…rejection (closes #46)\n\nExtends the response_format rescue trigger to also match OpenAI native's\nstrict-schema-validation rejection error pattern. The rescue downgrade\n(drop response_format, fall back to prompted JSON) is unchanged and\nalready in place; only the matcher pattern was too narrow — tun\n[…]\ntrict?: boolean` opt-out from issue #46 deferred to beta.1\nalongside the resilient-fallback preset (LP-REQ-01), where it naturally\nfits as a deliberate API addition with multi-adapter behavior matrix.",
          "is_bot": false,
          "headline": "fix(adapter-openai): isJsonModeRejection covers OpenAI strict-schema-…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-18T01:43:37Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "170f8e2e2fd059ce42c3d75170fd54969d65b901",
          "body": null,
          "is_bot": false,
          "headline": "fix(migrate): prefer-const on the replace() output",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-15T23:22:13Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "b40f49e0a1f91a7ab0a3295d9461186fe5904735",
          "body": "Implements seven mechanisms (A-G) to reduce the risk of accidental\nupgrades across breaking alphas in production code:\n\nA. docs/migration/alpha-19-to-alpha-20.md — per-release migration page\n   with the requestsPerHour type-level breakage as the lead item plus a\n   one-line fix and a codemod referen\n[…]\ngrate codemod).\n\nVersioning: 7 publishable + 1 new package (@llm-ports/migrate) all at\n0.1.0-alpha.20.1. consumer-type-check is private (no publish). Added\nboth to .changeset/pre.json initialVersions.",
          "is_bot": false,
          "headline": "feat(alpha.20.1): migration safeguards across docs, install, and tooling",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-15T23:19:36Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "66275f11a4feacb08959da428b569202b09b048b",
          "body": "The fourth alpha shape-lock before beta.0. Additive only — no breaking\nchanges vs alpha.19.1. Backwards compatible: existing callers and env\nconfigs see identical behavior.\n\nNew types in @llm-ports/core:\n- BudgetScope = \"tenant\" | \"customer\" | \"user\" | \"agent\" | \"session\"\n- BudgetScopeRef = { scope:\n[…]\nns enforced via CostSession\n\nTest stats: 678 across 7 packages (was 654 in alpha.19.1; +24 new).\n\nVersioning: manual bump to 0.1.0-alpha.20 to preserve the planned\nalpha sequence (.20 → .21 → beta.0).",
          "is_bot": false,
          "headline": "feat(alpha.20): BudgetScope + minute/session gating grammar",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-13T20:36:37Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "2f13c318f06c622d11b00fb680ce75c0c1096b39",
          "body": "Closes the gaps Babak flagged after alpha.19.1 published:\n\n- docs/guides/cost-gating.md, docs/migration/from-direct-sdk.md: rename\n  stale cost.cacheDiscountUSD references to cost.cacheSavingsUSD (the\n  alpha.18 → alpha.19 field rename had not propagated to these pages).\n- docs/migration/alpha-18-to\n[…]\nrom navigation); Migration\n  sidebar now links the alpha.18 → alpha.19 BREAKING-tagged entry.\n\nVitePress build verified clean (6.62s). Docs-only commit: no version\nbump, no republish, no test changes.",
          "is_bot": false,
          "headline": "docs: alpha.19.1 follow-up cleanup across the docs site",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-13T02:42:58Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "0b3cb4792f1a3043e015aff24337ecabee059aa4",
          "body": "…ility factories\n\nThe shape committed in alpha.19 is now backed by verified per-mode behavior\non the cloud adapters and pass-through on every capability factory. Closes\nthe gap between alpha.19's locked surface and the docs that prematurely\ndescribed per-mode adapter behaviors in present tense.\n\nada\n[…]\netScope) →\nalpha.21 (observability hooks) → beta.0 sequence. changeset pre-mode\nwould have rolled to alpha.20 by default; this fixes a real gap in\nalpha.19 rather than expanding into alpha.20's scope.",
          "is_bot": false,
          "headline": "feat(alpha.19.1): CacheControl behavior across cloud adapters + capab…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-12T22:55:59Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "3aadfff56c88970f698d7272300dde2bb8005cbc",
          "body": "Used as the cover image for the alpha.19 dev.to ship article and as\nthe image attachment for the X (Twitter) thread on the alpha.19\nrelease. Lives at assets/ so its raw GitHub URL is stable:\n  https://raw.githubusercontent.com/baabakk/llm-ports/main/assets/llm-ports.png",
          "is_bot": false,
          "headline": "chore(assets): add llm-ports.png for social cards + dev.to cover",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-12T20:01:41Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "02556479853fb4d09821fe4422f32edb0e9fa275",
          "body": "7 publishable packages bumped to 0.1.0-alpha.19:\n- @llm-ports/core (minor; new CacheControl public type + cacheSavingsUSD rename)\n- @llm-ports/adapter-openai, -anthropic, -google, -ollama, -vercel (patch)\n- @llm-ports/capabilities (patch)\n\n10 example workspace projects bumped along for the ride.\n\nGenerated by `pnpm changeset version` from .changeset/alpha-19-*.md.",
          "is_bot": false,
          "headline": "release(alpha.19): version + CHANGELOG bumps",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-12T19:19:15Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "c0ef1d72d96fcef7cc7f1a91484755f6461f651f",
          "body": "…AKING)\n\nLocks the CacheControl shape so beta.0 ships the right abstraction over\nthe three caching patterns the major providers expose (Anthropic explicit\ncache_control markers, OpenAI implicit always-on cache, Google Gemini\ncreateCachedContent handle). Renames cost.cacheDiscountUSD to\ncost.cacheSav\n[…]\n- New: docs/concepts/cache.md (locked shape + per-provider behavior table).\n- New: docs/migration/alpha-18-to-alpha-19.md (step-by-step migration).\n- Updated: docs/v0-1-status.md (alpha.19 row added).",
          "is_bot": false,
          "headline": "feat(alpha.19): CacheControl shape lock + cacheSavingsUSD rename (BRE…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-12T19:17:58Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "0c124c392172dc99b8cee3e56418586a68dddb42",
          "body": "Auto-generated by changeset version. 7 published packages bumped to\n0.1.0-alpha.18; example workspaces + adapter-contract-tests + benchmarks\nbumped via @llm-ports/* linked-group.",
          "is_bot": false,
          "headline": "release(alpha.18): version + CHANGELOG bumps",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-05T09:13:28Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "79e0dd9eeed2dda0df0d0bdf349a9b07cf1f8b0a",
          "body": "Largest single correctness fix in the v0.1 line. Closes the architectural\nbug where a 400 context-window overflow got wrapped as\nProviderUnavailableError, causing the registry to fall back to another\nprovider that would fail the same way.\n\nNEW classes in @llm-ports/core/src/errors.ts:\n- LLMPortError\n[…]\nkspace (up from 577 in alpha.17). 29\nnew error-taxonomy tests + 5 ollama onRetry + 4 google onRetry. Several\nalpha.17-era adapter-openai tests updated to assert the new typed\nclasses (4 quirks files).",
          "is_bot": false,
          "headline": "feat(alpha.18): typed-error taxonomy + alpha.17 closeout (BREAKING)",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-05T09:13:17Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "210920c393c2b5592cd98194805c312bede91b38",
          "body": "…missing disables)\n\nPre-existing lint errors that the CI surfaced when alpha.17 pushed. All\n4 are mechanical eslint-disable fixes; no behavior change.\n\n- adapter-anthropic/src/adapter.ts:67: typescript-eslint renamed\n  no-require-imports -> no-var-requires; add both disable names so the\n  comment su\n[…]\n the\n  intentional 'const session = this' alias used inside the getPort()\n  closure (no-this-alias).\n\n577 tests still passing; lint now clean (3 pre-existing unused-var\nwarnings remain; not blocking).",
          "is_bot": false,
          "headline": "fix(lint): unblock CI on alpha.17 push (4 errors from rule renames + …",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-05T08:01:50Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "ecd13f4692699d1cd2f909d7a7a33d6ac50ecdb0",
          "body": "Auto-generated by changeset version. 7 published packages bumped to\n0.1.0-alpha.17; example workspaces and adapter-contract-tests +\nbenchmarks bumped in lockstep via the @llm-ports/* linked-group.",
          "is_bot": false,
          "headline": "release(alpha.17): version + CHANGELOG bumps",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-05T07:17:56Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "4087d6f309f36ffdb28c65cc202379ac296e6a3a",
          "body": "First alpha of the v0.1 line approved by Babak per the BEPA-internal\nRELEASE-PLAN-0.1.0-roadmap-to-1.0.md.\n\nFive additive items + RerankPort skeleton (no breaking changes):\n\n- @llm-ports/core: new RerankPort interface in src/ports/rerank-port.ts.\n  Sibling of LLMPort and EmbeddingsPort. Modeling rer\n[…]\nest.ts\nat lines 163 and 192. No code change; the master plan item is closed by\nverifying the existing tests pin the property.\n\nWorkspace tests: 577 passing (up from 567 in alpha.16). Zero regressions.",
          "is_bot": false,
          "headline": "feat(alpha.17): RerankPort skeleton + jittered backoff + onRetry parity",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-06-05T07:17:45Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "1c5f8b22435f00bb6749a3159b7c32825adfbe90",
          "body": "Auto-generated by changeset version. 7 published packages bumped to\n0.1.0-alpha.16; example workspaces and internal-only packages\n(adapter-contract-tests, benchmarks) bumped in lockstep via the\n@llm-ports/* linked-group config.",
          "is_bot": false,
          "headline": "release(alpha.16): version + changelog bumps for providerExtras",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-30T20:37:16Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "df2b83802dfc81d7e4510724034b9dff55cfb75f",
          "body": "Add providerExtras?: Record<string, unknown> to all 5 *Options interfaces.\nPer-call escape hatch for provider-specific request fields the port does\nnot model. Shallow-merged into the SDK request body AFTER typed port\nfields, so callers can override typed defaults.\n\nThreaded through:\n- All 5 LLMPort \n[…]\n { vllm: {...} }) so the public type signature does\nnot endorse any one OSS-serving runtime.\n\n15 new tests (6 adapter-openai quirks + 9 capability passthrough);\n567 tests passing across the workspace.",
          "is_bot": false,
          "headline": "feat(alpha.16): providerExtras escape hatch for vLLM + SGLang",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-30T20:37:06Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "2d17a4c3965b793b9fae52ea0bd0c2f7b85948da",
          "body": null,
          "is_bot": false,
          "headline": "chore(release): bump @llm-ports/adapter-openai to 0.1.0-alpha.15",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-27T08:14:30Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "e1cd8c5ad34899aeeb50d8e0ca86c3f767dfc9f8",
          "body": "…ambaNova\n\nEmpirically verified 2026-05-27 — BEPA A/B harness forced\nuseStrictResponseFormat: true on a SambaNova adapter and MiniMax-M2.7\nwent from 0/10 → 10/10 schema-valid on a nested production scoring\nschema. 3987ms avg, $0.041/10-calls. SambaNova accepts strict\nresponse_format: json_schema and\n[…]\nether AI as the new unknown-compat exemplar. 144\nadapter-openai tests passing.\n\nSub-task 2 (Anthropic structured-output discipline via tool-use-with-\ninput_schema) is structural library work for v0.2.",
          "is_bot": false,
          "headline": "feat(adapter-openai): expand useStrictResponseFormat auto-detect to S…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-27T08:13:56Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "fa3d28b3ff2510ff25fa1818ad010a72e414c9a5",
          "body": null,
          "is_bot": false,
          "headline": "chore(release): bump @llm-ports/adapter-openai to 0.1.0-alpha.14",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-27T04:14:30Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "da17ec87e4fd08e47bc5d9335d631debde639cb0",
          "body": "…penAI native + Groq\n\nBehavior change: generateStructured against OpenAI native (no baseURL)\nor Groq (api.groq.com) now uses strict response_format: json_schema by\ndefault. Cerebras was the only auto-detect target in alpha.9; everyone\nelse silently paid the un-strict retry-with-feedback tax.\n\nEviden\n[…]\n\nExports autoDetectStrictResponseFormat helper.\n\n15 new tests; 143 adapter-openai / 552 workspace passing.\n\nDiscovered by BEPA Upwork-scoring A/B harness (Development_Logs.md\n2026-05-26T20:45 -07:00).",
          "is_bot": false,
          "headline": "feat(adapter-openai): expand useStrictResponseFormat auto-detect to O…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-27T04:13:19Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "14fcb6cf462ffe7556e42e4cc055ad0e56f4ed79",
          "body": "…y passthrough + repair extensions\n\n- README.md: bump pointer to alpha.13; closed-issues paragraph expanded\n  to cover alpha.10/11/12/13 (Claude 4.5+ catalog, generateStructured\n  usage accumulation, reasoningEffort passthrough, capability factory\n  port-surface alignment).\n- docs/v0-1-status.md: st\n[…]\nncy trade-off table, when NOT\n  to use it.\n- docs/.vitepress/config.ts: wire new reasoning-effort guide into the\n  Guides sidebar.\n\nLocal pnpm docs:build clean. deploy-docs workflow will fire on push.",
          "is_bot": false,
          "headline": "docs(site): alpha.12 + alpha.13 surface — reasoningEffort + capabilit…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-27T03:24:33Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "8002fa4230459f1bc7164bf3be5a24bd876d9d9d",
          "body": null,
          "is_bot": false,
          "headline": "chore(release): bump packages to 0.1.0-alpha.13",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-27T03:11:43Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "7c27b2d1624b6128aa30c7e370e1edf28700feff",
          "body": "…viderAlias + extend repair\n\nAll 7 capability factories now thread the missing port options through to\nthe underlying call:\n- reasoningEffort: per-factory, on Create*Config\n- signal: per-call, on *Input\n- forceProviderAlias: per-call, on *Input\n\nCloses BEPA TD-LLMPORTS-CAPABILITIES-REASONING-EFFORT \n[…]\ny into the expected shape.\n- Pattern 8 (new): single-element array unwrap when object expected.\n\n29 repair tests (was 18) + 13 capability passthrough tests. 537 tests\npassing workspace-wide (was 508).",
          "is_bot": false,
          "headline": "feat(capabilities,core): pass-through reasoningEffort/signal/forcePro…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-27T03:10:29Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "0b38d0f75e5c598120217a981d6d5e083b27938f",
          "body": null,
          "is_bot": false,
          "headline": "chore(release): bump packages to 0.1.0-alpha.12",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-27T02:02:54Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "1d7842604ae41278130c87645ee5f2ee754b325b",
          "body": "Adds reasoningEffort?: \"low\" | \"medium\" | \"high\" to all 5 LLMPort *Options\ninterfaces. adapter-openai forwards it as reasoning_effort on the SDK call.\n\nCloses BEPA-side TD-LLMPORTS-REASONING-EFFORT: Groq's openai/gpt-oss-120b\ncontrols reasoning depth via this parameter (no separate model IDs per\neff\n[…]\n a non-reasoning model rejects the\nfield) is v0.2 scope.\n\n5 new tests covering all 4 call shapes (generateText / generateStructured /\nrunAgent / triple-effort-level). 508 tests passing workspace-wide.",
          "is_bot": false,
          "headline": "feat(core,adapter-openai): add reasoningEffort to *Options",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-27T02:01:53Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "4f9d75b7a7205d1f791b0cc780c1e476edb1a716",
          "body": null,
          "is_bot": false,
          "headline": "chore(release): bump 5 adapter packages to 0.1.0-alpha.11",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-26T11:25:48Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "c4e18250b5a0f4f8d554de5afda8f790341918f4",
          "body": "…h-feedback\n\nBug: lastUsage = parseUsage(response) OVERWROTE the usage tracker on each\nretry-with-feedback iteration. validationAttempts correctly reported 2,\nbut result.usage / result.cost only reflected the 2nd SDK call. Cost\naccounting under-reported by exactly the first attempt's cost.\n\nFix: las\n[…]\neen correct.\n\nReported by user 2026-05-26: claude-haiku-4-5 retry was returning\nvalidationAttempts: 2 but ~832 total tokens (single-call-shaped) — the\nmetric was right, the usage field wasn't summing.",
          "is_bot": false,
          "headline": "fix(adapter-*): generateStructured accumulates usage across retry-wit…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-26T11:24:33Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "f176b5f391d58e8bdc578360cdd574a1429584bd",
          "body": null,
          "is_bot": false,
          "headline": "chore(ci): re-trigger docs deploy after GitHub dispatch 500",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-26T11:07:09Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "0cd5666b69f6a21158107f5524c6a4745895b567",
          "body": "… strict-JSON, listModels, opus-4-7\n\n- README.md: bump version pointer to alpha.9 (all 7 packages); add #9 / #32\n  to closed-issues list; trim \"still open\" entries for what just shipped.\n- docs/v0-1-status.md: add listModels + checkPricingFreshness + strict-JSON +\n  browser-flag rows to \"stable\" tab\n[…]\n why we don't auto-update bundled tables.\n- docs/.vitepress/config.ts: wire the new model-discovery guide into the\n  Guides sidebar.\n\nBuild verified locally; deploy-docs workflow will trigger on push.",
          "is_bot": false,
          "headline": "docs(site): alpha.9 + alpha.10 surface — Gemini parity, browser flag,…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-26T11:00:31Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "eadc2bc7bc0638ecba26b8a32decb55a5b8e26ea",
          "body": null,
          "is_bot": false,
          "headline": "chore(release): bump @llm-ports/adapter-anthropic to 0.1.0-alpha.10",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-26T10:53:22Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "a239d8c224772e000058681ef2b83c17ed4e33fc",
          "body": "…d family\n\nSymptom: streamText against claude-opus-4-7 hard-failed with 400\n\"temperature is deprecated for this model.\" because the static catalog\nonly covered 4-5. Non-streaming methods auto-recovered via the in-adapter\ncapability-fallback retry, but streaming methods can't mid-stream retry.\n\nFix:\n\n[…]\nionAttempts to lock in the\n1-on-first-success / 2-on-retry semantics (filed after a user observation\nthat conflated the field with the strict-mode-fixes-Cerebras issue;\nverified the field is correct).",
          "is_bot": false,
          "headline": "fix(adapter-anthropic): seed temperatureLocked for claude-opus-4-7 an…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-26T10:52:08Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "aede17c0a50ca3df2a5d6f0000759be38571906a",
          "body": "- @llm-ports/core: minor (listModels, ProviderModelInfo, Registry.checkPricingFreshness)\n- @llm-ports/capabilities: patch (re-exports)\n- @llm-ports/adapter-openai: minor (useStrictResponseFormat for Cerebras), patch (dangerouslyAllowBrowser, listModels)\n- @llm-ports/adapter-anthropic: patch (dangero\n[…]\n- @llm-ports/adapter-google: minor (multi-turn runAgent, native responseSchema, listModels)\n- @llm-ports/adapter-ollama: minor (listModels)\n- @llm-ports/adapter-vercel: patch (README browser-flag doc)",
          "is_bot": false,
          "headline": "chore(release): bump 7 packages to 0.1.0-alpha.9",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-26T10:29:24Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "d3e52789cb2edd98a5ddf7e8de3a424e354261ba",
          "body": null,
          "is_bot": false,
          "headline": "Merge alpha.9 bundle",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-26T10:26:50Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "286f1325af5c2fd88d9aaee345d6cccda8a17aca",
          "body": "…trict JSON\n\nCloses #9 (listModels half), #32 (dangerouslyAllowBrowser).\n\nadapter-google:\n- runAgent now multi-turn via Gemini function-calling loop. Translates\n  tools to Gemini's Tool[] shape (zod-to-json-schema, OpenAPI 3.0\n  subset), loops chat/function-call/function-response until model\n  retur\n[…]\normat = 8\n- adapter-anthropic: 2 browser-flag\n- adapter-google: 7 multi-turn runAgent + 6 native responseSchema = 13\n- core: 4 checkPricingFreshness\n\n486 tests total across the workspace; all passing.",
          "is_bot": false,
          "headline": "feat(alpha-9): Gemini parity + listModels + browser flag + Cerebras s…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-26T10:26:36Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "b54230d6726cb178989b4730ab7a037f8791c0de",
          "body": null,
          "is_bot": false,
          "headline": "docs(README): bump pointer to alpha.8 (5 adapter packages)",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-26T06:46:24Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "32b1397065fb9c382b8191db502d2d7b12889e96",
          "body": "…bilities unchanged)",
          "is_bot": false,
          "headline": "chore(release): bump 5 adapter packages to 0.1.0-alpha.8 (core + capa…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-26T06:44:34Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "6b6f139a9d795f757673ae0c3c27c680d7fbb2b3",
          "body": "Closes #7 (per-adapter README harmonization), #8 (.env.example per example),\nplus three v0.1-status gaps that didn't have GH issues (Vercel multi-turn\nrunAgent, full multimodal, bundled pricing).\n\nVercel adapter (the big one):\n- runAgent: replaces single-turn shim with Vercel native tools + maxSteps\n[…]\n env\n  vars that example actually references.\n\n459 tests passing across 7 packages (no change — alpha.8's work is\nintegration-test surface + docs, not unit-test material).\n\nBranch: feat/alpha-8-bundle",
          "is_bot": false,
          "headline": "feat(alpha-8): Vercel parity + compat-provider live tests + doc polish",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-26T06:43:21Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "fb7ffd8b7b59f6b0ffc48157a15da24b95831d9e",
          "body": "… flip",
          "is_bot": false,
          "headline": "docs(README): bump pointer to 0.1.0-alpha.7 + runtime-fallback status…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-23T22:49:40Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "aefda09b5999ec647062312a09543d3f0a53de94",
          "body": null,
          "is_bot": false,
          "headline": "chore(release): bump packages to 0.1.0-alpha.7",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-23T22:47:07Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "c8051691e98216a9c38d069e17fc068f166330d4",
          "body": "…de 20 prep\n\nCloses #9 (registry runtime fallback), #15 (forceProviderAlias), #26 (Node 20 deprecation prep).\n\nRegistry runtime fallback:\n- New RegistryOptions.runtimeFallback: \"default\" | \"none\" | { shouldFallback }\n- Default walks on ProviderUnavailableError; \"none\" preserves v0.1 behavior\n- selec\n[…]\nk + 5 forceProviderAlias).\nThe registry-edges TD-LLMP-09 test (documented OLD behavior) was inverted to\nassert the new alpha.7 behavior.\n\n459 tests passing across 7 packages.\nPublic API additive only.",
          "is_bot": false,
          "headline": "feat(alpha-7): registry runtime fallback + forceProviderAlias + CI No…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-23T22:45:50Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "d49a85233b1c857096af6f47dd01fd0bce65fe7a",
          "body": "…debar wiring, v0-1-status refresh\n\nNew pages:\n- docs/adapters/google.md — Gemini adapter (shipped alpha.5, no doc page until now). Covers\n  install, configure, pricing, feature matrix, why-this-vs-OpenAI-compat-baseURL, and\n  alpha.6 cancellation behavior.\n- docs/guides/cancellation.md — AbortSigna\n[…]\nalled out; Gemini\n  v0.2 scope items listed.\n- v0.3+ section: adapter-google moved out (now stable); browser-native local-model\n  adapter (#13) called out as the highest-impact remaining roadmap item.",
          "is_bot": false,
          "headline": "docs: alpha.5 + alpha.6 — Gemini adapter page, cancellation guide, si…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-23T11:29:23Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "3e44c4161ed263ef7ecd0586eb275d9aeb7cc5d7",
          "body": null,
          "is_bot": false,
          "headline": "docs(README): bump pointer to 0.1.0-alpha.6 (AbortSignal regression fix)",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-23T11:15:01Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "881c8f2147bd7d52414a8ac443df02c58ff9ada1",
          "body": null,
          "is_bot": false,
          "headline": "chore(release): bump packages to 0.1.0-alpha.6",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-23T11:13:09Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "34cd6cd19d7391ef50fbb42db0cfc34ad6b3b8af",
          "body": "…ch adapter's fetch\n\nCloses #24. Restores mid-flight cancellation that was missing in alpha.5.\n\nCore changes:\n- GenerateTextOptions, GenerateStructuredOptions, StreamTextOptions,\n  StreamStructuredOptions, RunAgentOptions all gain `signal?: AbortSignal`\n- New @llm-ports/core export `throwIfAborted(s\n[…]\n verified (everyone else)\n\n21 new tests (6 unit in core/abort.test.ts + 3 contract tests x 5 adapters).\nPublic API additive only. 446 tests passing across 7 packages.\n\nBranch: fix/abort-signal-options",
          "is_bot": false,
          "headline": "fix(alpha-6): thread signal?: AbortSignal through all 5 *Options + ea…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-23T11:11:43Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "278fa48901a4d567dd4f4a8011533a2f5383d4fd",
          "body": "…dapter + validation hardening + session cost gate",
          "is_bot": false,
          "headline": "docs(README): alpha.5 — 7 packages, 11 closed issues, native Gemini a…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-21T04:28:10Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "b3abe594e07e42e7b2e0ab486e8a20d8297cdbbc",
          "body": "Consumes 4 changesets:\n- validation-hardening (minor core + 4 adapter patches)\n- image-boundary-validation (minor across core + 4 adapters)\n- session-cost-gate (minor core)\n- adapter-google (minor — new package)\n\nAll packages now 0.1.0-alpha.5. 425 tests passing across 7 packages.",
          "is_bot": false,
          "headline": "chore(release): bump packages to 0.1.0-alpha.5",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-21T04:24:47Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "b00ff6589d5d8ed9bd9aae6859f727d85f87ff77",
          "body": "… cost gate + Gemini adapter\n\nFive-piece bundle for alpha.5:\n\n1. Validation hardening (core + 4 adapters)\n   - extractJSON falls back to jsonrepair when JSON.parse fails, gated on\n     \"input contains { or [\". Catches trailing commas, single quotes,\n     smart quotes, unquoted keys, Python literals,\n[…]\nupport for the\n     new adapter (Gemini: base64+url)\n\nTotal: 425 tests across 7 packages (was 345 across 6 in alpha.4, +80).\nAll typecheck clean. Public API additive only.\n\nBranch: feat/alpha-5-bundle",
          "is_bot": false,
          "headline": "feat(alpha-5): validation hardening + image boundary checks + session…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-21T04:23:18Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "9fa34d1bae8f1d66a2a9e57a04e9b7b2c97c8d8b",
          "body": "…tail\n\n- Version pointer 0.1.0-alpha.3 -> 0.1.0-alpha.4\n- Adds alpha.4 highlight: ImageSource.detail field for OpenAI vision\n  cost control + image conformance test in the contract suite\n\nNo behavior change.",
          "is_bot": false,
          "headline": "docs(README): bump pointer to 0.1.0-alpha.4 + announce ImageSource.de…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-21T02:53:29Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "d4d1273fec4ca36c74217f3fce272bc75edbe9ad",
          "body": "Consumes 2 pending changesets from image-pipeline hardening:\n- image-detail-field (minor: core + adapter-openai) — new\n  ImageSource.detail field for OpenAI vision cost control\n- image-contract-test (patch: anthropic, openai, ollama, vercel) —\n  new imageContentSupport declaration in contract tests\n\nAll packages bumped to 0.1.0-alpha.4. Public API additive only.\n345 tests passing.",
          "is_bot": false,
          "headline": "chore(release): bump packages to 0.1.0-alpha.4",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-21T02:50:47Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "004620ad6663c6fc9249fc934bc6e795b8083a19",
          "body": "Registry converts LLM_PROVIDER_VISION_ANTHROPIC env var to alias\n\"vision-anthropic\" (lowercase + underscores-to-hyphens). The script was\nreferencing the alias with underscores in task-route values and\ngenerateText taskType. Now matches the framework convention.\n\nVerified against real OpenAI gpt-4o-mini (base64 PNG with detail=\"low\"\n+ URL PNG with detail=\"auto\"). Both paths reached the model and got a\nresponse. Anthropic path hit a 400 credit-balance error (out of band;\nnot a wire-format issue).",
          "is_bot": false,
          "headline": "fix(live-vision): use kebab-case for provider + task aliases",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-21T02:49:33Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "f0885e64d40f2e6bb5d3183a14831cd2186c9673",
          "body": "…contract tests + live test\n\nThree related changes closing audit gaps surfaced by the image-pipeline\nreview:\n\n1. ImageSource gains optional `detail?: \"auto\" | \"low\" | \"high\"`.\n   Forwarded to OpenAI's image_url.detail. Lets vision-heavy workloads\n   choose between ~85 tokens/image (detail=\"low\" for \n[…]\ner-contract-tests: minor (new test surface)\n- @llm-ports/adapter-anthropic, -ollama, -vercel: patch (imageContentSupport flag)\n\n345 tests passing (+11 over alpha.3 baseline). Public API additive only.",
          "is_bot": false,
          "headline": "feat(core,adapter-openai): image-pipeline hardening — detail field + …",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-21T01:57:52Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "2bda447d32bb4ce1e3213152c564f32f290f763f",
          "body": "…lpha.3\n\n- \"Five medium-impact\" -> \"Six\": #12 closed, alpha.3 shipped\n- Note hoisted core utilities + KNOWN_REASONING_MODELS catalog\n- Drop the per-package \"alpha.2 vs alpha.1\" version chase; all packages\n  now at 0.1.0-alpha.3\n\nNo behavior change.",
          "is_bot": false,
          "headline": "docs(README): update alpha-bake summary + version pointer for 0.1.0-a…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-21T01:17:10Z",
          "body_truncated": false,
          "is_coding_agent": false
        },
        {
          "oid": "f1699105d7b1237045e3c34b4666ab525d2397e2",
          "body": "Consumes 6 pending changesets:\n- core-shared-utilities (minor) — 5 shared adapter utilities + retry-emit\n  + capability-learning + notify-learning hoisted to @llm-ports/core\n- adapter-anthropic-temperature-fix (minor) — closes #12; strips\n  temperature on Claude 4.5+ reasoning models with runtime le\n[…]\ntils (patch) — consume core utilities\n\nAll packages bumped to 0.1.0-alpha.3. Public API unchanged for the patch\nbumps; core + adapter-anthropic gain new exported surface (additive).\n334 tests passing.",
          "is_bot": false,
          "headline": "chore(release): bump packages to 0.1.0-alpha.3",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-21T00:38:41Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "61b27a02007505b57301101423657c7763ff5103",
          "body": "The KNOWN_REASONING_MODELS catalog adds two new compat providers worth\nnaming on the top-level visibility surfaces. Adoption funnel was:\n\n- Top-level README.md: previously listed \"Cerebras via OpenAI baseURL,\n  Groq, Together AI, Fireworks\" as providers needing pricingOverrides.\n  Now also names Cla\n[…]\ned)\" section listing the catalog patterns with provider\n  examples; bundled-pricing-coverage note clarifies that compat-provider\n  models require pricingOverrides.\n\nNo behavior change; no test impact.",
          "is_bot": false,
          "headline": "docs: surface Clarifai + SambaNova on home page + npm READMEs",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-21T00:14:02Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "371e1c8830888b1877f9043bc66a0c6800a2f71d",
          "body": "…iniMax-M2.7\n\nReplace placeholder $0/$0 pricing in worked-example configs with the live\npublic numbers:\n\n- Clarifai (FP8) — Qwen3.6 35B A3B FP8: $0.76 in / $0.43 out per 1M;\n  blended ~$0.72/1M; 262k context. Output cheaper than input is unusual;\n  it's an FP8 quantization economics quirk, not a doc\n[…]\n/quirks/known-reasoning-models.test.ts:\n  test pricingOverrides now use the real numbers (still mocks the SDK,\n  so no live cost incurred).\n- .changeset: pricing breakdown added to the changeset body.",
          "is_bot": false,
          "headline": "docs(adapter-openai): real pricing for Clarifai Qwen3.6 + SambaNova M…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-20T23:30:36Z",
          "body_truncated": true,
          "is_coding_agent": false
        },
        {
          "oid": "e5d058fc5495e9d72b8f919b695ab115011a237f",
          "body": "…6 + SambaNova MiniMax-M2.7)\n\nPre-seeds the capability learner at port creation so first calls against\nknown reasoning models skip the starvation-retry round-trip.\n\nCatalog covers:\n- OpenAI o-series (o1*, o3*, o4*)\n- OpenAI gpt-5-nano*\n- Cerebras gpt-oss-* (via baseURL=https://api.cerebras.ai/v1)\n- \n[…]\nModels with reasoning\" entry listing\n  catalog patterns + first-seen release.\n\nExports added: KNOWN_REASONING_MODELS from @llm-ports/adapter-openai.\nPublic API otherwise unchanged. All 334 tests pass.",
          "is_bot": false,
          "headline": "feat(adapter-openai): KNOWN_REASONING_MODELS catalog (Clarifai Qwen3.…",
          "author_name": "baabakk",
          "author_login": "baabakk",
          "committed_at": "2026-05-20T23:28:10Z",
          "body_truncated": true,
          "is_coding_agent": false
        }
      ],
      "releases_count": 82,
      "commits_last_year": 165,
      "latest_release_at": "2026-07-17T23:55:25Z",
      "latest_release_tag": "@llm-ports/core@0.1.0-alpha.27",
      "releases_from_tags": false,
      "days_since_last_push": 9,
      "active_weeks_last_year": 12,
      "days_since_latest_release": 13,
      "mean_days_between_releases": 3.8
    },
    "community": {
      "has_readme": true,
      "has_license": true,
      "has_description": true,
      "has_contributing": true,
      "health_percentage": 100,
      "has_issue_template": false,
      "has_code_of_conduct": true,
      "has_pull_request_template": true
    },
    "ecosystem": {
      "packages": [
        {
          "name": "@llm-ports/core",
          "exists": true,
          "license": "MIT",
          "keywords": [
            "llm",
            "ai",
            "typescript",
            "openai",
            "anthropic",
            "ollama",
            "ai-sdk",
            "generative-ai",
            "llm-routing",
            "llm-fallback",
            "llm-abstraction",
            "multi-provider",
            "multi-provider-llm",
            "ports-and-adapters",
            "hexagonal-architecture",
            "cost-control",
            "cost-gating",
            "vendor-lock-in",
            "provider-router",
            "ai-architecture",
            "production-llm"
          ],
          "ecosystem": "npm",
          "matches_repo": true,
          "registry_url": "https://www.npmjs.com/package/@llm-ports/core",
          "is_deprecated": false,
          "latest_version": "0.1.0-alpha.28",
          "repository_url": "https://github.com/baabakk/llm-ports",
          "versions_count": 24,
          "total_downloads": null,
          "dependents_count": null,
          "deprecation_note": null,
          "maintainers_count": 1,
          "monthly_downloads": 1825,
          "first_published_at": "2026-05-12T02:22:27.130000Z",
          "latest_published_at": "2026-07-22T12:51:43.497000Z",
          "latest_version_yanked": null,
          "days_since_latest_publish": 9
        },
        {
          "name": "@llm-ports/migrate",
          "exists": true,
          "license": "MIT",
          "keywords": [
            "llm-ports",
            "migrate",
            "codemod",
            "alpha"
          ],
          "ecosystem": "npm",
          "matches_repo": true,
          "registry_url": "https://www.npmjs.com/package/@llm-ports/migrate",
          "is_deprecated": false,
          "latest_version": "0.1.0-alpha.20.1",
          "repository_url": "https://github.com/baabakk/llm-ports",
          "versions_count": 1,
          "total_downloads": null,
          "dependents_count": null,
          "deprecation_note": null,
          "maintainers_count": 1,
          "monthly_downloads": 38,
          "first_published_at": "2026-06-15T23:25:02.835000Z",
          "latest_published_at": "2026-06-15T23:25:03.126000Z",
          "latest_version_yanked": null,
          "days_since_latest_publish": 45
        },
        {
          "name": "@llm-ports/capabilities",
          "exists": true,
          "license": "MIT",
          "keywords": [
            "llm",
            "ai",
            "typescript",
            "generative-ai",
            "llm-ports",
            "llm-capabilities",
            "capabilities",
            "classify",
            "score",
            "draft",
            "summarize",
            "extract",
            "plan",
            "analyze",
            "structured-output",
            "zod",
            "json-mode",
            "factory-pattern",
            "reusable-prompts",
            "production-llm"
          ],
          "ecosystem": "npm",
          "matches_repo": true,
          "registry_url": "https://www.npmjs.com/package/@llm-ports/capabilities",
          "is_deprecated": false,
          "latest_version": "0.1.0-alpha.28",
          "repository_url": "https://github.com/baabakk/llm-ports",
          "versions_count": 25,
          "total_downloads": null,
          "dependents_count": null,
          "deprecation_note": null,
          "maintainers_count": 1,
          "monthly_downloads": 1387,
          "first_published_at": "2026-05-12T02:22:26.644000Z",
          "latest_published_at": "2026-07-22T12:51:43.185000Z",
          "latest_version_yanked": null,
          "days_since_latest_publish": 9
        },
        {
          "name": "@llm-ports/adapter-aider",
          "exists": true,
          "license": "MIT",
          "keywords": [
            "llm-ports",
            "aider",
            "adapter",
            "subprocess",
            "agent"
          ],
          "ecosystem": "npm",
          "matches_repo": true,
          "registry_url": "https://www.npmjs.com/package/@llm-ports/adapter-aider",
          "is_deprecated": false,
          "latest_version": "0.1.0-alpha.28",
          "repository_url": "https://github.com/baabakk/llm-ports",
          "versions_count": 1,
          "total_downloads": null,
          "dependents_count": null,
          "deprecation_note": null,
          "maintainers_count": 1,
          "monthly_downloads": 65,
          "first_published_at": "2026-07-22T12:51:43.073000Z",
          "latest_published_at": "2026-07-22T12:51:43.356000Z",
          "latest_version_yanked": null,
          "days_since_latest_publish": 9
        },
        {
          "name": "@llm-ports/adapter-codex",
          "exists": true,
          "license": "MIT",
          "keywords": [
            "llm",
            "ai",
            "codex",
            "openai",
            "agent",
            "subprocess",
            "llm-ports",
            "adapter"
          ],
          "ecosystem": "npm",
          "matches_repo": true,
          "registry_url": "https://www.npmjs.com/package/@llm-ports/adapter-codex",
          "is_deprecated": false,
          "latest_version": "0.1.0-alpha.28",
          "repository_url": "https://github.com/baabakk/llm-ports",
          "versions_count": 1,
          "total_downloads": null,
          "dependents_count": null,
          "deprecation_note": null,
          "maintainers_count": 1,
          "monthly_downloads": 63,
          "first_published_at": "2026-07-22T12:51:43.071000Z",
          "latest_published_at": "2026-07-22T12:51:43.308000Z",
          "latest_version_yanked": null,
          "days_since_latest_publish": 9
        },
        {
          "name": "@llm-ports/adapter-google",
          "exists": true,
          "license": "MIT",
          "keywords": [
            "llm",
            "ai",
            "typescript",
            "google",
            "gemini",
            "google-genai",
            "vision",
            "multimodal",
            "ports-and-adapters",
            "llm-ports",
            "production-llm"
          ],
          "ecosystem": "npm",
          "matches_repo": true,
          "registry_url": "https://www.npmjs.com/package/@llm-ports/adapter-google",
          "is_deprecated": false,
          "latest_version": "0.1.0-alpha.28",
          "repository_url": "https://github.com/baabakk/llm-ports",
          "versions_count": 23,
          "total_downloads": null,
          "dependents_count": null,
          "deprecation_note": null,
          "maintainers_count": 1,
          "monthly_downloads": 1076,
          "first_published_at": "2026-05-21T04:25:17.740000Z",
          "latest_published_at": "2026-07-22T12:51:43.103000Z",
          "latest_version_yanked": null,
          "days_since_latest_publish": 9
        },
        {
          "name": "@llm-ports/adapter-ollama",
          "exists": true,
          "license": "MIT",
          "keywords": [
            "llm",
            "ai",
            "typescript",
            "ollama",
            "local-llm",
            "self-hosted",
            "llama",
            "llama3",
            "mistral",
            "phi",
            "qwen",
            "gemma",
            "ai-sdk",
            "generative-ai",
            "llm-ports",
            "llm-adapter",
            "llm-routing",
            "embeddings",
            "model-management",
            "local-to-cloud",
            "tool-use",
            "vision",
            "multi-provider",
            "offline-llm",
            "privacy"
          ],
          "ecosystem": "npm",
          "matches_repo": true,
          "registry_url": "https://www.npmjs.com/package/@llm-ports/adapter-ollama",
          "is_deprecated": false,
          "latest_version": "0.1.0-alpha.28",
          "repository_url": "https://github.com/baabakk/llm-ports",
          "versions_count": 26,
          "total_downloads": null,
          "dependents_count": null,
          "deprecation_note": null,
          "maintainers_count": 1,
          "monthly_downloads": 1086,
          "first_published_at": "2026-05-12T02:22:26.619000Z",
          "latest_published_at": "2026-07-22T12:51:42.859000Z",
          "latest_version_yanked": null,
          "days_since_latest_publish": 9
        },
        {
          "name": "@llm-ports/adapter-openai",
          "exists": true,
          "license": "MIT",
          "keywords": [
            "llm",
            "ai",
            "typescript",
            "openai",
            "openai-compatible",
            "gpt",
            "gpt-4",
            "gpt-4o",
            "gpt-5",
            "azure-openai",
            "groq",
            "together-ai",
            "fireworks",
            "deepinfra",
            "perplexity",
            "cerebras",
            "litellm",
            "ai-sdk",
            "generative-ai",
            "llm-ports",
            "llm-adapter",
            "llm-routing",
            "llm-fallback",
            "embeddings",
            "tool-use",
            "function-calling",
            "structured-output",
            "vision",
            "multi-provider",
            "cost-control",
            "reasoning-models"
          ],
          "ecosystem": "npm",
          "matches_repo": true,
          "registry_url": "https://www.npmjs.com/package/@llm-ports/adapter-openai",
          "is_deprecated": false,
          "latest_version": "0.1.0-alpha.28",
          "repository_url": "https://github.com/baabakk/llm-ports",
          "versions_count": 30,
          "total_downloads": null,
          "dependents_count": null,
          "deprecation_note": null,
          "maintainers_count": 1,
          "monthly_downloads": 2023,
          "first_published_at": "2026-05-12T02:22:26.648000Z",
          "latest_published_at": "2026-07-22T12:51:43.176000Z",
          "latest_version_yanked": null,
          "days_since_latest_publish": 9
        }
      ]
    },
    "popularity": {
      "forks": 0,
      "stars": 2,
      "watchers": 1,
      "fork_history": {
        "days": [],
        "complete": true,
        "collected": 0,
        "total_forks": 0
      },
      "star_history": null,
      "open_issues_and_prs": 13
    },
    "ai_readiness": {
      "has_nix": false,
      "example_dirs": [
        "examples"
      ],
      "has_llms_txt": false,
      "has_dockerfile": false,
      "has_mcp_signal": false,
      "bootstrap_files": [],
      "api_schema_files": [],
      "has_devcontainer": false,
      "typecheck_configs": [
        "examples/agent-with-approval/tsconfig.json",
        "examples/basic/tsconfig.json",
        "examples/email-triage/tsconfig.json",
        "examples/extract-from-pdf/tsconfig.json",
        "examples/local-with-ollama/tsconfig.json",
        "examples/migrate-from-vercel-ai/tsconfig.json",
        "examples/multi-provider/tsconfig.json",
        "examples/streaming-chat/tsconfig.json",
        "examples/with-onretry/tsconfig.json",
        "packages/adapter-aider/tsconfig.json",
        "packages/adapter-anthropic/tsconfig.json",
        "packages/adapter-codex/tsconfig.json",
        "packages/adapter-contract-tests/tsconfig.json",
        "packages/adapter-google/tsconfig.json",
        "packages/adapter-ollama/tsconfig.json",
        "packages/adapter-openai/tsconfig.json",
        "packages/adapter-vercel/tsconfig.json",
        "packages/benchmarks/tsconfig.json",
        "packages/capabilities/tsconfig.json",
        "packages/consumer-type-check/tsconfig.json",
        "packages/core/tsconfig.json",
        "packages/migrate/tsconfig.json",
        "packages/observability-contract/tsconfig.json"
      ],
      "toolchain_manifests": [],
      "largest_source_bytes": 82975,
      "source_files_sampled": 262,
      "oversized_source_files": 1,
      "agent_instruction_files": [],
      "agent_instruction_max_bytes": null
    },
    "dependencies": {
      "manifests": [
        "package.json"
      ],
      "advisories": {
        "error": null,
        "scope": "published_package",
        "source": "osv",
        "findings": [],
        "collected": true,
        "malicious": [],
        "truncated": false,
        "by_severity": {},
        "advisory_count": 0,
        "affected_count": 0,
        "assessed_count": 1,
        "malicious_count": 0,
        "assessed_package": "npm:@llm-ports/core@0.1.0-alpha.28",
        "unassessed_count": 0,
        "direct_affected_count": 0
      },
      "ecosystems": [
        "npm"
      ],
      "dependencies": [
        {
          "name": "@anthropic-ai/sdk",
          "manifest": "packages/adapter-anthropic/package.json",
          "ecosystem": "npm",
          "version_constraint": "^0.32.1"
        },
        {
          "name": "@llm-ports/core",
          "manifest": "packages/adapter-anthropic/package.json",
          "ecosystem": "npm",
          "version_constraint": "workspace:*"
        },
        {
          "name": "zod-to-json-schema",
          "manifest": "packages/adapter-anthropic/package.json",
          "ecosystem": "npm",
          "version_constraint": "^3.24.1"
        },
        {
          "name": "@llm-ports/core",
          "manifest": "packages/adapter-contract-tests/package.json",
          "ecosystem": "npm",
          "version_constraint": "workspace:*"
        },
        {
          "name": "vitest",
          "manifest": "packages/adapter-contract-tests/package.json",
          "ecosystem": "npm",
          "version_constraint": "^2.1.4"
        },
        {
          "name": "zod",
          "manifest": "packages/adapter-contract-tests/package.json",
          "ecosystem": "npm",
          "version_constraint": "^3.23.0"
        },
        {
          "name": "@llm-ports/core",
          "manifest": "packages/adapter-google/package.json",
          "ecosystem": "npm",
          "version_constraint": "workspace:*"
        },
        {
          "name": "zod-to-json-schema",
          "manifest": "packages/adapter-google/package.json",
          "ecosystem": "npm",
          "version_constraint": "^3.23.5"
        },
        {
          "name": "@llm-ports/core",
          "manifest": "packages/adapter-ollama/package.json",
          "ecosystem": "npm",
          "version_constraint": "workspace:*"
        },
        {
          "name": "ollama",
          "manifest": "packages/adapter-ollama/package.json",
          "ecosystem": "npm",
          "version_constraint": "^0.5.10"
        },
        {
          "name": "@llm-ports/core",
          "manifest": "packages/adapter-openai/package.json",
          "ecosystem": "npm",
          "version_constraint": "workspace:*"
        },
        {
          "name": "openai",
          "manifest": "packages/adapter-openai/package.json",
          "ecosystem": "npm",
          "version_constraint": "^4.73.0"
        },
        {
          "name": "zod-to-json-schema",
          "manifest": "packages/adapter-openai/package.json",
          "ecosystem": "npm",
          "version_constraint": "^3.24.1"
        },
        {
          "name": "@llm-ports/core",
          "manifest": "packages/adapter-vercel/package.json",
          "ecosystem": "npm",
          "version_constraint": "workspace:*"
        },
        {
          "name": "ai",
          "manifest": "packages/adapter-vercel/package.json",
          "ecosystem": "npm",
          "version_constraint": "^4.3.19"
        },
        {
          "name": "@llm-ports/core",
          "manifest": "packages/capabilities/package.json",
          "ecosystem": "npm",
          "version_constraint": "workspace:*"
        },
        {
          "name": "@llm-ports/core",
          "manifest": "packages/consumer-type-check/package.json",
          "ecosystem": "npm",
          "version_constraint": "workspace:*"
        },
        {
          "name": "@llm-ports/capabilities",
          "manifest": "packages/consumer-type-check/package.json",
          "ecosystem": "npm",
          "version_constraint": "workspace:*"
        },
        {
          "name": "zod",
          "manifest": "packages/consumer-type-check/package.json",
          "ecosystem": "npm",
          "version_constraint": "^3.25.76"
        },
        {
          "name": "jsonrepair",
          "manifest": "packages/core/package.json",
          "ecosystem": "npm",
          "version_constraint": "^3.14.0"
        },
        {
          "name": "nanoid",
          "manifest": "packages/observability-contract/package.json",
          "ecosystem": "npm",
          "version_constraint": "^5.0.9"
        }
      ],
      "all_dependencies": {
        "error": "GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository",
        "source": null,
        "packages": [],
        "collected": false,
        "truncated": false,
        "total_count": null,
        "direct_count": null,
        "indirect_count": null
      }
    },
    "maintainership": {
      "issues": {
        "open_prs": 0,
        "merged_prs": 0,
        "open_issues": 13,
        "closed_ratio": 0.639,
        "closed_issues": 23,
        "closed_unmerged_prs": 0
      },
      "bus_factor": 1,
      "bot_contributors": 0,
      "top_contributors": [
        {
          "type": "User",
          "login": "baabakk",
          "commits": 165,
          "avatar_url": "https://avatars.githubusercontent.com/u/11369431?v=4"
        }
      ],
      "contributors_sampled": 1,
      "top_contributor_share": 1
    },
    "quality_signals": {
      "has_ci": true,
      "has_tests": true,
      "ci_workflows": [
        "ci.yml",
        "deploy-docs.yml"
      ],
      "has_docs_dir": true,
      "linter_configs": [
        ".eslintrc.cjs"
      ],
      "has_editorconfig": false,
      "has_linter_config": true,
      "has_precommit_config": false
    },
    "security_signals": {
      "lockfiles": [
        "pnpm-lock.yaml"
      ],
      "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": 0,
            "reason": "project has 0 contributing companies or organizations -- score normalized to 0",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#contributors"
          },
          {
            "name": "Dangerous-Workflow",
            "score": 10,
            "reason": "no dangerous workflow patterns detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dangerous-workflow"
          },
          {
            "name": "Dependency-Update-Tool",
            "score": 0,
            "reason": "no update tool detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dependency-update-tool"
          },
          {
            "name": "Fuzzing",
            "score": 0,
            "reason": "project is not fuzzed",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
          },
          {
            "name": "License",
            "score": 10,
            "reason": "license file detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
          },
          {
            "name": "Maintained",
            "score": 0,
            "reason": "project was created within the last 90 days. Please review its contents carefully",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#maintained"
          },
          {
            "name": "Packaging",
            "score": null,
            "reason": "packaging workflow not detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
          },
          {
            "name": "Pinned-Dependencies",
            "score": 0,
            "reason": "dependency not pinned by hash detected -- score normalized to 0",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#pinned-dependencies"
          },
          {
            "name": "SAST",
            "score": 0,
            "reason": "no SAST tool detected",
            "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": null,
            "reason": "no releases found",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#signed-releases"
          },
          {
            "name": "Token-Permissions",
            "score": 0,
            "reason": "detected GitHub workflow tokens with excessive permissions",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
          },
          {
            "name": "Vulnerabilities",
            "score": 0,
            "reason": "22 existing vulnerabilities detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
          }
        ],
        "commit": "d1ed31b72bd6c237f280eeac049113d385a61a79",
        "ran_at": "2026-07-31T16:51:11Z",
        "aggregate_score": 2.8,
        "scorecard_version": "v5.5.0"
      },
      "has_codeql_workflow": false,
      "has_security_policy": true,
      "has_dependabot_config": false
    },
    "contribution_flow": {
      "collected": true,
      "ci_last_run_at": "2026-07-22T12:51:30Z",
      "oldest_open_prs": [],
      "last_merged_pr_at": null,
      "ci_last_conclusion": "SUCCESS",
      "oldest_open_issues": [
        {
          "number": 13,
          "created_at": "2026-05-20T14:34:32Z",
          "last_comment_at": "2026-05-21T03:31:51Z",
          "last_comment_author": "baabakk"
        },
        {
          "number": 17,
          "created_at": "2026-05-20T14:36:17Z",
          "last_comment_at": null,
          "last_comment_author": null
        },
        {
          "number": 30,
          "created_at": "2026-05-26T05:28:13Z",
          "last_comment_at": "2026-05-27T02:32:03Z",
          "last_comment_author": "baabakk"
        },
        {
          "number": 35,
          "created_at": "2026-05-26T20:07:26Z",
          "last_comment_at": null,
          "last_comment_author": null
        },
        {
          "number": 45,
          "created_at": "2026-06-16T23:04:44Z",
          "last_comment_at": null,
          "last_comment_author": null
        },
        {
          "number": 53,
          "created_at": "2026-07-02T08:22:11Z",
          "last_comment_at": null,
          "last_comment_author": null
        },
        {
          "number": 54,
          "created_at": "2026-07-02T08:43:04Z",
          "last_comment_at": null,
          "last_comment_author": null
        },
        {
          "number": 55,
          "created_at": "2026-07-02T08:43:14Z",
          "last_comment_at": null,
          "last_comment_author": null
        },
        {
          "number": 56,
          "created_at": "2026-07-02T08:43:33Z",
          "last_comment_at": null,
          "last_comment_author": null
        },
        {
          "number": 57,
          "created_at": "2026-07-02T08:43:43Z",
          "last_comment_at": null,
          "last_comment_author": null
        },
        {
          "number": 58,
          "created_at": "2026-07-02T08:43:57Z",
          "last_comment_at": null,
          "last_comment_author": null
        },
        {
          "number": 59,
          "created_at": "2026-07-02T08:44:07Z",
          "last_comment_at": null,
          "last_comment_author": null
        },
        {
          "number": 60,
          "created_at": "2026-07-02T08:44:24Z",
          "last_comment_at": "2026-07-10T09:47:18Z",
          "last_comment_author": "richardchen874-sys"
        }
      ]
    }
  },
  "config": {
    "disabled_metrics": [],
    "disabled_categories": [],
    "disabled_components": {}
  },
  "source": {
    "url": "https://github.com/baabakk/llm-ports",
    "host": "github.com",
    "name": "llm-ports",
    "owner": "baabakk"
  },
  "metrics": {
    "overall": {
      "key": "overall",
      "band": "good",
      "name": "Overall health",
      "note": "The weighted overall 60 is calibrated to 65 on the published index scale (record calibration 2026-08-02).",
      "notes": [
        {
          "code": "overall_calibration",
          "params": {
            "raw": 60,
            "calibrated": 65,
            "calibration": "2026-08-02"
          }
        }
      ],
      "value": 65,
      "inputs": {
        "security": 42,
        "vitality": 73,
        "community": 49,
        "governance": 46,
        "calibration": "2026-08-02",
        "engineering": 88,
        "ai_readiness": 55,
        "weighted_overall_raw": 60
      },
      "components": []
    },
    "categories": [
      {
        "key": "vitality",
        "band": "good",
        "name": "Vitality",
        "value": 73,
        "weight": 0.21,
        "metrics": [
          {
            "key": "development_activity",
            "band": "moderate",
            "name": "Development activity",
            "note": null,
            "notes": [],
            "value": 55,
            "inputs": {
              "commits_last_year": 165,
              "human_commit_share": 1,
              "days_since_last_push": 9,
              "active_weeks_last_year": 12
            },
            "components": [
              {
                "key": "push_recency",
                "name": "Push recency",
                "detail": "last push 9 days ago",
                "points": 28.8,
                "status": "partial",
                "details": [
                  {
                    "code": "push_recency",
                    "params": {
                      "days": 9
                    }
                  }
                ],
                "max_points": 36
              },
              {
                "key": "commit_cadence",
                "name": "Commit cadence",
                "detail": "12/52 weeks with commits",
                "points": 8.3,
                "status": "partial",
                "details": [
                  {
                    "code": "commit_cadence_weeks",
                    "params": {
                      "weeks": 12
                    }
                  }
                ],
                "max_points": 36
              },
              {
                "key": "commit_volume",
                "name": "Commit volume",
                "detail": "165 commits in the last year",
                "points": 18,
                "status": "met",
                "details": [
                  {
                    "code": "commits_last_year",
                    "params": {
                      "count": 165
                    }
                  }
                ],
                "max_points": 18
              },
              {
                "key": "openssf_scorecard_maintained",
                "name": "OpenSSF Scorecard: Maintained",
                "detail": "project was created within the last 90 days. Please review its contents carefully",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 10
              }
            ]
          },
          {
            "key": "release_discipline",
            "band": "exceptional",
            "name": "Release discipline",
            "note": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.",
            "notes": [
              {
                "code": "excluded_no_data",
                "params": {
                  "components": [
                    "openssf_scorecard_signed_releases"
                  ]
                }
              },
              {
                "code": "weights_renormalized",
                "params": {}
              }
            ],
            "value": 100,
            "inputs": {
              "releases_count": 82,
              "latest_release_tag": "@llm-ports/core@0.1.0-alpha.27",
              "releases_from_tags": false,
              "days_since_latest_release": 13,
              "mean_days_between_releases": 3.8
            },
            "components": [
              {
                "key": "ships_releases",
                "name": "Ships releases",
                "detail": "82 releases published",
                "points": 27,
                "status": "met",
                "details": [
                  {
                    "code": "releases_published",
                    "params": {
                      "count": 82
                    }
                  }
                ],
                "max_points": 27
              },
              {
                "key": "release_recency",
                "name": "Release recency",
                "detail": "latest release 13 days ago",
                "points": 36,
                "status": "met",
                "details": [
                  {
                    "code": "release_recency",
                    "params": {
                      "days": 13
                    }
                  }
                ],
                "max_points": 36
              },
              {
                "key": "release_cadence",
                "name": "Release cadence",
                "detail": "a release every ~3.8 days",
                "points": 27,
                "status": "met",
                "details": [
                  {
                    "code": "release_cadence",
                    "params": {
                      "gap": 3.8
                    }
                  }
                ],
                "max_points": 27
              },
              {
                "key": "openssf_scorecard_signed_releases",
                "name": "OpenSSF Scorecard: Signed-Releases",
                "detail": "no releases found",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "no_data",
                    "params": {}
                  }
                ],
                "max_points": 10
              }
            ]
          },
          {
            "key": "abandonment",
            "band": "exceptional",
            "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": "weak",
        "name": "Community & Adoption",
        "value": 49,
        "weight": 0.17,
        "metrics": [
          {
            "key": "popularity",
            "band": "critical",
            "name": "Popularity & adoption",
            "note": null,
            "notes": [],
            "value": 1,
            "inputs": {
              "forks": 0,
              "stars": 2,
              "watchers": 1,
              "growth_state": "unverified",
              "growth_factor_pct": 100,
              "growth_unverified_reason": "no_history"
            },
            "components": [
              {
                "key": "stars",
                "name": "Stars",
                "detail": "2 stars",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "stars",
                    "params": {
                      "count": 2
                    }
                  }
                ],
                "max_points": 60
              },
              {
                "key": "forks",
                "name": "Forks",
                "detail": "0 forks",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "forks",
                    "params": {
                      "count": 0
                    }
                  }
                ],
                "max_points": 25
              },
              {
                "key": "watchers",
                "name": "Watchers",
                "detail": "1 watchers",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "watchers",
                    "params": {
                      "count": 1
                    }
                  }
                ],
                "max_points": 15
              }
            ]
          },
          {
            "key": "community_health",
            "band": "excellent",
            "name": "Community health",
            "note": null,
            "notes": [],
            "value": 92,
            "inputs": {
              "has_readme": true,
              "has_license": true,
              "readme_badges": null,
              "has_contributing": true,
              "has_issue_template": false,
              "has_code_of_conduct": true,
              "readme_badge_services": [],
              "has_pull_request_template": true
            },
            "components": [
              {
                "key": "readme",
                "name": "README",
                "detail": null,
                "points": 22.5,
                "status": "met",
                "details": [],
                "max_points": 22.5
              },
              {
                "key": "license",
                "name": "License",
                "detail": "recognized license (MIT)",
                "points": 22.5,
                "status": "met",
                "details": [
                  {
                    "code": "license_standard",
                    "params": {}
                  },
                  {
                    "code": "license_spdx",
                    "params": {
                      "spdx": "MIT"
                    }
                  }
                ],
                "max_points": 22.5
              },
              {
                "key": "contributing_guide",
                "name": "CONTRIBUTING guide",
                "detail": null,
                "points": 18,
                "status": "met",
                "details": [],
                "max_points": 18
              },
              {
                "key": "code_of_conduct",
                "name": "Code of conduct",
                "detail": null,
                "points": 13.5,
                "status": "met",
                "details": [],
                "max_points": 13.5
              },
              {
                "key": "issue_template",
                "name": "Issue template",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.2
              },
              {
                "key": "pr_template",
                "name": "PR template",
                "detail": null,
                "points": 6.3,
                "status": "met",
                "details": [],
                "max_points": 6.3
              }
            ]
          },
          {
            "key": "ecosystem_adoption",
            "band": "good",
            "name": "Ecosystem adoption (downloads)",
            "note": "Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.",
            "notes": [
              {
                "code": "excluded_no_data",
                "params": {
                  "components": [
                    "registry_dependents"
                  ]
                }
              },
              {
                "code": "weights_renormalized",
                "params": {}
              }
            ],
            "value": 65,
            "inputs": {
              "packages": [
                "@llm-ports/core",
                "@llm-ports/migrate",
                "@llm-ports/capabilities",
                "@llm-ports/adapter-aider",
                "@llm-ports/adapter-codex",
                "@llm-ports/adapter-google",
                "@llm-ports/adapter-ollama",
                "@llm-ports/adapter-openai"
              ],
              "dependents": null,
              "ecosystems": "npm",
              "total_downloads": null,
              "monthly_downloads": 7563
            },
            "components": [
              {
                "key": "monthly_downloads",
                "name": "Monthly downloads",
                "detail": "7,563 downloads/month across npm",
                "points": 51.7,
                "status": "partial",
                "details": [
                  {
                    "code": "downloads_monthly",
                    "params": {
                      "count": 7563,
                      "ecosystems": "npm"
                    }
                  }
                ],
                "max_points": 80
              },
              {
                "key": "registry_dependents",
                "name": "Registry dependents",
                "detail": "not reported by this ecosystem",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "not_reported_by_this_ecosystem",
                    "params": {}
                  }
                ],
                "max_points": 20
              }
            ]
          }
        ],
        "description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
      },
      {
        "key": "governance",
        "band": "weak",
        "name": "Sustainability & Governance",
        "value": 46,
        "weight": 0.23,
        "metrics": [
          {
            "key": "maintainer_resilience",
            "band": "critical",
            "name": "Maintainer resilience (bus factor)",
            "note": null,
            "notes": [],
            "value": 10,
            "inputs": {
              "bus_factor": 1,
              "contributors_sampled": 1,
              "top_contributor_share": 1
            },
            "components": [
              {
                "key": "bus_factor",
                "name": "Bus factor",
                "detail": "1 contributor(s) cover half of all commits",
                "points": 9,
                "status": "partial",
                "details": [
                  {
                    "code": "bus_factor",
                    "params": {
                      "count": 1
                    }
                  }
                ],
                "max_points": 54
              },
              {
                "key": "commit_distribution",
                "name": "Commit distribution",
                "detail": "top contributor authored 100% of commits",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "top_contributor_share",
                    "params": {
                      "share": 100
                    }
                  }
                ],
                "max_points": 22.5
              },
              {
                "key": "contributor_breadth",
                "name": "Contributor breadth",
                "detail": "1 contributors",
                "points": 1.4,
                "status": "partial",
                "details": [
                  {
                    "code": "contributors_sampled",
                    "params": {
                      "count": 1
                    }
                  }
                ],
                "max_points": 13.5
              },
              {
                "key": "openssf_scorecard_contributors",
                "name": "OpenSSF Scorecard: Contributors",
                "detail": "project has 0 contributing companies or organizations -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 10
              }
            ]
          },
          {
            "key": "responsiveness",
            "band": "weak",
            "name": "Issue & PR responsiveness",
            "note": "Excluded from scoring (no data or not applicable): PR acceptance, Newcomer PR acceptance. Remaining weights renormalized.",
            "notes": [
              {
                "code": "excluded_no_data",
                "params": {
                  "components": [
                    "pr_acceptance",
                    "newcomer_pr_acceptance"
                  ]
                }
              },
              {
                "code": "weights_renormalized",
                "params": {}
              }
            ],
            "value": 47,
            "inputs": {
              "merged_prs": 0,
              "open_issues": 13,
              "closed_issues": 23,
              "prs_merged_7d": null,
              "prs_decided_7d": null,
              "prs_merged_30d": null,
              "prs_decided_30d": null,
              "issue_closed_ratio": 0.639,
              "closed_unmerged_prs": 0,
              "first_time_authors_30d": null,
              "first_time_prs_merged_30d": null,
              "first_time_prs_decided_30d": null
            },
            "components": [
              {
                "key": "issue_resolution",
                "name": "Issue resolution",
                "detail": "64% of issues closed",
                "points": 26.8,
                "status": "partial",
                "details": [
                  {
                    "code": "issues_closed_share",
                    "params": {
                      "share": 64
                    }
                  }
                ],
                "max_points": 42
              },
              {
                "key": "pr_acceptance",
                "name": "PR acceptance",
                "detail": "no decided pull requests or no data",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "no_decided_prs_or_data",
                    "params": {}
                  }
                ],
                "max_points": 30
              },
              {
                "key": "newcomer_pr_acceptance",
                "name": "Newcomer PR acceptance",
                "detail": "no first-time contributor's PR decided in 30d",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "no_newcomer_prs",
                    "params": {
                      "days": 30
                    }
                  }
                ],
                "max_points": 13
              },
              {
                "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": "weak",
            "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": 46,
            "inputs": {
              "followers": 2,
              "owner_type": "User",
              "is_verified": null,
              "owner_login": "baabakk",
              "public_repos": 32,
              "account_age_days": 4163
            },
            "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": "2 followers of baabakk",
                "points": 3.4,
                "status": "partial",
                "details": [
                  {
                    "code": "owner_followers",
                    "params": {
                      "count": 2,
                      "login": "baabakk"
                    }
                  }
                ],
                "max_points": 25
              },
              {
                "key": "track_record",
                "name": "Track record",
                "detail": "32 public repos, account ~11 yr old",
                "points": 23.1,
                "status": "partial",
                "details": [
                  {
                    "code": "public_repos",
                    "params": {
                      "count": 32
                    }
                  },
                  {
                    "code": "account_age_years",
                    "params": {
                      "years": 11
                    }
                  }
                ],
                "max_points": 25
              }
            ]
          },
          {
            "key": "package_maintenance",
            "band": "exceptional",
            "name": "Package maintenance",
            "note": null,
            "notes": [],
            "value": 100,
            "inputs": {
              "packages": [
                "@llm-ports/core",
                "@llm-ports/migrate",
                "@llm-ports/capabilities",
                "@llm-ports/adapter-aider",
                "@llm-ports/adapter-codex",
                "@llm-ports/adapter-google",
                "@llm-ports/adapter-ollama",
                "@llm-ports/adapter-openai"
              ],
              "ecosystems": "npm",
              "any_deprecated": false,
              "min_days_since_publish": 9
            },
            "components": [
              {
                "key": "published_resolvable",
                "name": "Published & resolvable",
                "detail": "8 package(s) on npm",
                "points": 25,
                "status": "met",
                "details": [
                  {
                    "code": "packages_published",
                    "params": {
                      "count": 8,
                      "ecosystems": "npm"
                    }
                  }
                ],
                "max_points": 25
              },
              {
                "key": "publish_recency",
                "name": "Publish recency",
                "detail": "latest publish 9 days ago",
                "points": 35,
                "status": "met",
                "details": [
                  {
                    "code": "publish_recency",
                    "params": {
                      "days": 9
                    }
                  }
                ],
                "max_points": 35
              },
              {
                "key": "version_history",
                "name": "Version history",
                "detail": "30 published versions",
                "points": 20,
                "status": "met",
                "details": [
                  {
                    "code": "published_versions",
                    "params": {
                      "count": 30
                    }
                  }
                ],
                "max_points": 20
              },
              {
                "key": "not_deprecated",
                "name": "Not deprecated",
                "detail": "active, not deprecated or yanked",
                "points": 20,
                "status": "met",
                "details": [
                  {
                    "code": "package_not_deprecated",
                    "params": {}
                  }
                ],
                "max_points": 20
              }
            ]
          }
        ],
        "description": "Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?"
      },
      {
        "key": "engineering",
        "band": "excellent",
        "name": "Engineering Quality",
        "value": 88,
        "weight": 0.19,
        "metrics": [
          {
            "key": "engineering_practices",
            "band": "excellent",
            "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": "2 workflow(s)",
                "points": 24,
                "status": "met",
                "details": [
                  {
                    "code": "ci_workflows",
                    "params": {
                      "count": 2
                    }
                  }
                ],
                "max_points": 24
              },
              {
                "key": "tests_present",
                "name": "Tests present",
                "detail": null,
                "points": 24,
                "status": "met",
                "details": [],
                "max_points": 24
              },
              {
                "key": "linter_config",
                "name": "Linter config",
                "detail": ".eslintrc.cjs",
                "points": 16,
                "status": "met",
                "details": [
                  {
                    "code": "file_list",
                    "params": {
                      "files": ".eslintrc.cjs"
                    }
                  }
                ],
                "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": "exceptional",
            "name": "Documentation",
            "note": null,
            "notes": [],
            "value": 100,
            "inputs": {
              "topics": [
                "ai",
                "ai-architecture",
                "anthropic",
                "cost-control",
                "generative-ai",
                "llm",
                "llm-abstraction",
                "llm-fallback",
                "llm-routing",
                "multi-provider",
                "ollama",
                "openai",
                "software-architecture",
                "typescript",
                "vendor-lock-in",
                "multi-provider-ai-support"
              ],
              "has_wiki": true,
              "homepage": "https://baabakk.github.io/llm-ports/",
              "has_readme": true,
              "has_docs_dir": true,
              "has_description": true
            },
            "components": [
              {
                "key": "readme",
                "name": "README",
                "detail": null,
                "points": 30,
                "status": "met",
                "details": [],
                "max_points": 30
              },
              {
                "key": "documentation_directory",
                "name": "Documentation directory",
                "detail": null,
                "points": 25,
                "status": "met",
                "details": [],
                "max_points": 25
              },
              {
                "key": "documentation_homepage_site",
                "name": "Documentation / homepage site",
                "detail": "https://baabakk.github.io/llm-ports/",
                "points": 15,
                "status": "met",
                "details": [],
                "max_points": 15
              },
              {
                "key": "repository_description",
                "name": "Repository description",
                "detail": null,
                "points": 10,
                "status": "met",
                "details": [],
                "max_points": 10
              },
              {
                "key": "topics",
                "name": "Topics",
                "detail": "16 topics",
                "points": 10,
                "status": "met",
                "details": [
                  {
                    "code": "topics_count",
                    "params": {
                      "count": 16
                    }
                  }
                ],
                "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": "weak",
        "name": "Security",
        "value": 42,
        "weight": 0.16,
        "metrics": [
          {
            "key": "security_posture",
            "band": "at_risk",
            "name": "Security posture",
            "note": "Excluded from scoring (no data or not applicable): CI-Tests, Packaging, Signed-Releases. Remaining weights renormalized.",
            "notes": [
              {
                "code": "excluded_no_data",
                "params": {
                  "components": [
                    "ci_tests",
                    "packaging",
                    "signed_releases"
                  ]
                }
              },
              {
                "code": "weights_renormalized",
                "params": {}
              }
            ],
            "value": 28,
            "inputs": {
              "source": "openssf_scorecard",
              "checks_evaluated": 15,
              "scorecard_version": "v5.5.0",
              "checks_inconclusive": 3,
              "scorecard_aggregate": 2.8
            },
            "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 0 contributing companies or organizations -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 2.5
              },
              {
                "key": "dangerous_workflow",
                "name": "Dangerous-Workflow",
                "detail": "no dangerous workflow patterns detected",
                "points": 10,
                "status": "met",
                "details": [],
                "max_points": 10
              },
              {
                "key": "dependency_update_tool",
                "name": "Dependency-Update-Tool",
                "detail": "no update tool detected",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "fuzzing",
                "name": "Fuzzing",
                "detail": "project is not fuzzed",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 5
              },
              {
                "key": "license",
                "name": "License",
                "detail": "license file detected",
                "points": 2.5,
                "status": "met",
                "details": [],
                "max_points": 2.5
              },
              {
                "key": "maintained",
                "name": "Maintained",
                "detail": "project was created within the last 90 days. Please review its contents carefully",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "packaging",
                "name": "Packaging",
                "detail": "packaging workflow not detected",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "no_data",
                    "params": {}
                  }
                ],
                "max_points": 5
              },
              {
                "key": "pinned_dependencies",
                "name": "Pinned-Dependencies",
                "detail": "dependency not pinned by hash detected -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 5
              },
              {
                "key": "sast",
                "name": "SAST",
                "detail": "no SAST tool detected",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 5
              },
              {
                "key": "security_policy",
                "name": "Security-Policy",
                "detail": "security policy file detected",
                "points": 5,
                "status": "met",
                "details": [],
                "max_points": 5
              },
              {
                "key": "signed_releases",
                "name": "Signed-Releases",
                "detail": "no releases found",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "no_data",
                    "params": {}
                  }
                ],
                "max_points": 7.5
              },
              {
                "key": "token_permissions",
                "name": "Token-Permissions",
                "detail": "detected GitHub workflow tokens with excessive permissions",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "vulnerabilities",
                "name": "Vulnerabilities",
                "detail": "22 existing vulnerabilities detected",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.5
              }
            ]
          },
          {
            "key": "dependency_advisories",
            "band": "exceptional",
            "name": "Dependency advisories",
            "note": "Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the npm:@llm-ports/core@0.1.0-alpha.28 runtime dependency closure — what installing the published package pulls in — 1 packages. Reachability is not analyzed.",
            "notes": [
              {
                "code": "excluded_no_data",
                "params": {
                  "components": [
                    "no_advisories_left_outstanding"
                  ]
                }
              },
              {
                "code": "weights_renormalized",
                "params": {}
              },
              {
                "code": "advisories_scope_published",
                "params": {
                  "package": "npm:@llm-ports/core@0.1.0-alpha.28",
                  "assessed": 1
                }
              },
              {
                "code": "advisories_reachability",
                "params": {}
              }
            ],
            "value": 100,
            "inputs": {
              "source": "osv",
              "advisories": 0,
              "affected_packages": 0,
              "assessed_packages": 1,
              "unassessed_packages": 0,
              "affected_by_severity": "none",
              "direct_affected_packages": 0
            },
            "components": [
              {
                "key": "direct_dependencies_free_of_known_advisories",
                "name": "Direct dependencies free of known advisories",
                "detail": "no direct dependency carries a known advisory",
                "points": 35,
                "status": "met",
                "details": [
                  {
                    "code": "no_direct_advisories",
                    "params": {}
                  }
                ],
                "max_points": 35
              },
              {
                "key": "indirect_dependencies_free_of_known_advisories",
                "name": "Indirect dependencies free of known advisories",
                "detail": "no indirect dependency carries a known advisory",
                "points": 25,
                "status": "met",
                "details": [
                  {
                    "code": "no_indirect_advisories",
                    "params": {}
                  }
                ],
                "max_points": 25
              },
              {
                "key": "no_advisories_left_outstanding",
                "name": "No advisories left outstanding",
                "detail": "no advisory carries a publication date",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "advisories_no_publication_date",
                    "params": {}
                  }
                ],
                "max_points": 40
              }
            ]
          },
          {
            "key": "malicious_dependencies",
            "band": "exceptional",
            "name": "Malicious dependencies",
            "note": null,
            "notes": [],
            "value": 100,
            "inputs": {
              "source": "osv",
              "meaning": "reported as a malicious package by the OpenSSF corpus; the remedy is removal or moving off the compromised name, never an upgrade of the same artifact. Versions the registry has since pulled are listed but not scored",
              "packages": [],
              "red_flag": false,
              "assessed_packages": 1,
              "malicious_packages": 0,
              "direct_malicious_packages": 0,
              "withdrawn_malicious_packages": 0,
              "installable_malicious_packages": 0
            },
            "components": [
              {
                "key": "no_dependency_reported_as_a_malicious_package",
                "name": "No dependency reported as a malicious package",
                "detail": "no dependency is reported as a malicious package",
                "points": 100,
                "status": "met",
                "details": [
                  {
                    "code": "no_malicious_dependencies",
                    "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": "moderate",
        "name": "AI Readiness",
        "value": 55,
        "weight": 0.04,
        "metrics": [
          {
            "key": "ai_agent_context",
            "band": "weak",
            "name": "Agent context & guidance",
            "note": null,
            "notes": [],
            "value": 40,
            "inputs": {
              "has_llms_txt": false,
              "legible_history_share": 0.99,
              "agent_instruction_files": [],
              "agent_instruction_max_bytes": null
            },
            "components": [
              {
                "key": "agent_instructions",
                "name": "Agent instructions",
                "detail": "no CLAUDE.md / AGENTS.md / editor rules",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "no_agent_instructions",
                    "params": {}
                  }
                ],
                "max_points": 45
              },
              {
                "key": "machine_readable_docs_llms_txt",
                "name": "Machine-readable docs (llms.txt)",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 15
              },
              {
                "key": "legible_commit_history",
                "name": "Legible commit history",
                "detail": "99 of 100 human commits state their intent (structured subject or explanatory body)",
                "points": 40,
                "status": "met",
                "details": [
                  {
                    "code": "legible_history",
                    "params": {
                      "legible": 99,
                      "sampled": 100
                    }
                  }
                ],
                "max_points": 40
              }
            ]
          },
          {
            "key": "ai_verify_loop",
            "band": "moderate",
            "name": "Verify loop (build / test / typecheck)",
            "note": null,
            "notes": [],
            "value": 54,
            "inputs": {
              "has_nix": false,
              "has_tests": true,
              "lockfiles": [
                "pnpm-lock.yaml"
              ],
              "has_dockerfile": false,
              "typed_language": true,
              "bootstrap_files": [],
              "has_devcontainer": false,
              "has_linter_config": true,
              "typecheck_configs": [
                "examples/agent-with-approval/tsconfig.json",
                "examples/basic/tsconfig.json",
                "examples/email-triage/tsconfig.json",
                "examples/extract-from-pdf/tsconfig.json",
                "examples/local-with-ollama/tsconfig.json",
                "examples/migrate-from-vercel-ai/tsconfig.json",
                "examples/multi-provider/tsconfig.json",
                "examples/streaming-chat/tsconfig.json",
                "examples/with-onretry/tsconfig.json",
                "packages/adapter-aider/tsconfig.json",
                "packages/adapter-anthropic/tsconfig.json",
                "packages/adapter-codex/tsconfig.json",
                "packages/adapter-contract-tests/tsconfig.json",
                "packages/adapter-google/tsconfig.json",
                "packages/adapter-ollama/tsconfig.json",
                "packages/adapter-openai/tsconfig.json",
                "packages/adapter-vercel/tsconfig.json",
                "packages/benchmarks/tsconfig.json",
                "packages/capabilities/tsconfig.json",
                "packages/consumer-type-check/tsconfig.json",
                "packages/core/tsconfig.json",
                "packages/migrate/tsconfig.json",
                "packages/observability-contract/tsconfig.json"
              ],
              "agent_commit_share": 0,
              "toolchain_manifests": [],
              "dependency_bot_commit_share": 0
            },
            "components": [
              {
                "key": "one_command_bootstrap",
                "name": "One-command bootstrap",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "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": ".eslintrc.cjs",
                "points": 11,
                "status": "met",
                "details": [
                  {
                    "code": "file_list",
                    "params": {
                      "files": ".eslintrc.cjs"
                    }
                  }
                ],
                "max_points": 11
              },
              {
                "key": "static_type_checking",
                "name": "Static type checking",
                "detail": "examples/agent-with-approval/tsconfig.json, examples/basic/tsconfig.json, examples/email-triage/tsconfig.json, examples/extract-from-pdf/tsconfig.json, examples/local-with-ollama/tsconfig.json, examples/migrate-from-vercel-ai/tsconfig.json, examples/multi-provider/tsconfig.json, examples/streaming-chat/tsconfig.json, examples/with-onretry/tsconfig.json, packages/adapter-aider/tsconfig.json, packages/adapter-anthropic/tsconfig.json, packages/adapter-codex/tsconfig.json, packages/adapter-contract-tests/tsconfig.json, packages/adapter-google/tsconfig.json, packages/adapter-ollama/tsconfig.json, packages/adapter-openai/tsconfig.json, packages/adapter-vercel/tsconfig.json, packages/benchmarks/tsconfig.json, packages/capabilities/tsconfig.json, packages/consumer-type-check/tsconfig.json, packages/core/tsconfig.json, packages/migrate/tsconfig.json, packages/observability-contract/tsconfig.json",
                "points": 11,
                "status": "met",
                "details": [
                  {
                    "code": "file_list",
                    "params": {
                      "files": "examples/agent-with-approval/tsconfig.json, examples/basic/tsconfig.json, examples/email-triage/tsconfig.json, examples/extract-from-pdf/tsconfig.json, examples/local-with-ollama/tsconfig.json, examples/migrate-from-vercel-ai/tsconfig.json, examples/multi-provider/tsconfig.json, examples/streaming-chat/tsconfig.json, examples/with-onretry/tsconfig.json, packages/adapter-aider/tsconfig.json, packages/adapter-anthropic/tsconfig.json, packages/adapter-codex/tsconfig.json, packages/adapter-contract-tests/tsconfig.json, packages/adapter-google/tsconfig.json, packages/adapter-ollama/tsconfig.json, packages/adapter-openai/tsconfig.json, packages/adapter-vercel/tsconfig.json, packages/benchmarks/tsconfig.json, packages/capabilities/tsconfig.json, packages/consumer-type-check/tsconfig.json, packages/core/tsconfig.json, packages/migrate/tsconfig.json, packages/observability-contract/tsconfig.json"
                    }
                  }
                ],
                "max_points": 11
              },
              {
                "key": "reproducible_environment",
                "name": "Reproducible environment",
                "detail": "lockfile",
                "points": 10,
                "status": "met",
                "details": [
                  {
                    "code": "file_list",
                    "params": {
                      "files": "lockfile"
                    }
                  }
                ],
                "max_points": 10
              },
              {
                "key": "demonstrated_agent_practice",
                "name": "Demonstrated agent practice",
                "detail": "no agent-authored commits among the last 100",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "no_agent_authored_commits",
                    "params": {
                      "sampled": 100
                    }
                  }
                ],
                "max_points": 10
              },
              {
                "key": "automated_maintenance",
                "name": "Automated maintenance",
                "detail": "no automated dependency updates observed",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "no_dependency_automation",
                    "params": {}
                  }
                ],
                "max_points": 8
              },
              {
                "key": "openssf_scorecard_pinned_dependencies",
                "name": "OpenSSF Scorecard: Pinned-Dependencies",
                "detail": "dependency not pinned by hash detected -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 10
              }
            ]
          },
          {
            "key": "ai_code_legibility",
            "band": "exceptional",
            "name": "Code legibility for models",
            "note": null,
            "notes": [],
            "value": 100,
            "inputs": {
              "primary_language": "TypeScript",
              "largest_source_bytes": 82975,
              "source_files_sampled": 262,
              "oversized_source_files": 1
            },
            "components": [
              {
                "key": "type_checkable_code",
                "name": "Type-checkable code",
                "detail": "TypeScript (statically typed)",
                "points": 45,
                "status": "met",
                "details": [
                  {
                    "code": "statically_typed_language",
                    "params": {
                      "language": "TypeScript"
                    }
                  }
                ],
                "max_points": 45
              },
              {
                "key": "manageable_file_sizes",
                "name": "Manageable file sizes",
                "detail": "1/262 source files over 60KB",
                "points": 54.8,
                "status": "partial",
                "details": [
                  {
                    "code": "oversized_source_files",
                    "params": {
                      "kb": 60,
                      "sampled": 262,
                      "oversized": 1
                    }
                  }
                ],
                "max_points": 55
              }
            ]
          },
          {
            "key": "ai_interfaces",
            "band": "weak",
            "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? Carries a deliberately small weight: agent tooling is a real maintenance signal, but its absence must never gate the top of the scale (calibration saturates at raw 91, so 100/100 remains reachable with AI Readiness at zero)."
      }
    ],
    "classification": {
      "labels": [
        "library"
      ],
      "scores": {
        "library": 6,
        "network-service": 2
      },
      "primary": "library",
      "evidence": [
        {
          "tier": "distribution",
          "label": "library",
          "source": "registry:npm",
          "weight": 6
        },
        {
          "tier": "tags",
          "label": "network-service",
          "source": "tag:self-hosted",
          "weight": 2
        }
      ],
      "artifacts": [],
      "confidence": "medium",
      "host_extension": false,
      "runs_as_process": false,
      "consumed_by_code": true
    },
    "metrics_version": "2.3.1"
  },
  "warnings": [
    "Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token",
    "GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository"
  ],
  "report_type": "repository",
  "generated_at": "2026-07-31T16:51:16.783637Z",
  "schema_version": "0.27.0",
  "badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/b/baabakk/llm-ports.svg",
  "full_name": "baabakk/llm-ports",
  "license_state": "standard",
  "license_spdx": "MIT"
}

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 v2.3.1, schema v0.27.0 — full methodology · metrics wiki.

How one result sits in the wider record: aggregate statisticsnpm.