refactor(templates): generate AGENTS.md for claude code instead of CLAUDE.md by inference-gateway-maintainer[bot] · Pull Request #495 · inference-gateway/adl-cli

inference-gateway-maintainer · 2026-10-15T18:10:27Z

Summary

Claude Code reads AGENTS.md natively, so the separate CLAUDE.md template is removed. Enabling spec.development.ai.orchestrators.claudecode now generates the shared AGENTS.md (same as codex, opencode and infer).

Removed internal/templates/common/ai/claude.md.tmpl and its registry mapping
AIAgentToggles.AnyAgentsMD() now includes ClaudeCode
.gitattributes template no longer lists CLAUDE.md
Updated adl init prompt/flag text, README and tests
Follow-up cleanup (chore(templates) commit): dropped the retired CLAUDE.md/GEMINI.md entries from the generated .dockerignore so its list matches what the generator actually writes, tagged .gemini/settings.json as linguist-generated in the generated .gitattributes, and pointed the pre-v0.8.0 AI migration hint and a builtin-tools doc comment at AGENTS.md

Notes

Existing projects keep their old CLAUDE.md/GEMINI.md on regenerate - the generator just stops writing it. Deliberately not deleting stale files since they may contain user edits.
.adl-ignore intentionally still lists only TODO placeholders users must implement, so .gemini/settings.json has no entry; it is a fully generated file like Taskfile.yml.
The vendored schema descriptions still mention CLAUDE.md. They come from upstream inference-gateway/adl and are tracked there: [DOCS] Schema descriptions still reference CLAUDE.md and GEMINI.md adl#217. Once upstream fixes and releases, sync here with task fetch-schema and task generate-types.
Gemini CLI does not read AGENTS.md by default, so enabling gemini also generates .gemini/settings.json with context.fileName: AGENTS.md.

Testing

go test ./... passes
golangci-lint run - 0 issues
task lint:md clean
task ci passes after the cleanup commit (fmt, lint, test, build, verify-schema), including new assertions that the generated .dockerignore no longer lists CLAUDE.md/GEMINI.md and that .gitattributes tags .gemini/settings.json

no docs ticket: internal-only refactor

edenreich · 2026-10-15T18:15:46Z

@claude please drop all different from AGENTS.md files - all orchestrators should be using AGENTS.md at this point and time.

inference-gateway-maintainer · 2026-10-15T18:16:44Z

Claude finished @edenreich's task in 4m 2s —— View job

GEMINI.md dropped - every orchestrator now reads AGENTS.md

Gather context
Delete internal/templates/common/ai/gemini.md.tmpl (210 lines) and its registry mapping
AnyAgentsMD() removed - with gemini included it was identical to Any(), so addAIFiles and .gitattributes just use Any()
Generate .gemini/settings.json when gemini.enabled (see note below)
Gemini workflow header comment, adl init --ai flag text, README
Tests updated, go test ./... + golangci-lint run (0 issues) + markdownlint README.md clean

One thing I added on purpose

Gemini CLI does not read AGENTS.md by default - its context file name defaults to GEMINI.md and is configurable via the context.fileName setting (docs/reference/configuration.md in google-gemini/gemini-cli). So just deleting the template would have left gemini-enabled projects with no instructions file it could find. Enabling gemini now also writes:

{
  "context": {
    "fileName": "AGENTS.md"
  }
}

to .gemini/settings.json. Verified by generating a gemini-enabled manifest - valid JSON, no generated-file header prepended.

Left as-is

.dockerignore still lists CLAUDE.md and GEMINI.md, same reasoning as the existing PR note: a hand-written one stays out of the image.
.gemini/settings.json is not tagged linguist-generated and not added to .adl-ignore - it is a 5-line generated config, not a TODO placeholder.
Existing projects keep their old GEMINI.md/CLAUDE.md on regenerate - the generator just stops writing them.
Vendored schema descriptions still mention CLAUDE.md/GEMINI.md; they come from upstream inference-gateway/adl.

I did not run task examples:generate in full (only the AI example plus a gemini-enabled manifest), and prettier --check README.md fails both before and after my change, so I left README formatting alone. Risk to know: if a Gemini CLI version older than the context.fileName settings schema is used, it will look for GEMINI.md and find nothing.
| Branch feat/drop-claude-md-template

Co-authored-by: Eden Reich <16985712+edenreich@users.noreply.github.com>

edenreich · 2026-10-15T18:26:34Z

@infer can you address these? why was claude leaving these as-is use /ponytail:ponytail

inference-gateway-maintainer · 2026-10-15T18:27:37Z

Model: ollama_cloud/glm-5.3-flash · Action: v0.56.1 · CLI: v0.229.0 · View Job

Todos

Identify exact leftovers: dockerignore, linguist tag, stale files, schema descriptions
Fix: dockerignore stale entries, gemini linguist tag, validator hint + builtin_config comment, small tests
Run checks, commit, push
File upstream tracking issue for vendored schema descriptions
Apply updated PR body, final verification

Pull Request

#495

✅ Infer Result: Success

All four leftovers are addressed now, pushed as 055ec03 chore(templates): clean up AGENTS.md leftover (task ci green: fmt, lint 0 issues, tests, build, verify-schema).

Why the previous run left them as-is: it judged each one "harmless either way" and documented the reasoning instead of touching code - a judgment call rather than an explicit user request. Fair enough, but the dockerignore entries and the missing linguist tag were fixable at near-zero cost, so they are fixed now, with tests.

.dockerignore: dropped the retired CLAUDE.md/GEMINI.md entries; the list now matches what the generator actually writes (AGENTS.md, plus README/CONFIGURATIONS). Added assertions to TestDockerignoreTemplate_ContainsExpectedExclusions so the retired names can't come back.
.gemini/settings.json: now tagged linguist-generated=true in the generated .gitattributes under the gemini toggle, with a matching assertion in TestGenerator_AI_AllAgentsEnabled. Deliberately still not in .adl-ignore - that file's contract is TODO placeholders users must implement (tool implementations, custom services, bare skills); settings.json has none, same as Taskfile.yml.
Stale CLAUDE.md/GEMINI.md in old projects: still not deleted on regenerate, and that is correct. The generator has no prune pass anywhere in the codebase, and deleting files users may have hand-edited is data loss. Users delete them by hand when they notice.
Vendored schema descriptions (spec.development and spec.development.ai still mention CLAUDE.md): cannot patch here - internal/schema/schema.json is vendored and types.go is regenerated from it, task verify-schema would fail on drift. Filed upstream: inference-gateway/adl#217. Once released, sync with task fetch-schema && task generate-types and bump ADL_SCHEMA_VERSION.
Bonus cleanup the earlier run missed: the pre-v0.8.0 AI migration hint in internal/schema/validator.go and a doc comment in internal/schema/builtin_config.go still said CLAUDE.md - both now say AGENTS.md.

PR body updated to reflect all of this. Skipped: rewriting the two historical comments referencing the original CLAUDE.md-era bug report (they describe what happened, not what generates today), and any prune pass for stale files. Risk: a project that already regenerated while the PR was in flight, then updates dockerignore by rerunning generate, loses the image exclusion for a stale hand-written CLAUDE.md until they delete it.

Model: ollama_cloud/glm-5.3-flash · Action: v0.56.1 · CLI: v0.229.0 · Exit Code: 0 · Duration: 2m 42s

Tokens: 1,902,428 in · 18,287 out · 1,920,715 total (23 requests)

Tool calls: 41 total · 100% success rate

Traces

Session: 1792088884-895ff9f8

session (headless, success)                                                                        2m34s
├── chat ollama_cloud/glm-5.3-flash                                                                 8.4s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       8.4s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     8.3s
│           ╰── POST [inference-gateway, server]                                                    8.3s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 8.3s
├── execute_tool Read call_jvyis2ws                                                                243µs
├── execute_tool Bash call_otvvpaa4                                                                495ms
├── chat ollama_cloud/glm-5.3-flash                                                                12.5s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                      12.5s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]    12.5s
│           ╰── POST [inference-gateway, server]                                                   12.5s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                12.5s
├── execute_tool TodoWrite call_h3qipyho                                                            82µs
├── execute_tool Bash call_yilgdg8x                                                                404ms
├── execute_tool Grep call_a8mu9kcb                                                                272ms
├── chat ollama_cloud/glm-5.3-flash                                                                15.1s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                      15.1s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]    15.1s
│           ╰── POST [inference-gateway, server]                                                   15.1s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                15.1s
├── execute_tool Read call_jyjk2n2k                                                                  1ms
├── execute_tool Read call_e77j918e                                                                763µs
├── execute_tool Read call_ojpf2dx5                                                                780µs
├── execute_tool Read call_qopktkm1                                                                813µs
├── chat ollama_cloud/glm-5.3-flash                                                                 5.0s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       5.0s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     5.0s
│           ╰── POST [inference-gateway, server]                                                    5.0s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 5.0s
├── execute_tool Grep call_zho96o67                                                                 11ms
├── execute_tool Read call_270dhuhm                                                                571µs
├── chat ollama_cloud/glm-5.3-flash                                                                 4.8s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       4.8s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     4.8s
│           ╰── POST [inference-gateway, server]                                                    4.8s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 4.8s
├── execute_tool Grep call_pvnpb0q2                                                                366ms
├── chat ollama_cloud/glm-5.3-flash                                                                10.1s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                      10.0s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]    10.0s
│           ╰── POST [inference-gateway, server]                                                   10.0s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                10.0s
├── execute_tool Read call_q92kkjn0                                                                764µs
├── execute_tool Read call_xni7gs2b                                                                882µs
├── execute_tool Read call_jlhuftof                                                                727µs
├── execute_tool Read call_43w5wngh                                                                688µs
├── chat ollama_cloud/glm-5.3-flash                                                                16.0s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                      16.0s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]    15.9s
│           ╰── POST [inference-gateway, server]                                                   15.9s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                15.9s
├── execute_tool TodoWrite call_oea4qirh                                                            89µs
├── execute_tool Read call_hxg05cbr                                                                562µs
├── execute_tool Edit call_km0msdvn                                                                939µs
├── execute_tool Edit call_6uphf0ry                                                                943µs
├── execute_tool Edit call_bm697rrm                                                                934µs
├── chat ollama_cloud/glm-5.3-flash                                                                 6.4s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       6.3s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     6.3s
│           ╰── POST [inference-gateway, server]                                                    6.3s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 6.3s
├── execute_tool Edit call_5l0kp1v5                                                                  2ms
├── execute_tool Edit call_at4dqs4k                                                                  1ms
├── execute_tool Edit call_tr4nr06f                                                                  1ms
├── chat ollama_cloud/glm-5.3-flash                                                                 2.3s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       2.2s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     2.2s
│           ╰── POST [inference-gateway, server]                                                    2.2s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 2.2s
├── execute_tool TodoWrite call_lhegouhm                                                           175µs
├── execute_tool Bash call_uocqm4kx                                                                12.1s
├── chat ollama_cloud/glm-5.3-flash                                                                11.3s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                      11.3s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]    11.2s
│           ╰── POST [inference-gateway, server]                                                   11.2s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                11.2s
├── execute_tool Bash call_q7it7elc                                                                  6ms
├── chat ollama_cloud/glm-5.3-flash                                                                 2.1s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       2.1s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     2.1s
│           ╰── POST [inference-gateway, server]                                                    2.1s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 2.1s
├── execute_tool Bash call_2kmkr762                                                                  8ms
├── chat ollama_cloud/glm-5.3-flash                                                                 2.2s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       2.1s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     2.1s
│           ╰── POST [inference-gateway, server]                                                    2.1s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 2.1s
├── execute_tool Bash call_vv2mky01                                                                 10ms
├── chat ollama_cloud/glm-5.3-flash                                                                 2.2s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       2.2s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     2.2s
│           ╰── POST [inference-gateway, server]                                                    2.2s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 2.2s
├── execute_tool TodoWrite call_p7bp76kb                                                            48µs
├── execute_tool Bash call_6liqjzga                                                                 1.6s
├── chat ollama_cloud/glm-5.3-flash                                                                 2.7s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       2.7s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     2.6s
│           ╰── POST [inference-gateway, server]                                                    2.6s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 2.6s
├── chat ollama_cloud/glm-5.3-flash                                                                 2.6s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       2.5s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     2.5s
│           ╰── POST [inference-gateway, server]                                                    2.5s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 2.5s
├── execute_tool Bash call_m2vyl4wi                                                                314ms
├── chat ollama_cloud/glm-5.3-flash                                                                 6.9s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       6.9s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     6.8s
│           ╰── POST /proxy/{provider}/{path...} [inference-gateway, server]                        6.8s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 6.8s
├── execute_tool Write call_52off1up                                                                 1ms
├── chat ollama_cloud/glm-5.3-flash                                                                 1.4s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       1.4s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     1.3s
│           ╰── POST [inference-gateway, server]                                                    1.3s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 1.3s
├── execute_tool Bash call_cwi2j45p                                                                 1.7s
├── chat ollama_cloud/glm-5.3-flash                                                                 1.5s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       1.5s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     1.5s
│           ╰── POST [inference-gateway, server]                                                    1.5s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 1.5s
├── execute_tool Bash call_g2ryatc6                                                                451ms
├── chat ollama_cloud/glm-5.3-flash                                                                 4.4s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       4.4s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     4.3s
│           ╰── POST [inference-gateway, server]                                                    4.3s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 4.3s
├── execute_tool Write call_onuqnq41                                                                 1ms
├── chat ollama_cloud/glm-5.3-flash                                                                 2.0s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       2.0s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     1.9s
│           ╰── POST [inference-gateway, server]                                                    1.9s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 1.9s
├── execute_tool TodoWrite call_9b8rq719                                                            63µs
├── execute_tool Bash call_mykd1ro9                                                                 2.1s
├── chat ollama_cloud/glm-5.3-flash                                                                 1.4s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       1.4s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     1.4s
│           ╰── POST [inference-gateway, server]                                                    1.4s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 1.4s
├── execute_tool Bash call_hqk7bm9k                                                                  6ms
├── chat ollama_cloud/glm-5.3-flash                                                                 1.9s
│   ╰── POST /v1/chat/completions [inference-gateway, server]                                       1.9s
│       ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     1.9s
│           ╰── POST [inference-gateway, server]                                                    1.9s
│               ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 1.9s
├── execute_tool TodoWrite call_x2le9msb                                                            60µs
╰── chat ollama_cloud/glm-5.3-flash                                                                 5.0s
    ╰── POST /v1/chat/completions [inference-gateway, server]                                       5.0s
        ╰── POST 127.0.0.1:8080/proxy/ollama_cloud/chat/completions [inference-gateway, client]     5.0s
            ╰── POST [inference-gateway, server]                                                    5.0s
                ╰── POST ollama.com/v1/chat/completions [inference-gateway, client]                 5.0s

Stats

Tool Calls

╭───────────┬───────┬───────┬────────╮
│ Tool      │ Calls │ Fail% │ Avg    │
├───────────┼───────┼───────┼────────┤
│ Bash      │ 12    │ 0%    │ 1602ms │
│ Read      │ 11    │ 0%    │ 781µs  │
│ Edit      │ 6     │ 0%    │ 1ms    │
│ TodoWrite │ 6     │ 0%    │ 56µs   │
│ Grep      │ 3     │ 0%    │ 216ms  │
│ Write     │ 2     │ 0%    │ 1ms    │
╰───────────┴───────┴───────┴────────╯

Token Usage

╭────────────────────────────┬─────────┬─────────┬────────────┬─────────┬──────╮
│ Model                      │ Prompt  │ Cached  │ Completion │ Total   │ Cost │
├────────────────────────────┼─────────┼─────────┼────────────┼─────────┼──────┤
│ ollama_cloud/glm-5.3-flash │ 1902428 │ 1518720 │ 18287      │ 1920715 │ -    │
╰────────────────────────────┴─────────┴─────────┴────────────┴─────────┴──────╯

Sessions

╭───────────┬──────────┬──────────╮
│ Execution │ Mode     │ Sessions │
├───────────┼──────────┼──────────┤
│ headless  │ headless │ 1        │
╰───────────┴──────────┴──────────╯

Triggered by edenreich · Infer Action · OSS

Drop retired CLAUDE.md and GEMINI.md entries from the generated .dockerignore, tag .gemini/settings.json as linguist-generated in .gitattributes, and point the pre-v0.8.0 AI migration hint plus a builtin-tools doc comment at AGENTS.md. Kept on purpose: the generator still does not delete stale CLAUDE.md/GEMINI.md files (it can lose user edits), and .adl-ignore keeps covering only TODO placeholders, so .gemini/settings.json has no ignore entry.

## [0.68.1](v0.68.0...v0.68.1) (2026-10-15) ### ♻️ Improvements * **templates:** generate AGENTS.md for claude code instead of CLAUDE.md ([#495](#495)) ([1755c57](1755c57)) ### 🔧 Miscellaneous * sync ADL schema to v0.29.1 ([#496](#496)) ([78fb5bd](78fb5bd))

inference-gateway-releaser · 2026-10-15T18:53:29Z

🎉 This PR is included in version 0.68.1 🎉

The release is available on:

Your semantic-release bot 📦🚀

feat(templates): generate AGENTS.md for claude code instead of CLAUDE.md

781e868

inference-gateway-maintainer Bot requested a review from a team as a code owner October 15, 2026 18:10

inference-gateway-maintainer Bot and others added 2 commits October 15, 2026 18:20

feat(templates): use AGENTS.md for gemini too

75f71dd

Co-authored-by: Eden Reich <16985712+edenreich@users.noreply.github.com>

feat(templates): drop GEMINI.md template

f8bf287

Co-authored-by: Eden Reich <16985712+edenreich@users.noreply.github.com>

inference-gateway-maintainer Bot mentioned this pull request Oct 15, 2026

[DOCS] Schema descriptions still reference CLAUDE.md and GEMINI.md inference-gateway/adl#217

Closed

3 tasks

edenreich changed the title ~~feat(templates): generate AGENTS.md for claude code instead of CLAUDE.md~~ refactor(templates): generate AGENTS.md for claude code instead of CLAUDE.md Oct 15, 2026

edenreich merged commit 1755c57 into main Oct 15, 2026
5 checks passed

edenreich deleted the feat/drop-claude-md-template branch October 15, 2026 18:35

inference-gateway-maintainer Bot mentioned this pull request Oct 15, 2026

fix(schema): drop CLAUDE.md/GEMINI.md from descriptions inference-gateway/adl#218

Merged

inference-gateway-releaser Bot added the released label Oct 15, 2026

Navigation Menu

Repository navigation

refactor(templates): generate AGENTS.md for claude code instead of CLAUDE.md - #495

refactor(templates): generate AGENTS.md for claude code instead of CLAUDE.md#495
edenreich merged 4 commits into
mainfrom
feat/drop-claude-md-template

inference-gateway-maintainer Bot commented Oct 15, 2026 •

edited

Loading

Uh oh!

edenreich commented Oct 15, 2026 •

edited

Loading

Uh oh!

inference-gateway-maintainer Bot commented Oct 15, 2026 •

edited

Loading

Uh oh!

edenreich commented Oct 15, 2026

Uh oh!

inference-gateway-maintainer Bot commented Oct 15, 2026 •

edited

Loading

Uh oh!

Uh oh!

inference-gateway-releaser Bot commented Oct 15, 2026

Uh oh!

Reviewers

Uh oh!

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Conversation

inference-gateway-maintainer Bot commented Oct 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Notes

Testing

Uh oh!

edenreich commented Oct 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

inference-gateway-maintainer Bot commented Oct 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

GEMINI.md dropped - every orchestrator now reads AGENTS.md

One thing I added on purpose

Left as-is

Uh oh!

edenreich commented Oct 15, 2026

Uh oh!

inference-gateway-maintainer Bot commented Oct 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Todos

Pull Request

✅ Infer Result: Success

Uh oh!

Uh oh!

inference-gateway-releaser Bot commented Oct 15, 2026

Uh oh!

Reviewers

Uh oh!

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

inference-gateway-maintainer Bot commented Oct 15, 2026 •

edited

Loading

edenreich commented Oct 15, 2026 •

edited

Loading

inference-gateway-maintainer Bot commented Oct 15, 2026 •

edited

Loading

inference-gateway-maintainer Bot commented Oct 15, 2026 •

edited

Loading