Regenerate tools: the A-Z insider directory was missing - #36
Merged
Merged
Conversation
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
codegen:check has been failing on main with real content drift, not the documented Windows CRLF false positive — the diff body was populated. The backend shipped GET /v1/insiders/directory in insiderapi #238 and the MCP never picked it up, so the one channel that reaches the most users was a tool short. Regenerating adds exactly that: 19 tools to 20, seventeen insertions, nothing removed or changed. The tool browses insiders alphabetically by surname and returns one row per FILER GROUP, which is the part of #238 worth having here — a fund group files a single Form 4 listing several reporting owners, and listing each separately spent about 11% of a capped surface describing the same actors more than once. mcp-test.mjs pins the registered tool count, so it moves 35 to 36, and get_insider_directory joins EXPECTED_TOOLS rather than only being counted. Not released. Publishing is a separate step and needs a version bump.
theodor90
force-pushed
the
codegen-insider-directory
branch
from
August 25, 2026 12:59
586df95 to
464b2b1
Compare
Merged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
codegen:checkhas been failing onmainwith real content drift — not the documented Windows CRLF false positive. The diff body was populated, which is the distinguishing signal.The backend shipped
GET /v1/insiders/directoryin insiderapi #238 and the MCP never picked it up, so the channel with the widest reach (MCP downloads run ~2.7× the SDKs) was a tool short.What regenerating changes
Exactly one tool. 19 → 20, seventeen insertions, nothing removed or modified:
The tool browses insiders alphabetically by surname and returns one row per filer group — the part of #238 worth having here. A fund group files a single Form 4 listing several reporting owners (the fund, its GP, its management company), each a real EDGAR filer with its own CIK; listing all of them spent about 11% of a capped surface describing the same actors more than once.
Test
mcp-test.mjspins the registered tool count, so it moves 35 → 36.get_insider_directoryalso joinsEXPECTED_TOOLS, so it's asserted present by name rather than only counted — a count alone would pass if some other tool appeared and this one didn't.Verification
codegen:checknow reports in sync with the live OpenAPI spec, and re-run after committing it stays clean — so this is not the CRLF artefact reappearing.GENERATED_TOOLSis consumed by a loop insrc/index.ts, so the new tool registers with no wiring change.Not released
Publishing is a separate step and needs a version bump — this only makes the repo match the spec.