gut(media): remove media-understanding and link-understanding pipelines#514
Merged
alexey-pelykh merged 1 commit intomainfrom Mar 9, 2026
Merged
Conversation
…es (#425) Middleware should not process media/links itself — CLI runtimes (Claude, Gemini, Codex) handle their own media understanding. STT remains as channel-level infrastructure. - Delete src/media-understanding/ (55 files, ~6200 lines) - Delete src/link-understanding/ (6 files) - Inline STT provider utilities from media-understanding into src/stt/ - Rewrite stt/preflight.ts to use STT's own transcribeAudioWithProvider - Simplify discord voice transcription to delegate to stt/preflight - Remove applyMediaUnderstanding/applyLinkUnderstanding from get-reply - Remove MediaUnderstanding/LinkUnderstanding from MsgContext type - Remove mediaDecisions from status display and command handlers - Remove image/video/links config types, Zod schemas, help, and labels - Keep tools.media.audio config path (used by STT) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2481cea to
7651c4c
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
src/media-understanding/(55 files, ~5500 lines) — the image/video/audio understanding pipeline that processed media via AI providers (Anthropic, OpenAI, Google, etc.)src/link-understanding/(6 files, ~700 lines) — the URL fetching and summarization pipelinesrc/stt/) as channel-level infrastructure, inlining shared utilities that were previously imported from media-understandingMediaUnderstandingConfig/MediaUnderstandingModelConfigof scope/capabilities/attachments fields, keeps only what STT needsRationale
RemoteClaw is middleware, not a platform. Media and link understanding are agent-level concerns — CLI runtimes (Claude, Gemini, Codex, OpenCode) handle them natively. STT/TTS remain because they're channel-level infrastructure (converting voice messages to text before routing to the agent).
Part of #415 (gut dead upstream subsystems).
Closes #425
Impact
MsgContexttype: removedMediaUnderstanding,MediaUnderstandingDecisions,LinkUnderstandingfieldstools.links.*,tools.media.image.*,tools.media.video.*, narrowedtools.media.audio.*/statuscommand: no longer shows media understanding decisionsTest plan
pnpm buildpassespnpm formatpassespnpm tsgopassespnpm lintpassespnpm testpasses (3 pre-existing failures inupdate-cli.test.tsunrelated to this PR)🤖 Generated with Claude Code