eeymoo/claw-code
1
0
Fork 0
mirror of https://github.com/instructkr/claw-code.git synced 2026-04-28 00:14:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

roadmap: #225 filed — Audio API typed taxonomy is structurally absent: zero /v1/audio/transcriptions + zero /v1/audio/translations + zero /v1/audio/speech endpoint surface across both Anthropic-native and OpenAI-compat lanes, zero TranscriptionRequest / SpeechRequest / AudioVoice / AudioFormat / AudioMediaType / AudioSource / Modality / AudioRequestConfig / SpeechResponse / TranscriptionResponse typed model in rust/crates/api/src/types.rs, zero Audio variant on InputContentBlock (3-arm exhaustive: Text/ToolUse/ToolResult), zero Audio variant on OutputContentBlock (4-arm exhaustive: Text/ToolUse/Thinking/RedactedThinking), zero modalities/audio fields on MessageRequest for gpt-4o-audio request-side opt-in, zero transcribe/translate/synthesize_speech methods on Provider trait at rust/crates/api/src/providers/mod.rs:17-30 (only send_message + stream_message exist), zero audio dispatch on ProviderClient enum at rust/crates/api/src/client.rs:8-14 (three variants Anthropic/Xai/OpenAi, zero Whisper/ElevenLabs/Cartesia/Deepgram/AssemblyAI/Speechmatics partner-routing variants), zero multipart/form-data upload affordance with reqwest::multipart feature flag absent from rust/crates/api/Cargo.toml (rg returns zero hits for multipart across rust/), zero claw audio/transcribe/speak/tts/whisper CLI subcommand at rust/crates/rusty-claude-cli/src/main.rs, zero /transcribe/whisper/tts slash command, AND the existing /voice + /listen + /speak slash commands at rust/crates/commands/src/lib.rs:295-301+603-609+610-616 advertise audio-capability summaries but are all gated under STUB_COMMANDS at rust/crates/rusty-claude-cli/src/main.rs:8333+8388+8389 (advertised-but-unbuilt shape ×3, the largest single-pinpoint advertised-but-unbuilt slash-command count catalogued, strict-superset of #220's /image+/screenshot ×2 and #223's /files ×1), zero whisper-1/tts-1/tts-1-hd/gpt-4o-audio-preview/gpt-4o-realtime-preview/gpt-4o-mini-tts/gpt-4o-mini-transcribe entries in MODEL_REGISTRY, zero audio_input_per_minute/audio_output_per_minute/tts_per_million_chars/whisper_per_minute fields in ModelPricing struct (rust/crates/runtime/src/usage.rs:9-15 has only four text-token-only fields), zero audio-model recognition in pricing_for_model substring-matcher (#209+#224 cluster overlap) — uniquely manifesting a fusion shape combining #223's transport-plumbing-absence (multipart/form-data) + #224's provider-asymmetric-delegation (Anthropic does not offer audio at all per docs.anthropic.com/audio explicitly recommending AssemblyAI/Deepgram/OpenAI-Whisper, OpenAI offers GA whisper-1+tts-1+tts-1-hd+gpt-4o-audio-preview+gpt-4o-realtime-preview+gpt-4o-mini-tts+gpt-4o-mini-transcribe, Google Gemini Live API offers bidirectional audio modality, six-plus recommended partners ElevenLabs/Cartesia/PlayHT/Deepgram/AssemblyAI/Speechmatics) + #220's advertised-but-unbuilt-slash-commands (×3, the largest count catalogued) + #218's modalities-request-side-absence (gpt-4o-audio-preview's modalities:[text,audio] opt-in) + symmetric-input-output content-block-taxonomy axis (#225's first-of-its-kind contribution to the cluster doctrine since prior members have either input-only [#220] or output-only [#214,#224] or stateless [#221/#222/#223] modality coverage) — making #225 the first cluster member where four independent prior shape-axes converge in a single pinpoint and the largest fusion-shape gap catalogued so far (Jobdori cycle #377 / extends #168c emission-routing audit / explicit follow-on candidate from #224's provider-asymmetric-delegation shape — the first-named of two named candidates: Audio API typed taxonomy (this pinpoint #225) / Image-generation API typed taxonomy (open candidate for #226), Audio chosen because it inherits #223's multipart-transport-plumbing dimension that Image-generation does not — the multipart sibling of #223 that the cycle hint explicitly identifies / sibling-shape cluster grows to twenty-four / wire-format-parity cluster grows to fifteen / capability-parity cluster grows to seven / multimodal-IO cluster grows to three: #220 input-only + #224 output-only + #225 full-duplex-bidirectional / advertised-but-unbuilt cluster grows to four / multipart-transport cluster grows to two / provider-asymmetric-delegation cluster grows to two / nine-layer-fusion-shape (endpoint-URL-set-of-three + multipart-form-data-transport-plumbing + data-model-taxonomy-with-input-AND-output-content-blocks + modalities-request-side-opt-in + Provider-trait-method-set-of-three-with-Unsupported-fallback + ProviderClient-enum-dispatch-with-six-partner-third-lanes + advertised-but-unbuilt-slash-commands-×3 + CLI-subcommand-surface + pricing-tier-with-per-minute-and-per-million-chars-and-per-million-audio-tokens-compound-cost-model) is the largest single-pinpoint fusion catalogued / external validation: forty-seven ecosystem references covering three first-class audio-endpoint specs on OpenAI side, one Anthropic non-coverage statement, one Google Gemini Live API spec, six first-class STT providers, six first-class TTS providers, one full-duplex bidirectional-audio endpoint OpenAI /v1/realtime, three first-class CLI/SDK typed-surface implementations, six first-class local-audio-providers, one community-maintained Common Voice benchmark, seven coding-agent peers with audio capability, one canonical Anthropic-recommended three-partner-set / claw-code is the sole client/agent/CLI with zero /v1/audio/{transcriptions,translations,speech} integration AND zero ElevenLabs/Cartesia/Deepgram/AssemblyAI/Speechmatics/Whisper partner-routing AND three advertised-but-unbuilt slash commands AND zero modalities request-side opt-in AND zero Audio content-block taxonomy variant on either input or output side AND zero multipart-form-data transport plumbing for audio uploads — all six gaps unique to claw-code in the surveyed ecosystem)

Browse Source
This commit is contained in:
YeonGyu-Kim
2026-04-26 03:47:33 +09:00
parent e857c76e4a
commit 24ed7f280a
1 changed files with 137 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

137
ROADMAP.md
View File

File diff suppressed because one or more lines are too long