Repository navigation
bump schema, add new verbs, regen sdk - #10
Merged
Merged
Conversation
davehorton
approved these changes
Oct 14, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The SDK was pinned to jambonz schema v0.3.8; upstream is now v0.4.23. I bumped the pin, re-synced all schemas, regenerated the pydantic models and type stubs, and wired up the new verbs.
New features now supported
5 new verbs (registry entries added in verb_registry.py):
transfer — blind/warm transfer with built-in failure handling
room — synonym for conference (Voice-AI-friendly name)
gptlive_s2s, qwen_s2s, voicelive_s2s — three new speech-to-speech vendors
New/updated components (auto-generated): handoff, hangup, transferOptions, 4 new recognizer vendors (xai, zoom, gradium, modulate), plus new fields across existing verbs — notably agent gained handoff, hangup, toolFiller, mcpServers, noiseIsolation, earlyGeneration and a properly-typed inline llm. Removed upstream: cobalt/nuance/verbio recognizers.
Three codegen fixes the version jump required
Conference verb enum — upstream changed verb from a const to enum: ["conference","room"]. The code generator mishandled this, emitting a broken Literal["conference#"] field that silently broke the whole Conference model. Added a VERB_ENUM_FIXUPS post-gen patch in regen_models.py to repair it.
Model registry — taught src/jambonz_sdk/_models/_registry.py to index a model under every literal verb value, so room resolves to the Conference model (validates against the conference shape, serializes verb: "room").
Public re-exports — broadened the export heuristic so Transfer/Handoff (which subclass TransferOptions, not JambonzModel directly) are exported.
Also removed a now-obsolete Agent.llm override and updated README/AGENTS.md verb lists.
Verification
311 tests pass (was 291; +20 for the new verbs), ruff clean on src/+tests/
Confirmed serialization: conference→verb:"conference", room→verb:"room", transfer→verb:"transfer", all with validation (unknown fields rejected)
The public export diff matches the schema changes exactly — no existing exports dropped or renamed
One note: mypy strict reports more errors than before (72 vs a pre-existing baseline of 31), but all new ones are in auto-generated vendor files — the same patterns mypy already flagged at baseline. None are in the hand-written code I edited (those two files are mypy-clean). mypy strict was never green on generated code in this repo.