public/galaxy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add unified models UI and Rig Bedrock runtime

Browse Source
This commit is contained in:
rkw6086
2026-08-04 17:25:19 -05:00
parent a3c68e9c30
commit b0ad07f6f2
41 changed files with 2122 additions and 564 deletions
Download Patch File Download Diff File Expand all files Collapse all files
plans/galaxy-local-first-rig.md
+24 -7
View File
@@ -336,9 +336,26 @@ rendering and non-Rig compatibility runtimes, not in Rig's executable tool path.
### Phase 4 — Bedrock through Rig
- Implement Bedrock client construction and model resolution through `rig-bedrock`.
- Compare request behavior for system prompts, images, tool schemas, cache controls, reasoning,
inference profiles, token usage, and context limits.
- [x] Pin `rig-bedrock` 0.40.0 and construct it from Galaxy's already-resolved AWS SDK client so
profile, SSO, static-key, region, and egress ownership stay at Galaxy's explicit boundary.
- [x] Resolve context markers, ARNs, existing inference profiles, and regional inference-profile
prefixes before passing a model ID to Rig.
- [x] Reuse one Galaxy-to-Rig request adapter and one Rig-to-`AgentEvent` streaming lifecycle for
OpenAI-compatible and Bedrock providers; handle Bedrock's required base64 image representation at
that single request boundary.
- [x] Add hermetic compatibility fixtures for system prompts, images, tool calls/results, cache
enablement, cancellation, inference profiles, token limits, usage/cache usage, and max-token stop
normalization without contacting AWS.
- [x] Preserve signed Bedrock reasoning blocks in Galaxy conversation history so adaptive-thinking
tool-call turns can be replayed without losing their signatures.
- [x] Define the Rig 0.40 parity policy: Galaxy retains structured tool-result error state locally
and sends an explicit `[ERROR]` result prefix because Rig core has no Bedrock status field;
Rig owns system/message cache checkpoints, tool-schema caching is treated as an optimization,
and one-hour cache-TTL requests stay on the compatibility runtime.
- [x] Add a model-by-model Rig switch to the unified Models page and route opted-in Bedrock models
through the same request, event, permission, history, and UI adapter as OpenAI-compatible models.
- [ ] Run opt-in live semantic comparisons for system prompts, images, tools, reasoning, usage, and
context limits before selecting the Rig runtime for any configured Bedrock model.
- Keep a short-lived compatibility fallback for unsupported Bedrock behavior, measured by tests.
- Delete custom Bedrock translation code only after parity is proven.
@@ -418,7 +435,7 @@ contract is what the UI and persistence observe.
## Immediate next vertical slice
Begin Phase 4 with a focused `rig-bedrock` compatibility spike. Establish client construction and
model/inference-profile resolution first, then add semantic parity fixtures for system prompts,
images, tool schemas, cache controls, reasoning, usage, and context limits before routing any
configured Bedrock model away from the existing compatibility implementation.
Finish Phase 4 with opt-in live Bedrock semantic comparisons for system prompts, images, tools,
signed reasoning, usage, cancellation, and context limits. Keep per-model Rig routing opt-in until
those live fixtures pass, then make Rig the default for supported models and retain the compatibility
runtime only for explicitly unsupported cache behavior.