andy/noema
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(llm): Amazon Bedrock provider over a standard-library SigV4 signer

Browse Source 
Kind `bedrock` speaks the Converse API for chat roles and InvokeModel for
Titan and Cohere embeddings. Requests are signed with AWS Signature
Version 4 implemented with crypto/hmac and crypto/sha256 only; the signer
is pinned by tests to signatures botocore produces for the same requests,
with and without a session token, so drift fails the build.

The credential is one secret reference, ACCESS_KEY_ID:SECRET_ACCESS_KEY
[:SESSION_TOKEN], encrypted together like every other provider key. The
region is read from the endpoint host, which must be a Bedrock runtime
host over HTTPS unless private endpoints are explicitly allowed; other
hosts are refused. Provider errors are scrubbed of the secret and token.

Migration 0024 widens the provider kind constraint; existing rows are
untouched and the down migration refuses while bedrock rows exist rather
than dropping configuration. UI kind selects, docs/llm-providers.md,
ADR-0010, ARCHITECTURE and the changelog are updated.
This commit is contained in:
Andy Dixon
2026-08-24 22:03:48 +01:00
parent 7d608c2783
commit f165adc5f2
14 changed files with 497 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ARCHITECTURE.md
+1 -1
View File
@@ -95,7 +95,7 @@ A **belief** is a proposition with `status` (hypothesis → tentative → likely
## 8. Language models and prompts
`internal/llm` defines `LanguageModel` and `Embedder` interfaces. Providers (OpenAI-compatible, Anthropic, Ollama/llama.cpp; Bedrock behind the same interface later) are configured in the database with secret *references*, not secrets. **Roles** (classify, extract, hypothesise, summarise, narrate, respond, embed…) map to a primary model and fallbacks. Every call is recorded (`llm_request`/`llm_response` events plus `llm_calls` with prompt version, parameters, seed, usage, latency, cost) for inspection and replay.
`internal/llm` defines `LanguageModel` and `Embedder` interfaces. Providers (OpenAI-compatible, Anthropic, Ollama/llama.cpp, Amazon Bedrock via a standard-library SigV4 signer) are configured in the database with secret *references*, not secrets. **Roles** (classify, extract, hypothesise, summarise, narrate, respond, embed…) map to a primary model and fallbacks. Every call is recorded (`llm_request`/`llm_response` events plus `llm_calls` with prompt version, parameters, seed, usage, latency, cost) for inspection and replay.
Prompts are named and versioned rows; templates receive structured data. Untrusted content is passed in clearly delimited data blocks with an explicit instruction that it is data, and model output is parsed into typed JSON and validated. Model output never becomes an action without passing through the capability layer, and never becomes a belief without an evidence link.