LCORE-870: Add AWS Bedrock inference provider support#1449
Merged
Conversation
- Updated documentation - Added AWS Bedrock e2e test - Patched other providers e2e test (missing mcp)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Contributor
WalkthroughAdds AWS Bedrock as a supported inference provider: updates CI matrix and secrets, exposes Bedrock credential vars in Docker Compose, documents Bedrock in README/docs, and introduces example and e2e runtime configs for Bedrock-based setups plus a small test config tweak. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes 🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
✨ Simplify code
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 5
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@examples/bedrock-run.yaml`:
- Around line 54-57: The YAML currently contains a placeholder secret
openai_api_key: '********' which is not runnable; update the provider config
(provider_id/provider_type config block) to load the Braintrust key from an
environment variable instead of a literal placeholder (e.g., reference a
BRAINTRUST/OpenAI API env var in the config for openai_api_key) so the
scoring-provider can initialize at runtime; ensure the env var name is
documented or matches your runtime secrets naming convention.
- Around line 137-157: The default_embedding_model (provider_id:
sentence-transformers, model_id: nomic-ai/nomic-embed-text-v1.5) referenced
under vector_stores must be registered in the models list so embeddings can
resolve; add a models entry (e.g., model_id: nomic-embed-text-v1.5 or matching
identifier) with provider_id: sentence-transformers, model_type: embedding (or
llm if your schema requires model_type) and provider_model_id set to
nomic-ai/nomic-embed-text-v1.5 so that default_embedding_model points to a
registered resource (update the existing models array near the top that contains
custom-bedrock-model).
In `@README.md`:
- Line 216: Update the compatibility table entry that currently lists the
Bedrock model as deepseek.v3-v1 to use the exact tested model identifier
deepseek.v3-v1:0 so it matches the runnable configs (see
examples/bedrock-run.yaml and tests/e2e/configs/run-bedrock.yaml which use
deepseek.v3-v1:0); change the table cell value to deepseek.v3-v1:0 to avoid
copy/paste misconfiguration.
In `@tests/e2e/configs/run-bedrock.yaml`:
- Around line 54-57: The E2E config contains a hardcoded placeholder credential
for openai_api_key; replace the literal '********' under the provider config
(provider_id/provider_type/config/openai_api_key) with an environment-backed
reference so tests remain runnable in CI (e.g., read from OPENAI_API_KEY or the
project's secret/template mechanism), and update any test harness or docs to
require that environment variable.
- Around line 137-157: The default_embedding_model referenced by vector_stores
(provider_id: sentence-transformers, model_id: nomic-ai/nomic-embed-text-v1.5)
is not registered in registered_resources.models; add a matching model
registration entry to registered_resources.models with the same provider_id and
model_id (and set model_type to an embedding type if your schema uses one) so
the RAG toolgroup (toolgroup_id: builtin::rag) can resolve embeddings at
runtime.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro
Run ID: 30e53654-7079-452e-b5b6-a413864b57ce
📒 Files selected for processing (8)
.github/workflows/e2e_tests_providers.yamlREADME.mddocker-compose-library.yamldocker-compose.yamldocs/providers.mdexamples/bedrock-run.yamltests/e2e/configs/run-bedrock.yamltests/e2e/configs/run-rhelai.yaml
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (5)
- GitHub Check: build-pr
- GitHub Check: E2E: server mode / ci
- GitHub Check: E2E Tests for Lightspeed Evaluation job
- GitHub Check: E2E: library mode / ci
- GitHub Check: Konflux kflux-prd-rh02 / lightspeed-stack-on-pull-request
🧰 Additional context used
🧠 Learnings (1)
📚 Learning: 2025-12-18T10:21:09.038Z
Learnt from: are-ces
Repo: lightspeed-core/lightspeed-stack PR: 935
File: run.yaml:114-115
Timestamp: 2025-12-18T10:21:09.038Z
Learning: In Llama Stack version 0.3.x, telemetry provider configuration is not supported under the `providers` section in run.yaml configuration files. Telemetry can be enabled with just `telemetry.enabled: true` without requiring an explicit provider block.
Applied to files:
examples/bedrock-run.yamltests/e2e/configs/run-bedrock.yaml
🔇 Additional comments (5)
tests/e2e/configs/run-rhelai.yaml (1)
57-59: Good addition for MCP tool runtime coverage.Adding
model-context-protocolhere keeps this E2E config aligned with MCP-enabled test scenarios.docs/providers.md (1)
40-40: Bedrock support table update looks consistent.The row now reflects actual project support state introduced in this PR.
.github/workflows/e2e_tests_providers.yaml (1)
16-16: Matrix + secret wiring for Bedrock is correctly plumbed.The Bedrock environment is added to test coverage, and the token is propagated in both deployment modes.
Also applies to: 200-200, 232-232
docker-compose.yaml (1)
67-68: Bedrock token env injection in server-mode compose is correct.This enables Bedrock credential propagation into the
llama-stackservice.docker-compose-library.yaml (1)
73-74: Library-mode compose Bedrock env wiring looks good.This keeps credential propagation consistent across both deployment modes.
Comment on lines
+54
to
+57
| - provider_id: braintrust | ||
| provider_type: inline::braintrust | ||
| config: | ||
| openai_api_key: '********' |
Contributor
There was a problem hiding this comment.
Replace placeholder Braintrust key with env-based configuration.
openai_api_key: '********' is not runnable configuration and may fail scoring-provider initialization/use.
🔐 Proposed fix
- provider_id: braintrust
provider_type: inline::braintrust
config:
- openai_api_key: '********'
+ openai_api_key: ${env.OPENAI_API_KEY}🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@examples/bedrock-run.yaml` around lines 54 - 57, The YAML currently contains
a placeholder secret openai_api_key: '********' which is not runnable; update
the provider config (provider_id/provider_type config block) to load the
Braintrust key from an environment variable instead of a literal placeholder
(e.g., reference a BRAINTRUST/OpenAI API env var in the config for
openai_api_key) so the scoring-provider can initialize at runtime; ensure the
env var name is documented or matches your runtime secrets naming convention.
| | Azure | gpt-5-chat, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, o1-mini | No or limited | remote::azure | | | ||
| | VertexAI | google/gemini-2.0-flash, google/gemini-2.5-flash, google/gemini-2.5-pro [^1] | Yes | remote::vertexai | [1](examples/vertexai-run.yaml) | | ||
| | WatsonX | meta-llama/llama-3-3-70b-instruct | Yes | remote::watsonx | [1](examples/watsonx-run.yaml) | | ||
| | AWS Bedrock | deepseek.v3-v1 | Yes | remote::bedrock | [1](examples/bedrock-run.yaml) | |
Contributor
There was a problem hiding this comment.
Use the exact tested Bedrock model identifier in compatibility table.
Line 216 lists deepseek.v3-v1, but the actual runnable configs use deepseek.v3-v1:0 (examples/bedrock-run.yaml Line 141 and tests/e2e/configs/run-bedrock.yaml Line 141). Aligning this avoids copy/paste misconfiguration.
📝 Suggested doc fix
-| AWS Bedrock | deepseek.v3-v1 | Yes | remote::bedrock | [1](examples/bedrock-run.yaml) |
+| AWS Bedrock | deepseek.v3-v1:0 | Yes | remote::bedrock | [1](examples/bedrock-run.yaml) |📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| | AWS Bedrock | deepseek.v3-v1 | Yes | remote::bedrock | [1](examples/bedrock-run.yaml) | | |
| | AWS Bedrock | deepseek.v3-v1:0 | Yes | remote::bedrock | [1](examples/bedrock-run.yaml) | |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@README.md` at line 216, Update the compatibility table entry that currently
lists the Bedrock model as deepseek.v3-v1 to use the exact tested model
identifier deepseek.v3-v1:0 so it matches the runnable configs (see
examples/bedrock-run.yaml and tests/e2e/configs/run-bedrock.yaml which use
deepseek.v3-v1:0); change the table cell value to deepseek.v3-v1:0 to avoid
copy/paste misconfiguration.
Comment on lines
+54
to
+57
| - provider_id: braintrust | ||
| provider_type: inline::braintrust | ||
| config: | ||
| openai_api_key: '********' |
Contributor
There was a problem hiding this comment.
Avoid non-runnable placeholder credentials in E2E config.
openai_api_key: '********' should be environment-backed to keep this config executable and deterministic in CI.
🔐 Proposed fix
- provider_id: braintrust
provider_type: inline::braintrust
config:
- openai_api_key: '********'
+ openai_api_key: ${env.OPENAI_API_KEY}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| - provider_id: braintrust | |
| provider_type: inline::braintrust | |
| config: | |
| openai_api_key: '********' | |
| - provider_id: braintrust | |
| provider_type: inline::braintrust | |
| config: | |
| openai_api_key: ${env.OPENAI_API_KEY} |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@tests/e2e/configs/run-bedrock.yaml` around lines 54 - 57, The E2E config
contains a hardcoded placeholder credential for openai_api_key; replace the
literal '********' under the provider config
(provider_id/provider_type/config/openai_api_key) with an environment-backed
reference so tests remain runnable in CI (e.g., read from OPENAI_API_KEY or the
project's secret/template mechanism), and update any test harness or docs to
require that environment variable.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
.github/workflows/e2e_tests_providers.yaml (1)
200-232:⚠️ Potential issue | 🟡 MinorFail fast if Bedrock credentials are missing.
Line 200 and Line 232 pass
AWS_BEARER_TOKEN_BEDROCK, but there’s no upfront validation step (unlike VertexAI). Add a guard to avoid late test failures with less actionable logs.🔧 Proposed fix
+ - name: Validate Bedrock credentials + if: matrix.environment == 'bedrock' + env: + AWS_BEARER_TOKEN_BEDROCK: ${{ secrets.AWS_BEARER_TOKEN_BEDROCK }} + run: | + if [ -z "$AWS_BEARER_TOKEN_BEDROCK" ]; then + echo "❌ AWS_BEARER_TOKEN_BEDROCK is not set. Configure it in repository secrets." + exit 1 + fi + echo "✅ Bedrock credential is configured" + - name: Run services (Server Mode)🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.github/workflows/e2e_tests_providers.yaml around lines 200 - 232, Add an explicit guard that fails fast when the AWS_BEARER_TOKEN_BEDROCK secret is missing: in the workflow step that sets AWS_BEARER_TOKEN_BEDROCK (the "Run services (Library Mode)" / preceding run: block where docker compose is started), detect if the OPENAI_API_KEY and AWS_BEARER_TOKEN_BEDROCK env vars are empty and exit with a clear error if AWS_BEARER_TOKEN_BEDROCK is not provided; update the run block that contains docker compose up -d to perform this check before starting services so tests don’t proceed with missing Bedrock credentials.
♻️ Duplicate comments (2)
examples/bedrock-run.yaml (1)
54-57:⚠️ Potential issue | 🟡 MinorReplace placeholder Braintrust key with an environment variable.
Line 57 hardcodes
'********', which is not executable configuration.🔐 Proposed fix
- provider_id: braintrust provider_type: inline::braintrust config: - openai_api_key: '********' + openai_api_key: ${env.OPENAI_API_KEY}🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@examples/bedrock-run.yaml` around lines 54 - 57, Replace the hardcoded placeholder openai_api_key value in the provider config block (provider_id/provider_type/config -> openai_api_key) with an environment variable reference (e.g., use a YAML env substitution or template such as ${BRAINTRUST_API_KEY}) so real credentials are not committed; update any README or runtime docs to instruct setting BRAINTRUST_API_KEY in the environment before running.tests/e2e/configs/run-bedrock.yaml (1)
54-57:⚠️ Potential issue | 🟡 MinorReplace placeholder Braintrust key with env-backed configuration.
Line 57 uses a literal placeholder (
'********'), which makes this config non-runnable in CI/runtime.🔐 Proposed fix
- provider_id: braintrust provider_type: inline::braintrust config: - openai_api_key: '********' + openai_api_key: ${env.OPENAI_API_KEY}🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@tests/e2e/configs/run-bedrock.yaml` around lines 54 - 57, The config currently hardcodes openai_api_key as a literal placeholder ('********'); update the provider config (provider_id/provider_type block) so openai_api_key is read from an environment-backed value instead of a literal—replace the placeholder with an env variable reference used by our test harness (e.g., a ${BRAINTRUST_API_KEY}-style reference or equivalent in your YAML loader) and ensure any test setup/export uses that BRAINTRUST_API_KEY env var so the tests can run in CI/runtime.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@examples/bedrock-run.yaml`:
- Around line 1-163: The example and e2e Bedrock YAMLs have diverged;
consolidate them by extracting the shared manifest into a single template and
updating both consumers to render from that template (e.g., create a canonical
template for the top-level keys like version, providers, registered_resources,
vector_stores and have examples/bedrock-run and the e2e run-bedrock config
generated from it), or add a CI diff check that compares the generated output
against the committed files and fails if they differ; implement template
generation (or CI check) and update any build/test scripts that reference the
current static files to use the new template/render step so the configs stay in
sync.
---
Outside diff comments:
In @.github/workflows/e2e_tests_providers.yaml:
- Around line 200-232: Add an explicit guard that fails fast when the
AWS_BEARER_TOKEN_BEDROCK secret is missing: in the workflow step that sets
AWS_BEARER_TOKEN_BEDROCK (the "Run services (Library Mode)" / preceding run:
block where docker compose is started), detect if the OPENAI_API_KEY and
AWS_BEARER_TOKEN_BEDROCK env vars are empty and exit with a clear error if
AWS_BEARER_TOKEN_BEDROCK is not provided; update the run block that contains
docker compose up -d to perform this check before starting services so tests
don’t proceed with missing Bedrock credentials.
---
Duplicate comments:
In `@examples/bedrock-run.yaml`:
- Around line 54-57: Replace the hardcoded placeholder openai_api_key value in
the provider config block (provider_id/provider_type/config -> openai_api_key)
with an environment variable reference (e.g., use a YAML env substitution or
template such as ${BRAINTRUST_API_KEY}) so real credentials are not committed;
update any README or runtime docs to instruct setting BRAINTRUST_API_KEY in the
environment before running.
In `@tests/e2e/configs/run-bedrock.yaml`:
- Around line 54-57: The config currently hardcodes openai_api_key as a literal
placeholder ('********'); update the provider config (provider_id/provider_type
block) so openai_api_key is read from an environment-backed value instead of a
literal—replace the placeholder with an env variable reference used by our test
harness (e.g., a ${BRAINTRUST_API_KEY}-style reference or equivalent in your
YAML loader) and ensure any test setup/export uses that BRAINTRUST_API_KEY env
var so the tests can run in CI/runtime.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro
Run ID: 1a37577b-e11e-4312-9938-bc6f74c58185
📒 Files selected for processing (3)
.github/workflows/e2e_tests_providers.yamlexamples/bedrock-run.yamltests/e2e/configs/run-bedrock.yaml
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (4)
- GitHub Check: E2E: library mode / ci
- GitHub Check: build-pr
- GitHub Check: E2E: server mode / ci
- GitHub Check: E2E Tests for Lightspeed Evaluation job
🧰 Additional context used
🧠 Learnings (1)
📚 Learning: 2025-12-18T10:21:09.038Z
Learnt from: are-ces
Repo: lightspeed-core/lightspeed-stack PR: 935
File: run.yaml:114-115
Timestamp: 2025-12-18T10:21:09.038Z
Learning: In Llama Stack version 0.3.x, telemetry provider configuration is not supported under the `providers` section in run.yaml configuration files. Telemetry can be enabled with just `telemetry.enabled: true` without requiring an explicit provider block.
Applied to files:
tests/e2e/configs/run-bedrock.yamlexamples/bedrock-run.yaml
🔇 Additional comments (2)
.github/workflows/e2e_tests_providers.yaml (1)
16-16: Bedrock matrix wiring looks correct.
bedrockis correctly added to the environment matrix and aligns with the existingrun-${environment}.yamlselection flow.tests/e2e/configs/run-bedrock.yaml (1)
142-147: Embedding model mapping is now internally consistent.
vector_stores.default_embedding_modelpoints toall-mpnet-base-v2, and that model is registered underregistered_resources.models.Also applies to: 161-163
Comment on lines
+1
to
+163
| version: 2 | ||
|
|
||
| apis: | ||
| - agents | ||
| - batches | ||
| - datasetio | ||
| - eval | ||
| - files | ||
| - inference | ||
| - safety | ||
| - scoring | ||
| - tool_runtime | ||
| - vector_io | ||
|
|
||
| benchmarks: [] | ||
| datasets: [] | ||
| image_name: starter | ||
| # external_providers_dir: /opt/app-root/src/.llama/providers.d | ||
|
|
||
| providers: | ||
| inference: | ||
| - config: | ||
| api_key: ${env.AWS_BEARER_TOKEN_BEDROCK} | ||
| region_name: us-east-2 | ||
| provider_id: aws-bedrock | ||
| provider_type: remote::bedrock | ||
| - provider_id: openai | ||
| provider_type: remote::openai | ||
| config: | ||
| api_key: ${env.OPENAI_API_KEY} | ||
| - config: {} | ||
| provider_id: sentence-transformers | ||
| provider_type: inline::sentence-transformers | ||
| files: | ||
| - config: | ||
| metadata_store: | ||
| table_name: files_metadata | ||
| backend: sql_default | ||
| storage_dir: ${env.SQLITE_STORE_DIR:=~/.llama/storage/files} | ||
| provider_id: meta-reference-files | ||
| provider_type: inline::localfs | ||
| safety: | ||
| - config: | ||
| excluded_categories: [] | ||
| provider_id: llama-guard | ||
| provider_type: inline::llama-guard | ||
| scoring: | ||
| - provider_id: basic | ||
| provider_type: inline::basic | ||
| config: {} | ||
| - provider_id: llm-as-judge | ||
| provider_type: inline::llm-as-judge | ||
| config: {} | ||
| - provider_id: braintrust | ||
| provider_type: inline::braintrust | ||
| config: | ||
| openai_api_key: '********' | ||
| tool_runtime: | ||
| - config: {} # Enable the RAG tool | ||
| provider_id: rag-runtime | ||
| provider_type: inline::rag-runtime | ||
| - config: {} # Enable MCP (Model Context Protocol) support | ||
| provider_id: model-context-protocol | ||
| provider_type: remote::model-context-protocol | ||
| vector_io: | ||
| - config: # Define the storage backend for RAG | ||
| persistence: | ||
| namespace: vector_io::faiss | ||
| backend: kv_default | ||
| provider_id: faiss | ||
| provider_type: inline::faiss | ||
| agents: | ||
| - config: | ||
| persistence: | ||
| agent_state: | ||
| namespace: agents_state | ||
| backend: kv_default | ||
| responses: | ||
| table_name: agents_responses | ||
| backend: sql_default | ||
| provider_id: meta-reference | ||
| provider_type: inline::meta-reference | ||
| batches: | ||
| - config: | ||
| kvstore: | ||
| namespace: batches_store | ||
| backend: kv_default | ||
| provider_id: reference | ||
| provider_type: inline::reference | ||
| datasetio: | ||
| - config: | ||
| kvstore: | ||
| namespace: huggingface_datasetio | ||
| backend: kv_default | ||
| provider_id: huggingface | ||
| provider_type: remote::huggingface | ||
| - config: | ||
| kvstore: | ||
| namespace: localfs_datasetio | ||
| backend: kv_default | ||
| provider_id: localfs | ||
| provider_type: inline::localfs | ||
| eval: | ||
| - config: | ||
| kvstore: | ||
| namespace: eval_store | ||
| backend: kv_default | ||
| provider_id: meta-reference | ||
| provider_type: inline::meta-reference | ||
| scoring_fns: [] | ||
| server: | ||
| port: 8321 | ||
| storage: | ||
| backends: | ||
| kv_default: | ||
| type: kv_sqlite | ||
| db_path: ${env.KV_STORE_PATH:=~/.llama/storage/kv_store.db} | ||
| sql_default: | ||
| type: sql_sqlite | ||
| db_path: ${env.SQL_STORE_PATH:=~/.llama/storage/sql_store.db} | ||
| stores: | ||
| metadata: | ||
| namespace: registry | ||
| backend: kv_default | ||
| inference: | ||
| table_name: inference_store | ||
| backend: sql_default | ||
| max_write_queue_size: 10000 | ||
| num_writers: 4 | ||
| conversations: | ||
| table_name: openai_conversations | ||
| backend: sql_default | ||
| prompts: | ||
| namespace: prompts | ||
| backend: kv_default | ||
| registered_resources: | ||
| models: | ||
| - model_id: custom-bedrock-model | ||
| model_type: llm | ||
| provider_id: aws-bedrock | ||
| provider_model_id: deepseek.v3-v1:0 | ||
| - model_id: all-mpnet-base-v2 | ||
| model_type: embedding | ||
| provider_id: sentence-transformers | ||
| provider_model_id: all-mpnet-base-v2 | ||
| metadata: | ||
| embedding_dimension: 768 | ||
| shields: | ||
| - shield_id: llama-guard | ||
| provider_id: llama-guard | ||
| provider_shield_id: openai/gpt-4o-mini | ||
| vector_stores: [] | ||
| datasets: [] | ||
| scoring_fns: [] | ||
| benchmarks: [] | ||
| tool_groups: | ||
| - toolgroup_id: builtin::rag # Register the RAG tool | ||
| provider_id: rag-runtime | ||
| vector_stores: | ||
| default_provider_id: faiss | ||
| default_embedding_model: | ||
| provider_id: sentence-transformers | ||
| model_id: all-mpnet-base-v2 |
Contributor
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Reduce drift risk between example and e2e Bedrock configs.
This file is nearly identical to tests/e2e/configs/run-bedrock.yaml; consider generating both from one template (or adding a CI diff check) to prevent silent divergence.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@examples/bedrock-run.yaml` around lines 1 - 163, The example and e2e Bedrock
YAMLs have diverged; consolidate them by extracting the shared manifest into a
single template and updating both consumers to render from that template (e.g.,
create a canonical template for the top-level keys like version, providers,
registered_resources, vector_stores and have examples/bedrock-run and the e2e
run-bedrock config generated from it), or add a CI diff check that compares the
generated output against the committed files and fails if they differ; implement
template generation (or CI check) and update any build/test scripts that
reference the current static files to use the new template/render step so the
configs stay in sync.
Contributor
PR Reviewer Guide 🔍Here are some key observations to aid the review process:
|
Contributor
|
/retest |
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
2 participants
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.
Description
Add AWS Bedrock as a fully supported inference provider with documentation, example configurations, and e2e test coverage.
Type of change
Tools used to create PR
Related Tickets & Documents
Checklist before requesting a review
Testing
tests/e2e/configs/run-bedrock.yamlconfiguration.github/workflows/e2e_tests_providers.yaml)deepseek.v3-v1model (tool calling supported)examples/bedrock-run.yamlTest results available here.
Summary by CodeRabbit
New Features
Documentation
Tests
Chores