Draft
Conversation
|
Important Review skippedDraft detected. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Repository UI Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
Enables encrypted user embedding storage + cosine search with experimental /v1/rag endpoints for local/dev testing. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Use Sage's 20k default char_limit and reject oversized updates via /v1/agent/memory/blocks/:label. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Restructure agent chat to emit messages per-step via SSE instead of batching all messages into a single JSON response. This mirrors Sage's Signal delivery pattern: messages are sent immediately as produced, persisted synchronously (so the next step sees them in context), and embeddings update async. - Split process_message into prepare() + public step() so the handler drives the loop - Chat handler emits agent.message, agent.done, agent.error SSE events - Persistence moved from runtime to handler (send first, store sync, embed async) - Added ExecutedTool to carry tool results for handler-side persistence - Updated sage-in-maple doc to reflect conversations API isolation done Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Sage uses kimi-k2 as the default model with a 256k context window. The agent config was incorrectly defaulting to deepseek-r1-0528 with 100k context. Fixed in both the runtime code and the migration SQL. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
The get_or_create_agent_config helper in mod.rs still had the old deepseek-r1-0528 / 100k defaults. Extracted DEFAULT_MODEL, DEFAULT_CONTEXT_WINDOW, DEFAULT_COMPACTION_THRESHOLD as pub constants in runtime.rs and use them from both creation sites. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Adds encrypted attachment_text storage and a vision pre-step for input_image so agents and embeddings see [Uploaded Image: ...] descriptions. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
AnthonyRonning
commented
Mar 5, 2026
| user_id UUID NOT NULL REFERENCES users(uuid) ON DELETE CASCADE, | ||
|
|
||
| label TEXT NOT NULL, | ||
| description TEXT, |
Contributor
Author
There was a problem hiding this comment.
I don't think we need to persist description here. Probably best it is hardcoded into the code in case we need to configure this later
AnthonyRonning
commented
Mar 5, 2026
| label TEXT NOT NULL, | ||
| description TEXT, | ||
| value_enc BYTEA NOT NULL, | ||
| char_limit INTEGER NOT NULL DEFAULT 5000, |
Contributor
Author
There was a problem hiding this comment.
do we need to enforce char_limit at the db layer or allow it to be configured? another case for this just being hard coded.
Use custom rustPlatform from rust-overlay to match rust-toolchain.toml. Add outputHashes for baml-ids, minijinja, and rig-core git dependencies. Update PCR values for dev and prod. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
AnthonyRonning
commented
Mar 5, 2026
| conversation_id BIGINT REFERENCES conversations(id) ON DELETE SET NULL, | ||
|
|
||
| enabled BOOLEAN NOT NULL DEFAULT FALSE, | ||
| model TEXT NOT NULL DEFAULT 'kimi-k2-5', |
Contributor
Author
There was a problem hiding this comment.
remove kimi default from sql layer, we should always pass this in
Hide the primary Maple relationship behind a main agent thread while giving users focused subagent chats that share memory and code-owned runtime defaults. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Mirror the conversations API so clients can list agents and browse main-agent and subagent items with consistent cursor semantics. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
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
1 participant
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.
No description provided.