chore(deps): update rust crate agent-core to 0.6.0 by renovate[bot] · Pull Request #13 · omnidotdev/synapse

renovate · 2026-03-10T01:14:16Z

This PR contains the following updates:

Package	Type	Update	Change
agent-core	workspace.dependencies	minor	`0.1.0` → `0.6.0`

Release Notes

deepmesa/agent-core (agent-core)

`v0.6.0`

Compare Source

Added

Event Sink Abstraction (Pluggable Frontends)

New interface module for custom frontend integration
EventSink trait for receiving events from the engine
- ChannelEventSink: Channel-backed sink with backpressure support
- SimpleEventSink: Minimal stdout sink for CLI tools
InputSource trait for providing input to the engine
- ChannelInputSource: Channel-backed input with helper channel() method
PermissionPolicy trait for automatic permission handling
- AutoApprovePolicy: Auto-approve all requests (headless/trusted environments)
- DenyAllPolicy: Deny all requests (sandboxed environments)
- InteractivePolicy: Forward all requests to user (default for TUI)
- PolicyDecision enum with Allow, AllowWithGrant, Deny, AskUser variants
- supports_interaction() method for handling user questions in headless mode

AgentAir Frontend Methods

run_with_frontend(): Run agent with custom sink, source, and policy
Inline policy handling for PermissionRequired and BatchPermissionRequired events
Auto-cancel user interactions when policy doesn't support interaction

Simplified Agent Setup

SimpleConfig struct for quick agent configuration
AgentAir::with_config(name, path, prompt): One-line agent creation

Changed

Re-export interface types at agent module level for convenience

`v0.5.0`

Compare Source

Added

Agent Skills Support

New skills module implementing the Agent Skills open format
SkillDiscovery for scanning directories for SKILL.md files
SkillRegistry thread-safe registry with XML generation for system prompts
YAML frontmatter parser with name/description validation
Default search paths: $PWD/.skills/ (project) and ~/.agent-air/skills/ (user)

AgentAir Skill Methods

load_skills(): Discover and register skills from configured paths
load_skills_from(): One-shot loading from custom paths
reload_skills(): Hot reload with added/removed tracking
refresh_session_skills(): Update session system prompts with current skills
add_skill_path(): Add custom skill search directories
skill_registry(): Access the skill registry directly
Automatic skills XML injection on session creation

ListSkillsTool

New tool allowing LLM to discover available skills at runtime
Returns name, description, and SKILL.md path for each skill
register_list_skills_tool() method on AgentAir

Changed

AgentError now includes SessionNotFound variant for skill refresh errors

`v0.4.0`

Compare Source

Changed

Split agent-air into workspace with three crates:
- agent-air-runtime: Core engine (controller, client, permissions, tools)
- agent-air-tui: TUI frontend (ratatui, widgets, themes, commands)
- agent-air: Meta-crate re-exporting both (backwards compatible)
TUI methods moved from AgentAir to TuiRunner
New AgentAirExt trait provides into_tui() conversion
Headless agents can now depend on agent-air-runtime only

`v0.3.0`

Compare Source

Added

LLM Provider Support

Google Gemini provider with streaming, tool calling, safety ratings, and grounding/citation metadata
OpenAI streaming support with SSE parser
OpenAI-compatible provider support for 13+ providers (Groq, Together, Fireworks, Mistral, Perplexity, DeepSeek, OpenRouter, Ollama, LM Studio, Anyscale, Cerebras, SambaNova, xAI)
Provider registry with base_url support, context limits, default models, and env var configuration
Amazon Bedrock provider with Converse API, AWS SigV4 signing, streaming, and session token support
Cohere provider with Chat API v2, streaming, and tool calling
Azure OpenAI support with resource/deployment configuration and API versioning
AI21 Labs to known providers registry

Tools

GrepTool using ripgrep libraries with three output modes (files_with_matches, content, count), context lines, file type and glob filtering
GlobTool for fast file pattern matching with globset, sorted by modification time, hidden file filtering
BashTool for shell command execution with timeout, working directory persistence, background execution, output limiting, and dangerous command detection
EditFileTool for find-and-replace with exact matching, replace_all, and multi-stage fuzzy matching (whitespace-insensitive, Levenshtein-based)
MultiEditTool for atomic multiple find-and-replace with overlap detection, reverse-order application, dry-run mode
LsTool for directory listing with filtering, sorting, and long format options
FileRead and DirectoryRead permission categories for fine-grained file operation control
CategorySession scope allowing users to grant permission for all operations in a category

Environment & Configuration

EnvironmentContext for injecting working directory, platform, OS version, and date into system prompts
AgentAir::load_environment_context() for one-line enablement
LLMRegistry::with_environment_context() to inject context into all sessions
AgentConfig::channel_buffer_size() for customizing buffer sizes

Changed

Streaming enabled by default for all providers (Anthropic, OpenAI, Google)
Default channel buffer size increased from 100 to 500
Controller now uses backpressure (blocks on full UI channel instead of dropping events)
Fuzzy match output now shows average similarity percentage
Permission panel UI updated with "Grant All in Category" option and new permission category icons

Fixed

Gemini tool calling: use function name as tool_use_id (Gemini matches by name, not unique ID)
OpenAI streaming: add stream_options.include_usage to ensure token counts are reported for compaction logic
Streaming cache clearing made consistent in ChatView::append_streaming()

Removed

Duplicate registries from LLMController (were never used)
Dead select branches for user interaction/permission events in controller
Duplicate escape_json_string from openai/types.rs (uses common::escape_json_string)

`v0.2.0`

Compare Source

Added

Trait-based slash command system with CommandRegistry
ConversationView trait and NavigationHelper for widgets
Builder patterns and custom action support for key handling
Optional callback for dynamic processing messages
Design note for controller event loop mutex pattern

Changed

Converted status bar to first-class widget
Simplified theme system with declarative macros
Wrapped conversation in Arc for O(1) cloning
Changed Widget::render to take &mut self
Replaced Result<T, String> with proper error types
Consolidated duplicate channel size constants
Refactored widgets to use parameters
Split layout module into separate files
Improved question panel UX and added from_controller_tx getter

Documentation

Updated README and added Rust docs

Configuration

📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

If you want to rebase/retry this PR, check this box

This PR was generated by Mend Renovate. View the repository job log.

…imiting Add typed Rust HTTP client for Synapse's API surface (LLM, MCP, STT, TTS). Mount STT and TTS endpoint routers in the server. Replace Redis-based rate limit storage with in-memory cache storage.

Implement Phase 5 of Synapse integration plan: - Smart model routing with heuristic query analysis via tiktoken - Three routing strategies: threshold, cost-constrained, cascade - Circuit breaker health tracking with automatic recovery probing - Model registry with cost/quality profiles and runtime latency - Failover with equivalence groups and configurable retry attempts - Virtual model names (auto, fast, best, cheap) for routing shortcuts - Feedback tracker for live per-model latency and error rate metrics New crate: synapse-routing (analysis, registry, strategies, feedback) Modified: synapse-llm (health tracker, router integration, error types), synapse-config (failover and routing config schemas), integration-tests (failover scenarios and mock failure harness)

Introduce weighted score strategy that combines quality, cost, and latency into a single objective. Extract shared feedback-adjusted scoring into a dedicated module and simplify config defaults with derive macros.

Add `embedded` feature flag with optional synapse-llm, synapse-config, and synapse-core dependencies. Restructure SynapseClient to dispatch on a Backend enum (Remote vs Embedded), extract helper methods to free functions, and add cfg-gated Llm error variant. Remote behavior is unchanged; embedded arms return placeholder errors for now.

…bedded mode Set default-features = false on synapse-llm in workspace root so synapse-client embedded mode doesn't pull in axum. Synapse-server explicitly enables the http feature.

…ed mode Debug formatting produced "toolcalls" instead of "tool_calls" for FinishReason::ToolCalls. Use serde serialization which respects the rename_all = "snake_case" attribute. Also: use state.list_models() in handler, remove redundant stream assignment in client.

…action, and strategy registry Enhance the routing engine with richer query analysis (vision, long-context, multi-turn detection), capability-based model filtering, a pluggable Strategy trait with StrategyRegistry for custom strategies, and regex-based task classification. Wire the new structured analysis pipeline through synapse-llm.

…ts and usage metering Introduce synapse-billing crate with Aether API client, async usage recorder, and entitlement/usage caching. Wire billing identity resolution, entitlement gating, and token metering into the server middleware stack. Support BYOK, managed, and hybrid API key modes.

…, and provider trait Add OpenAI-compatible embeddings routing crate with EmbeddingRequest (supporting single/array input via EmbedInput), EmbeddingResponse, EmbeddingsError with IntoResponse, and EmbeddingsProvider async trait.

Implement OpenAiEmbeddingsProvider that POSTs to the OpenAI embeddings API, strips the "provider/" model prefix, and maps errors to the EmbeddingsError variants. Follows the STT whisper provider pattern.

…erver Add EmbeddingsConfig to synapse-config, build EmbeddingsServerBuilder with provider dispatch, and mount POST /v1/embeddings endpoint in the main server.

OpenAI-compatible POST /v1/images/generations endpoint with provider dispatch, config, error handling, and server mount

… recovery window

…re-gated)

Add STT/TTS/embeddings/image-gen feature keys to BillingConfig with route-to-feature mapping. Extend entitlement middleware from 2 checks to 5: api_access, modality gating, requests meter, input tokens meter, and output tokens meter. Broaden webhook cache invalidation to cover all entitlement and usage keys.

- Switch rate limiting from memory-only to Valkey-backed distributed storage - Add Google (Gemini 2.5 Pro/Flash) and AWS Bedrock providers to prod config with routing models, failover groups, and billing - Add synapse-cache crate: Valkey-backed exact-match response cache keyed by SHA-256 of canonical request, only for deterministic (temp=0) non-streaming - Add synapse-guardrails crate: configurable rule engine with keyword blocklists, regex patterns, max input tokens, and PII detection (SSN, credit card, email, phone) with block/warn actions - Wire cache into LlmState behind feature flag, guardrails as axum middleware

Strips Gemini and AWS Bedrock from launch lineup to reduce surface area. Launch with OpenAI, Anthropic, and Nvidia (8 models). Google and Bedrock can be re-added post-launch if users request them.

…a cache

Allow resolving keys of any category (ai, voice, etc) by provider name

Resolve BYOK provider keys from Gatekeeper's vault as an overlay on synapse-api keys, with moka-backed caching and event-driven invalidation via Vortex webhook events.

…ilover path

Previously the auth middleware passed through requests with no Authorization header or non-synapse tokens, allowing unauthenticated access to upstream providers. Now returns 401 for missing or invalid-format tokens on non-public paths.

Bump changesets deps to latest, bump changesets/action to v1.7.0, fix repo name in changeset config, add missing config fields, add workflow_dispatch and version_commit detection, add changelog extraction in publish job, add timeouts, add .changeset/README.md, add node_modules to gitignore, and track bun.lock.

CORS origin updated from dashboard.synapse.omni.dev to synapse.omni.dev. Upstream 429 responses now return RateLimited instead of Upstream error, triggering equivalence group failover to alternative providers.

OPTIONS requests now bypass auth middleware so the CORS layer can handle preflight. Upstream 401/403 errors map to LlmError::Unauthorized (non-retryable) instead of LlmError::Upstream, returning a clear 401 to the client rather than a misleading 502 after failed failover.

Add Manual variant to KeyMode for UI-created API keys (treated as managed billing). Change token limit fields from u64 to i64 so the -1 unlimited sentinel from synapse-api can be deserialized.

Bump toolchain from 1.90.0 to 1.93.0 for AWS SDK compat. Remove invalid [dev-dependencies] from workspace manifest. Update all Cargo dependencies via cargo update.

renovate · 2026-03-10T01:14:18Z

⚠️ Artifact update problem

Renovate failed to update an artifact related to this branch. You probably do not want to merge this PR as-is.

♻ Renovate will retry this branch, including artifacts, only when one of the following happens:

any of the package files in this branch needs updating, or
the branch becomes conflicted, or
you click the rebase/retry checkbox if found above, or
you rename this PR's title to start with "rebase!" to trigger it manually

The artifact failure details are included below:

File name: Cargo.lock

Command failed: cargo update --config net.git-fetch-with-cli=true --manifest-path Cargo.toml --package agent-core@0.1.0 --precise 0.6.0
    Updating crates.io index
error: failed to select a version for the requirement `agent-core-runtime = "^0.6.0"`
  version 0.6.0 is yanked
location searched: crates.io index
required by package `agent-core v0.6.0`
    ... which satisfies dependency `agent-core = "^0.6.0"` of package `synapse-client v0.1.0 (/tmp/renovate/repos/github/omnidotdev/synapse-gateway/crates/synapse-client)`
    ... which satisfies path dependency `synapse-client` (locked to 0.1.0) of package `integration-tests v0.1.0 (/tmp/renovate/repos/github/omnidotdev/synapse-gateway/crates/integration-tests)`

changeset-bot · 2026-03-10T01:14:21Z

⚠️ No Changeset found

Latest commit: 42eb61c

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

renovate · 2026-03-13T00:12:52Z

Renovate Ignore Notification

Because you closed this PR without merging, Renovate will ignore this update (0.6.0). You will get a PR once a newer version is released. To ignore this dependency forever, add it to the ignoreDeps array of your Renovate config.

If you accidentally closed this PR, or if you changed your mind: rename this PR to get a fresh replacement PR.

coopbri added 30 commits February 6, 2026 10:26

chore: initial commit

edf159a

style: add emojis to CI workflow names

e24c1cf

feat: add synapse-client crate, mount STT/TTS routes, refactor rate l…

265176a

…imiting Add typed Rust HTTP client for Synapse's API surface (LLM, MCP, STT, TTS). Mount STT and TTS endpoint routers in the server. Replace Redis-based rate limit storage with in-memory cache storage.

chore: update references for repo rename to synapse-server

7161dca

feat(synapse-routing): add multi-objective score routing strategy

7e63454

Introduce weighted score strategy that combines quality, cost, and latency into a single objective. Extract shared feedback-adjusted scoring into a dedicated module and simplify config defaults with derive macros.

feat(synapse-llm): split router.rs into state.rs and handler.rs

cbde251

feat(synapse-core): add RequestContext::empty() for embedded use

f901946

feat(synapse-llm): feature-gate HTTP handlers behind http feature

9af7028

feat(synapse-llm): add high-level complete/complete_stream methods

38d353f

refactor(synapse-llm): use high-level methods in HTTP handlers

8c283ce

fix(synapse-llm): disable default features in workspace for proper em…

f7070d2

…bedded mode Set default-features = false on synapse-llm in workspace root so synapse-client embedded mode doesn't pull in axum. Synapse-server explicitly enables the http feature.

feat(synapse-client): add embedded mode with in-process synapse-llm

04a922f

test(synapse-client): add integration tests for embedded mode

2dc29bf

style: fix clippy warnings from embedded mode changes

d44daa9

fix(docker): add cache mount IDs with project prefix

fcfe9b3

fix(docker): remove cache mounts unsupported by Railway

7f8ccc2

fix(docker): remove cache mounts unsupported by Railway

a036cce

chore: update lockfile after embeddings crate review fixes

3e4f5f6

feat(synapse-embeddings): add OpenAI embeddings provider

8b8a8ad

Implement OpenAiEmbeddingsProvider that POSTs to the OpenAI embeddings API, strips the "provider/" model prefix, and maps errors to the EmbeddingsError variants. Follows the STT whisper provider pattern.

feat(synapse-embeddings): add OpenAI embeddings provider

7c757e0

Implement OpenAiEmbeddingsProvider that POSTs to the OpenAI embeddings API, strips the "provider/" model prefix, and maps errors to the EmbeddingsError variants. Follows the STT whisper provider pattern.

feat(synapse-embeddings): wire server, router, and config into main s…

39c747c

…erver Add EmbeddingsConfig to synapse-config, build EmbeddingsServerBuilder with provider dispatch, and mount POST /v1/embeddings endpoint in the main server.

feat(synapse-imagegen): add image generation crate with OpenAI provider

49f8e5c

OpenAI-compatible POST /v1/images/generations endpoint with provider dispatch, config, error handling, and server mount

feat(synapse-routing): add provider failover with health tracking and…

a4c664e

… recovery window

feat(synapse-routing): add ONNX ML routing strategy foundation (featu…

e41f6b6

…re-gated)

coopbri and others added 24 commits February 28, 2026 01:53

chore: remove Google and Bedrock providers from prod config

2751f73

Strips Gemini and AWS Bedrock from launch lineup to reduce surface area. Launch with OpenAI, Anthropic, and Nvidia (8 models). Google and Bedrock can be re-added post-launch if users request them.

fix(openapi): correct local dev port to 6000

fb23c99

feat(synapse): add VaultClient for Gatekeeper key resolution with mok…

07e8381

…a cache

fix(vault): remove hardcoded ai category from vault resolve request

b9b74d8

Allow resolving keys of any category (ai, voice, etc) by provider name

feat(auth): integrate Gatekeeper vault for BYOK key resolution

8733368

Resolve BYOK provider keys from Gatekeeper's vault as an overlay on synapse-api keys, with moka-backed caching and event-driven invalidation via Vortex webhook events.

style: apply cargo fmt and fix clippy for Rust edition 2024

9fcac9f

feat(ci): add AUR and Homebrew publishing to release pipeline

d447bc0

chore: remove agentic artifacts

e18808d

fix: resolve clippy warnings for CI

652bf52

fix: collapse nested if-let for clippy collapsible_if

49bd473

fix: resolve clippy warnings in integration tests

639a8c4

fix(tests): use implicit model names in failover tests to exercise fa…

b8e9c2b

…ilover path

chore: reset version to 0.0.0 for initial changeset release

fe1d975

chore: add initial release changeset

bb17220

fix: correct CORS origin and enable 429 failover

835d71b

CORS origin updated from dashboard.synapse.omni.dev to synapse.omni.dev. Upstream 429 responses now return RateLimited instead of Upstream error, triggering equivalence group failover to alternative providers.

fix: support manual key mode and signed token limits

448c580

Add Manual variant to KeyMode for UI-created API keys (treated as managed billing). Change token limit fields from u64 to i64 so the -1 unlimited sentinel from synapse-api can be deserialized.

chore: add cargo-husky pre-commit hooks for fmt, clippy, and test

09bd0cd

chore: upgrade dependencies and Rust toolchain to 1.93

c06bf3e

Bump toolchain from 1.90.0 to 1.93.0 for AWS SDK compat. Remove invalid [dev-dependencies] from workspace manifest. Update all Cargo dependencies via cargo update.

chore(deps): update rust crate agent-core to 0.6.0

42eb61c

coopbri closed this Mar 13, 2026

coopbri force-pushed the master branch from c4a2a5c to 4ee7600 Compare March 13, 2026 00:12

renovate bot deleted the renovate/agent-core-0.x branch March 13, 2026 00:12

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

chore(deps): update rust crate agent-core to 0.6.0#13

chore(deps): update rust crate agent-core to 0.6.0#13
renovate[bot] wants to merge 101 commits intomasterfrom
renovate/agent-core-0.x

renovate bot commented Mar 10, 2026

Uh oh!

renovate bot commented Mar 10, 2026

Uh oh!

changeset-bot bot commented Mar 10, 2026

Uh oh!

renovate bot commented Mar 13, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

renovate bot commented Mar 10, 2026

Release Notes

v0.6.0

Added

Event Sink Abstraction (Pluggable Frontends)

AgentAir Frontend Methods

Simplified Agent Setup

Changed

v0.5.0

Added

Agent Skills Support

AgentAir Skill Methods

ListSkillsTool

Changed

v0.4.0

Changed

v0.3.0

Added

LLM Provider Support

Tools

Environment & Configuration

Changed

Fixed

Removed

v0.2.0

Added

Changed

Documentation

Configuration

Uh oh!

renovate bot commented Mar 10, 2026

⚠️ Artifact update problem

File name: Cargo.lock

Uh oh!

changeset-bot bot commented Mar 10, 2026

⚠️ No Changeset found

Uh oh!

renovate bot commented Mar 13, 2026

Renovate Ignore Notification

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

`v0.6.0`

`v0.5.0`

`v0.4.0`

`v0.3.0`

`v0.2.0`