feat(integrations): stock-price tools and expanded Parallel surface#911
Merged
Merged
Conversation
Adds five new `stock_*` tools (quote, exchange_rate, options, crypto_series, commodity) backed by the financial-apis backend route, and four new `parallel_*` tools (chat, research, enrich, dataset) for the expanded Parallel API. Wires both surfaces into the researcher and planner agents so questions like "what is the price of BTC?" route to a dedicated data tool instead of the generic web search. New `integrations.stock_prices` toggle gates registration.
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (1)
📝 WalkthroughWalkthroughExpanded integrations with new parallel tools and a new stock_prices integration; updated planner/researcher agent tool allowlists; added config toggle for stock_prices; and wired conditional runtime registration of the new tools. Changes
Sequence Diagram(s)sequenceDiagram
participant Agent as Agent (planner / researcher)
participant Runtime as Runtime / Tool Registry
participant Integration as Integration Client
participant Backend as Integrations Backend
Agent->>Runtime: Request plan or invoke tool (e.g., `parallel_research` / `stock_quote`)
Runtime->>Integration: Validate params, build payload, POST /agent-integrations/{parallel|stock}/...
Integration->>Backend: Forward POST to backend endpoint
Backend-->>Integration: 200 OK + JSON (result, costUsd, optional findallId)
Integration-->>Runtime: Return ToolResult (formatted text + cost metadata)
Runtime-->>Agent: Deliver ToolResult
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
src/openhuman/integrations/parallel.rs (1)
1-920: Consider splitting this file in a follow-up.The file now exceeds ~1200 lines (including tests). Per coding guidelines, source files should be ≤ ~500 lines. Consider extracting the new tools into a sibling file (e.g.,
parallel_advanced.rsorparallel_chat.rs+parallel_research.rs) to improve maintainability.This is a non-blocking suggestion for a future cleanup. As per coding guidelines: "Source files should be ≤ ~500 lines; split modules when growing to improve maintainability."
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@src/openhuman/integrations/parallel.rs` around lines 1 - 920, The file is too large; split the Parallel integration into smaller modules to meet the ≤~500-line guideline—extract related tools and their response types into new files and re-export them from the parent module. For example, move ParallelChatTool (plus ChatResponse/ChatChoice/ChatMessage), ParallelResearchTool (ResearchResponse), ParallelEnrichTool (EnrichResponse), and ParallelDatasetTool (DatasetResponse) into one or more new files (e.g., parallel_chat.rs, parallel_research.rs, parallel_enrich.rs / parallel_dataset.rs) while keeping ParallelSearchTool, ParallelExtractTool, and shared utilities (truncate_chars, IntegrationClient use, async_trait/serde imports) in the original file or a shared helpers file; update the module declarations to pub use or pub mod the new files and adjust imports (retain symbols: ParallelChatTool, ParallelResearchTool, ParallelEnrichTool, ParallelDatasetTool, ParallelSearchTool, ParallelExtractTool, truncate_chars, SearchResponse, ExtractResponse) so callers keep the same API.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@src/openhuman/integrations/parallel.rs`:
- Around line 1-920: The file is too large; split the Parallel integration into
smaller modules to meet the ≤~500-line guideline—extract related tools and their
response types into new files and re-export them from the parent module. For
example, move ParallelChatTool (plus ChatResponse/ChatChoice/ChatMessage),
ParallelResearchTool (ResearchResponse), ParallelEnrichTool (EnrichResponse),
and ParallelDatasetTool (DatasetResponse) into one or more new files (e.g.,
parallel_chat.rs, parallel_research.rs, parallel_enrich.rs /
parallel_dataset.rs) while keeping ParallelSearchTool, ParallelExtractTool, and
shared utilities (truncate_chars, IntegrationClient use, async_trait/serde
imports) in the original file or a shared helpers file; update the module
declarations to pub use or pub mod the new files and adjust imports (retain
symbols: ParallelChatTool, ParallelResearchTool, ParallelEnrichTool,
ParallelDatasetTool, ParallelSearchTool, ParallelExtractTool, truncate_chars,
SearchResponse, ExtractResponse) so callers keep the same API.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 4bcfbd35-cc73-4afd-9542-df8ae06b42e1
📒 Files selected for processing (7)
src/openhuman/agent/agents/planner/agent.tomlsrc/openhuman/agent/agents/researcher/agent.tomlsrc/openhuman/config/schema/tools.rssrc/openhuman/integrations/mod.rssrc/openhuman/integrations/parallel.rssrc/openhuman/integrations/stock_prices.rssrc/openhuman/tools/ops.rs
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@src/openhuman/tools/ops.rs`:
- Around line 303-338: Add unit tests that assert the tool registry includes the
new Parallel* (ParallelChatTool, ParallelResearchTool, ParallelEnrichTool,
ParallelDatasetTool) and Stock* (StockQuoteTool, StockExchangeRateTool,
StockOptionsTool, StockCryptoSeriesTool, StockCommodityTool) registrations when
their respective toggles (root_config.integrations.parallel.enabled and
root_config.integrations.stock_prices.enabled) are true, and that they are
absent when those toggles are false; locate the registry-building function that
pushes these tools (the code that calls
crate::openhuman::integrations::ParallelChatTool::new,
ParallelResearchTool::new, ParallelEnrichTool::new, ParallelDatasetTool::new,
StockQuoteTool::new, StockExchangeRateTool::new, StockOptionsTool::new,
StockCryptoSeriesTool::new, StockCommodityTool::new) and add focused tests that
construct a minimal root_config with toggles on/off, run the registry creation,
and assert presence/absence of the corresponding tool types (and add similar
assertions to the relevant JSON-RPC e2e test file if integration coverage is
required).
🪄 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: defaults
Review profile: CHILL
Plan: Pro
Run ID: 4794addf-1a59-43a6-ac83-19139a00a034
📒 Files selected for processing (2)
src/openhuman/config/schema/tools.rssrc/openhuman/tools/ops.rs
Comment on lines
+303
to
+338
| tools.push(Box::new( | ||
| crate::openhuman::integrations::ParallelChatTool::new(Arc::clone(&client)), | ||
| )); | ||
| tools.push(Box::new( | ||
| crate::openhuman::integrations::ParallelResearchTool::new(Arc::clone(&client)), | ||
| )); | ||
| tools.push(Box::new( | ||
| crate::openhuman::integrations::ParallelEnrichTool::new(Arc::clone(&client)), | ||
| )); | ||
| tools.push(Box::new( | ||
| crate::openhuman::integrations::ParallelDatasetTool::new(Arc::clone(&client)), | ||
| )); | ||
| tracing::debug!("[integrations] registered parallel tools"); | ||
| } else { | ||
| tracing::debug!("[integrations] parallel disabled — skipping"); | ||
| } | ||
| if root_config.integrations.stock_prices.enabled { | ||
| tools.push(Box::new( | ||
| crate::openhuman::integrations::StockQuoteTool::new(Arc::clone(&client)), | ||
| )); | ||
| tools.push(Box::new( | ||
| crate::openhuman::integrations::StockExchangeRateTool::new(Arc::clone(&client)), | ||
| )); | ||
| tools.push(Box::new( | ||
| crate::openhuman::integrations::StockOptionsTool::new(Arc::clone(&client)), | ||
| )); | ||
| tools.push(Box::new( | ||
| crate::openhuman::integrations::StockCryptoSeriesTool::new(Arc::clone(&client)), | ||
| )); | ||
| tools.push(Box::new( | ||
| crate::openhuman::integrations::StockCommodityTool::new(Arc::clone(&client)), | ||
| )); | ||
| tracing::debug!("[integrations] registered stock_prices tools"); | ||
| } else { | ||
| tracing::debug!("[integrations] stock_prices disabled — skipping"); | ||
| } |
Contributor
There was a problem hiding this comment.
Add regression tests for new toggle-gated tool registrations.
Lines 303-338 add nine new tool registrations, but this file’s tests do not assert presence/absence of these new parallel_* and stock_* tools under enabled/disabled toggles. Please add focused registry tests to lock this behavior.
✅ Suggested test scaffold
+ #[test]
+ fn all_tools_registers_new_parallel_and_stock_tools_when_enabled() {
+ let tmp = TempDir::new().unwrap();
+ let security = Arc::new(SecurityPolicy::default());
+ let mem_cfg = MemoryConfig {
+ backend: "markdown".into(),
+ ..MemoryConfig::default()
+ };
+ let mem: Arc<dyn Memory> =
+ Arc::from(crate::openhuman::memory::create_memory(&mem_cfg, tmp.path()).unwrap());
+ let browser = BrowserConfig::default();
+ let http = crate::openhuman::config::HttpRequestConfig::default();
+ let mut cfg = test_config(&tmp);
+ cfg.integrations.parallel.enabled = true;
+ cfg.integrations.stock_prices.enabled = true;
+
+ let tools = all_tools(
+ Arc::new(cfg.clone()),
+ &security,
+ mem,
+ &browser,
+ &http,
+ tmp.path(),
+ &HashMap::new(),
+ &cfg,
+ );
+ let names: Vec<&str> = tools.iter().map(|t| t.name()).collect();
+ for expected in [
+ "parallel_chat",
+ "parallel_research",
+ "parallel_enrich",
+ "parallel_dataset",
+ "stock_quote",
+ "stock_exchange_rate",
+ "stock_options",
+ "stock_crypto_series",
+ "stock_commodity",
+ ] {
+ assert!(names.contains(&expected), "{expected} must be registered; got: {names:?}");
+ }
+ }
+
+ #[test]
+ fn all_tools_skips_new_parallel_and_stock_tools_when_disabled() {
+ let tmp = TempDir::new().unwrap();
+ let security = Arc::new(SecurityPolicy::default());
+ let mem_cfg = MemoryConfig {
+ backend: "markdown".into(),
+ ..MemoryConfig::default()
+ };
+ let mem: Arc<dyn Memory> =
+ Arc::from(crate::openhuman::memory::create_memory(&mem_cfg, tmp.path()).unwrap());
+ let browser = BrowserConfig::default();
+ let http = crate::openhuman::config::HttpRequestConfig::default();
+ let mut cfg = test_config(&tmp);
+ cfg.integrations.parallel.enabled = false;
+ cfg.integrations.stock_prices.enabled = false;
+
+ let tools = all_tools(
+ Arc::new(cfg.clone()),
+ &security,
+ mem,
+ &browser,
+ &http,
+ tmp.path(),
+ &HashMap::new(),
+ &cfg,
+ );
+ let names: Vec<&str> = tools.iter().map(|t| t.name()).collect();
+ for unexpected in [
+ "parallel_chat",
+ "parallel_research",
+ "parallel_enrich",
+ "parallel_dataset",
+ "stock_quote",
+ "stock_exchange_rate",
+ "stock_options",
+ "stock_crypto_series",
+ "stock_commodity",
+ ] {
+ assert!(
+ !names.contains(&unexpected),
+ "{unexpected} must NOT be registered; got: {names:?}"
+ );
+ }
+ }As per coding guidelines: “Ship unit tests and coverage for behavior you are adding or changing before building additional features on top” and “Rust code must be unit-tested for new/changed behavior before stacking features; run via cargo test and extend tests/json_rpc_e2e.rs for RPC integration tests”.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@src/openhuman/tools/ops.rs` around lines 303 - 338, Add unit tests that
assert the tool registry includes the new Parallel* (ParallelChatTool,
ParallelResearchTool, ParallelEnrichTool, ParallelDatasetTool) and Stock*
(StockQuoteTool, StockExchangeRateTool, StockOptionsTool, StockCryptoSeriesTool,
StockCommodityTool) registrations when their respective toggles
(root_config.integrations.parallel.enabled and
root_config.integrations.stock_prices.enabled) are true, and that they are
absent when those toggles are false; locate the registry-building function that
pushes these tools (the code that calls
crate::openhuman::integrations::ParallelChatTool::new,
ParallelResearchTool::new, ParallelEnrichTool::new, ParallelDatasetTool::new,
StockQuoteTool::new, StockExchangeRateTool::new, StockOptionsTool::new,
StockCryptoSeriesTool::new, StockCommodityTool::new) and add focused tests that
construct a minimal root_config with toggles on/off, run the registry creation,
and assert presence/absence of the corresponding tool types (and add similar
assertions to the relevant JSON-RPC e2e test file if integration coverage is
required).
The two echo-style postprocess tests (whitespace-only context and
conversation context) shared the global LocalAiService singleton and
OPENHUMAN_OLLAMA_BASE_URL env var with sibling tests but did not
acquire LOCAL_AI_TEST_MUTEX, allowing another test's mock response
('Hello, world.') to leak in and fail the exact-equality assertion.
This was referenced May 8, 2026
AusAgentSmith
pushed a commit
to AusAgentSmith/openhuman
that referenced
this pull request
May 23, 2026
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.
Summary
Add five
stock_*tools and four newparallel_*tools so research-style agents can answer questions like "what is the price of BTC?" with a dedicated market-data call instead of a generic web search, and tackle deeper, structured research without bouncing through search/extract loops.Backed by:
/agent-integrations/financial-apis/*Changes
New module —
src/openhuman/integrations/stock_prices.rs(5 tools, all backend-proxied):stock_quote—GLOBAL_QUOTEfor stocks/indices (AAPL, SPY)stock_exchange_rate— FX and crypto spot price (BTC/USD, EUR/USD) — the canonical "price of BTC" pathstock_options— realtime options chain (optional greeks)stock_crypto_series— daily OHLCVstock_commodity— WTI / BRENT / NATURAL_GASExtended —
src/openhuman/integrations/parallel.rs(4 new tools):parallel_chat— research-grounded chat (speed/lite/base/core)parallel_research— Task API deep research; blocks inline (wait=true)parallel_enrich— sync structured enrichment with required output schemaparallel_dataset— FindAll dataset generation, returnsfindall_idWiring:
IntegrationsConfig.stock_prices: IntegrationToggle(defaults on, like the others)tools/ops.rsregisters all new tools, gated by their respective togglesagents/researcher/agent.toml) gains the full Parallel + stock-prices surfaceagents/planner/agent.toml) gains read-only research and stock tools so plans can be grounded in real numbersPer the renaming ask, the user-facing name is stock_prices rather than "alphavantage" — the Alpha Vantage provider is an implementation detail of the backend route.
Test plan
cargo checkcleancargo test --lib openhuman::integrations::— 66/66 pass (16 new tests for the new tools: metadata, schema-required fields, validation rejection, response deserialisation)stock_exchange_rateSummary by CodeRabbit
New Features
Tests