CAMEL-23382: camel-ai-tool - align spring-ai-chat with camel-ai-tool …

[zbendhiba]

…component

Description

Step 3: Wire camel-spring-ai-chat producer to discover tools from AiToolRegistry

Summary

Migrate the camel-spring-ai-chat producer from camel-spring-ai-tools (CamelToolExecutorCache) to the unified camel-ai-tool module (AiToolRegistry).

• Bridge adapter: new AiToolSpecToSpringAi converts AiToolSpec → Spring AI ToolCallback, with explicit handling of all AiToolResult subtypes and WARN logging on execution errors
• Tool deduplication: uses LinkedHashSet to prevent duplicate tools when tags overlap
• Dependency swap: camel-spring-ai-tools → camel-ai-tool in pom.xml
• Tests: migrated to AiToolRegistry, replaced Thread.sleep() with Awaitility
• Docs: updated component docs and upgrade guide with migration instructions

No changes to other modules.

Roadmap

• Step 1: Create the new camel-ai-tool module - CAMEL-23382: camel-ai-tool - create unified AI tool component #24473
• Step 2: Wire camel-langchain4j-agent producer to AiToolRegistry
• Step 3 (this PR): Wire camel-spring-ai-chat producer to AiToolRegistry
• Step 4: Wire camel-langchain4j-tools producer to AiToolRegistry
• Step 5: Deprecate camel-langchain4j-tools consumer, remove camel-spring-ai-tools
• Step 6: Add tool support to camel-openai

[gnodet]

Claude Code on behalf of gnodet

Clean migration — well-structured step in the `camel-spring-ai-tools` → `camel-ai-tool` unification roadmap.

Changes reviewed:

Bridge adapter (`AiToolSpecToSpringAi`) ✅

• Converts framework-agnostic `AiToolSpec` → Spring AI `ToolCallback` via `FunctionToolCallback.builder()`
• Exhaustive `AiToolResult` subtype handling: `Success` returns value, `ArgumentError` returns message, `ExecutionError` logs WARN and returns generic error
• Exchange lifecycle is clean: `createExchange()` in try, `releaseExchange()` in finally
• Properly passes `inputSchema` when the spec has a JSON schema

Producer wiring (`SpringAiChatProducer`) ✅

• `CamelToolExecutorCache.getInstance()` → `AiToolRegistry.getOrCreate(getCamelContext())` — context-scoped instead of singleton
• Tool dedup via `LinkedHashSet` prevents duplicates when tags overlap (e.g., a tool tagged `weather,info` appearing in both tag queries)
• Clean stream pipeline: collect unique specs → map to ToolCallback

Tests ✅

• `Thread.sleep(500/1000)` → `Awaitility.await().atMost(5/10, SECONDS).untilAsserted(...)` — proper async assertion
• Removed manual `@AfterEach` cache cleanup — registry lifecycle tied to CamelContext
• `testMultipleToolsWithSameTag` → `testToolExecutionWithDifferentInput` — better name for what it actually tests

Documentation ✅

• Component docs: all `spring-ai-tools` references → `ai-tool`, xref links updated
• Upgrade guide: clear before/after migration example, notes that chat producer URI is unchanged, lists the dependency swap

No issues found.

[github-actions]

🌟 Thank you for your contribution to the Apache Camel project! 🌟
🤖 CI automation will test this PR automatically.

🐫 Apache Camel Committers, please review the following items:

• First-time contributors require MANUAL approval for the GitHub Actions to run
• You can use the command /component-test (camel-)component-name1 (camel-)component-name2.. to request a test from the test bot although they are normally detected and executed by CI.
• You can label PRs using skip-tests and test-dependents to fine-tune the checks executed by this PR.
• Build and test logs are available in the summary page. Only Apache Camel committers have access to the summary.

⚠️ Be careful when sharing logs. Review their contents before sharing them publicly.

[github-actions]

🧪 CI tested the following changed modules:

• components/camel-spring-parent/camel-spring-ai/camel-spring-ai-chat
• docs

---

🔬 Scalpel shadow comparison — Scalpel: 10 tested, 28 compile-only — current: 9 all tested

Maveniverse Scalpel detected 38 affected modules (current approach: 9).

⚠️ Modules only in Scalpel (29)

• apache-camel
• camel-allcomponents
• camel-catalog
• camel-catalog-console
• camel-catalog-lucene
• camel-catalog-maven
• camel-catalog-suggest
• camel-componentdsl
• camel-csimple-maven-plugin
• camel-endpointdsl
• camel-endpointdsl-support
• camel-itest
• camel-jbang-core
• camel-jbang-it
• camel-jbang-main
• camel-jbang-plugin-edit
• camel-jbang-plugin-generate
• camel-jbang-plugin-kubernetes
• camel-jbang-plugin-test
• camel-kamelet-main
• camel-launcher
• camel-report-maven-plugin
• camel-route-parser
• camel-yaml-dsl
• camel-yaml-dsl-deserializers
• camel-yaml-dsl-maven-plugin
• coverage
• docs
• dummy-component

Skip-tests mode would test 10 modules (2 direct + 8 downstream), skip tests for 28 (generated code, meta-modules)

Modules Scalpel would test (10)

• camel-jbang-mcp
• camel-jbang-plugin-mcp
• camel-jbang-plugin-route-parser
• camel-jbang-plugin-tui
• camel-jbang-plugin-validate
• camel-launcher-container
• camel-spring-ai-chat
• camel-yaml-dsl-validator
• camel-yaml-dsl-validator-maven-plugin
• docs

Modules with tests skipped (28)

• apache-camel
• camel-allcomponents
• camel-catalog
• camel-catalog-console
• camel-catalog-lucene
• camel-catalog-maven
• camel-catalog-suggest
• camel-componentdsl
• camel-csimple-maven-plugin
• camel-endpointdsl
• camel-endpointdsl-support
• camel-itest
• camel-jbang-core
• camel-jbang-it
• camel-jbang-main
• camel-jbang-plugin-edit
• camel-jbang-plugin-generate
• camel-jbang-plugin-kubernetes
• camel-jbang-plugin-test
• camel-kamelet-main
• camel-launcher
• camel-report-maven-plugin
• camel-route-parser
• camel-yaml-dsl
• camel-yaml-dsl-deserializers
• camel-yaml-dsl-maven-plugin
• coverage
• dummy-component

ℹ️ Shadow mode — Scalpel observes but does not affect test execution. Learn more

⚠️ Some tests are disabled on GitHub Actions (@DisabledIfSystemProperty(named = "ci.env.name")) and require manual verification:

• components/camel-spring-parent/camel-spring-ai/camel-spring-ai-chat: 21 test(s) disabled on GitHub Actions

All tested modules (38 modules)

• Camel :: All Components Sync point
• Camel :: Assembly
• Camel :: Catalog :: CSimple Maven Plugin (deprecated)
• Camel :: Catalog :: Camel Catalog
• Camel :: Catalog :: Camel Report Maven Plugin
• Camel :: Catalog :: Camel Route Parser
• Camel :: Catalog :: Console
• Camel :: Catalog :: Dummy Component
• Camel :: Catalog :: Lucene (deprecated)
• Camel :: Catalog :: Maven
• Camel :: Catalog :: Suggest
• Camel :: Component DSL
• Camel :: Coverage
• Camel :: Docs
• Camel :: Endpoint DSL
• Camel :: Endpoint DSL :: Support
• Camel :: Integration Tests
• Camel :: JBang :: Core
• Camel :: JBang :: Integration tests
• Camel :: JBang :: MCP
• Camel :: JBang :: Main
• Camel :: JBang :: Plugin :: Edit
• Camel :: JBang :: Plugin :: Generate
• Camel :: JBang :: Plugin :: Kubernetes
• Camel :: JBang :: Plugin :: MCP
• Camel :: JBang :: Plugin :: Route Parser
• Camel :: JBang :: Plugin :: TUI
• Camel :: JBang :: Plugin :: Testing
• Camel :: JBang :: Plugin :: Validate
• Camel :: Kamelet Main
• Camel :: Launcher
• Camel :: Launcher :: Container
• Camel :: Spring AI :: Chat
• Camel :: YAML DSL
• Camel :: YAML DSL :: Deserializers
• Camel :: YAML DSL :: Maven Plugins
• Camel :: YAML DSL :: Validator
• Camel :: YAML DSL :: Validator Maven Plugin

---

⚙️ View full build and test results

[oscerd]

LGTM. Nice migration — routing spring-ai-chat through the unified AiToolRegistry/AiToolExecutor rather than its own tool-call handling, and importantly it preserves the security hardening: the bridge passes the raw untrusted LLM args map straight to AiToolExecutor.execute(...) (AiToolSpecToSpringAi.java:46), which drops undeclared args, validates required ones, and rejects camel*/org.apache.camel.* names case-insensitively before setHeader — the CVE-2025-27636 guard — so there's no raw unfiltered header map in the production path. It also follows AiToolResult's note by returning a generic "Tool execution failed" to the LLM for ExecutionError (logging the detail at WARN) while surfacing only framework-generated ArgumentError messages. Tests present, Thread.sleep→Awaitility, upgrade-guide entry added, CI green.

Reviewed with Claude Code on behalf of Andrea Cosentino. This review was generated by an AI agent and may contain inaccuracies; please verify all suggestions before applying.