feat(agents): add get_effective_system_prompt and stable instruction api

[MoShiha]

Confirm role, goal, backstory, system_template, and prompt_template as stable public API (safe to read and write after construction) by updating their Field descriptions in BaseAgent.

Add Agent.get_effective_system_prompt() -> str, which returns the fully rendered system prompt as it would be sent to the LLM. Respects system_template and prompt_template overrides, and immediately reflects in-place writes to role, goal, and backstory.

This is the read/write seam that DSPy optimizers and other instrumentation tools need to inspect and update agent instructions without patching internals. See: #5818

Summary by CodeRabbit

• New Features

  • Added the ability to preview the fully rendered system prompt that will be sent at execution time.

• Documentation

  • Clarified agent instruction fields (role, goal, backstory) as stable public API and safe to read/write after construction.

• Tests

  • Added tests verifying instruction fields are readable/writable and that the rendered system prompt is non-empty and reflects updates.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro Plus

Run ID: 77003bf1-8204-4b52-8ff4-ee1991e87b5d

📥 Commits

Reviewing files that changed from the base of the PR and between c56597f and 630466c.

📒 Files selected for processing (1)

• lib/crewai/src/crewai/agent/core.py

---

📝 Walkthrough

Walkthrough

Adds Agent.get_effective_system_prompt(), expands BaseAgent field descriptions for role/goal/backstory as stable public API, and adds tests verifying read/write behavior and rendered system prompt content and template substitution.

Changes

Stable Agent Instruction API

Layer / File(s)	Summary
Stable API field descriptions lib/crewai/src/crewai/agents/agent_builder/base_agent.py	BaseAgent.role, .goal, and .backstory field descriptions expanded to explicitly document these as stable public API fields and clarify read/write safety and instrumentation behavior.
get_effective_system_prompt() implementation lib/crewai/src/crewai/agent/core.py	Agent class gains get_effective_system_prompt() method that renders the execution-time system prompt via Prompts(...).task_execution() with tools disabled and returns the rendered system string or fallback prompt.
Instruction API validation tests lib/crewai/tests/agents/test_agent_instruction_api.py	New test suite with fixture and tests validating instruction field readability, writeability, non-empty effective prompt, live reflection of field mutations, and template substitution without raw token leakage.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Possibly related PRs

• crewAIInc/crewAI#5774: Changes the prompt-construction path used by the new get_effective_system_prompt().

Suggested labels

size/L

Poem

🐰 I sniff the prompt, all tidy and bright,
Role, goal, backstory—stable by night,
Tests hop around, ensuring no quirks,
Rendered system prompt does all the work,
A little rabbit cheers and takes flight.

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately describes the two main additions: the new get_effective_system_prompt() method and the designation of instruction fields as stable API.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@lib/crewai/src/crewai/agent/core.py`:
- Line 1297: The call currently coerces None to False by using
bool(self.use_system_prompt); change it to pass self.use_system_prompt through
unchanged so semantics match the runtime execution path. Locate the call in
creawi.agent.core (around the code that builds the prompt/request where
use_system_prompt is passed) and replace bool(self.use_system_prompt) with
self.use_system_prompt so None remains None and behavior is identical to the
actual execution path.

🪄 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: Organization UI

Review profile: CHILL

Plan: Pro Plus

Run ID: e87848b7-a96a-4700-a5d6-02a915bb859a

📥 Commits

Reviewing files that changed from the base of the PR and between a95d267 and c56597f.

📒 Files selected for processing (3)

• lib/crewai/src/crewai/agent/core.py
• lib/crewai/src/crewai/agents/agent_builder/base_agent.py
• lib/crewai/tests/agents/test_agent_instruction_api.py