get_answer

One-call RAG synthesis over the wiki: it retrieves, gates on confidence, and returns a cited 2-5 sentence answer with fallback file targets. The first tool to call on any code question.

Collapses search → read → reason into one round-trip. The tool retrieves the most relevant wiki pages, enriches the top hits with symbol docstrings and source excerpts, hands them to the LLM, and returns a synthesized answer with citations and a confidence label. If confidence is low, it returns best_guesses, a justified, per-file candidate list with excerpts, instead of an empty answer, letting the agent pick one to verify rather than skim the field.

When to call

Always first on any code question, before search_codebase or manual file exploration.
If confidence is "medium" or "low", follow up with search_codebase and get_context on the fallback_targets.
Works best when the question names explicit identifiers (a class, function, or module name).

Parameters

Parameter	Type	Description
`question`required	string	The developer's question, in natural language.
`scope`	string	Optional path prefix to restrict retrieval (e.g. "src/auth/").
`repo`	string	Repository alias. Usually omitted; pass when the question is about a specific repo in a workspace.

Returns

Field	Description
`answer`	Synthesized 2-5 sentence answer (empty if synthesis was gated)
`citations`	File paths the answer references
`confidence`	`"high"`, `"medium"`, or `"low"`
`retrieval_quality`	`"high"`, `"partial"`, or `"weak"`: a separate signal from `confidence`. `confidence` says how much to trust the synthesised text; `retrieval_quality` says whether to re-read the source before acting on it
`fallback_targets`	Top file paths from retrieval; agent should `get_context` on these for verification
`candidates`	The ranked shortlist of files retrieval resolved, one `{path, lines?}` entry each, up to 5. Present whenever retrieval resolved anything, including high-confidence answers where `retrieval` is deliberately empty. It's where to look next, not evidence the answer is right
`retrieval`	Top 5 wiki hits with `title`, `target_path`, `score`, `summary`, and (for top 2 file pages) symbols with docstrings and source excerpts
`symbol_bodies`	When the answer names a function/method/class, the full live body of each question-named symbol, inlined so no `get_symbol` follow-up is needed
`best_guesses`	On a low-confidence, gated response: a per-file candidate list, each with `file`, `why_relevant`, `score`, and (when available) an `excerpt`, so the agent can pick one to verify instead of skimming several
`episodes`	At most one dated fact recorded about this checkout, present only when its scope intersects the answer
`note`	Context string explaining why synthesis was skipped or hedged
`_meta`	Timing, cache hit, answer hint

Example

get_answer("how does the authentication flow work?")
get_answer(
    "how are database migrations handled?",
    scope="backend/",
)

Things worth knowing

Six confidence gates keep the tool honest:
1. Dominance ratio: if the top retrieval score isn't 1.2× the second, synthesis is skipped and excerpts returned instead.
2. Hedge-phrase detection: if the LLM admits insufficiency in its own answer, confidence is downgraded high → low.
3. Identifier-citation gate: if the question names symbols but none appear in the top retrieval hits, confidence is downgraded high → medium.
4. Value grounding: on value-shaped questions (default / threshold / limit / how many), every number the answer asserts must appear somewhere in the retrieved material, or confidence is capped at low.
5. Citation-source gate: a high-confidence answer must cite at least one page that contributed real source material (hydrated symbols with signatures/bodies), not just a file summary, or it's downgraded to medium.
6. Claim-support / frame grounding: on "why" and mechanism-shaped questions, a high-confidence answer must name its mechanism in terms the cited material actually contains; an unsupported term downgrades it to medium.
Question-aware symbol promotion: symbols matching identifiers extracted from the question get longer docstrings (400 chars) and a 40-line source body excerpt, so "how does X work?" questions can be answered without hedging.
Intersection retrieval: relational questions ("how does X talk to Y?") are split into two queries; hits appearing in both get a 2× boost.
Caching: questions are normalized and hashed; repeat questions hit the answer cache instantly. Hedged cached answers are bypassed for re-synthesis when the symbol pipeline is updated.
No LLM provider configured? Falls back to retrieval-only: ranked hits + snippets at confidence="low".
candidates vs retrieval. retrieval is evidence: enriched hits to re-read when the prose needs checking, and it shrinks as confidence rises. candidates is navigation: a flatter, longer shortlist of every file retrieval resolved, present even on high-confidence answers.

get_answer is the highest-leverage tool in the set. Most "what does this codebase do?" or "where is X handled?" questions are answered in a single call.

get_answer

One-call RAG synthesis over the wiki: it retrieves, gates on confidence, and returns a cited 2-5 sentence answer with fallback file targets. The first tool to call on any code question.

When to call

Always first on any code question, before search_codebase or manual file exploration.
If confidence is "medium" or "low", follow up with search_codebase and get_context on the fallback_targets.
Works best when the question names explicit identifiers (a class, function, or module name).

Parameters

Parameter	Type	Description
`question`required	string	The developer's question, in natural language.
`scope`	string	Optional path prefix to restrict retrieval (e.g. "src/auth/").
`repo`	string	Repository alias. Usually omitted; pass when the question is about a specific repo in a workspace.

Returns

Field	Description
`answer`	Synthesized 2-5 sentence answer (empty if synthesis was gated)
`citations`	File paths the answer references
`confidence`	`"high"`, `"medium"`, or `"low"`
`retrieval_quality`	`"high"`, `"partial"`, or `"weak"`: a separate signal from `confidence`. `confidence` says how much to trust the synthesised text; `retrieval_quality` says whether to re-read the source before acting on it
`fallback_targets`	Top file paths from retrieval; agent should `get_context` on these for verification
`candidates`	The ranked shortlist of files retrieval resolved, one `{path, lines?}` entry each, up to 5. Present whenever retrieval resolved anything, including high-confidence answers where `retrieval` is deliberately empty. It's where to look next, not evidence the answer is right
`retrieval`	Top 5 wiki hits with `title`, `target_path`, `score`, `summary`, and (for top 2 file pages) symbols with docstrings and source excerpts
`symbol_bodies`	When the answer names a function/method/class, the full live body of each question-named symbol, inlined so no `get_symbol` follow-up is needed
`best_guesses`	On a low-confidence, gated response: a per-file candidate list, each with `file`, `why_relevant`, `score`, and (when available) an `excerpt`, so the agent can pick one to verify instead of skimming several
`episodes`	At most one dated fact recorded about this checkout, present only when its scope intersects the answer
`note`	Context string explaining why synthesis was skipped or hedged
`_meta`	Timing, cache hit, answer hint

Example

get_answer("how does the authentication flow work?")
get_answer(
    "how are database migrations handled?",
    scope="backend/",
)

Things worth knowing

Six confidence gates keep the tool honest:
1. Dominance ratio: if the top retrieval score isn't 1.2× the second, synthesis is skipped and excerpts returned instead.
2. Hedge-phrase detection: if the LLM admits insufficiency in its own answer, confidence is downgraded high → low.
3. Identifier-citation gate: if the question names symbols but none appear in the top retrieval hits, confidence is downgraded high → medium.
4. Value grounding: on value-shaped questions (default / threshold / limit / how many), every number the answer asserts must appear somewhere in the retrieved material, or confidence is capped at low.
5. Citation-source gate: a high-confidence answer must cite at least one page that contributed real source material (hydrated symbols with signatures/bodies), not just a file summary, or it's downgraded to medium.
6. Claim-support / frame grounding: on "why" and mechanism-shaped questions, a high-confidence answer must name its mechanism in terms the cited material actually contains; an unsupported term downgrades it to medium.
Question-aware symbol promotion: symbols matching identifiers extracted from the question get longer docstrings (400 chars) and a 40-line source body excerpt, so "how does X work?" questions can be answered without hedging.
Intersection retrieval: relational questions ("how does X talk to Y?") are split into two queries; hits appearing in both get a 2× boost.
Caching: questions are normalized and hashed; repeat questions hit the answer cache instantly. Hedged cached answers are bypassed for re-synthesis when the symbol pipeline is updated.
No LLM provider configured? Falls back to retrieval-only: ranked hits + snippets at confidence="low".
candidates vs retrieval. retrieval is evidence: enriched hits to re-read when the prose needs checking, and it shrinks as confidence rises. candidates is navigation: a flatter, longer shortlist of every file retrieval resolved, present even on high-confidence answers.

get_answer is the highest-leverage tool in the set. Most "what does this codebase do?" or "where is X handled?" questions are answered in a single call.

When to call

Parameters

Returns

Example

Things worth knowing

On this page

get_answer

When to call

Parameters

Returns

Example

Things worth knowing

On this page