danvics/haiku.rag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Remove dead code from iterative research planning refactor

Browse source
This commit is contained in:
Yiorgis Gozadinos 2026-01-31 10:36:11 +02:00
parent 42f2d0fd0e
commit ac76ecee86
No known key found for this signature in database
14 changed files with 20 additions and 76 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
CHANGELOG.md
View file

@ -9,6 +9,13 @@
- Simpler flow: `plan_next` → `search_one` → loop back until complete → `synthesize`
- Consolidated `build_conversational_graph()` into `build_research_graph(output_mode="conversational")`
### Removed
- **Dead config options**: Removed vestigial fields from iterative planning refactor
- `confidence_threshold` from `ResearchConfig` and `ResearchState` (LLM decides completion via `is_complete`)
- `max_sub_questions` from `QAConfig` (iterative flow uses one question at a time)
- `sub_questions` field from `ResearchContext` (no longer populated)
## [0.27.2] - 2026-01-29
### Added

1
docs/agents.md
View file

@ -244,7 +244,6 @@ custom_config = AppConfig(
provider="openai",
model="gpt-4o-mini",
max_iterations=5,
confidence_threshold=0.85,
max_concurrency=3,
)
)

2
docs/cli.md
View file

@ -255,7 +255,7 @@ Flags:
- `--context`: Background context for the research
- `--context-file`: Path to a file containing background context
Research parameters like `max_iterations`, `confidence_threshold`, and `max_concurrency` are configured in your [configuration file](configuration/index.md) under the `research` section.
Research parameters like `max_iterations` and `max_concurrency` are configured in your [configuration file](configuration/index.md) under the `research` section.
## Server

2
docs/configuration/index.md
View file

@ -85,7 +85,6 @@ qa:
provider: ollama
name: gpt-oss
enable_thinking: false
max_sub_questions: 3
max_iterations: 2
max_concurrency: 1
@ -95,7 +94,6 @@ research:
name: ""
enable_thinking: false
max_iterations: 3
confidence_threshold: 0.8
max_concurrency: 1
search:

20
docs/configuration/qa-research.md
View file

@ -32,17 +32,15 @@ qa:
provider: ollama
name: gpt-oss
enable_thinking: false
max_sub_questions: 3 # Maximum sub-questions for deep QA
max_iterations: 2 # Maximum search iterations per sub-question
max_concurrency: 1 # Sub-questions processed in parallel
max_iterations: 2 # Maximum search iterations
max_concurrency: 1 # Concurrent search operations
```
- **model**: LLM configuration (see [Providers](providers.md#model-settings))
- **max_sub_questions**: For deep QA mode, maximum number of sub-questions to generate (default: 3)
- **max_iterations**: Maximum search/evaluate cycles per sub-question (default: 2)
- **max_concurrency**: Number of sub-questions to process in parallel (default: 1)
- **max_iterations**: Maximum search iterations (default: 2)
- **max_concurrency**: Number of concurrent search operations (default: 1)
Deep QA mode (`haiku-rag ask --deep`) decomposes complex questions into sub-questions, processes them in parallel batches, and synthesizes the results.
Deep QA mode (`haiku-rag ask --deep`) uses the research graph with a single iteration for quick, focused answers.
## Research Configuration
@ -55,13 +53,11 @@ research:
name: "" # Empty to use qa model
enable_thinking: false
max_iterations: 3
confidence_threshold: 0.8
max_concurrency: 1
```
- **model**: LLM configuration. Leave provider/model empty to inherit from `qa` (see [Providers](providers.md#model-settings))
- **max_iterations**: Maximum search/evaluate cycles (default: 3)
- **confidence_threshold**: Stop when confidence score meets/exceeds this (default: 0.8)
- **max_concurrency**: Sub-questions searched in parallel per iteration (default: 1)
- **max_iterations**: Maximum planning/search iterations (default: 3)
- **max_concurrency**: Concurrent search operations (default: 1)
The research workflow plans sub-questions, searches in parallel batches, evaluates findings, and iterates until reaching the confidence threshold or max iterations.
The research workflow uses an iterative feedback loop: the planner proposes one question at a time, sees the answer, then decides whether to continue or synthesize. This continues until the planner marks research as complete or `max_iterations` is reached.

1
haiku_rag_slim/haiku/rag/agents/chat/agent.py
View file

@ -249,7 +249,6 @@ def create_chat_agent(config: AppConfig) -> Agent[ChatDeps, str]:
state = ResearchState(
context=context,
max_iterations=1,
confidence_threshold=0.0,
search_filter=doc_filter,
max_concurrency=ctx.deps.config.research.max_concurrency,
)

3
haiku_rag_slim/haiku/rag/agents/research/dependencies.py
View file

@ -13,9 +13,6 @@ class ResearchContext(BaseModel):
"""Context shared across research agents."""
original_question: str = Field(description="The original research question")
sub_questions: list[str] = Field(
default_factory=list, description="Decomposed sub-questions"
)
qa_responses: list[Any] = Field(
default_factory=list, description="Structured QA pairs used during research"
)

24
haiku_rag_slim/haiku/rag/agents/research/graph.py
View file

@ -27,17 +27,8 @@ from haiku.rag.config.models import AppConfig
from haiku.rag.utils import build_prompt, get_model
def format_context_for_prompt(
context: ResearchContext,
include_pending_questions: bool = True,
) -> str:
"""Format the research context as XML for prompts.
Args:
context: The research context to format.
include_pending_questions: Whether to include pending sub-questions.
Set to False for synthesis prompts where pending questions aren't relevant.
"""
def format_context_for_prompt(context: ResearchContext) -> str:
"""Format the research context as XML for prompts."""
context_data: dict[str, object] = {}
if context.session_context:
@ -45,9 +36,6 @@ def format_context_for_prompt(
context_data["question"] = context.original_question
if include_pending_questions and context.sub_questions:
context_data["pending_questions"] = context.sub_questions
if context.qa_responses:
context_data["prior_answers"] = [
{
@ -267,9 +255,7 @@ def build_research_graph(
deps_type=ResearchDependencies,
)
context_xml = format_context_for_prompt(
state.context, include_pending_questions=False
)
context_xml = format_context_for_prompt(state.context)
prompt = (
"Generate a comprehensive research report based on all gathered information.\n\n"
f"{context_xml}\n\n"
@ -301,9 +287,7 @@ def build_research_graph(
deps_type=ResearchDependencies,
)
context_xml = format_context_for_prompt(
state.context, include_pending_questions=False
)
context_xml = format_context_for_prompt(state.context)
prompt = (
f"Answer the question based on the gathered evidence.\n\n{context_xml}"
)

8
haiku_rag_slim/haiku/rag/agents/research/state.py
View file

@ -29,9 +29,6 @@ class ResearchState(BaseModel):
)
iterations: int = Field(default=0, description="Current iteration number")
max_iterations: int = Field(default=3, description="Maximum allowed iterations")
confidence_threshold: float = Field(
default=0.8, description="Confidence threshold for completion", ge=0.0, le=1.0
)
max_concurrency: int = Field(
default=1, description="Maximum concurrent search operations", ge=1
)
@ -45,7 +42,6 @@ class ResearchState(BaseModel):
context: ResearchContext,
config: "AppConfig",
max_iterations: int | None = None,
confidence_threshold: float | None = None,
) -> "ResearchState":
"""Create a ResearchState from an AppConfig.
@ -53,15 +49,11 @@ class ResearchState(BaseModel):
context: The ResearchContext containing the question
config: The AppConfig object
max_iterations: Override max iterations (None uses config default)
confidence_threshold: Override threshold (None uses config, 0.0 disables check)
"""
return cls(
context=context,
max_iterations=max_iterations
if max_iterations is not None
else config.research.max_iterations,
confidence_threshold=confidence_threshold
if confidence_threshold is not None
else config.research.confidence_threshold,
max_concurrency=config.research.max_concurrency,
)

1
haiku_rag_slim/haiku/rag/app.py
View file

@ -399,7 +399,6 @@ class HaikuRAGApp:
context=context,
config=self.config,
max_iterations=1,
confidence_threshold=0.0,
)
state.search_filter = filter
deps = ResearchDeps(client=self.client)

2
haiku_rag_slim/haiku/rag/config/models.py
View file

@ -78,7 +78,6 @@ class QAConfig(BaseModel):
enable_thinking=False,
)
)
max_sub_questions: int = 3
max_iterations: int = 2
max_concurrency: int = 1
@ -92,7 +91,6 @@ class ResearchConfig(BaseModel):
)
)
max_iterations: int = 3
confidence_threshold: float = 0.8
max_concurrency: int = 1

1
haiku_rag_slim/haiku/rag/mcp.py
View file

@ -199,7 +199,6 @@ def create_mcp_server(
context=context,
config=config,
max_iterations=2,
confidence_threshold=0.0,
)
deps = ResearchDeps(client=rag)

22
tests/agents/research/test_research_graph.py
View file

@ -30,7 +30,6 @@ async def test_graph_end_to_end(allow_model_requests, temp_db_path, qa_corpus):
state = ResearchState(
context=ResearchContext(original_question=doc["question"]),
max_iterations=1,
confidence_threshold=0.5,
max_concurrency=1,
)
@ -155,27 +154,6 @@ def test_format_context_for_prompt_with_session_context():
assert "What is Y?" in result
def test_format_context_for_prompt_excludes_pending_questions():
"""Test format_context_for_prompt can exclude pending questions."""
from haiku.rag.agents.research.dependencies import ResearchContext
from haiku.rag.agents.research.graph import format_context_for_prompt
context = ResearchContext(
original_question="Main question?",
sub_questions=["Sub Q1?", "Sub Q2?"],
)
# With pending questions (default)
with_pending = format_context_for_prompt(context, include_pending_questions=True)
assert "Sub Q1?" in with_pending
# Without pending questions (for synthesis)
without_pending = format_context_for_prompt(
context, include_pending_questions=False
)
assert "Sub Q1?" not in without_pending
def test_format_context_for_prompt_with_prior_answers():
"""Test format_context_for_prompt includes prior_answers."""
from haiku.rag.agents.research.dependencies import ResearchContext

2
tests/agents/research/test_search_filter.py
View file

@ -78,7 +78,6 @@ async def test_research_graph_uses_search_filter(
state = ResearchState(
context=ResearchContext(original_question="Tell me about animals"),
max_iterations=1,
confidence_threshold=0.5,
search_filter=filter_clause,
)
@ -116,7 +115,6 @@ async def test_search_filter_none_searches_all(allow_model_requests, client_with
state = ResearchState(
context=ResearchContext(original_question="Tell me about animals"),
max_iterations=1,
confidence_threshold=0.5,
search_filter=None,
)