kami
7a0d4d0ee2
Makes the research feature runnable end-to-end, off by default. - config: [tools.research] (enabled, searxng_url, max_results, max_fetch_bytes). - registration: web_search/web_fetch are built into BOTH the default and per-workspace tool registries when research.enabled, sharing one HTTP client threaded from Main (none built on the static path). Egress stays harness-enforced: web_fetch is T2 (operator-approved) and the existing NetworkHostRule still applies. - workflow: examples/workflows/research.toml — decompose → gather → report, with the three artifact schemas and prompts. Fan-out (search per sub-question, fetch per source) runs as repeated tool calls inside the gather stage (Correx has no parallel agents); per-source synthesis into the dossier is the compression step, so the report stage consumes summaries, never raw pages. ResearchWorkflowTest validates the graph contract. To run: set [tools.research].enabled, register the 3 [[artifacts]], copy research.toml + prompts + schemas into the workflows dir, start SearXNG. Launch like any workflow (the T2 fetch approval surfaces as an approval card; the report opens in the artifact viewer). Follow-ups (noted, not blocking): batch fetch-approval at the source-list level (§3), a dedicated SourceFetched/LowQualityExtraction event (quality + content hash are already in tool-result metadata), dynamic per-session egress allowlist, and the web approval client (§6).
80 lines
2.9 KiB
TOML
80 lines
2.9 KiB
TOML
# Deep research workflow: decompose -> gather (search + fetch) -> report
|
|
#
|
|
# A native Correx workflow (research-workflow-spec): one graph, two network tools, no new
|
|
# orchestration machinery. The fan-out the spec describes (search per sub-question, fetch per
|
|
# source) happens *inside* the gather stage as repeated tool calls — Correx runs stages linearly
|
|
# (no parallel agents), so the model drives the fan-out itself.
|
|
#
|
|
# Per-source synthesis is the compression mechanism, not a nicety: the gather stage summarizes
|
|
# each fetched page into the source_dossier and the raw page text is discarded. The report stage
|
|
# consumes only those summaries, so research survives the token budget.
|
|
#
|
|
# Requires (in ~/.config/correx/config.toml):
|
|
# [tools.research]
|
|
# enabled = true
|
|
# searxng_url = "http://localhost:8888" # your self-hosted SearXNG (format=json enabled)
|
|
# [[artifacts]]
|
|
# id = "research_plan"; schema_path = "schemas/research_plan.json"; llm_emitted = true
|
|
# [[artifacts]]
|
|
# id = "source_dossier"; schema_path = "schemas/source_dossier.json"; llm_emitted = true
|
|
# [[artifacts]]
|
|
# id = "research_report"; schema_path = "schemas/research_report.json"; llm_emitted = true
|
|
#
|
|
# web_fetch is T2: the operator approves fetches before they leave the machine. web_search is T1
|
|
# (it only ever touches the configured SearXNG instance).
|
|
|
|
id = "research"
|
|
start = "decompose"
|
|
description = "Deep research: decompose a question, search + fetch sources, synthesize a cited report."
|
|
|
|
# 1. Question -> sub-questions + search queries. Reuses the planning discipline; read-only.
|
|
[[stages]]
|
|
id = "decompose"
|
|
prompt = "prompts/research_decompose.md"
|
|
produces = [{ name = "research_plan", kind = "research_plan" }]
|
|
token_budget = 8192
|
|
max_retries = 2
|
|
|
|
# 2. Run the searches, fetch promising sources, and summarize each one (per-source synthesis).
|
|
# web_search (T1) hits only SearXNG; web_fetch (T2) is operator-approved per source.
|
|
[[stages]]
|
|
id = "gather"
|
|
prompt = "prompts/research_gather.md"
|
|
needs = ["research_plan"]
|
|
produces = [{ name = "source_dossier", kind = "source_dossier" }]
|
|
allowed_tools = ["web_search", "web_fetch"]
|
|
token_budget = 32768
|
|
max_retries = 2
|
|
|
|
# 3. Cross-source synthesis into a cited report. Consumes the dossier summaries only — never raw pages.
|
|
[[stages]]
|
|
id = "report"
|
|
prompt = "prompts/research_report.md"
|
|
needs = ["source_dossier"]
|
|
produces = [{ name = "research_report", kind = "research_report" }]
|
|
token_budget = 16384
|
|
max_retries = 2
|
|
|
|
# --- forward edges ---
|
|
|
|
[[transitions]]
|
|
id = "decompose-to-gather"
|
|
from = "decompose"
|
|
to = "gather"
|
|
condition_type = "artifact_validated"
|
|
condition_artifact_id = "research_plan"
|
|
|
|
[[transitions]]
|
|
id = "gather-to-report"
|
|
from = "gather"
|
|
to = "report"
|
|
condition_type = "artifact_validated"
|
|
condition_artifact_id = "source_dossier"
|
|
|
|
[[transitions]]
|
|
id = "report-done"
|
|
from = "report"
|
|
to = "done"
|
|
condition_type = "artifact_validated"
|
|
condition_artifact_id = "research_report"
|