claw/src/runtime/scene_registry.rs

use std::fs;
use std::path::{Path, PathBuf};

use serde::Deserialize;
use serde_json::{Map, Value};

const STAGED_SCENE_ROOT: &str = "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging";

#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum DispatchMode {
    DirectBrowser,
    AgentBrowser,
}

#[derive(Debug, Clone, PartialEq, Eq)]
pub struct SceneRegistryEntry {
    pub id: String,
    pub name: String,
    pub summary: String,
    pub tags: Vec<String>,
    pub inputs: Vec<String>,
    pub outputs: Vec<String>,
    pub skill_package: String,
    pub skill_tool: String,
    pub skill_artifact_type: String,
    pub dispatch_mode: DispatchMode,
    pub expected_domain: String,
    pub aliases: Vec<String>,
    pub default_args: Map<String, Value>,
}

#[derive(Debug, Deserialize)]
struct SceneMetadata {
    id: String,
    name: String,
    summary: String,
    #[serde(default)]
    tags: Vec<String>,
    #[serde(default)]
    inputs: Vec<String>,
    #[serde(default)]
    outputs: Vec<String>,
    skill: SceneSkillMetadata,
}

#[derive(Debug, Deserialize)]
struct SceneSkillMetadata {
    package: String,
    tool: String,
    artifact_type: String,
}

#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
struct SceneMatchScore {
    matched_terms: usize,
    longest_term: usize,
}

#[derive(Debug, Clone, Copy, PartialEq, Eq)]
struct SceneMatchResult {
    score: SceneMatchScore,
    has_strong_phrase_hit: bool,
}

#[derive(Debug, Clone)]
struct SceneRuntimePolicy {
    scene_id: &'static str,
    dispatch_mode: DispatchMode,
    expected_domain: &'static str,
    aliases: &'static [&'static str],
}

const FIRST_SLICE_POLICIES: [SceneRuntimePolicy; 2] = [
    SceneRuntimePolicy {
        scene_id: "fault-details-report",
        dispatch_mode: DispatchMode::DirectBrowser,
        expected_domain: "sgcc.example.invalid",
        aliases: &["故障明细", "故障明细报表", "导出故障明细"],
    },
    SceneRuntimePolicy {
        scene_id: "95598-repair-city-dispatch",
        dispatch_mode: DispatchMode::AgentBrowser,
        expected_domain: "95598.example.invalid",
        aliases: &["95598抢修市指", "市指抢修监测", "95598抢修队列", "95598抢修市指监测"],
    },
];

pub fn load_first_slice_scene_registry() -> Vec<SceneRegistryEntry> {
    load_scene_registry_from_root(Path::new(STAGED_SCENE_ROOT))
}

pub fn load_scene_registry_from_root(root: &Path) -> Vec<SceneRegistryEntry> {
    let mut registry = Vec::new();
    for policy in FIRST_SLICE_POLICIES {
        if let Some(entry) = load_scene_entry(root, &policy) {
            registry.push(entry);
        }
    }
    registry
}

pub fn match_scene_instruction(instruction: &str) -> Option<SceneRegistryEntry> {
    let registry = load_first_slice_scene_registry();
    match_scene_instruction_in_registry(&registry, instruction)
}

pub fn match_scene_instruction_in_registry(
    registry: &[SceneRegistryEntry],
    instruction: &str,
) -> Option<SceneRegistryEntry> {
    let normalized_instruction = normalize_for_match(instruction);
    if normalized_instruction.is_empty() {
        return None;
    }

    let mut best_match: Option<(SceneMatchResult, &SceneRegistryEntry)> = None;
    let mut ambiguous = false;
    let mut strong_phrase_hits = 0;

    for entry in registry {
        let Some(result) = score_scene_instruction(entry, &normalized_instruction) else {
            continue;
        };
        if result.has_strong_phrase_hit {
            strong_phrase_hits += 1;
        }

        match &best_match {
            None => {
                best_match = Some((result, entry));
                ambiguous = false;
            }
            Some((current_result, _)) if result.score > current_result.score => {
                best_match = Some((result, entry));
                ambiguous = false;
            }
            Some((current_result, current_entry)) if result.score == current_result.score => {
                if result.has_strong_phrase_hit && current_result.has_strong_phrase_hit {
                    if current_entry.id != entry.id {
                        ambiguous = true;
                    }
                } else if result.has_strong_phrase_hit && !current_result.has_strong_phrase_hit {
                    best_match = Some((result, entry));
                    ambiguous = false;
                } else if current_result.has_strong_phrase_hit && !result.has_strong_phrase_hit {
                    ambiguous = false;
                } else if current_entry.id != entry.id {
                    ambiguous = true;
                }
            }
            Some(_) => {}
        }
    }

    if ambiguous || strong_phrase_hits > 1 {
        None
    } else {
        best_match.map(|(_, entry)| entry.clone())
    }
}

fn load_scene_entry(root: &Path, policy: &SceneRuntimePolicy) -> Option<SceneRegistryEntry> {
    let scene_path = scene_json_path(root, policy.scene_id);
    let contents = fs::read_to_string(scene_path).ok()?;
    let metadata: SceneMetadata = serde_json::from_str(&contents).ok()?;
    if metadata.id != policy.scene_id {
        return None;
    }

    Some(SceneRegistryEntry {
        id: policy.scene_id.to_string(),
        name: metadata.name,
        summary: metadata.summary,
        tags: metadata.tags,
        inputs: metadata.inputs,
        outputs: metadata.outputs,
        skill_package: metadata.skill.package,
        skill_tool: metadata.skill.tool,
        skill_artifact_type: metadata.skill.artifact_type,
        dispatch_mode: policy.dispatch_mode,
        expected_domain: policy.expected_domain.to_string(),
        aliases: policy.aliases.iter().map(|alias| (*alias).to_string()).collect(),
        default_args: Map::new(),
    })
}

fn scene_json_path(root: &Path, scene_id: &str) -> PathBuf {
    root.join("scenes").join(scene_id).join("scene.json")
}

fn score_scene_instruction(
    entry: &SceneRegistryEntry,
    normalized_instruction: &str,
) -> Option<SceneMatchResult> {
    let mut matched_terms = 0;
    let mut longest_term = 0;
    let mut has_strong_phrase_hit = false;

    for term in candidate_match_terms(entry) {
        let normalized_term = normalize_for_match(&term);
        if normalized_term.len() < 2 {
            continue;
        }
        if normalized_instruction.contains(&normalized_term) {
            matched_terms += 1;
            longest_term = longest_term.max(normalized_term.len());
            if normalized_term.len() >= 6 {
                has_strong_phrase_hit = true;
            }
        }
    }

    if matched_terms == 0 {
        None
    } else {
        Some(SceneMatchResult {
            score: SceneMatchScore {
                matched_terms,
                longest_term,
            },
            has_strong_phrase_hit,
        })
    }
}

fn candidate_match_terms(entry: &SceneRegistryEntry) -> Vec<String> {
    let mut terms = Vec::new();
    terms.push(entry.id.clone());
    terms.push(entry.name.clone());
    terms.push(entry.summary.clone());
    terms.extend(entry.tags.iter().cloned());
    terms.extend(entry.aliases.iter().cloned());
    terms
}

fn normalize_for_match(value: &str) -> String {
    value
        .chars()
        .filter(|ch| !ch.is_whitespace() && *ch != '-' && *ch != '_' && *ch != ':')
        .flat_map(|ch| ch.to_lowercase())
        .collect()
}