# Context

> ⚠️ 已归档（2026-08-21）：本文是历史术语表，部分定义已与 v2 管线不一致，不再作为当前依据，正文不再更新；当前以 `PLAN_ai_analysis_v2.md` 和代码为准。

## Glossary

### Operation Fact
A fact directly extracted from replay command data, such as command time, player, command name, UnitId, asset id, special power id, production queue, or target position.

### UnitId (ObjectId)
The numeric identifier of a unit instance in the replay. `ObjectId` in raw replay data and `UnitId` in the AI analysis context refer to the same thing: a number (e.g., `239`, `246`) that identifies a specific unit or building instance during the game session. The AI is tasked with guessing what game asset type (e.g., `AlliedBarracks`, `CelestialScoutDrone`) a given UnitId corresponds to.

### UnitId Guess
A hypothesis about what game object (asset type) a UnitId (numeric identifier) represents. A UnitId Guess is not a fact unless it is directly supported by replay data or game rules.

### Operation
Any player action recorded in the replay log, including selection (select unit, create/select control group), command (move, attack, ability use), production/construction (start building, place building, start producing), and miscellaneous actions (select protocol, stance switch, rally point set). All are operations; the distinction between "运营类" (economy/construction) and non-operational operations in the AI prompt is a pragmatic optimization to reduce reasoning cost, not a domain concept.

### Evidence Level
The confidence assigned to a UnitId Guess or tactical conclusion. Valid levels are: confirmed (确定), highly likely (高度可能), possible (可能), uncertain (不确定), and ruled out (已排除).

> **Note:** The Chinese prompt text uses "不确定" (not "待确认"/pending confirmation) to match the `Uncertain` enum value. There is no implied promise of future confirmation — uncertainty simply means the current evidence is insufficient for a stronger conclusion.

### Analysis Segment
A time-bounded section of the replay operations, chosen by the LLM during the initial assessment phase. Segments are defined by start/end timestamps and may overlap. The LLM decides the segmentation based on observed gameplay phases (e.g., opening, early-mid game, mid game). Each segment is analyzed in a separate AI request round.

### Validation Rule
A deterministic rule that checks LLM claims against Operation Facts and known game rules.

### Validation Issue
A machine-detected problem in an LLM claim, such as a direct contradiction, weak evidence, missing alternative, or impossible timeline.

### Game Knowledge
Domain knowledge about the game or mod that the AI may use during analysis, such as unit capabilities, faction rules, map geometry, build restrictions, and known exceptions. Game knowledge may be used both to shape prompt guidance and to power deterministic validation.

### Knowledge Scope
The applicability boundary of a piece of game knowledge. A mod is a game version and defines its own complete knowledge set. Within a mod, scope can be global (applies to all factions and maps on that mod), faction-specific, or map-specific. There is no separate "mod scope" because the mod IS the top-level scope selector — the replay's mod determines which knowledge set is loaded.

### Knowledge Set
A named collection of game knowledge entries for a specific game version (mod). Each knowledge set is self-contained and complete for its mod — there is no cross-set inheritance or conditional sharing. The set is organized hierarchically by scope: `global/` entries apply across all factions and maps; `factions/{name}/` entries are scoped to a faction; `maps/{id}/` entries are scoped to a map. The replay's mod name directly selects which knowledge set to load (e.g., `"default"` for base game, `"corona"` for the Corona mod).

### Knowledge Entry
The smallest reusable unit of game knowledge within a knowledge set. A knowledge entry has an identifier, a set of predefined tags, and a text description (markdown). It is the unified format used both for prompt rendering and for validation queries. Scope is inherited from the entry's path position within the knowledge set (global, faction, or map), not stored in the entry itself.

### Knowledge Tag
A predefined label attached to a `KnowledgeEntry` to enable querying by validation logic. Tags belong to a finite taxonomy covering capabilities (e.g., `builder`, `pack`, `unpack`, `amphibious`, `returnToProducer`), types (e.g., `infantry`, `vehicle`, `aircraft`, `naval`, `structure`), combat roles (e.g., `antiInfantry`, `antiVehicle`, `antiAir`, `antiNaval`, `antiStructure`), and special power references (e.g., `specialPower:PackReplaceSelf`).

### Revision Pass
(Partially implemented) A hidden LLM request that receives the prior draft, validation issues, and relevant Operation Facts, then produces a corrected analysis without exposing apology or correction chatter to the user. Currently, validation issues are detected and logged, but no automatic revision pass is triggered. The revision logic still needs to be wired into `AIChatPanel`.