@blxzer/cursor-trellis 0.2.9 → 0.3.2

package/dist/templates/markdown/spec/guides/cursor-context-injection-guide.md.txt

@@ -10,11 +10,11 @@ Cursor has **four** channels that can put text in front of the model. They are *
 
 | Channel | How it loads | Reliable on Cursor? | Trellis content here |
 |---|---|---|---|
-| `.cursor/rules/*.mdc` (`alwaysApply: true`) | Prepended before **every** prompt, independent path | ✅ **Yes** | `trellis-triage.mdc` (Request Triage hard gate) |
+| `.cursor/rules/*.mdc` (`alwaysApply: true`) | Prepended before **every** prompt, independent path | ✅ **Yes** | `cstl-triage.mdc` (Request Triage hard gate) |
 | `beforeSubmitPrompt` hook → `additional_context` | Per user message; router emits `## 代码库检索计划` | ⚠️ **Verify on your Cursor build** (docs list field; forum reports vary) | `inject-retrieval-plan.py` + `retrieval-routing.mdc` enforcement |
 | `AGENTS.md` (repo root + nested) | Read automatically, treated as an always-on rule | ✅ **Yes** | smart-search-first rule, command surface, remote policy (the `<!-- TRELLIS:START -->` block) |
 | `sessionStart` hook → `additional_context` | Hook fires, JSON parsed... **but content never reaches the model's system context** | ❌ **No (confirmed bug)** | workflow.md Phase Index + Task Dashboard + first-reply notice |
-| `.trellis/workflow.md` (read on demand) | Only if the agent explicitly runs `get_context.py` or reads the file | ⚠️ Depends on agent taking action | Full Request Triage section, Task Ladder, workflow-state breadcrumbs |
+| `.cstl/workflow.md` (read on demand) | Only if the agent explicitly runs `get_context.py` or reads the file | ⚠️ Depends on agent taking action | Full Request Triage section, Task Ladder, workflow-state breadcrumbs |
 | **`task.py generate-dispatch-prompt` → Task `prompt`** (CLI Layer 2) | Main session runs Trellis script before `Task(...)` | ✅ **Yes (primary for subagent task context on Cursor)** | Full embed: marker, `Selected task:`, prd/jsonl/spec bodies |
 
 **Key takeaway**: anything that must reach the model **every turn without the agent choosing to load it** must live in `.cursor/rules` or `AGENTS.md`. Subagent task context on Cursor uses **CLI Layer 2** before Task dispatch; `preToolUse` hook injection is best-effort only (see forum reports + 2026-06-22 spike). Anything in `workflow.md` that depends on `sessionStart` injection is **invisible to Cursor agents** until the bug is fixed.
@@ -42,10 +42,10 @@ Because of the bug, Trellis routes content by reliability on Cursor:
 
 | Trellis content | Where it lives | Why |
 |---|---|---|
-| **Request Triage hard gate** (classify every turn, emit `[Triage: <Mode>]`) | `.cursor/rules/trellis-triage.mdc` (`alwaysApply: true`) | Must be visible every turn; sessionStart path is broken |
+| **Request Triage hard gate** (classify every turn, emit `[Triage: <Mode>]`) | `.cursor/rules/cstl-triage.mdc` (`alwaysApply: true`) | Must be visible every turn; sessionStart path is broken |
 | **smart-search-first web routing** | `AGENTS.md` (TRELLIS:START block) | AGENTS.md is a reliable always-on channel |
 | **Command surface** (what's user-invocable vs internal skill) | `AGENTS.md` (TRELLIS:START block) | Same |
-| **Workflow phases, Task Ladder, workflow-state breadcrumbs** | `.trellis/workflow.md` | Loaded on demand via `get_context.py` / `trellis-start` / `trellis-continue`; NOT auto-injected on Cursor |
+| **Workflow phases, Task Ladder, workflow-state breadcrumbs** | `.cstl/workflow.md` | Loaded on demand via `get_context.py` / `cstl-start` / `cstl-continue`; NOT auto-injected on Cursor |
 
 **If a new "must-always-be-visible" rule is added to Trellis**: ship it as a `.cursor/rules/*.mdc` (Cursor) — do **not** rely on adding it to `workflow.md` and expecting sessionStart to deliver it.
 
@@ -62,6 +62,6 @@ Because of the bug, Trellis routes content by reliability on Cursor:
 ## Related
 
 - `cursor-subagent-policy.md` — Task tool scenes, model routing (this guide is about **context injection**, that one is about **subagent dispatch**).
-- `.trellis/workflow.md` → `### Request Triage` — the full Triage decision tree (the rule in `.cursor/rules/trellis-triage.mdc` is the slim always-apply version pointing here).
+- `.cstl/workflow.md` → `### Request Triage` — the full Triage decision tree (the rule in `.cursor/rules/cstl-triage.mdc` is the slim always-apply version pointing here).
 - Task `06-19-cursor-rules-triage` (archive) — the investigation that produced this guide.
 - Cursor forum thread: https://forum.cursor.com/t/sessionstart-hook-additional-context-is-never-injected-into-agents-initial-system-context/158452

package/dist/templates/markdown/spec/guides/cursor-semantic-compliance.md.txt

@@ -16,7 +16,7 @@ Use the same patterns as telemetry:
 python -c "from common.retrieval_tool_classification import classify_tool_calls; print(classify_tool_calls(['Grep','codebase_search'], platform='cursor'))"
 ```
 
-(Run from `.trellis/scripts` with `PYTHONPATH` set to that directory.)
+(Run from `.cstl/scripts` with `PYTHONPATH` set to that directory.)
 
 On **cursor**, `semantic_executed` = `platform_semantic_executed`. Track `fast_context_count` and `cursor_fast_context_misuse` separately.
 
@@ -33,3 +33,9 @@ Plan-level presence does not imply execution-level use.
 ## Agent instructions
 
 When `platform-semantic` is in the route list, `render_agent_instructions` appends **语义合规（Cursor）** requiring one built-in semantic search before Top-1 and logging the host tool name.
+
+## Native live proof (OC-15, 2026-07-02)
+
+Controlled main-session run (`07-02-child-oc15-semantic-proof`): 3/3 conceptual queries with router `platform-semantic` executed host tool **`SemanticSearch`** → `platform_semantic_executed=true` (`cursor_env=native`). See `research/native-semantic-execution-proof.md`.
+
+**Caveat:** Proves observability + compliant-agent behavior; does not guarantee all sessions follow the plan (historical evals show Grep-only gaps when agents skip semantic).