trueline-mcp 2.9.0 → 2.10.4

package/README.md

@@ -58,11 +58,17 @@ source file, that's 10-20 lines instead of hundreds.
 ```
 
 The agent sees the full structure, then uses `trueline_read` to fetch only
-the ranges it needs. A 500-line file where the agent needs one 20-line
-function? It reads 20 lines, not 500.
+the ranges it needs. Ranges are specified inline on each path:
+
+```
+file_paths: ["src/server.ts:25-45", "src/utils.ts:1-10,80-90"]
+```
+
+A 500-line file where the agent needs one 20-line function? It reads 20
+lines, not 500. Multiple files with different ranges in a single call.
 
 `trueline_search` finds lines by literal string or regex and returns them
-with edit-ready checksums, no outline or read step needed. For targeted
+with edit-ready refs, no outline or read step needed. For targeted
 edits where the agent knows what it's looking for, this is the fastest path.
 
 ### Edit: compact and verified
@@ -96,7 +102,7 @@ content that doesn't match what's on disk, the edit is rejected. If the
 agent targets the wrong lines, the edit is rejected. Nothing hits disk
 unless the hashes match.
 
-`trueline_verify` checks whether held checksums are still valid without
+`trueline_verify` checks whether held refs are still valid without
 re-reading the file. When nothing changed (the common case), the response
 is a single line.
 
@@ -108,8 +114,9 @@ workflow:
 
 - **SessionStart** injects instructions telling the agent how and when
   to use each trueline tool, calibrated per platform.
-- **PreToolUse** intercepts calls to the built-in edit tool and blocks
-  them, forcing the agent through hash-verified edits instead.
+- **PreToolUse** intercepts calls to the built-in read and edit tools,
+  redirecting reads of files over 3 KB to trueline and blocking
+  unverified edits entirely.
 
 With hooks, agent compliance is ~98%. Without hooks (instruction-only
 platforms like OpenCode and Codex CLI), compliance is ~60%. The
@@ -123,13 +130,18 @@ adapt advice accordingly.
 ## Where it helps most
 
 trueline's overhead is an MCP round-trip per tool call. For small files
-(under ~200 lines), the built-in tools are perfectly fine, and the
-injected instructions tell the agent so.
+(under ~3 KB), the built-in tools are perfectly fine and pass through
+without interception.
 
 The payoff comes on larger files and multi-file editing sessions, where
 targeted reads and compact edits avoid sending hundreds or thousands of
 redundant lines through the context window.
 
+In a typical 20-turn session exploring 8 files and editing 3, trueline
+saves roughly 11,000 tokens of mid-session context plus 623 tokens per
+turn from leaner instructions, for an estimated $1.58 per session in
+reduced API cost.
+
 ## Design
 
 See [DESIGN.md](DESIGN.md) for the protocol specification, hash