@interf/compiler 0.7.0 → 0.7.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +9 -8
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -2,16 +2,16 @@
2
2
 
3
3
  Interf prepares portable context for your agents.
4
4
 
5
- Agents now run real work from folders of PDFs, exports, notes, and transcripts. They don't reliably assemble the full picture from them: missed evidence, links lost across files, or answers that sound confident but are wrong. A chart inside one PDF can be obvious to a human analyst and easy for an agent to miss.
5
+ Point an agent at a folder of files. It gets a partial picture. It picks up false hypotheses from a shallow read. Then it carries those into the work — missed evidence, links lost across files, confident answers that are wrong.
6
6
 
7
- The fix is structure: summarize the files, organize by category, link what belongs together. You tell Interf Compiler how — that's a compilation workflow.
7
+ The fix is structure: summarize the files, organize by category, link what belongs together. You tell Interf Compiler how. That's a compilation workflow.
8
8
 
9
- `Interf Compiler` is the local runtime that runs compilation workflows on your files. Your local agent executes each stage. The compiler builds portable context — a local folder your agent reads. If the first build misses your questions, Interf improves the compilation workflow and builds again.
9
+ `Interf Compiler` is a local runtime. It runs your compilation workflow on your files. Your local agent executes each stage. The output is portable context — a local folder your agent reads. If the first build misses your questions, Interf improves the workflow and builds again.
10
10
 
11
11
  ```text
12
12
  project-root/
13
13
  bristol-office-analysis/
14
- report.pdf
14
+ report.md
15
15
  notes.md
16
16
  exports/
17
17
  interf.json # main config: works, source paths, questions, workflow choices, and defaults
@@ -28,7 +28,9 @@ The project root is the control plane. Your agent starts from `interf/<work>/` w
28
28
 
29
29
  ## What a Run Looks Like
30
30
 
31
- A recent public run — one PDF market report, two questions, two agents on the same setup produced:
31
+ Same files, same questions. What changes is whether the context was prepared first.
32
+
33
+ A recent public run — one market report, two questions, two agents on the same setup — produced:
32
34
 
33
35
  <!-- PUBLIC_BENCHMARK_TABLE:START -->
34
36
  | Agent | Source files | Portable context |
@@ -45,9 +47,10 @@ The table is a sample, not a leaderboard. Run it on your own files. If you run m
45
47
 
46
48
  ## Design Choices
47
49
 
50
+ - `Local-first`: your files, your questions, and your agent stay on your machine. No cloud, no uploads.
51
+ - `File over app`: the portable context is a local folder next to the source files. Inspect it, diff it, version it.
48
52
  - `Check before build`: run `interf test --target raw` first — sometimes the source files already pass on your questions.
49
53
  - `Scored on your own questions`: every build is checked against questions you wrote from the files. If the portable context does not help, `interf test` tells you.
50
- - `File over app`: the portable context is a local folder next to the source files. Inspect it, diff it, version it.
51
54
  - `Bring your own AI`: use Claude Code, Codex, or another local agent.
52
55
  - `Explicit`: no hidden store, no hidden index. The portable context is plain files on disk.
53
56
 
@@ -110,8 +113,6 @@ interf/workflows/interf-default/
110
113
  improve/ # how Interf revises this compilation workflow if questions still fail
111
114
  ```
112
115
 
113
- Think of it as method -> output shape.
114
-
115
116
  - `workflow.json` describes the method: expected inputs, stages, and how the files should be processed.
116
117
  - `workflow.schema.json` describes the output contract: what files and folders the output must contain. Technically, this is the `context interface`, declared in `workflow.schema.json` and enforced by the compiler.
117
118
  - `compile/stages/<stage>/` is where you author one folder per stage — a small, specific phase like `summarize` or `structure`. You write the instructions; the compiler runs them with your local agent.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@interf/compiler",
3
- "version": "0.7.0",
3
+ "version": "0.7.1",
4
4
  "description": "Local, open-source context compiler for agent work. Build portable context from your files with a compilation workflow you define. Check on your own questions.",
5
5
  "type": "module",
6
6
  "bin": {