@interf/compiler 0.7.1 → 0.7.2

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 +20 -23
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -2,11 +2,13 @@
2
2
 
3
3
  Interf prepares portable context for your agents.
4
4
 
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.
5
+ **Hallucinations aren't an agent problem. They're a data preparation problem.**
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
+ You ask your agent to analyze every file, miss nothing. It skims, guesses, answers anyway often with confident answers that are wrong.
8
8
 
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.
9
+ The fix is a map your agent navigates the full picture of your files, organized for this work. You tell Interf how to build it, in plain English that's a compilation workflow.
10
+
11
+ `Interf Compiler` is the local runtime that runs it. It enforces every stage and records proof of work — what ran, what was read, what was produced. 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
12
 
11
13
  ```text
12
14
  project-root/
@@ -24,11 +26,11 @@ project-root/
24
26
  bristol-office-analysis/ # saved source-files vs portable-context comparisons
25
27
  ```
26
28
 
27
- The project root is the control plane. Your agent starts from `interf/<work>/` when the source files are not enough.
29
+ Your agent starts from `interf/<work>/` when the source files are not enough.
28
30
 
29
31
  ## What a Run Looks Like
30
32
 
31
- Same files, same questions. What changes is whether the context was prepared first.
33
+ Same files, same questions. What changes is whether the portable context was prepared first.
32
34
 
33
35
  A recent public run — one market report, two questions, two agents on the same setup — produced:
34
36
 
@@ -43,16 +45,16 @@ Codex passed on the raw files; Claude Code only passed after Interf prepared the
43
45
 
44
46
  That gives you a readiness signal for the work and a fair comparison on the same files.
45
47
 
46
- The table is a sample, not a leaderboard. Run it on your own files. If you run more than one local agent, the same pass gives you a fair comparison between them on the same files.
48
+ The table is a sample, not a leaderboard. Run it on your own files. If you run more than one local agent, one `interf test` pass scores each of them.
47
49
 
48
50
  ## Design Choices
49
51
 
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.
52
- - `Check before build`: run `interf test --target raw` first sometimes the source files already pass on your questions.
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.
52
+ - `Per-work`: every portable context is built for one specific piece of agent work, not a generic index over your files.
53
+ - `Deterministic`: the compilation workflow is your method. Interf Compiler enforces every stage and records proof of work — no runtime discovery, no guessing.
54
+ - `Local-first and private`: your files, your questions, and your agent runs stay on your machine. No cloud, no uploads, no telemetry.
54
55
  - `Bring your own AI`: use Claude Code, Codex, or another local agent.
55
- - `Explicit`: no hidden store, no hidden index. The portable context is plain files on disk.
56
+ - `File over app`: the portable context is a local folder next to the source files — no hidden store, no hidden index. Inspect it, diff it, version it.
57
+ - `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.
56
58
 
57
59
  ## Install
58
60
 
@@ -78,7 +80,7 @@ Requires Node.js 20+ and a local coding agent such as Claude Code or Codex. Run
78
80
 
79
81
  ## Portable Context
80
82
 
81
- `interf/<work>/` is the local folder Interf Compiler builds from your files — a context layer your agents navigate, not a replacement for your files. For the built-in `interf-default`, it includes:
83
+ `interf/<work>/` is the local folder Interf Compiler builds from your files — a map your agent navigates, not a replacement for your files. For the built-in `interf-default`, it includes:
82
84
 
83
85
  ```text
84
86
  interf/bristol-office-analysis/
@@ -92,11 +94,11 @@ interf/bristol-office-analysis/
92
94
 
93
95
  The source files stay the source of truth. Interf builds next to them; it does not replace them.
94
96
 
95
- The portable context is a folder you can inspect, diff, version, or hand to a different agent. The portable context carries its own `raw/` snapshot, so the evidence the agent works from stays attached to the result.
97
+ The portable context is self-contained it carries its own `raw/` snapshot, so the evidence the agent works from stays attached to the result. Hand it to a different agent and the folder stands on its own.
96
98
 
97
99
  ## Workflow Packages
98
100
 
99
- A compilation workflow is how you tell Interf Compiler to organize and structure your files so your agents can reliably work from them. `interf init` copies the built-in `interf-default` into your project at `interf/workflows/interf-default/` — it is a real folder you can inspect and edit. Fork it with `interf create workflow` when you need a different method, a different output, or both.
101
+ A compilation workflow is how you tell Interf Compiler to organize and structure your files so your agents can reliably work from them. The built-in `interf-default` lives at `interf/workflows/interf-default/`. Fork it with `interf create workflow` when you need a different method, a different output, or both.
100
102
 
101
103
  ```text
102
104
  interf/workflows/interf-default/
@@ -119,9 +121,9 @@ interf/workflows/interf-default/
119
121
  - `use/query/` holds the instructions your agent follows when it reads the portable context for live work.
120
122
  - `improve/` holds the instructions Interf follows when the first build misses and the compilation workflow itself needs editing.
121
123
 
122
- A workflow package bundles a compilation workflow. Interf Compiler runs it on your files. Your local agent runs each stage. The result is a local folder your agents can read.
124
+ A workflow package bundles a compilation workflow. Interf Compiler runs it on your files and enforces each stage. The result is a local folder your agents can read.
123
125
 
124
- ## Self-Improving Workflows
126
+ ## Workflow Improvement
125
127
 
126
128
  When the first build still misses questions, Interf edits the workflow package itself and compiles again. Same files, same questions, different preparation.
127
129
 
@@ -129,12 +131,7 @@ Interf saves every scored run under `interf/tests/<work>/`. You can inspect what
129
131
 
130
132
  ## How the Pieces Fit
131
133
 
132
- - `interf.json` is the project control file. It names the work, points at the source files, saves the questions, and selects the compilation workflow.
133
- - A workflow package bundles a compilation workflow.
134
- - `workflow.json` defines the method.
135
- - `workflow.schema.json` defines the output contract, or context interface, the compiler must build.
136
- - `Interf Compiler` is the local runtime. It runs the compilation workflow, your agent runs each stage, and the portable context lands next to the source files.
137
- - The portable context is the local folder built for your agents. Technically, that folder is the compiled context.
134
+ `interf.json` names the work and selects the compilation workflow. `Interf Compiler` runs that workflow and writes the portable context — technically, the compiled context as a local folder next to your source files.
138
135
 
139
136
  ## interf.json
140
137
 
@@ -156,7 +153,7 @@ Interf saves every scored run under `interf/tests/<work>/`. You can inspect what
156
153
  }
157
154
  ```
158
155
 
159
- The `workflow` field is the key choice per work. It points to a folder id under `interf/workflows/`. Set it to `interf-default` (the built-in default, copied locally on init) or to a compilation workflow you have authored. A different compilation workflow is a different method and a different output. Same files, different portable context.
156
+ The `workflow` field is the key choice per work. It points to a folder id under `interf/workflows/`. Set it to `interf-default` (the built-in default) or to a compilation workflow you have authored. A different compilation workflow is a different method and a different output. Same files, different portable context.
160
157
 
161
158
  ## Questions
162
159
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@interf/compiler",
3
- "version": "0.7.1",
3
+ "version": "0.7.2",
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": {