chain-modules/text-summarize
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

Compare commits

base: chain-modules:main
Branches Tags
chain-modules:main
chain-modules:v0.1.0
..
compare: chain-modules:v0.1.0
Branches Tags
chain-modules:main
chain-modules:v0.1.0

No commits in common. "main" and "v0.1.0" have entirely different histories.
main ... v0.1.0

11 changed files with 48 additions and 506 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.forgejo/workflows/ci.yml
View file

@ -30,7 +30,7 @@ jobs:
git fetch --depth=1 origin "$GITHUB_SHA"
git checkout -q FETCH_HEAD
# The chain-module-sdk dependency is a git dep against a repo
# The fai-module-sdk dependency is a git dep against a repo
# that lives in another Forgejo org. The repo-scoped
# GITHUB_TOKEN cannot read it, and the Forgejo instance has
# REQUIRE_SIGNIN_VIEW=true so anonymous read is also denied.

223
.forgejo/workflows/sign.yml
View file

@ -1,223 +0,0 @@
# F∆I module bundle signing workflow (cosign key-pinning model).
#
# Drop-in template for any module repo under chain-modules/.
# Triggers on tag push (vX.Y.Z) — builds the module, packs the
# .fai bundle, signs the bundle bytes with the Flemming.AI
# signing key (ECDSA P-256), and attaches bundle + .sig sidecar
# to the matching Forgejo Release.
#
# The hub-side verifier ships in 0.12.0+: when an operator sets
# `require_signatures: true`, install downloads the .sig sidecar
# from `<wasm_url>.sig` and verifies it against the pinned store
# public key (built-in for `bundled` / `official`, per-store
# config for everything else).
#
# Adopt by copying this file to `.forgejo/workflows/sign.yml` in
# the module repo and replacing the MODULE_NAME placeholder.
# Add the signing key to Forgejo secrets as FAI_SIGNING_KEY (PEM,
# unencrypted, ECDSA P-256). Rotation is a 5-minute key-roll +
# binary re-release; see infra/cosign/README.md.
name: sign-bundle
on:
push:
tags:
- 'v*.*.*'
env:
CARGO_TERM_COLOR: always
RUST_TOOLCHAIN: "1.86"
CARGO_NET_GIT_FETCH_WITH_CLI: "true"
jobs:
sign:
runs-on: ubuntu-latest
permissions:
contents: write # attach signature to release
env:
# The canonical module name as written in module.yaml.
# Used in the bundle filename + wasm path.
MODULE_NAME: text-summarize
steps:
# See fai/platform CI for background on the manual external
# checkout: the DinD runner cannot resolve forgejo:3000, so
# we clone via the external URL with $GITHUB_TOKEN.
- name: Checkout via external URL
run: |
set -eu
mkdir -p "$GITHUB_WORKSPACE"
cd "$GITHUB_WORKSPACE"
git init -q
git remote add origin \
"https://x-access-token:${GITHUB_TOKEN}@git.flemming.ai/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "$GITHUB_SHA"
git checkout -q FETCH_HEAD
# The chain-module-sdk dependency lives in another Forgejo org
# behind REQUIRE_SIGNIN_VIEW. MODULE_SDK_PAT (org-level
# secret, read-only on fai/module-sdk) authenticates cargo's
# git fetch via insteadOf.
- name: Configure git URL rewrite for SDK fetch
env:
SDK_PAT: ${{ secrets.MODULE_SDK_PAT }}
run: |
git config --global \
"url.https://x-access-token:${SDK_PAT}@git.flemming.ai/.insteadOf" \
"https://git.flemming.ai/"
- name: Install system dependencies
run: |
apt-get update -qq
apt-get install -y --no-install-recommends \
curl \
ca-certificates \
build-essential \
pkg-config \
libssl-dev \
git \
jq \
openssl
- name: Install Rust toolchain
run: |
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \
| sh -s -- -y \
--profile minimal \
--default-toolchain "$RUST_TOOLCHAIN" \
--target wasm32-wasip2
echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
- name: Build module (wasm32-wasip2)
run: cargo build --release --target wasm32-wasip2
- name: Install fai CLI
# Pinned to the production channel; signing requires the
# `fai pack` command. Override FAI_VERSION when bundle
# format compatibility matters.
run: |
curl -fsSL https://get.chain.flemming.ai | sh -s -- --no-bootstrap
# The installer drops fai at $HOME/.local/bin
echo "$HOME/.local/bin" >> "$GITHUB_PATH"
export PATH="$HOME/.local/bin:$PATH"
fai --version
- name: Stage bundle inputs
# The wasm artefact is named after the Cargo package
# (underscored), which may differ from the module name
# in module.yaml (dashed). Resolve it from Cargo.toml so
# the template stays agnostic to the project's naming
# convention.
run: |
set -eu
CARGO_NAME=$(grep -E '^name *= *"' Cargo.toml \
| head -1 | sed 's/.*"\(.*\)".*/\1/')
mkdir -p staging
cp module.yaml staging/
cp "target/wasm32-wasip2/release/${CARGO_NAME}.wasm" staging/module.wasm
if [ -f sbom.cdx.json ]; then cp sbom.cdx.json staging/; fi
if [ -f MODULE.md ]; then cp MODULE.md staging/; fi
if [ -f MODULE.de.md ]; then cp MODULE.de.md staging/; fi
- name: Pack bundle
id: pack
run: |
export PATH="$HOME/.local/bin:$PATH"
BUNDLE="${{ env.MODULE_NAME }}-${{ github.ref_name }}.fai"
fai pack staging --output "$BUNDLE"
echo "bundle=$BUNDLE" >> "$GITHUB_OUTPUT"
ls -la "$BUNDLE"
- name: Sign bundle (Flemming.AI signing key)
env:
FAI_SIGNING_KEY_PEM: ${{ secrets.FAI_SIGNING_KEY }}
run: |
if [ -z "${FAI_SIGNING_KEY_PEM:-}" ]; then
cat >&2 <<'EOF'
FAI_SIGNING_KEY secret is empty or undefined.
This workflow signs module bundles with the Flemming.AI
module-signing key (ECDSA P-256, PKCS#8 PEM, unencrypted).
The matching public key is pinned in the fai-hub binary at
infra/cosign/official.pub — hubs that require_signatures
will reject anything not signed with this key.
To configure:
1. Forgejo -> chain-modules org -> Settings -> Secrets
2. Add secret FAI_SIGNING_KEY (org-level recommended)
3. Paste the unencrypted PEM (BEGIN PRIVATE KEY ...)
The encrypted source-of-truth lives on Stefan's Mac at
~/.fai-secrets/flemming-ai-signing.key (passphrase in
mSecure under "Ch∆In — Module Signing Key (Private)").
See fai/platform infra/cosign/OPERATOR-HANDOFF.md for the
full setup runbook and rotation process.
EOF
exit 1
fi
umask 077
echo "$FAI_SIGNING_KEY_PEM" > /tmp/signing-key.pem
openssl dgst -sha256 \
-sign /tmp/signing-key.pem \
-out "${{ steps.pack.outputs.bundle }}.sig.raw" \
"${{ steps.pack.outputs.bundle }}"
base64 < "${{ steps.pack.outputs.bundle }}.sig.raw" \
> "${{ steps.pack.outputs.bundle }}.sig"
rm "${{ steps.pack.outputs.bundle }}.sig.raw"
shred -u /tmp/signing-key.pem || rm -f /tmp/signing-key.pem
ls -la "${{ steps.pack.outputs.bundle }}.sig"
- name: Round-trip verify
# Sanity-check: the freshly-signed bundle must verify
# against the well-known public key before we publish it.
run: |
curl -fsSL https://git.flemming.ai/fai/platform/raw/branch/main/infra/cosign/official.pub \
-o /tmp/official.pub
openssl dgst -sha256 \
-verify /tmp/official.pub \
-signature <(base64 -d < "${{ steps.pack.outputs.bundle }}.sig") \
"${{ steps.pack.outputs.bundle }}"
- name: Attach bundle + signature to Forgejo Release
run: |
set -eu
BUNDLE="${{ steps.pack.outputs.bundle }}"
SIG="$BUNDLE.sig"
REL_JSON=$(curl -sS \
-H "Authorization: token ${GITHUB_TOKEN}" \
"https://git.flemming.ai/api/v1/repos/${GITHUB_REPOSITORY}/releases/tags/${GITHUB_REF_NAME}")
REL_ID=$(echo "$REL_JSON" | jq -r '.id // empty')
if [ -z "$REL_ID" ] || [ "$REL_ID" = "null" ]; then
REL_ID=$(curl -sS -X POST \
-H "Authorization: token ${GITHUB_TOKEN}" \
-H "Content-Type: application/json" \
"https://git.flemming.ai/api/v1/repos/${GITHUB_REPOSITORY}/releases" \
-d "{\"tag_name\":\"${GITHUB_REF_NAME}\",\"name\":\"${GITHUB_REF_NAME}\",\"draft\":false,\"prerelease\":false,\"body\":\"Auto-generated by sign-bundle workflow\"}" \
| jq -r '.id')
fi
upload_one() {
local asset_path="$1" asset
asset=$(basename "$asset_path")
EXISTING=$(curl -sS \
-H "Authorization: token ${GITHUB_TOKEN}" \
"https://git.flemming.ai/api/v1/repos/${GITHUB_REPOSITORY}/releases/${REL_ID}/assets" \
| jq -r ".[] | select(.name==\"${asset}\") | .id")
if [ -n "$EXISTING" ]; then
curl -sS -X DELETE \
-H "Authorization: token ${GITHUB_TOKEN}" \
"https://git.flemming.ai/api/v1/repos/${GITHUB_REPOSITORY}/releases/${REL_ID}/assets/${EXISTING}" \
|| true
fi
curl -sS -X POST \
-H "Authorization: token ${GITHUB_TOKEN}" \
-F "attachment=@${asset_path}" \
"https://git.flemming.ai/api/v1/repos/${GITHUB_REPOSITORY}/releases/${REL_ID}/assets?name=${asset}" \
> /dev/null
echo "uploaded $asset"
}
upload_one "$BUNDLE"
upload_one "$SIG"
echo "release ${GITHUB_REF_NAME} ready: https://git.flemming.ai/${GITHUB_REPOSITORY}/releases/tag/${GITHUB_REF_NAME}"

24
Cargo.lock generated
View file

@ -39,11 +39,17 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
[[package]]
name = "chain-module-sdk"
name = "equivalent"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
[[package]]
name = "fai-module-sdk"
version = "0.1.2"
source = "git+https://git.flemming.ai/fai/chain-module-sdk-rust.git?branch=main#98e98e9371f7409560a1ef08bc0923d9a2506449"
source = "git+https://git.flemming.ws/fai/module-sdk.git?branch=main#f209fbc86f531b53e576f3cdbdf75750eef3b07a"
dependencies = [
"chain-module-sdk-macros",
"fai-module-sdk-macros",
"serde",
"serde_json",
"thiserror",
@ -51,21 +57,15 @@ dependencies = [
]
[[package]]
name = "chain-module-sdk-macros"
name = "fai-module-sdk-macros"
version = "0.1.2"
source = "git+https://git.flemming.ai/fai/chain-module-sdk-rust.git?branch=main#98e98e9371f7409560a1ef08bc0923d9a2506449"
source = "git+https://git.flemming.ws/fai/module-sdk.git?branch=main#f209fbc86f531b53e576f3cdbdf75750eef3b07a"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "equivalent"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
[[package]]
name = "form_urlencoded"
version = "1.2.2"
@ -267,7 +267,7 @@ dependencies = [
name = "text_summarize"
version = "0.1.0"
dependencies = [
"chain-module-sdk",
"fai-module-sdk",
"serde",
"serde_json",
"thiserror",

2
Cargo.toml
View file

@ -17,7 +17,7 @@ description = "F∆I module providing text.summarize"
crate-type = ["cdylib", "rlib"]
[dependencies]
chain-module-sdk = { git = "https://git.flemming.ai/fai/chain-module-sdk-rust.git", branch = "main" }
fai-module-sdk = { git = "https://git.flemming.ws/fai/module-sdk.git", branch = "main" }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
thiserror = "2"

2
LICENSE
View file

@ -58,7 +58,7 @@ APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets "[]" replaced with your own identifying information. (Don't include the brackets!) The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same "printed page" as the copyright notice for easier identification within third-party archives.
Copyright 2026 Flemming.AI
Copyright 2026 fai-modules
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.

97
MODULE.de.md
View file

@ -1,97 +0,0 @@
# text.summarize
Ollama-basierte treue Zusammenfassung. Sendet Quelltext an
einen konfigurierten LLM-Endpunkt mit einem Treue-vor-Kreativität-
System-Prompt und liefert die Zusammenfassung plus
audit-taugliche Modell-Herkunfts-Felder.
## Capability
- `text.summarize@0.1.0`
## Eingaben
| Name | Typ | Beschreibung |
| ----------- | ---- | ---------------------------------------------------------------------------------- |
| `text` | text | Quelltext. |
| `style` | text | Optionaler Stil-Hinweis (z.B. `one paragraph`, `three bullet points`, `a tweet`). Default: `one paragraph`. |
| `language` | text | Optionaler Ziel-Sprache (z.B. `German`, `ja-JP`). Leer = Quellsprache. |
| `endpoint` | text | Ollama-förmiger `/api/chat`-Endpunkt. |
| `model` | text | Modell-ID am Endpunkt. |
| `api_key` | text | Optionaler Bearer-Token für Cloud-Endpunkte. |
## Ausgaben
| Name | Typ | Beschreibung |
| ---------------- | ---- | ------------------------------------------------------------------ |
| `summary` | text | Die Zusammenfassung. |
| `style` | text | Echo des Stil-Inputs. |
| `language` | text | Echo des Sprach-Inputs. |
| `model_endpoint` | text | URL, gegen die zusammengefasst wurde. |
| `model_name` | text | Modell-ID wie an die LLM-API gesendet. |
| `model_digest` | text | SHA-256-Digest des bedienenden Ollama-Modells (wenn erreichbar). |
## Treue vor Kreativität
Der System-Prompt ist so getrimmt, dass die Zusammenfassung
aus dem Quelltext herleitbar bleibt — keine Spekulation, kein
mitgedachter Kontext, keine „kreativen" Umformulierungen, die
abdriften. Geeignet für Compliance-Flows, in denen eine
halluzinierte Zusammenfassung schlimmer ist als eine
ausführliche. Das Modell behält die Freiheit, die das vom
Operator gewählte LLM ihm gibt; dieses Modul ist der Prompt
+ Audit-Rahmen, kein fine-tuned Modell.
## Berechtigungen
```yaml
permissions:
- "net: localhost"
- "net: 127.0.0.1"
- "net: api.openai.com"
- "net: api.anthropic.com"
```
Analog `text.translate` — lokales Ollama per Default, Cloud
per Operator-Policy zuschaltbar.
## Grenzen in v0.1.0
- Single-Shot. Sehr lange Quelltexte (> 32k Tokens je nach
Modell) brauchen einen vorgeschalteten Chunker; v0.1.0
macht noch keine automatische Chunked-Summarise+Reduce-
Pipeline.
- Keine strukturierte Ausgabe. `summary` ist Freitext.
JSON-formatierte Zusammenfassungen
(`{ key_points: [], conclusions: [] }`) sind ein
v0.2.0-Kandidat.
## Beispiel-Flow
```yaml
name: extract-summarise
inputs:
document: bytes
steps:
- id: extract
use: text.extract@^0
with:
document: $inputs.document
- id: summarise
use: text.summarize@^0
with:
text: $extract.extracted.pages[*].text
style: "three bullet points"
endpoint: "http://localhost:11434/api/chat"
model: "qwen2.5:14b"
outputs:
summary: $summarise.summary
audit_model: $summarise.model_digest
```
## Build
```bash
cargo build --release --target wasm32-wasip2
# Ausgabe: target/wasm32-wasip2/release/text_summarize.wasm
```

94
MODULE.md
View file

@ -1,94 +0,0 @@
# text.summarize
Ollama-backed faithful summarisation. Sends source text to a
configured LLM endpoint with a fidelity-over-creativity system
prompt and emits the summary plus audit-grade
model-provenance fields.
## Capability
- `text.summarize@0.1.0`
## Inputs
| Name | Type | Description |
| ----------- | ---- | ---------------------------------------------------------------------------- |
| `text` | text | Source text to summarise. |
| `style` | text | Optional style hint (e.g. `one paragraph`, `three bullet points`, `a tweet`). Default: `one paragraph`. |
| `language` | text | Optional output-language hint (e.g. `German`, `ja-JP`). Empty = same as source. |
| `endpoint` | text | Ollama-shaped `/api/chat` endpoint URL. |
| `model` | text | Model identifier the endpoint serves. |
| `api_key` | text | Optional bearer token for cloud-hosted endpoints. |
## Outputs
| Name | Type | Description |
| ---------------- | ---- | ------------------------------------------------------------ |
| `summary` | text | The summary. |
| `style` | text | Echo of the input style. |
| `language` | text | Echo of the input language. |
| `model_endpoint` | text | URL the summary was generated against. |
| `model_name` | text | Model identifier as supplied to the LLM API. |
| `model_digest` | text | SHA-256 digest of the served Ollama model (when reachable). |
## Fidelity over creativity
The system prompt is tuned so the summary is derivable from
the source — no speculation, no implied context, no
"creative" rephrasing that drifts. Suitable for compliance
flows where a hallucinated summary is worse than a verbose
one. The model still has the freedom the operator's chosen
LLM gives it; this module is the prompt + audit harness, not
a fine-tuned model.
## Permissions
```yaml
permissions:
- "net: localhost"
- "net: 127.0.0.1"
- "net: api.openai.com"
- "net: api.anthropic.com"
```
Same shape as `text.translate` — local Ollama by default,
opt-in cloud via operator policy.
## Limits in v0.1.0
- Single-shot. Very long source texts (>32k tokens depending
on the model) need an upstream chunker; v0.1.0 does not yet
do automatic chunked-summarise + reduce.
- No structured output. `summary` is free-form text. JSON-
formatted summaries (e.g. `{ key_points: [], conclusions:
[] }`) are a v0.2.0 candidate.
## Example flow
```yaml
name: extract-summarise
inputs:
document: bytes
steps:
- id: extract
use: text.extract@^0
with:
document: $inputs.document
- id: summarise
use: text.summarize@^0
with:
text: $extract.extracted.pages[*].text
style: "three bullet points"
endpoint: "http://localhost:11434/api/chat"
model: "qwen2.5:14b"
outputs:
summary: $summarise.summary
audit_model: $summarise.model_digest
```
## Build
```bash
cargo build --release --target wasm32-wasip2
# Output: target/wasm32-wasip2/release/text_summarize.wasm
```

8
README.md
View file

@ -1,6 +1,6 @@
# text-summarize
Provides the `text.summarize` capability for Ch∆In.
Provides the `text.summarize` capability for F∆I Platform.
## Build
@ -15,7 +15,7 @@ cargo test # host-side unit + integration tests
fai test . # load the wasm component in the runtime sandbox
```
## Authoring with chain-module-sdk
## Authoring with fai-module-sdk
The module body is one decorated function:
@ -29,12 +29,12 @@ pub fn invoke(_ctx: Context, inputs: Inputs) -> Result<Outputs, ModuleError> {
The macro hides the wit_bindgen call, the Guest impl, the
Payload variant matching, and the `wit_bindgen::export!`
invocation. See `chain-module-sdk` documentation for the full
invocation. See `fai-module-sdk` documentation for the full
surface.
## SDK source
The Cargo.toml git-deps `chain-module-sdk` from
The Cargo.toml git-deps `fai-module-sdk` from
`https://git.flemming.ws/fai/module-sdk.git`. If your environment requires
authentication for that host (e.g. Forgejo with
`REQUIRE_SIGNIN_VIEW=true`), set up `git config insteadOf` with

BIN
module.wasm
View file

Binary file not shown.

100
module.yaml
View file

@ -1,5 +1,4 @@
schema_version: 3
provider: chain
schema_version: 1
name: text-summarize
version: 0.1.0
@ -10,79 +9,36 @@ provides:
# Inputs the invoke function accepts.
inputs:
text:
type: text
description:
en: Source text to summarise.
de: Quelltext, der zusammengefasst werden soll.
style:
type: text
description:
en: |
Style / shape of the summary, e.g. "one paragraph",
"three bullet points", "a tweet". Defaults to
"one paragraph" when omitted.
de: |
Stil/Form der Zusammenfassung, z. B. "ein Absatz",
"drei Bulletpoints", "ein Tweet". Default ist
"ein Absatz".
language:
type: text
description:
en: |
Optional output language hint, e.g. "German", "ja-JP".
Empty = same language as the source.
de: |
Optionale Ausgabesprache, z. B. "German", "ja-JP".
Leer = gleiche Sprache wie die Quelle.
endpoint:
type: text
description:
en: Ollama-shaped /api/chat endpoint.
de: Ollama-kompatibler /api/chat-Endpunkt.
model:
type: text
description:
en: Model identifier (e.g. "qwen2.5:14b").
de: Modell-Identifier (z. B. "qwen2.5:14b").
api_key:
type: text
description:
en: Optional bearer token for cloud-hosted endpoints.
de: Optionaler Bearer-Token für Cloud-Endpunkte.
# Source text to summarise.
text: text
# Style / shape of the summary, e.g. "one paragraph",
# "three bullet points", "a tweet". Defaults to
# "one paragraph" when omitted.
style: text
# Optional output language hint, e.g. "German", "ja-JP".
# Empty = same language as the source.
language: text
# Ollama-shaped /api/chat endpoint.
endpoint: text
# Model identifier (e.g. "qwen2.5:14b").
model: text
# Optional bearer token for cloud-hosted endpoints.
api_key: text
# Outputs produced.
outputs:
summary:
type: text
description:
en: The summary text.
de: Die zusammengefasste Antwort.
style:
type: text
description:
en: Echo of the style input for downstream audit.
de: Echo des Style-Inputs für Downstream-Audit.
language:
type: text
description:
en: Echo of the language input.
de: Echo des Language-Inputs.
model_endpoint:
type: text
description:
en: Endpoint the summary was generated against.
de: Endpunkt, gegen den die Zusammenfassung erzeugt wurde.
model_name:
type: text
description:
en: Model identifier as supplied to the LLM API.
de: An die LLM-API übergebenes Modell.
model_digest:
type: text
description:
en: SHA-256 digest of the served Ollama model (when reachable).
de: SHA-256-Digest des bedienten Ollama-Modells (wenn erreichbar).
# The summary text.
summary: text
# Echo of the style input for downstream audit.
style: text
# Echo of the language input.
language: text
# Endpoint the summary was generated against.
model_endpoint: text
# Model identifier as supplied to the LLM API.
model_name: text
# SHA-256 digest of the served Ollama model (when reachable).
model_digest: text
# Permissions required.
permissions:

2
src/lib.rs
View file

@ -9,7 +9,7 @@
mod llm;
use chain_module_sdk::prelude::*;
use fai_module_sdk::prelude::*;
const SYSTEM_PROMPT: &str = "You are a careful summarisation assistant. \
Produce a faithful, neutral summary of the user's text in the user's language. \