'openai' reads as the cloud company — an operator running
self-hosted vLLM should be able to write what they mean. The new
value speaks the identical OpenAI wire (a guard test asserts the
emitted request stays byte-identical to api: openai, so the alias
can never drift into a dialect) but yields vLLM-specific error
hints (vllm serve, port 8000) instead of generic OpenAI prose.
Manifest + docs name the value in DE and EN.
Signed-off-by: flemming-it <sf@flemming.it>
Port the multi-API client from llm.chat (llm.rs kept in lockstep):
the optional api input selects the dialect, default stays the
unchanged v0.1.x Ollama behavior. openai covers vLLM, LM Studio,
LiteLLM and cloud OpenAI; api-specific error hints; api_key sent
as Bearer (ollama/openai) or x-api-key (anthropic). model_digest
stays an Ollama-only best-effort probe and is documented as such.
Proven end-to-end against a hermetic OpenAI-wire fake (request
shape validated, response parsed) via a hub flow run.
Signed-off-by: flemming-it <sf@flemming.it>
Brings module.yaml in line with F∆I 0.12.0's capability naming
convention. The legacy schema_version 1 (with implicit provider)
still loads in 0.12.0 via the grace-period default, but this
bump makes the publisher identity explicit and unblocks
storage-layout migration via 'fai migrate'.
See fai/platform docs/reference/capability-namespaces.yaml +
docs/operations/migration-to-0.12.md.
Signed-off-by: flemming-it <sf@flemming.it>
Ollama-backed summarisation module — fourth real F∆I capability,
following text.extract / llm.chat / text.translate. Completes
the text-processing trio for compose-grade workflows
(extract -> translate -> summarise, or any subset).
Capability:
Inputs:
text : text (source text)
style : text (e.g. "one paragraph", "three bullets";
defaults to "one paragraph")
language : text (output language hint; empty = source)
endpoint : text (Ollama /api/chat URL)
model : text
api_key : text (optional)
Outputs:
summary : text
style : text (echo for audit)
language : text (echo for audit)
model_endpoint : text
model_name : text
model_digest : text (Ollama /api/show probe; empty for
non-Ollama or transient failures)
Permissions: net to localhost / 127.0.0.1 / api.openai.com /
api.anthropic.com.
System prompt is conservative: faithful, neutral, preserves
named entities, no editorialising, no metadata. Reuses the LLM
client + digest-probe pattern from llm-chat / text-translate;
the duplication is acceptable at four modules and will be
factored into a shared crate when a fifth lands.
15 host-side tests cover prompt-building (style + language +
empty-language), Ollama-shaped response parsing, URL transform,
digest extraction, end-to-end success / probe-failure / non-
Ollama paths.
Wasm artifact: 118 KB. Built with v1.0 fai:platform imports.
Bootstrapped via 'fai new module text.summarize'.
Signed-off-by: flemming-it <sf@flemming.it>
