riffer 0.54.0 → 0.56.0
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.
- checksums.yaml +4 -4
- data/.claude/rules/rbs-inline.md +6 -6
- data/.release-please-manifest.json +1 -1
- data/.ruby-version +1 -1
- data/CHANGELOG.md +46 -0
- data/README.md +26 -1
- data/Steepfile +2 -2
- data/UPGRADING.md +3 -0
- data/docs/AGENTS.md +37 -12
- data/docs/AGENT_LIFECYCLE.md +1 -1
- data/docs/CATALOG.md +8 -8
- data/docs/CONFIGURATION.md +95 -17
- data/docs/GUARDRAILS.md +2 -0
- data/docs/MCP.md +3 -4
- data/docs/MESSAGES.md +112 -15
- data/docs/STABILITY.md +32 -0
- data/docs/STREAM_EVENTS.md +17 -1
- data/docs/TESTING.md +22 -1
- data/docs/TOOLS.md +11 -11
- data/docs/TRACING.md +1 -1
- data/docs/providers/AMAZON_BEDROCK.md +3 -1
- data/docs/providers/ANTHROPIC.md +44 -44
- data/docs/providers/CUSTOM_PROVIDERS.md +59 -0
- data/docs/providers/GEMINI.md +76 -26
- data/docs/providers/GOOGLE_CLOUD.md +363 -0
- data/docs/providers/MOCK_PROVIDER.md +2 -0
- data/docs/providers/OPENAI.md +3 -1
- data/docs/providers/PROVIDERS.md +30 -18
- data/docs-site/manifest.yml +6 -0
- data/lib/riffer/agent/run.rb +28 -13
- data/lib/riffer/agent/session.rb +33 -10
- data/lib/riffer/agent/structured_output.rb +6 -1
- data/lib/riffer/config/anthropic.rb +9 -0
- data/lib/riffer/config/future.rb +53 -0
- data/lib/riffer/config/gemini.rb +9 -0
- data/lib/riffer/config/google_cloud.rb +38 -0
- data/lib/riffer/config/pricing.rb +5 -15
- data/lib/riffer/config.rb +19 -0
- data/lib/riffer/deprecation/event.rb +25 -0
- data/lib/riffer/deprecation.rb +60 -0
- data/lib/riffer/http/client.rb +141 -0
- data/lib/riffer/http.rb +5 -0
- data/lib/riffer/mcp/client.rb +0 -1
- data/lib/riffer/messages/assistant/server_tool_part.rb +73 -0
- data/lib/riffer/messages/assistant/text_part.rb +52 -0
- data/lib/riffer/messages/assistant.rb +64 -17
- data/lib/riffer/params/any_of.rb +37 -9
- data/lib/riffer/params/param.rb +35 -14
- data/lib/riffer/params.rb +34 -19
- data/lib/riffer/providers/amazon_bedrock.rb +38 -5
- data/lib/riffer/providers/anthropic/client.rb +49 -0
- data/lib/riffer/providers/anthropic.rb +19 -452
- data/lib/riffer/providers/anthropic_compatible/messages_api/stream.rb +219 -0
- data/lib/riffer/providers/anthropic_compatible/messages_api.rb +315 -0
- data/lib/riffer/providers/anthropic_compatible.rb +5 -0
- data/lib/riffer/providers/anthropic_vertex.rb +66 -0
- data/lib/riffer/providers/base.rb +19 -13
- data/lib/riffer/providers/gemini/client.rb +17 -85
- data/lib/riffer/providers/gemini.rb +213 -81
- data/lib/riffer/providers/google_cloud/client.rb +106 -0
- data/lib/riffer/providers/google_cloud.rb +99 -0
- data/lib/riffer/providers/open_ai.rb +21 -16
- data/lib/riffer/providers/repository.rb +2 -0
- data/lib/riffer/stream_events/server_tool_done.rb +21 -0
- data/lib/riffer/testing.rb +6 -0
- data/lib/riffer/version.rb +1 -1
- data/lib/riffer/wire/sse.rb +51 -0
- data/lib/riffer/wire.rb +31 -0
- data/lib/riffer.rb +20 -0
- data/rbs_collection.lock.yaml +24 -4
- data/sig/_private/faraday.rbs +8 -0
- data/sig/_private/googleauth.rbs +7 -0
- data/sig/generated/riffer/agent/run.rbs +5 -0
- data/sig/generated/riffer/agent/session.rbs +6 -0
- data/sig/generated/riffer/config/anthropic.rbs +6 -0
- data/sig/generated/riffer/config/future.rbs +29 -0
- data/sig/generated/riffer/config/gemini.rbs +6 -0
- data/sig/generated/riffer/config/google_cloud.rbs +28 -0
- data/sig/generated/riffer/config/pricing.rbs +0 -9
- data/sig/generated/riffer/config.rbs +10 -0
- data/sig/generated/riffer/deprecation/event.rbs +17 -0
- data/sig/generated/riffer/deprecation.rbs +27 -0
- data/sig/generated/riffer/http/client.rbs +59 -0
- data/sig/generated/riffer/http.rbs +4 -0
- data/sig/generated/riffer/messages/assistant/server_tool_part.rbs +44 -0
- data/sig/generated/riffer/messages/assistant/text_part.rbs +35 -0
- data/sig/generated/riffer/messages/assistant.rbs +24 -11
- data/sig/generated/riffer/params/any_of.rbs +13 -5
- data/sig/generated/riffer/params/param.rbs +10 -5
- data/sig/generated/riffer/params.rbs +8 -4
- data/sig/generated/riffer/providers/amazon_bedrock.rbs +14 -2
- data/sig/generated/riffer/providers/anthropic/client.rbs +34 -0
- data/sig/generated/riffer/providers/anthropic.rbs +5 -124
- data/sig/generated/riffer/providers/anthropic_compatible/messages_api/stream.rbs +81 -0
- data/sig/generated/riffer/providers/anthropic_compatible/messages_api.rbs +108 -0
- data/sig/generated/riffer/providers/anthropic_compatible.rbs +4 -0
- data/sig/generated/riffer/providers/anthropic_vertex.rbs +45 -0
- data/sig/generated/riffer/providers/base.rbs +5 -0
- data/sig/generated/riffer/providers/gemini/client.rbs +11 -34
- data/sig/generated/riffer/providers/gemini.rbs +66 -4
- data/sig/generated/riffer/providers/google_cloud/client.rbs +71 -0
- data/sig/generated/riffer/providers/google_cloud.rbs +64 -0
- data/sig/generated/riffer/providers/open_ai.rbs +7 -2
- data/sig/generated/riffer/stream_events/server_tool_done.rbs +15 -0
- data/sig/generated/riffer/testing.rbs +4 -0
- data/sig/generated/riffer/wire/sse.rbs +23 -0
- data/sig/generated/riffer/wire.rbs +17 -0
- data/sig/generated/riffer.rbs +15 -0
- data/sig/manual/riffer/deprecation.rbs +5 -0
- data/sig/manual/riffer/providers/anthropic_compatible/messages_api.rbs +8 -0
- data/sig/manual/riffer/providers/gemini.rbs +8 -0
- data/sig/manual/riffer/providers/google_cloud.rbs +8 -0
- data/sig/manual/riffer/wire.rbs +5 -0
- metadata +76 -5
- data/sig/_private/anthropic.rbs +0 -17
- data/sig/_private/riffer/providers/anthropic.rbs +0 -6
- data/sig/_private/riffer/providers/gemini.rbs +0 -7
data/docs/MESSAGES.md
CHANGED
|
@@ -57,7 +57,7 @@ msg = Riffer::Messages::Assistant.new("", tool_calls: [
|
|
|
57
57
|
{id: "call_123", call_id: "call_123", name: "weather_tool", arguments: '{"city":"Tokyo"}'}
|
|
58
58
|
])
|
|
59
59
|
msg.tool_calls # => [{id: "call_123", ...}]
|
|
60
|
-
msg.to_h # => {role:
|
|
60
|
+
msg.to_h # => {role: :assistant, parts: [{part: :tool_call, ...}]}
|
|
61
61
|
|
|
62
62
|
# Accessing token usage data (when available from provider)
|
|
63
63
|
if msg.token_usage
|
|
@@ -134,7 +134,7 @@ The `to_h` representation includes `structured_output` only when present:
|
|
|
134
134
|
|
|
135
135
|
```ruby
|
|
136
136
|
msg = Riffer::Messages::Assistant.new('{"sentiment":"positive"}', structured_output: {sentiment: "positive"})
|
|
137
|
-
msg.to_h # => {role: :assistant,
|
|
137
|
+
msg.to_h # => {role: :assistant, parts: [{part: :text, text: '{"sentiment":"positive"}'}], structured_output: {sentiment: "positive"}}
|
|
138
138
|
```
|
|
139
139
|
|
|
140
140
|
#### Reasoning
|
|
@@ -170,13 +170,14 @@ A `type` outside the three values raises `Riffer::ArgumentError`. `format` is a
|
|
|
170
170
|
|
|
171
171
|
`reasoning?` is true when the message carries any part. `reasoning_text` joins the `text` of the `:text` and `:summary` parts with blank lines, skipping `:encrypted` parts, and is `nil` when there is nothing to join. The run's final assistant message projects its parts onto `response.reasoning` (see [Agent Lifecycle — Response Attributes](AGENT_LIFECYCLE.md#response-attributes)).
|
|
172
172
|
|
|
173
|
-
Parts round-trip through `to_h` / `from_hash` like every other message field, so an application that persists sessions can store and replay them.
|
|
173
|
+
Parts round-trip through `to_h` / `from_hash` like every other message field, so an application that persists sessions can store and replay them. `to_h` writes each reasoning part as a [`parts`](#parts) entry tagged `part: :reasoning`, and each part omits the fields it doesn't carry:
|
|
174
174
|
|
|
175
175
|
```ruby
|
|
176
176
|
msg.to_h
|
|
177
|
-
# => {role: :assistant,
|
|
178
|
-
# {type: :summary, text: "The user wants the answer.", format: "mock-v1"},
|
|
179
|
-
# {type: :encrypted, data: "b3BhcXVl", format: "mock-v1"}
|
|
177
|
+
# => {role: :assistant, parts: [
|
|
178
|
+
# {part: :reasoning, type: :summary, text: "The user wants the answer.", format: "mock-v1"},
|
|
179
|
+
# {part: :reasoning, type: :encrypted, data: "b3BhcXVl", format: "mock-v1"},
|
|
180
|
+
# {part: :text, text: "42"}
|
|
180
181
|
# ]}
|
|
181
182
|
|
|
182
183
|
Riffer::Messages::Base.from_hash(msg.to_h).reasoning # => [ReasoningPart, ReasoningPart]
|
|
@@ -184,14 +185,108 @@ Riffer::Messages::Base.from_hash(msg.to_h).reasoning # => [ReasoningPart, Reaso
|
|
|
184
185
|
|
|
185
186
|
**The replay contract.** A provider adapter replays only the parts whose `format` it recognizes and silently skips the rest, so history that travelled through another provider is never rejected. A part with no `format` is never replayed; adapters that surface reasoning text but cannot yet send it back emit their parts that way, so the text is kept for display without risking a rejected request. Parts are never reordered, merged, or edited — riffer treats them as opaque, because the provider's signature covers their exact bytes.
|
|
186
187
|
|
|
187
|
-
An application that would rather not store
|
|
188
|
+
An application that would rather not store reasoning can drop the reasoning entries of `parts` when it serializes:
|
|
188
189
|
|
|
189
190
|
```ruby
|
|
190
|
-
msg.to_h
|
|
191
|
+
hash = msg.to_h
|
|
192
|
+
hash[:parts] = hash[:parts].reject { |part| part[:part] == :reasoning }
|
|
191
193
|
```
|
|
192
194
|
|
|
193
195
|
To drop parts from the in-memory session mid-run instead, `Session#update(id:, reasoning: [])` rewrites the message in place; it needs [message ids](#ids) enabled to address it.
|
|
194
196
|
|
|
197
|
+
#### Parts
|
|
198
|
+
|
|
199
|
+
`parts` is the assistant turn in the order the provider produced it. `content`, `tool_calls` and `reasoning` are views over it. Some providers interleave reasoning, server-side tools and text in one turn, and Anthropic needs the turn back in that order: Claude signs each thinking block over every block before it. Sending earlier turns back unchanged also keeps the model's own reasoning and search results, and keeps the prompt cache warm, since the history doesn't change between requests.
|
|
200
|
+
|
|
201
|
+
A part is one of:
|
|
202
|
+
|
|
203
|
+
| Class | Holds |
|
|
204
|
+
| ---------------- | -------------------------------------------------------------------------------------------------------------------------------------- |
|
|
205
|
+
| `TextPart` | One stretch of answer text (`text`). `data` keeps the provider's block when it carries more than the text, such as Anthropic citations |
|
|
206
|
+
| `ReasoningPart` | A thinking block (see [Reasoning](#reasoning)) |
|
|
207
|
+
| `ToolCall` | A function call riffer runs (see [Tool Calls](#tool-calls)) |
|
|
208
|
+
| `ServerToolPart` | A call (`kind: :call`) or result (`kind: :result`) of a tool the provider ran itself, such as web search |
|
|
209
|
+
|
|
210
|
+
`TextPart` carries:
|
|
211
|
+
|
|
212
|
+
| Field | Type | Description |
|
|
213
|
+
| -------- | --------- | ------------------------------------------------------------------------------------------------------ |
|
|
214
|
+
| `text` | `String` | The answer text |
|
|
215
|
+
| `data` | `String?` | The provider's whole block as JSON, kept when it carries more than the text (e.g. Anthropic citations) |
|
|
216
|
+
| `format` | `String?` | The wire format of `data`, owned by the adapter that produced it |
|
|
217
|
+
|
|
218
|
+
`ServerToolPart` carries:
|
|
219
|
+
|
|
220
|
+
| Field | Type | Description |
|
|
221
|
+
| -------- | --------- | --------------------------------------------------------------------------------------------- |
|
|
222
|
+
| `name` | `String` | The tool's name (e.g. `"web_search"`) |
|
|
223
|
+
| `kind` | `Symbol` | `:call` or `:result` |
|
|
224
|
+
| `data` | `String` | The provider's block as JSON, unchanged |
|
|
225
|
+
| `id` | `String?` | The provider's identifier, shared by a call and its result |
|
|
226
|
+
| `format` | `String?` | The wire format, owned by the adapter that produced the part (e.g. `"anthropic-messages-v1"`) |
|
|
227
|
+
|
|
228
|
+
A `kind` outside `:call` and `:result` raises `Riffer::ArgumentError`.
|
|
229
|
+
|
|
230
|
+
```ruby
|
|
231
|
+
msg = Riffer::Messages::Assistant.new(parts: [
|
|
232
|
+
Riffer::Messages::Assistant::TextPart.new("Let me check. "),
|
|
233
|
+
Riffer::Messages::Assistant::ServerToolPart.new(name: "web_search", kind: :call, id: "srvtoolu_1", data: "{...}", format: "anthropic-messages-v1"),
|
|
234
|
+
Riffer::Messages::Assistant::ServerToolPart.new(name: "web_search", kind: :result, id: "srvtoolu_1", data: "{...}", format: "anthropic-messages-v1"),
|
|
235
|
+
Riffer::Messages::Assistant::ReasoningPart.new(type: :text, text: "", signature: "CAQS...", format: "anthropic-messages-v1"),
|
|
236
|
+
Riffer::Messages::Assistant::TextPart.new("The latest stable Ruby version is 4.0.9.")
|
|
237
|
+
])
|
|
238
|
+
|
|
239
|
+
msg.content # => "Let me check. The latest stable Ruby version is 4.0.9."
|
|
240
|
+
msg.reasoning # => [ReasoningPart]
|
|
241
|
+
msg.reasoning? # => true; server tool parts don't count as reasoning
|
|
242
|
+
```
|
|
243
|
+
|
|
244
|
+
- `content` joins the text parts with no separator.
|
|
245
|
+
- `Assistant.new(content, tool_calls:, reasoning:)` builds the parts in a fixed order: reasoning, then `content` as one text part (none when empty), then tool calls.
|
|
246
|
+
- Passing `parts:` together with `content`, `tool_calls:` or `reasoning:` raises `Riffer::ArgumentError`.
|
|
247
|
+
- `ServerToolPart#data` holds the provider's block as JSON, unchanged. It follows the same replay contract as reasoning: only the adapter that recognizes its `format` sends it back, and other adapters skip it. The same goes for a `TextPart` that carries `data`; other adapters send its `text`.
|
|
248
|
+
|
|
249
|
+
`to_h` writes the turn as a `parts` key, so it keeps the order, the server tool parts and the `data` of text parts. Each entry is the part's own hash plus a `part` tag (`:text`, `:reasoning`, `:tool_call` or `:server_tool`). It doesn't write `content`, `tool_calls` or `reasoning`; read those from the message:
|
|
250
|
+
|
|
251
|
+
```ruby
|
|
252
|
+
msg.to_h
|
|
253
|
+
# => {role: :assistant, parts: [
|
|
254
|
+
# {part: :text, text: "Let me check. "},
|
|
255
|
+
# {part: :server_tool, name: "web_search", kind: :call, data: "{...}", id: "srvtoolu_1", format: "anthropic-messages-v1"},
|
|
256
|
+
# ...
|
|
257
|
+
# ]}
|
|
258
|
+
|
|
259
|
+
{content: msg.content, tool_calls: msg.tool_calls.map(&:to_h), reasoning: msg.reasoning.map(&:to_h)}
|
|
260
|
+
```
|
|
261
|
+
|
|
262
|
+
`from_hash` reads this shape and the older one with `content`, `tool_calls` and `reasoning` keys, so stored sessions still load. Rebuilt from the older shape, the turn is in the fixed order, without server tool parts or the `data` of text parts. A hash with `parts` and a non-nil `content`, or a non-empty `tool_calls` or `reasoning`, raises `Riffer::ArgumentError`.
|
|
263
|
+
|
|
264
|
+
**Editing a turn.** Riffer sends the parts back as they are. When you change a turn's text (in an output guardrail, or with `Session#update`), keeping the rest of the turn consistent is up to you:
|
|
265
|
+
|
|
266
|
+
- Drop that turn's reasoning parts. They were signed over the old text, so Anthropic would reject them or drop them silently, and they may still hold the text you removed.
|
|
267
|
+
- Keep server tool parts and tool calls, so the model doesn't search again and tool results keep their call.
|
|
268
|
+
- Put the new text after the last server tool part and before the first tool call.
|
|
269
|
+
|
|
270
|
+
```ruby
|
|
271
|
+
def redact(message, text)
|
|
272
|
+
kept = message.parts.reject do |part|
|
|
273
|
+
part.is_a?(Riffer::Messages::Assistant::ReasoningPart) || part.is_a?(Riffer::Messages::Assistant::TextPart)
|
|
274
|
+
end
|
|
275
|
+
index = kept.index { |part| part.is_a?(Riffer::Messages::Assistant::ToolCall) } || kept.length
|
|
276
|
+
parts = kept.insert(index, Riffer::Messages::Assistant::TextPart.new(text))
|
|
277
|
+
|
|
278
|
+
Riffer::Messages::Assistant.new(
|
|
279
|
+
parts: parts,
|
|
280
|
+
id: message.id,
|
|
281
|
+
token_usage: message.token_usage,
|
|
282
|
+
finish_reason: message.finish_reason,
|
|
283
|
+
finish_reason_raw: message.finish_reason_raw
|
|
284
|
+
)
|
|
285
|
+
end
|
|
286
|
+
```
|
|
287
|
+
|
|
288
|
+
`Assistant.new(text)` and `Session#update(id:, content:)` don't follow these rules. They rebuild the turn in the fixed order, which keeps the reasoning and drops server tool parts. Use `Session#update(id:, parts:)` to replace the parts as given.
|
|
289
|
+
|
|
195
290
|
### Tool
|
|
196
291
|
|
|
197
292
|
Tool messages contain the results of tool executions:
|
|
@@ -360,12 +455,14 @@ Without this step, the same model can receive different input depending on the p
|
|
|
360
455
|
|
|
361
456
|
### Merge rules
|
|
362
457
|
|
|
363
|
-
| Message type | Content | Auxiliary data
|
|
364
|
-
| ------------ | -------------------- |
|
|
365
|
-
| `System` | Joined with `"\n\n"` | —
|
|
366
|
-
| `User` | Joined with `"\n\n"` | `files` arrays concatenated
|
|
367
|
-
| `Assistant` | Joined with `"\n\n"` | `tool_calls` arrays concatenated | Yes |
|
|
368
|
-
| `Tool` | — | —
|
|
458
|
+
| Message type | Content | Auxiliary data | Merged? |
|
|
459
|
+
| ------------ | -------------------- | ------------------------------------------------ | ---------------------------------------- |
|
|
460
|
+
| `System` | Joined with `"\n\n"` | — | Yes |
|
|
461
|
+
| `User` | Joined with `"\n\n"` | `files` arrays concatenated | Yes |
|
|
462
|
+
| `Assistant` | Joined with `"\n\n"` | `tool_calls` and `reasoning` arrays concatenated | Yes |
|
|
463
|
+
| `Tool` | — | — | Never (each has a unique `tool_call_id`) |
|
|
464
|
+
|
|
465
|
+
When either assistant message has [parts](#parts) its fields can't rebuild, the merged message concatenates the two `parts` lists instead, with a `"\n\n"` text part between the texts.
|
|
369
466
|
|
|
370
467
|
### Example
|
|
371
468
|
|
|
@@ -434,7 +531,7 @@ class Riffer::Messages::Base
|
|
|
434
531
|
end
|
|
435
532
|
```
|
|
436
533
|
|
|
437
|
-
Subclasses implement `role` and optionally extend `to_h` with additional fields.
|
|
534
|
+
Subclasses implement `role` and optionally extend `to_h` with additional fields. `Assistant` writes `parts` in place of `content`.
|
|
438
535
|
|
|
439
536
|
## Editing history after the fact
|
|
440
537
|
|
data/docs/STABILITY.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
# Stability
|
|
2
|
+
|
|
3
|
+
This page covers which parts of Riffer you can depend on, how changes to them are announced, and how breaking releases work. Riffer is not at 1.0 yet; the [roadmap](https://github.com/janeapp/riffer/issues/528) tracks the path there.
|
|
4
|
+
|
|
5
|
+
## Public API
|
|
6
|
+
|
|
7
|
+
The public API is everything documented in these guides. You can build on it, and it changes only in the ways this page describes.
|
|
8
|
+
|
|
9
|
+
Everything else is internal, even when Ruby lets you reach it. That includes classes, methods and constants that appear in the [API reference](https://riffer.ai/api/) but not in a guide. Internal code can change in any release without notice. At 1.0, every public constant will be documented and everything else marked private.
|
|
10
|
+
|
|
11
|
+
## Experimental features
|
|
12
|
+
|
|
13
|
+
Experimental features are labelled _experimental_ in the guides, like the [prompted structured output strategy](AGENTS.md#structured-output-strategy-experimental). They can change in any minor release, and the [CHANGELOG](https://github.com/janeapp/riffer/blob/main/CHANGELOG.md) notes each change.
|
|
14
|
+
|
|
15
|
+
## Deprecations
|
|
16
|
+
|
|
17
|
+
A breaking change to the public API lands first as a new API or an [opt-in flag](CONFIGURATION.md#future-flags), and the old way prints a deprecation warning. The warning appears for at least one release before the old way is removed, and it names the earliest version it can be removed in. For larger changes, it also names a date.
|
|
18
|
+
|
|
19
|
+
## Breaking releases
|
|
20
|
+
|
|
21
|
+
Before 1.0, any minor release can include breaking changes, but never without notice: an earlier release deprecates what's changing first, so you'll see the warnings before anything breaks. Each breaking release comes with an upgrade guide in [UPGRADING.md](https://github.com/janeapp/riffer/blob/main/UPGRADING.md), and the CHANGELOG lists its changes under **⚠ BREAKING CHANGES**.
|
|
22
|
+
|
|
23
|
+
After 1.0, breaking changes ship only in major versions.
|
|
24
|
+
|
|
25
|
+
## Saved formats
|
|
26
|
+
|
|
27
|
+
Saved formats are the data Riffer produces for you to store and load later, such as [serialized agents](SERIALIZATION.md) and [messages persisted with `to_h`](MESSAGES.md#parts).
|
|
28
|
+
|
|
29
|
+
- Riffer can read a new format at least one release before it starts writing it, so a deploy that runs a release alongside the one before it keeps working.
|
|
30
|
+
- Anything saved by a 1.x release loads in every later 1.x release.
|
|
31
|
+
|
|
32
|
+
See [Serialization → Versioning](SERIALIZATION.md#versioning) for how agent data records its format version.
|
data/docs/STREAM_EVENTS.md
CHANGED
|
@@ -55,6 +55,8 @@ event.to_h # => {role: :assistant, content: "Hello, how can I help you?"}
|
|
|
55
55
|
|
|
56
56
|
Fires once per model response, after its last `TextDelta`, and contains the response's full text: every text block the provider returned, concatenated in order, so it always equals the joined `TextDelta` contents. A response that carries no text (for example, only tool calls) emits no `TextDone`.
|
|
57
57
|
|
|
58
|
+
The agent loop builds the message's [text parts](MESSAGES.md#parts) from the `TextDelta` events: the deltas between two other parts (reasoning, a tool call, a server tool block) form one text part. An adapter that sends no deltas gets one text part, from `TextDone`, at the end of the turn.
|
|
59
|
+
|
|
58
60
|
### ToolCallDelta
|
|
59
61
|
|
|
60
62
|
Emitted when tool call arguments are being streamed:
|
|
@@ -156,6 +158,20 @@ event.to_h # => {role: :assistant, query: "Ruby language", sources: [...]}
|
|
|
156
158
|
|
|
157
159
|
Contains the search query and an array of source hashes with `title` and `url` keys.
|
|
158
160
|
|
|
161
|
+
### ServerToolDone
|
|
162
|
+
|
|
163
|
+
Emitted when a block from a tool the provider ran itself (such as web search) is complete. It carries the block for replay; use `WebSearchStatus` and `WebSearchDone` to show progress.
|
|
164
|
+
|
|
165
|
+
```ruby
|
|
166
|
+
part = Riffer::Messages::Assistant::ServerToolPart.new(name: "web_search", kind: :call, data: "{...}", format: "anthropic-messages-v1")
|
|
167
|
+
event = Riffer::StreamEvents::ServerToolDone.new(part)
|
|
168
|
+
event.role # => :assistant
|
|
169
|
+
event.part # => the ServerToolPart
|
|
170
|
+
event.to_h # => {role: :assistant, part: {name: "web_search", kind: :call, data: "{...}", format: "anthropic-messages-v1"}}
|
|
171
|
+
```
|
|
172
|
+
|
|
173
|
+
The agent loop adds `part` to the assistant message's [parts](MESSAGES.md#parts). Only Anthropic emits it today.
|
|
174
|
+
|
|
159
175
|
### GuardrailTripwire
|
|
160
176
|
|
|
161
177
|
Emitted when a guardrail blocks execution during streaming:
|
|
@@ -310,7 +326,7 @@ When an agent uses tools during streaming, the flow is:
|
|
|
310
326
|
5. More text events stream in
|
|
311
327
|
6. Repeat until no more tool calls
|
|
312
328
|
|
|
313
|
-
> **Note:** When `web_search` is enabled, `WebSearchStatus` and `WebSearchDone` events may appear before text events as the provider performs a server-side search.
|
|
329
|
+
> **Note:** When `web_search` is enabled, `WebSearchStatus` and `WebSearchDone` events may appear before text events as the provider performs a server-side search. Gemini sends its `WebSearchDone` after the text.
|
|
314
330
|
|
|
315
331
|
```ruby
|
|
316
332
|
agent.stream("What's the weather in Tokyo?").each do |event|
|
data/docs/TESTING.md
CHANGED
|
@@ -16,7 +16,7 @@ require 'riffer/testing/rspec'
|
|
|
16
16
|
require 'riffer/testing/minitest'
|
|
17
17
|
```
|
|
18
18
|
|
|
19
|
-
Either one adds `stub_agent` and `
|
|
19
|
+
Either one adds `stub_agent`, `stub_tool` and `allow_deprecations` to every example and cleans up after each one. Neither RSpec nor minitest is a riffer dependency; the adapter files are only loaded when you require them yourself.
|
|
20
20
|
|
|
21
21
|
## Stubbing a tool
|
|
22
22
|
|
|
@@ -110,6 +110,27 @@ end
|
|
|
110
110
|
|
|
111
111
|
Tracking lives on `Riffer::Testing` itself, so `Riffer::Testing.stub_tool(...)` outside an example and `stub_tool(...)` inside one share one list. Tracking is not synchronized — stub from a single-threaded test, before concurrent lookups begin.
|
|
112
112
|
|
|
113
|
+
## Deprecations
|
|
114
|
+
|
|
115
|
+
Make your suite fail when it hits a deprecated riffer call, so you find each one before an upgrade removes it:
|
|
116
|
+
|
|
117
|
+
```ruby
|
|
118
|
+
# test/test_helper.rb
|
|
119
|
+
Riffer.config.deprecations = :raise
|
|
120
|
+
```
|
|
121
|
+
|
|
122
|
+
Every deprecated call then raises `Riffer::DeprecationError`, naming the line that made it. A test that uses a deprecated call on purpose wraps it in `allow_deprecations`:
|
|
123
|
+
|
|
124
|
+
```ruby
|
|
125
|
+
it 'still reads legacy pricing' do
|
|
126
|
+
allow_deprecations { Riffer.config.pricing.set('openai/gpt-5', input: 1.0, output: 2.0) }
|
|
127
|
+
|
|
128
|
+
# ...
|
|
129
|
+
end
|
|
130
|
+
```
|
|
131
|
+
|
|
132
|
+
`allow_deprecations` silences deprecations until the block returns or raises, and returns the block's value. It applies to the current thread or fiber and to threads and fibers started inside the block; other threads keep reporting. It is also available as `Riffer::Testing.allow_deprecations` outside an example. See [Configuration — Deprecations](CONFIGURATION.md#deprecations) for the other modes.
|
|
133
|
+
|
|
113
134
|
## When a stub leaks
|
|
114
135
|
|
|
115
136
|
Stubbing an identifier that is already taken raises `Riffer::DuplicateIdentifierError`:
|
data/docs/TOOLS.md
CHANGED
|
@@ -105,16 +105,16 @@ Options:
|
|
|
105
105
|
|
|
106
106
|
### Supported Types
|
|
107
107
|
|
|
108
|
-
| Ruby Type | JSON Schema Type
|
|
109
|
-
| -------------------------- |
|
|
110
|
-
| `String` | `string`
|
|
111
|
-
| `Integer` | `integer`
|
|
112
|
-
| `Float` | `number`
|
|
113
|
-
| `Riffer::Params::Boolean` | `boolean`
|
|
114
|
-
| `TrueClass` / `FalseClass` | `boolean`
|
|
115
|
-
| `Array` | `array`
|
|
116
|
-
| `Hash` | `object`
|
|
117
|
-
| `Riffer::Params::AnyOf` | `anyOf` of objects |
|
|
108
|
+
| Ruby Type | JSON Schema Type |
|
|
109
|
+
| -------------------------- | -------------------------------- |
|
|
110
|
+
| `String` | `string` |
|
|
111
|
+
| `Integer` | `integer` |
|
|
112
|
+
| `Float` | `number` |
|
|
113
|
+
| `Riffer::Params::Boolean` | `boolean` |
|
|
114
|
+
| `TrueClass` / `FalseClass` | `boolean` |
|
|
115
|
+
| `Array` | `array` |
|
|
116
|
+
| `Hash` | `object` |
|
|
117
|
+
| `Riffer::Params::AnyOf` | `anyOf` of objects or primitives |
|
|
118
118
|
|
|
119
119
|
`Riffer::Params::Boolean` is the preferred way to declare boolean parameters. `TrueClass` and `FalseClass` continue to work for backwards compatibility.
|
|
120
120
|
|
|
@@ -122,7 +122,7 @@ A `Float` param accepts a whole number too, since JSON Schema's `number` covers
|
|
|
122
122
|
|
|
123
123
|
### Nested Parameters
|
|
124
124
|
|
|
125
|
-
Tool params support the same nested DSL as structured output — nested objects (`Hash` with block), typed arrays (`Array, of:`), arrays of arrays (`Array, of: [Integer]`), arrays of objects (`Array` with block), and either/or shapes (`Riffer::Params::AnyOf` with `variant`
|
|
125
|
+
Tool params support the same nested DSL as structured output — nested objects (`Hash` with block), typed arrays (`Array, of:`), arrays of arrays (`Array, of: [Integer]`), arrays of objects (`Array` with block), and either/or shapes (`Riffer::Params::AnyOf` with `variant`s). See the [structured output section in Agents](AGENTS.md#nested-objects) for full syntax.
|
|
126
126
|
|
|
127
127
|
```ruby
|
|
128
128
|
class CreateOrderTool < Riffer::Tool
|
data/docs/TRACING.md
CHANGED
|
@@ -267,7 +267,7 @@ When enabled, content is serialized as GenAI-semconv JSON strings. File attachme
|
|
|
267
267
|
|
|
268
268
|
## Provider names
|
|
269
269
|
|
|
270
|
-
`gen_ai.provider.name` carries a GenAI-semconv well-known value where one exists: `openai`, `anthropic`, `aws.bedrock`, `azure.ai.openai`, `gcp.gemini`, `openrouter`. A custom provider that doesn't override the value defaults to the snake_cased form of its class name, so enabling tracing never breaks an otherwise-working provider.
|
|
270
|
+
`gen_ai.provider.name` carries a GenAI-semconv well-known value where one exists: `openai`, `anthropic`, `aws.bedrock`, `azure.ai.openai`, `gcp.gemini`, `gcp.vertex_ai`, `openrouter`. A custom provider that doesn't override the value defaults to the snake_cased form of its class name, so enabling tracing never breaks an otherwise-working provider.
|
|
271
271
|
|
|
272
272
|
## Stability
|
|
273
273
|
|
|
@@ -195,7 +195,7 @@ The agent-level [`reasoning`](../AGENTS.md#reasoning) setting defaults to Claude
|
|
|
195
195
|
|
|
196
196
|
Riffer sends the reasoning back to Bedrock on every later turn. How much of it Claude uses depends on the model; some only use the reasoning from the current tool-calling turn. For tool calls, sending it back is required: when thinking is enabled, Claude needs its earlier reasoning back to carry on after a tool result. You don't have to do anything; it happens as long as the assistant messages stay in the history.
|
|
197
197
|
|
|
198
|
-
If you persist sessions, keep the
|
|
198
|
+
If you persist sessions, keep the reasoning when you store messages (see [Messages — Reasoning](../MESSAGES.md#reasoning)). If you drop it, later turns lose the model's earlier reasoning, and a tool-calling turn with thinking enabled may be rejected.
|
|
199
199
|
|
|
200
200
|
Only reasoning that Bedrock produced is sent back to Bedrock. A conversation that switches providers midway still works: reasoning from other providers is kept on the messages but left out of Bedrock requests.
|
|
201
201
|
|
|
@@ -212,6 +212,8 @@ response = provider.generate_text(
|
|
|
212
212
|
)
|
|
213
213
|
```
|
|
214
214
|
|
|
215
|
+
Converse requires every document to have a name, unique across the request, made only of letters, digits, single spaces, hyphens, parentheses and square brackets, and at most 200 characters long. Riffer builds it from the file's `filename`: the extension is dropped, other characters become hyphens, the name is cut to 200 characters, a document without a filename is named `document`, and a repeated name gets a counter (`invoice`, `invoice (2)`). The model can see the name.
|
|
216
|
+
|
|
215
217
|
Any other URL scheme (e.g. `https://`) isn't something Bedrock accepts as a reference, so riffer downloads the file itself and sends the raw bytes — see [File Downloads](../CONFIGURATION.md#file-downloads) for the `allow_downloads` policy this requires.
|
|
216
218
|
|
|
217
219
|
**A `sha256:` on an `s3://` `FilePart` is a combination that always fails with the default setup.** Setting `sha256:` forces riffer to download and verify the file itself before Bedrock ever sees it, regardless of the URL scheme — but riffer's default downloader only fetches `https://` URLs, so an `s3://` source can never be verified out of the box. Either configure a custom `Riffer.config.files.downloader` that can reach S3, or omit `sha256:` and let the `s3://` URI pass straight through to Bedrock unverified.
|
data/docs/providers/ANTHROPIC.md
CHANGED
|
@@ -2,14 +2,6 @@
|
|
|
2
2
|
|
|
3
3
|
The Anthropic provider connects to Claude models via the Anthropic API.
|
|
4
4
|
|
|
5
|
-
## Installation
|
|
6
|
-
|
|
7
|
-
Add the Anthropic gem to your Gemfile:
|
|
8
|
-
|
|
9
|
-
```ruby
|
|
10
|
-
gem 'anthropic'
|
|
11
|
-
```
|
|
12
|
-
|
|
13
5
|
## Configuration
|
|
14
6
|
|
|
15
7
|
Configure your Anthropic API key:
|
|
@@ -20,18 +12,46 @@ Riffer.configure do |config|
|
|
|
20
12
|
end
|
|
21
13
|
```
|
|
22
14
|
|
|
23
|
-
|
|
15
|
+
When `config.anthropic.api_key` is unset, the provider reads `ANTHROPIC_API_KEY`; with neither set it raises `Riffer::ArgumentError`. Set `config.anthropic.base_url` (or `ANTHROPIC_BASE_URL`) to send requests somewhere other than `https://api.anthropic.com`, such as a gateway or proxy.
|
|
16
|
+
|
|
17
|
+
Riffer reads no other `ANTHROPIC_*` variables. The anthropic gem also read `ANTHROPIC_AUTH_TOKEN` and `ANTHROPIC_CUSTOM_HEADERS`; riffer does not. The key is already sent as `Authorization: Bearer`, and custom headers go in the client's `headers:` (see [HTTP Client](#http-client)).
|
|
18
|
+
|
|
19
|
+
## HTTP Client
|
|
20
|
+
|
|
21
|
+
The provider needs no Anthropic gem. Riffer ships its own Messages API transport, `Riffer::Providers::Anthropic::Client`, built on `Riffer::HTTP::Client`. The provider builds one from the configured credentials by default. To change timeouts, add retries or go through a proxy, build your own and assign it to `config.anthropic.client`:
|
|
24
22
|
|
|
25
23
|
```ruby
|
|
26
24
|
Riffer.configure do |config|
|
|
27
|
-
config.anthropic.client = Anthropic::Client.new(
|
|
25
|
+
config.anthropic.client = Riffer::Providers::Anthropic::Client.new(
|
|
28
26
|
api_key: ENV['ANTHROPIC_API_KEY'],
|
|
29
|
-
|
|
27
|
+
connection: Faraday.new(request: { open_timeout: 10, read_timeout: 120 })
|
|
30
28
|
)
|
|
31
29
|
end
|
|
32
30
|
```
|
|
33
31
|
|
|
34
|
-
|
|
32
|
+
| Option | Default | Description |
|
|
33
|
+
| ------------ | -------------------------------------- | ----------------------------------------------------------------- |
|
|
34
|
+
| `api_key` | required | Sent as `Authorization: Bearer <api_key>` |
|
|
35
|
+
| `base_url` | `https://api.anthropic.com` | API origin; requests go to `<base_url>/v1/messages` |
|
|
36
|
+
| `headers` | `{}` | Sent on every request; replaces riffer's headers of the same name |
|
|
37
|
+
| `connection` | Faraday defaults, 10s open / 600s read | Your own `Faraday::Connection`; see [Connections][connections] |
|
|
38
|
+
|
|
39
|
+
Timeouts, retries, proxies, beta headers and errors are covered in [Configuration → Connections][connections]. An API error becomes a `Riffer::APIError` whose message carries the Anthropic error type, e.g. `Anthropic API error (401): authentication_error: Invalid bearer token`. No requests are retried unless your connection adds retries.
|
|
40
|
+
|
|
41
|
+
The `anthropic-version` header is pinned to `2026-10-21`. To send another version, pass it in `headers:`:
|
|
42
|
+
|
|
43
|
+
```ruby
|
|
44
|
+
Riffer::Providers::Anthropic::Client.new(
|
|
45
|
+
api_key: ENV['ANTHROPIC_API_KEY'],
|
|
46
|
+
headers: {'anthropic-version' => '2023-06-01'}
|
|
47
|
+
)
|
|
48
|
+
```
|
|
49
|
+
|
|
50
|
+
Version `2026-10-21` removed `temperature`, `top_p` and `top_k`; sending any of them returns a 400. Pin `2023-06-01` to keep using them. See Anthropic's [API versions](https://platform.claude.com/docs/en/api/versioning) for the other changes.
|
|
51
|
+
|
|
52
|
+
The setting accepts a client instance or a no-argument `Proc`, resolved on every LLM call — see [Configuration → Provider Clients](../CONFIGURATION.md#provider-clients). An `Anthropic::Client` from the anthropic gem is not accepted and raises `Riffer::ArgumentError`.
|
|
53
|
+
|
|
54
|
+
[connections]: ../CONFIGURATION.md#connections
|
|
35
55
|
|
|
36
56
|
## Supported Models
|
|
37
57
|
|
|
@@ -45,14 +65,6 @@ model 'anthropic/claude-opus-4-5-20251101'
|
|
|
45
65
|
|
|
46
66
|
## Model Options
|
|
47
67
|
|
|
48
|
-
### temperature
|
|
49
|
-
|
|
50
|
-
Controls randomness:
|
|
51
|
-
|
|
52
|
-
```ruby
|
|
53
|
-
model_options temperature: 0.7
|
|
54
|
-
```
|
|
55
|
-
|
|
56
68
|
### max_tokens
|
|
57
69
|
|
|
58
70
|
Maximum tokens in response:
|
|
@@ -61,22 +73,6 @@ Maximum tokens in response:
|
|
|
61
73
|
model_options max_tokens: 4096
|
|
62
74
|
```
|
|
63
75
|
|
|
64
|
-
### top_p
|
|
65
|
-
|
|
66
|
-
Nucleus sampling parameter:
|
|
67
|
-
|
|
68
|
-
```ruby
|
|
69
|
-
model_options top_p: 0.95
|
|
70
|
-
```
|
|
71
|
-
|
|
72
|
-
### top_k
|
|
73
|
-
|
|
74
|
-
Top-k sampling parameter:
|
|
75
|
-
|
|
76
|
-
```ruby
|
|
77
|
-
model_options top_k: 250
|
|
78
|
-
```
|
|
79
|
-
|
|
80
76
|
### thinking
|
|
81
77
|
|
|
82
78
|
Enable extended thinking (reasoning) for supported models. Pass the thinking configuration hash directly as Anthropic expects:
|
|
@@ -193,9 +189,11 @@ The reasoning is kept on the assistant message as [reasoning parts](../MESSAGES.
|
|
|
193
189
|
|
|
194
190
|
### Reasoning Replay
|
|
195
191
|
|
|
196
|
-
Riffer sends
|
|
192
|
+
Riffer sends every earlier turn back to Anthropic as the API returned it: the `thinking`, `redacted_thinking`, text, web search and `tool_use` blocks, in their original order and unchanged (see [Messages — Parts](../MESSAGES.md#parts)). Order matters because Claude signs each thinking block over everything before it, including earlier blocks of the same turn. A turn sent back in a different order loses that reasoning, or is rejected with a 400 on accounts that enforce the binding. For tool calls, sending the reasoning back is required: when thinking is enabled, Claude needs its earlier thinking blocks back to carry on after a tool result. You don't have to do anything; it happens as long as the assistant messages stay in the history.
|
|
197
193
|
|
|
198
|
-
If you persist sessions,
|
|
194
|
+
If you persist sessions, `to_h` keeps the web search results and the turn's block order (see [Messages — Parts](../MESSAGES.md#parts)). Dropping the reasoning loses the model's earlier thinking, and a tool-calling turn with thinking enabled may be rejected.
|
|
195
|
+
|
|
196
|
+
If you change a turn's text, drop that turn's reasoning yourself; see [Editing a turn](../MESSAGES.md#parts).
|
|
199
197
|
|
|
200
198
|
Only reasoning that this provider produced is sent back to Anthropic. A conversation that switches providers midway still works: reasoning from other providers (including OpenRouter's `anthropic-claude-v1` parts) is kept on the messages but left out of Anthropic requests.
|
|
201
199
|
|
|
@@ -226,16 +224,18 @@ end
|
|
|
226
224
|
|
|
227
225
|
Anthropic emits sources with `title` and `url` on the `WebSearchDone` event.
|
|
228
226
|
|
|
227
|
+
Each `server_tool_use` block and its result block (`web_search_tool_result`, or `code_execution_tool_result` when a newer web search version runs the search from code execution) is kept on the assistant message as a `ServerToolPart` (see [Messages — Parts](../MESSAGES.md#parts)), and a streamed one also arrives as a `ServerToolDone` event. With `generate`, text blocks with citations keep their block too; a streamed turn keeps the text without its citations. Later turns send them back in place, so Claude reuses the results instead of searching again.
|
|
228
|
+
|
|
229
229
|
## Message Format
|
|
230
230
|
|
|
231
231
|
The provider converts Riffer messages to Anthropic format:
|
|
232
232
|
|
|
233
|
-
| Riffer Message | Anthropic Format
|
|
234
|
-
| -------------- |
|
|
235
|
-
| `System` | Added to `system` array as `{type: "text", text: ...}`
|
|
236
|
-
| `User` | `{role: "user", content: "..."}`
|
|
237
|
-
| `Assistant` | `{role: "assistant", content: [...]}
|
|
238
|
-
| `Tool` | `{role: "user", content: [{type: "tool_result", ...}]}`
|
|
233
|
+
| Riffer Message | Anthropic Format |
|
|
234
|
+
| -------------- | ------------------------------------------------------------------------ |
|
|
235
|
+
| `System` | Added to `system` array as `{type: "text", text: ...}` |
|
|
236
|
+
| `User` | `{role: "user", content: "..."}` |
|
|
237
|
+
| `Assistant` | `{role: "assistant", content: [...]}`, one block per part, in part order |
|
|
238
|
+
| `Tool` | `{role: "user", content: [{type: "tool_result", ...}]}` |
|
|
239
239
|
|
|
240
240
|
## Direct Provider Usage
|
|
241
241
|
|
|
@@ -169,6 +169,41 @@ class MyAgent < Riffer::Agent
|
|
|
169
169
|
end
|
|
170
170
|
```
|
|
171
171
|
|
|
172
|
+
## Anthropic-Compatible Endpoints
|
|
173
|
+
|
|
174
|
+
For a service that speaks the Anthropic Messages API, subclass `Riffer::Providers::AnthropicCompatible::MessagesAPI` instead of `Base`. It brings the request building, response parsing and streaming of the Anthropic provider; you supply the client. An endpoint that takes a bearer key can use `Riffer::Providers::Anthropic::Client` with its own `base_url`. For other auth, subclass `Riffer::HTTP::Client`:
|
|
175
|
+
|
|
176
|
+
```ruby
|
|
177
|
+
class AcmeClaude < Riffer::Providers::AnthropicCompatible::MessagesAPI
|
|
178
|
+
class Client < Riffer::HTTP::Client
|
|
179
|
+
def initialize(api_key:, connection: nil)
|
|
180
|
+
super(connection: connection)
|
|
181
|
+
@api_key = api_key
|
|
182
|
+
end
|
|
183
|
+
|
|
184
|
+
private
|
|
185
|
+
|
|
186
|
+
def url_for(path) = "https://llm.acme.example/#{path}"
|
|
187
|
+
def headers = { "api-key" => @api_key }
|
|
188
|
+
def error_label = "Acme"
|
|
189
|
+
end
|
|
190
|
+
|
|
191
|
+
private
|
|
192
|
+
|
|
193
|
+
def build_client
|
|
194
|
+
Client.new(api_key: ENV.fetch("ACME_API_KEY"))
|
|
195
|
+
end
|
|
196
|
+
|
|
197
|
+
# Only when the endpoint differs from POST v1/messages with the standard body:
|
|
198
|
+
def messages_path(model, stream:) = "models/#{model}:#{stream ? 'streamRawPredict' : 'rawPredict'}"
|
|
199
|
+
def request_body(params, stream:) = { anthropic_version: "acme-2025-01-01", **super.except(:model) }
|
|
200
|
+
end
|
|
201
|
+
|
|
202
|
+
Riffer::Providers::Repository.register(:acme) { AcmeClaude }
|
|
203
|
+
```
|
|
204
|
+
|
|
205
|
+
`messages_path` returns the path relative to the client's base URL; `request_body` returns the JSON body actually sent, and by default adds `stream: true` when streaming. Read credentials from your own configuration or environment in `build_client`, never from `ANTHROPIC_API_KEY`, so an Anthropic key is never sent to another vendor.
|
|
206
|
+
|
|
172
207
|
## Tool Support
|
|
173
208
|
|
|
174
209
|
Tools are converted in `build_request_params` and passed through to both `execute_generate` and `execute_stream`:
|
|
@@ -224,6 +259,9 @@ Riffer::StreamEvents::ToolCallDone.new(
|
|
|
224
259
|
Riffer::StreamEvents::ReasoningDelta.new("thinking...")
|
|
225
260
|
Riffer::StreamEvents::ReasoningDone.new(part)
|
|
226
261
|
|
|
262
|
+
# Server tool blocks (if supported); see the Ordered Parts section
|
|
263
|
+
Riffer::StreamEvents::ServerToolDone.new(server_tool_part)
|
|
264
|
+
|
|
227
265
|
# Web search (if supported)
|
|
228
266
|
Riffer::StreamEvents::WebSearchStatus.new("searching", query: "search query")
|
|
229
267
|
Riffer::StreamEvents::WebSearchDone.new(
|
|
@@ -308,6 +346,27 @@ yielder << Riffer::StreamEvents::ReasoningDone.new(part)
|
|
|
308
346
|
|
|
309
347
|
If your adapter surfaces reasoning text but cannot yet replay it, call `yield_reasoning_done(yielder, text)` instead. It wraps the text in a `:text` part with no `format`, which persists for display and is skipped on replay.
|
|
310
348
|
|
|
349
|
+
## Ordered Parts
|
|
350
|
+
|
|
351
|
+
By default the base class builds the assistant message's [parts](../MESSAGES.md#parts) from `extract_reasoning`, `extract_content` and `extract_tool_calls`, in that order. If your provider interleaves blocks in one turn and needs them back in that order, override `extract_parts` instead and return every block as a part, in response order:
|
|
352
|
+
|
|
353
|
+
```ruby
|
|
354
|
+
def extract_parts(response)
|
|
355
|
+
response.blocks.filter_map do |block|
|
|
356
|
+
case block.type
|
|
357
|
+
when "text" then Riffer::Messages::Assistant::TextPart.new(block.text)
|
|
358
|
+
when "thinking" then Riffer::Messages::Assistant::ReasoningPart.new(type: :text, text: block.text, signature: block.signature, format: "my-provider-v1")
|
|
359
|
+
when "tool_call" then Riffer::Messages::Assistant::ToolCall.new(call_id: block.id, name: block.name, arguments: block.arguments)
|
|
360
|
+
when "search" then Riffer::Messages::Assistant::ServerToolPart.new(name: "web_search", kind: :call, id: block.id, data: block.to_json, format: "my-provider-v1")
|
|
361
|
+
end
|
|
362
|
+
end
|
|
363
|
+
end
|
|
364
|
+
```
|
|
365
|
+
|
|
366
|
+
Then replay by walking `message.parts` rather than reading `content`, `tool_calls` and `reasoning` separately, and skip parts whose `format` you don't recognize.
|
|
367
|
+
|
|
368
|
+
For streaming, emit `ServerToolDone` for each server tool block, and keep text deltas, `ReasoningDone` and `ToolCallDone` in the order the blocks arrive. The agent loop builds the parts in that order.
|
|
369
|
+
|
|
311
370
|
## Reasoning Level
|
|
312
371
|
|
|
313
372
|
When an agent sets [`reasoning`](../AGENTS.md#reasoning), riffer resolves the level to `model_options` params before calling `build_request_params`, so your provider receives ordinary options and never sees the level itself. It uses the model's [catalog](../CATALOG.md#reasoning) entry under your registration key first, then your provider's default. Override the private `default_reasoning_options` to supply one:
|