mirror of
https://github.com/we-promise/sure.git
synced 2026-06-04 18:29:02 +00:00
* feat(ai): add Anthropic provider with chat parity (1/5)
Introduces Provider::Anthropic alongside Provider::Openai, implementing
the LlmConcept chat_response contract over the official anthropic Ruby
SDK. Batch ops, PDF, and RAG land in follow-up PRs.
- Provider::Anthropic uses Messages API for sync and streaming responses
- ChatConfig builds requests with ephemeral prompt-cache markers on the
system prompt and the last tool definition
- MessageFormatter reconstructs multi-turn history (text + tool_use +
tool_result blocks) from raw Message records, including the paired
user-role tool_result turn Anthropic requires after every tool_use
- ChatParser maps Anthropic Message into the shared ChatResponse Data
- Registry, Setting, User, Chat default model wired for ANTHROPIC_*
envs and Setting.anthropic_*; LLM_PROVIDER selects between providers
- Responder forwards raw conversation_history (Array<Message>) so
providers without hosted conversation state can rebuild context
- OpenAI provider accepts and ignores the new kwarg (no behavior change)
Tests cover provider init, model gating, MessageFormatter for all turn
shapes, ChatConfig request building (max_tokens, system cache, tool
conversion), ChatParser for text / tool_use / mixed blocks, Registry
discovery, and mocked chat_response success / error / function_request
paths. Live VCR cassettes recorded in a follow-up with a real key.
Stacked PRs: 2/5 batch ops + cost ledger, 3/5 PDF, 4/5 pgvector RAG,
5/5 settings UI + disclosure.
* fix(ai): address PR review on Anthropic provider foundation
Surface fixes raised by Codex + CodeRabbit on PR 1/5:
- Provider::Anthropic#chat_response now accepts (and ignores) a
`messages:` kwarg. Assistant::Responder passes both `messages:`
(OpenAI-shape) and `conversation_history:` (raw Message records) for
cross-provider parity, so the previous signature raised
ArgumentError on the first chat turn through the Anthropic provider.
- Provider::Anthropic#supports_model? bypasses the `claude` prefix
gate when a custom base_url is configured, mirroring the OpenAI
provider. Bedrock-shaped IDs like
`anthropic.claude-sonnet-4-5-20250929-v1:0` and
`claude-opus-4@20250514` are otherwise rejected by
Assistant::Provided#get_model_provider and the chat dies.
- Setting.anthropic_access_token is now in
EncryptedSettingFields::ENCRYPTED_FIELDS so the Anthropic API key
is encrypted at rest like every other provider secret. Previously
plaintext while siblings (openai_access_token, twelve_data_api_key,
external_assistant_token) were ciphertext.
- Chat.default_model falls back to whichever provider is actually
configured. Previously, with LLM_PROVIDER=anthropic but no
Anthropic credentials, the default model resolved to a Claude ID
that no registered provider supported, so chats failed even when
OpenAI was fully configured. Adds Provider::{Anthropic,Openai}#configured?
class methods for the readable callsite.
- Provider::Anthropic.effective_model uses
`ENV["ANTHROPIC_MODEL"].presence || Setting.anthropic_model` so the
Setting lookup is only performed when the env var is absent — the
previous `ENV.fetch(KEY, default)` evaluated the default arg
eagerly on every call.
- Provider::Anthropic::ChatConfig#anthropic_input_schema strips both
`:strict` and `"strict"` keys so JSON-decoded schemas with string
keys cannot leak the OpenAI-only flag through to Anthropic.
Test coverage added: supports_model? bypass on custom endpoints,
chat_response messages: kwarg compatibility, default_model fallback
in the three credential combinations, configured? against ENV +
Setting, strict-flag stripping for both key types, and a
`Setting.expects(:anthropic_model).never` assertion proving the
ENV-precedence test now exercises the lazy path.
All 4365 tests pass (1 pre-existing libvips env error unrelated).
* test(chat): make default_model tests resilient to ENV model overrides
CodeRabbit flagged on PR review: the new default_model tests asserted
against Provider::*::DEFAULT_MODEL, but Chat.default_model actually
returns Provider::*.effective_model.presence (which reads
OPENAI_MODEL / ANTHROPIC_MODEL from the environment). With either env
var set, the tests would fail intermittently even though routing was
correct.
- New default_model tests now assert against the provider's
effective_model directly, so they verify the routing decision
(which provider's value wins) without coupling to the constant.
- Pre-existing "creates with default model" assertions had the same
brittleness; switch them to compare against Chat.default_model so
the chosen model is whatever the env / Setting cascade resolves to.
Verified by running `ANTHROPIC_MODEL=claude-haiku-4-5 OPENAI_MODEL=gpt-4o
bin/rails test test/models/chat_test.rb` — 16 runs, 0 failures
(previously 2 pre-existing failures + 0 from the new tests).
* fix(ai): address local review on Anthropic foundation
- Provider::Anthropic#supports_pdf_processing? bypasses prefix gate for
custom endpoints, mirroring supports_model?
- Provider::Anthropic#initialize raises Error when custom_endpoint? AND
model.blank?, parity with Provider::Openai
- stream_chat_response captures partial usage on mid-stream errors and
records it via the new on_partial callback so chat_response can skip
the duplicate error row in the outer rescue
- safe_accumulated_message swallows the secondary failure when the SDK
cannot reconstruct a snapshot
- langfuse_client memoizes properly (||= instead of =) so repeated calls
don't churn Langfuse instances
- MessageFormatter sorts tool_calls by created_at then id so the
message array is deterministic across replays; skips tool_calls
missing both provider_call_id and provider_id rather than sending
`id: nil` and getting rejected by Anthropic
- Setting.anthropic_access_token default falls back through
ENV["ANTHROPIC_API_KEY"].presence (was missing .presence, so an
empty-string env value bled through)
- User#openai_configured? / #anthropic_configured? delegate to the
Provider::* class methods — single source of truth
- Assistant::Responder renames the OpenAI-shape history builder
conversation_history → openai_messages_payload so the kwarg name
matches the local method name (messages: openai_messages_payload,
conversation_history: chat_message_records)
- Assistant::Builtin stale-history comment updated to reference both
builders
Adds a streaming chat_response test using ad-hoc subclasses of the
SDK event types so the case/when dispatch matches via is_a? without
stubbing class-level === behavior.
* test(ai): add Anthropic tool_use round-trip + multi-tool turn coverage
Addresses @jjmata's "worth confirming" note on PR #1983: tool-use turns
from prior assistant messages must round-trip correctly when retrieved
from the database.
- New `ChatParser → ToolCall::Function → MessageFormatter` test walks
the full path: Anthropic response with a tool_use block →
ChatFunctionRequest → ToolCall::Function.from_function_request →
persisted on the AssistantMessage → MessageFormatter rebuild on the
next turn. Asserts the original `tool_use.id` is preserved end-to-end
as both `tool_use.id` and the paired `tool_result.tool_use_id`, and
that the original `input` hash and serialized result content survive.
- New multi-tool assistant turn test confirms two tool_use blocks on a
single assistant message render as two tool_use blocks followed by
two paired tool_result blocks in a single user-role follow-up,
matching Anthropic's required alternation.
Both tests exercise the existing PR1 code without behavior changes.
* test(ai): require "ostruct" explicitly in Anthropic provider tests
OpenStruct is moving out of Ruby's default load path (warning in 3.4+,
removed in 3.5+). Tests work today because ActiveSupport transitively
loads it, but that's incidental. Match the existing convention in
test/controllers/settings/hostings_controller_test.rb which explicitly
requires ostruct for the same reason.
* fix(ai): sanitize Langfuse warn logs, normalize tool_use.input, dedup history fetch
Addresses three open CodeRabbit findings on PR #1983.
- Provider::Anthropic Langfuse rescue branches no longer include
`e.full_message` in `Rails.logger.warn`. `full_message` bundles the
backtrace + cause chain and on some SDK error types includes the
serialized request/response payload (prompt, model output). Logs
now report `#{e.class}: #{e.message}` only. Three sites:
create_langfuse_trace, log_langfuse_generation, upsert_langfuse_trace.
Note: Provider::Openai has the same pattern (copy-pasted source) —
harmonization deferred to a follow-up cleanup PR; this commit fixes
only the Anthropic provider to keep PR scope tight.
- MessageFormatter#parse_arguments now coerces any non-Hash parsed
result to `{}`. Anthropic's Messages API requires `tool_use.input`
to be a JSON object (map); a stored ToolCall::Function record whose
arguments parse to a scalar, bool, or array (corrupt row, legacy
data, cross-provider bleed) would otherwise produce a payload the
API rejects. Normal flow stores Hash arguments end-to-end so the
fix is defensive — adds 2 tests covering scalar/array JSON strings
and non-String non-Hash inputs.
- Assistant::Responder dedups the chat-history fetch. The previous
layout fired two near-identical `chat.messages.where(...).includes(
:tool_calls).ordered` queries per LLM turn (one for the OpenAI-shape
payload, one for the raw-records kwarg). A new memoized
`complete_chat_messages` fetches once; `chat_message_records` filters
out the current message via `Array#reject`, `openai_messages_payload`
iterates the cached array unchanged. One SQL query per turn instead
of two. Memoization scope = single Responder instance (per LLM call),
so cache invalidation is not a concern.
All 4370 tests pass (1 pre-existing libvips env error unrelated).
Rubocop + brakeman clean.
* fix(ci): replace sk-ant- prefixed test placeholders
Pipelock secret scanner pattern-matches `sk-ant-*` as a real Anthropic
API key and fails the PR security-scan check. Test stubs and
ClimateControl env values used `sk-ant-test`, `sk-ant-from-setting`,
`sk-ant-x`, `sk-ant-y` as obvious placeholders, but the scanner does
not care about value entropy.
Switched to `fake-anthropic-key-*` / `fake-token-*` strings so the
scanner stops flagging them. No production code touched, no behavior
change — Provider::Anthropic still accepts any non-blank token.
238 lines
8.7 KiB
Ruby
238 lines
8.7 KiB
Ruby
require "test_helper"
|
|
require "ostruct"
|
|
|
|
class Provider::Anthropic::MessageFormatterTest < ActiveSupport::TestCase
|
|
test "builds a single user turn from prompt alone" do
|
|
formatter = Provider::Anthropic::MessageFormatter.new(prompt: "hi")
|
|
|
|
messages = formatter.build
|
|
|
|
assert_equal 1, messages.size
|
|
assert_equal({ role: "user", content: "hi" }, messages.first)
|
|
end
|
|
|
|
test "skips empty content from history" do
|
|
history = [ stub_user_message("") ]
|
|
|
|
messages = Provider::Anthropic::MessageFormatter.new(prompt: "next", conversation_history: history).build
|
|
|
|
assert_equal [ { role: "user", content: "next" } ], messages
|
|
end
|
|
|
|
test "renders text-only assistant history with no tool calls" do
|
|
history = [
|
|
stub_user_message("first question"),
|
|
stub_assistant_message("first answer")
|
|
]
|
|
|
|
messages = Provider::Anthropic::MessageFormatter.new(prompt: "second question", conversation_history: history).build
|
|
|
|
assert_equal({ role: "user", content: "first question" }, messages[0])
|
|
assert_equal "assistant", messages[1][:role]
|
|
assert_equal [ { type: "text", text: "first answer" } ], messages[1][:content]
|
|
assert_equal({ role: "user", content: "second question" }, messages[2])
|
|
end
|
|
|
|
test "renders assistant tool_call history with paired tool_result turn" do
|
|
tool_call = stub_tool_call(
|
|
id: "toolu_1",
|
|
name: "get_net_worth",
|
|
arguments: { "currency" => "USD" },
|
|
result: { "amount" => 12345, "currency" => "USD" }
|
|
)
|
|
assistant = stub_assistant_message("Your net worth is $12,345.", tool_calls: [ tool_call ])
|
|
history = [ stub_user_message("net worth?"), assistant ]
|
|
|
|
messages = Provider::Anthropic::MessageFormatter.new(prompt: "anything else?", conversation_history: history).build
|
|
|
|
assert_equal({ role: "user", content: "net worth?" }, messages[0])
|
|
assert_equal "assistant", messages[1][:role]
|
|
assert_equal "tool_use", messages[1][:content].first[:type]
|
|
assert_equal "toolu_1", messages[1][:content].first[:id]
|
|
assert_equal "get_net_worth", messages[1][:content].first[:name]
|
|
assert_equal({ "currency" => "USD" }, messages[1][:content].first[:input])
|
|
assert_equal "text", messages[1][:content].last[:type]
|
|
|
|
assert_equal "user", messages[2][:role]
|
|
assert_equal "tool_result", messages[2][:content].first[:type]
|
|
assert_equal "toolu_1", messages[2][:content].first[:tool_use_id]
|
|
assert_equal({ "amount" => 12345, "currency" => "USD" }.to_json, messages[2][:content].first[:content])
|
|
|
|
assert_equal({ role: "user", content: "anything else?" }, messages[3])
|
|
end
|
|
|
|
test "renders in-flight function_results as assistant tool_use + user tool_result" do
|
|
formatter = Provider::Anthropic::MessageFormatter.new(
|
|
prompt: "what is my net worth?",
|
|
function_results: [ {
|
|
call_id: "toolu_42",
|
|
name: "get_net_worth",
|
|
arguments: { "currency" => "USD" }.to_json,
|
|
output: { amount: 99, currency: "USD" }
|
|
} ]
|
|
)
|
|
|
|
messages = formatter.build
|
|
|
|
assert_equal({ role: "user", content: "what is my net worth?" }, messages[0])
|
|
assert_equal "assistant", messages[1][:role]
|
|
assert_equal "tool_use", messages[1][:content].first[:type]
|
|
assert_equal "toolu_42", messages[1][:content].first[:id]
|
|
assert_equal({ "currency" => "USD" }, messages[1][:content].first[:input])
|
|
|
|
assert_equal "user", messages[2][:role]
|
|
assert_equal "tool_result", messages[2][:content].first[:type]
|
|
assert_equal "toolu_42", messages[2][:content].first[:tool_use_id]
|
|
assert_includes messages[2][:content].first[:content], "99"
|
|
end
|
|
|
|
# Confirms the round-trip flagged in PR #1983 review: an Anthropic tool_use
|
|
# block returned by the model → ChatFunctionRequest → ToolCall::Function
|
|
# persisted on the AssistantMessage → MessageFormatter rebuild on the next
|
|
# turn produces an Anthropic-compatible history where tool_use_id pairs back
|
|
# to the original block.
|
|
test "ChatParser → ToolCall::Function → MessageFormatter round-trips tool_use_id" do
|
|
anthropic_response = OpenStruct.new(
|
|
id: "msg_abc",
|
|
model: "claude-sonnet-4-6",
|
|
content: [
|
|
OpenStruct.new(type: :tool_use, id: "toolu_round_trip", name: "get_net_worth", input: { "currency" => "USD" })
|
|
]
|
|
)
|
|
|
|
parsed = Provider::Anthropic::ChatParser.new(anthropic_response).parsed
|
|
function_request = parsed.function_requests.first
|
|
|
|
persisted_tool_call = ToolCall::Function.from_function_request(
|
|
function_request,
|
|
{ "amount" => 12345, "currency" => "USD" }
|
|
)
|
|
|
|
assistant = stub_assistant_message("Your net worth is $12,345.", tool_calls: [ persisted_tool_call ])
|
|
history = [ stub_user_message("net worth?"), assistant ]
|
|
|
|
rebuilt = Provider::Anthropic::MessageFormatter.new(prompt: "follow-up", conversation_history: history).build
|
|
|
|
tool_use_block = rebuilt[1][:content].find { |b| b[:type] == "tool_use" }
|
|
tool_result_block = rebuilt[2][:content].first
|
|
|
|
assert_equal "toolu_round_trip", tool_use_block[:id]
|
|
assert_equal "toolu_round_trip", tool_result_block[:tool_use_id]
|
|
assert_equal({ "currency" => "USD" }, tool_use_block[:input])
|
|
assert_equal({ "amount" => 12345, "currency" => "USD" }.to_json, tool_result_block[:content])
|
|
end
|
|
|
|
test "renders multi-tool assistant turn with all pairings preserved" do
|
|
tool_a = stub_tool_call(
|
|
id: "toolu_a",
|
|
name: "get_accounts",
|
|
arguments: {},
|
|
result: [ { "id" => 1, "name" => "Checking" } ]
|
|
)
|
|
tool_b = stub_tool_call(
|
|
id: "toolu_b",
|
|
name: "get_holdings",
|
|
arguments: {},
|
|
result: [ { "ticker" => "VTI", "qty" => 10 } ]
|
|
)
|
|
assistant = stub_assistant_message("Looked up your accounts and holdings.", tool_calls: [ tool_a, tool_b ])
|
|
|
|
messages = Provider::Anthropic::MessageFormatter.new(
|
|
prompt: "follow-up",
|
|
conversation_history: [ stub_user_message("accounts and holdings?"), assistant ]
|
|
).build
|
|
|
|
tool_uses = messages[1][:content].select { |b| b[:type] == "tool_use" }
|
|
tool_results = messages[2][:content]
|
|
|
|
assert_equal 2, tool_uses.size
|
|
assert_equal 2, tool_results.size
|
|
assert_equal [ "toolu_a", "toolu_b" ], tool_uses.map { |b| b[:id] }
|
|
assert_equal [ "toolu_a", "toolu_b" ], tool_results.map { |b| b[:tool_use_id] }
|
|
# Anthropic requires the user turn to follow the assistant turn that used tools
|
|
assert_equal "assistant", messages[1][:role]
|
|
assert_equal "user", messages[2][:role]
|
|
end
|
|
|
|
test "parses string arguments and nil outputs gracefully" do
|
|
formatter = Provider::Anthropic::MessageFormatter.new(
|
|
prompt: "go",
|
|
function_results: [ {
|
|
call_id: "toolu_x",
|
|
name: "noop",
|
|
arguments: "",
|
|
output: nil
|
|
} ]
|
|
)
|
|
|
|
messages = formatter.build
|
|
|
|
assert_equal({}, messages[1][:content].first[:input])
|
|
assert_equal "", messages[2][:content].first[:content]
|
|
end
|
|
|
|
# Anthropic's tool_use.input MUST be a JSON object (map). If a stored
|
|
# ToolCall::Function record carries arguments that parse to a scalar or
|
|
# array (corrupt row, legacy data, OpenAI cross-bleed), the formatter
|
|
# must coerce them to `{}` so we don't ship an invalid payload.
|
|
test "coerces non-Hash parsed arguments to empty Hash" do
|
|
[ '"hello"', "123", "true", "[1,2,3]" ].each do |non_object_json|
|
|
formatter = Provider::Anthropic::MessageFormatter.new(
|
|
prompt: "go",
|
|
function_results: [ {
|
|
call_id: "toolu_x",
|
|
name: "noop",
|
|
arguments: non_object_json,
|
|
output: nil
|
|
} ]
|
|
)
|
|
|
|
messages = formatter.build
|
|
|
|
assert_equal({}, messages[1][:content].first[:input],
|
|
"expected empty Hash for arguments=#{non_object_json.inspect}")
|
|
end
|
|
end
|
|
|
|
test "coerces non-Hash non-String arguments to empty Hash" do
|
|
formatter = Provider::Anthropic::MessageFormatter.new(
|
|
prompt: "go",
|
|
function_results: [ {
|
|
call_id: "toolu_x",
|
|
name: "noop",
|
|
arguments: [ 1, 2, 3 ],
|
|
output: nil
|
|
} ]
|
|
)
|
|
|
|
messages = formatter.build
|
|
|
|
assert_equal({}, messages[1][:content].first[:input])
|
|
end
|
|
|
|
private
|
|
def stub_user_message(content)
|
|
msg = UserMessage.new(content: content, ai_model: "claude-sonnet-4-6")
|
|
msg.id = SecureRandom.uuid
|
|
msg
|
|
end
|
|
|
|
def stub_assistant_message(content, tool_calls: [])
|
|
msg = AssistantMessage.new(content: content, ai_model: "claude-sonnet-4-6")
|
|
msg.id = SecureRandom.uuid
|
|
msg.stubs(:tool_calls).returns(tool_calls)
|
|
msg
|
|
end
|
|
|
|
def stub_tool_call(id:, name:, arguments:, result:)
|
|
tc = ToolCall::Function.new(
|
|
function_name: name,
|
|
function_arguments: arguments,
|
|
function_result: result
|
|
)
|
|
tc.stubs(:provider_call_id).returns(id)
|
|
tc.stubs(:provider_id).returns(id)
|
|
tc
|
|
end
|
|
end
|