mirror of
https://github.com/we-promise/sure.git
synced 2026-06-06 11:19:02 +00:00
eb27d3606315f2ffaafc25b3cf9dc6a60a10d838
3 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Guillem Arias Fauste
|
8ccc434b3d |
feat(ai): Anthropic native PDF processing (3/5) (#1985)
* 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.
* feat(ai): add Anthropic batch ops + LLM cost ledger (2/5)
Implements auto_categorize, auto_detect_merchants, and
enhance_provider_merchants on Provider::Anthropic via forced tool calls,
plus the cost-ledger plumbing they need.
- Provider::Anthropic::AutoCategorizer, AutoMerchantDetector,
ProviderMerchantEnhancer each define a single output tool whose
input_schema mirrors the desired output, then force the model to call
it via tool_choice: { type: "tool", name: ..., disable_parallel_tool_use: true }.
Anthropic guarantees the tool_use.input matches the schema, so there
is no JSON parsing fragility, no <think> tag stripping, and no
json_object/json_schema fallback ladders.
- Concerns::UsageRecorder mirrors the OpenAI sibling but persists
cache_creation_input_tokens / cache_read_input_tokens to dedicated
columns instead of metadata.
- Migration adds cache_creation_tokens, cache_read_tokens (nullable
integers) to llm_usages. OpenAI rows leave them null.
- LlmUsage::PRICING gains Claude 4.x rows (opus-4-7 $15/$75, sonnet-4-6
$3/$15, haiku-4-5 $1/$5 per MTok). infer_provider returns "anthropic"
for claude-* via the existing exact/prefix lookup.
- Provider::Anthropic#chat_response now persists cache columns directly
rather than stashing them in metadata.
- 25-transaction batch cap mirrors the OpenAI provider so the cost
ledger sees the same shape regardless of which provider ran a batch.
Tests cover the forced-tool-call path, null/None normalization,
case-insensitive merchant matching, the missing-tool_use error path,
and Anthropic-specific pricing + provider inference on LlmUsage.
Stacked on #1983 (PR 1/5). 3/5 PDF + vision next.
* fix(ai): attribute Bedrock model IDs to anthropic + clean nil enum
- LlmUsage.infer_provider now returns "anthropic" for Bedrock /
Vertex shaped IDs (anthropic.* and anthropic/*), so cost-ledger
filtering by provider stays correct even when no per-MTok rate is
stored. Previously these IDs fell through to the "openai" default.
- AutoCategorizer drops the redundant nil sentinel from the
category_name enum — the union type [string, null] already permits
null, and some JSON Schema validators reject nil literals inside
enum arrays.
* test(ai): require "ostruct" in Anthropic batch op tests
Same rationale as the PR1 ostruct fix — explicit require so the tests
don't depend on ActiveSupport's transitive load when Ruby 3.5+ removes
OpenStruct from the default load path.
* feat(ai): Anthropic native PDF processing (3/5)
Implements process_pdf and extract_bank_statement on Provider::Anthropic
using the native `document` content block — no rasterization, no text
pre-extraction.
- Provider::Anthropic::PdfProcessor classifies the document, summarizes
it, and extracts statement metadata via a forced report_document_analysis
tool whose input_schema mirrors the existing Provider::Openai output
(document_type from Import::DOCUMENT_TYPES, summary, extracted_data).
- Provider::Anthropic::BankStatementExtractor returns the same
{ transactions, period, account_holder, account_number, bank_name,
opening_balance, closing_balance } shape via report_bank_statement so
downstream pdf_import code is provider-agnostic.
- Both attach the PDF as
{ type: "document", source: { type: "base64", media_type: "application/pdf", data: <b64> } }
— Claude 3.5+ / 4.x accept this natively (up to 32MB / 100 pages).
No pdf-reader, no pdftoppm, no chunking for typical statements.
- supports_pdf_processing? (introduced in PR 1) already returns true for
claude-* models, gating process_pdf with a clear error otherwise.
- Cost ledger rows are persisted via the shared UsageRecorder concern,
including cache_creation/cache_read tokens.
Tests verify the document block shape, tool_choice forcing, normalized
document_type for unknown classifications, transaction normalization
(date / amount / reference → notes), and the missing-tool_use error
path. Blank pdf_content raises before any client call.
Stacked on #1984 (PR 2/5). 4/5 pgvector RAG next.
* fix(ai): guard PDF size + surface bank-statement truncation
- PdfProcessor and BankStatementExtractor raise upfront when
pdf_content.bytesize exceeds MAX_PDF_BYTES (32 MB, matching
Anthropic's hard limit). Previously a 100 MB PDF would be
base64-encoded (~133 MB) and packed into the JSON body before
the API rejected it — peak heap ~270 MB per Sidekiq worker.
- BankStatementExtractor inspects response.stop_reason; when the
model hit max_tokens it logs a warning and flags result[:truncated]
so downstream callers know the transaction list may be incomplete.
- ISO date pattern added to statement_period_start/end schema in
PdfProcessor so the model can't return "March 2026" — Anthropic
enforces the regex via the tool's input_schema.
Tests cover the size guard (raises before any client.messages call),
truncated-result flagging, and the warning log path.
* test(ai): require "ostruct" in Anthropic PDF tests
Match the explicit ostruct require added in PR1/PR2 — same Ruby 3.5+
load-path reason.
* fix(llm-usage): include Anthropic cache tokens in estimated_cost
calculate_cost only priced prompt + completion tokens, so estimated_cost
under-reported every cached call — the cache_creation/cache_read columns this PR
added were tracked but never billed. Verified against the Anthropic dashboard: a
cached chat turn billed $0.05 but the ledger recorded $0.038; the gap was exactly
the unpriced cache tokens.
Price them relative to the input rate (Anthropic: cache write 1.25x, read 0.1x)
and thread the cache counts from both recorders (chat + batch). OpenAI rows leave
the columns null (treated as 0), so they're unaffected. Ledger now reproduces the
dashboard ($0.054 for the test turn).
* chore(ai): guard chat usage double-record; flag deferred Anthropic batch wiring
- Hardening: guard the success-path record_llm_usage with
`unless partial_usage_recorded` so a future change that emits partial usage on
a normal stream can't silently double-bill (the symptom investigated in the
#1984 review). No behavior change today — on_partial only fires from the
mid-stream-error rescue, which re-raises past this line.
- Notice: the family auto-categorize / merchant-detect / merchant-enhance flows
still hardcode get_provider(:openai). Provider::Anthropic now implements those
batch ops but they aren't wired into the family flows yet — documented with
TODOs at each site for the follow-up.
* chore(ai): point family-flow TODOs at tracking issue #2113
* chore(ai): flag deferred Anthropic PDF wiring (TODO #2113)
The PDF import + bank-statement-extract flows hardcode get_provider(:openai).
Provider::Anthropic implements process_pdf / extract_bank_statement (this PR)
but they aren't wired into these paths yet — documented with TODOs at each
site. Tracked in #2113 (broadened to cover batch ops + PDF).
* chore(anthropic-pdf): drop redundant strip_heredoc; document no-dedup
- The squiggly heredoc (<<~) already strips indentation, so the trailing
.strip_heredoc was a no-op in both PDF extractors.
- Document why BankStatementExtractor intentionally does NOT deduplicate (unlike
the OpenAI extractor): we send the whole PDF as one native document block, so
there are no overlapping-chunk artifacts to dedupe, and deduping would wrongly
merge legitimate same-day, same-amount transactions.
* fix(anthropic): cap PDF bytes below the base64-encoded request limit
Anthropic's 32 MB limit is on the Messages request body, and the PDF is sent
base64-encoded (~4/3 larger) alongside the JSON envelope, so a 32 MB raw PDF
encodes to ~42 MB and is rejected. Cap the raw bytes at 3/4 of the request
budget minus a 1 MB envelope reserve (~23 MiB). Addresses Codex review on #1985.
|
||
|
soky srm
|
7908f7d8a4 |
Expand financial providers (#1407)
* Initial implementation * Tiingo fixes * Adds 2 providers, remove 2 * Add extra checks * FIX a big hotwire race condition // Fix hotwire_combobox race condition: when typing quickly, a slow response for // an early query (e.g. "A") can overwrite the correct results for the final query // (e.g. "AAPL"). We abort the previous in-flight request whenever a new one fires, // so stale Turbo Stream responses never reach the DOM. * pipelock * Update price_test.rb * Reviews * i8n * fixes * fixes * Update tiingo.rb * fixes * Improvements * Big revamp * optimisations * Update 20260408151837_add_offline_reason_to_securities.rb * Add missing tests, fixes * small rank tests * FIX tests * Update show.html.erb * Update resolver.rb * Update usd_converter.rb * Update holdings_controller.rb * Update holdings_controller.rb * Update holdings_controller.rb * Update holdings_controller.rb * Update holdings_controller.rb * Update _yahoo_finance_settings.html.erb |
||
|
MkDev11
|
6f8858b1a6 |
feat/Add AI-Powered Bank Statement Import (step 1, PDF import & analysis) (#808)
* feat: Add PDF import with AI-powered document analysis This enhances the import functionality to support PDF files with AI-powered document analysis. When a PDF is uploaded, it is processed by AI to: - Identify the document type (bank statement, credit card statement, etc.) - Generate a summary of the document contents - Extract key metadata (institution, dates, balances, transaction count) After processing, an email is sent to the user asking for next steps. Key changes: - Add PdfImport model for handling PDF document imports - Add Provider::Openai::PdfProcessor for AI document analysis - Add ProcessPdfJob for async PDF processing - Add PdfImportMailer for user notification emails - Update imports controller to detect and handle PDF uploads - Add PDF import option to the new import page - Add i18n translations for all new strings - Add comprehensive tests for the new functionality * Add bank statement import with AI extraction - Create ImportBankStatement assistant function for MCP - Add BankStatementExtractor with chunked processing for small context windows - Register function in assistant configurable - Make PdfImport#pdf_file_content public for extractor access - Increase OpenAI request timeout to 600s for slow local models - Increase DB connection pool to 20 for concurrent operations Tested with M-Pesa bank statement via remote Ollama (qwen3:8b): - Successfully extracted 18 transactions - Generated CSV and created TransactionImport - Works with 3000 char chunks for small context windows * Add pdf-reader gem dependency The BankStatementExtractor uses PDF::Reader to parse bank statement PDFs, but the gem was not properly declared in the Gemfile. This would cause NameError in production when processing bank statements. Added pdf-reader ~> 2.12 to Gemfile dependencies. * Fix transaction deduplication to preserve legitimate duplicates The previous deduplication logic removed ALL duplicate transactions based on [date, amount, name], which would drop legitimate same-day duplicates like multiple ATM withdrawals or card authorizations. Changed to only deduplicate transactions that appear in consecutive chunks (chunking artifacts) while preserving all legitimate duplicates within the same chunk or non-adjacent chunks. * Refactor bank statement extraction to use public provider method Address code review feedback: - Add public extract_bank_statement method to Provider::Openai - Remove direct access to private client via send(:client) - Update ImportBankStatement to use new public method - Add require 'set' to BankStatementExtractor - Remove PII-sensitive content from error logs - Add defensive check for nil response.error - Handle oversized PDF pages in chunking logic - Remove unused process_native and process_generic methods - Update email copy to reflect feature availability - Add guard for nil document_type in email template - Document pdf-reader gem rationale in Gemfile Tested with both OpenAI (gpt-4o) and Ollama (qwen3:8b): - OpenAI: 49 transactions extracted in 30s - Ollama: 40 transactions extracted in 368s - All encapsulation and error handling working correctly * Update schema.rb with ai_summary and document_type columns * Address PR #808 review comments - Rename :csv_file to :import_file across controllers/views/tests - Add PDF test fixture (sample_bank_statement.pdf) - Add supports_pdf_processing? method for graceful degradation - Revert unrelated database.yml pool change (600->3) - Remove month_start_day schema bleed from other PR - Fix PdfProcessor: use .strip instead of .strip_heredoc - Add server-side PDF magic byte validation - Conditionally show PDF import option when AI provider available - Fix ProcessPdfJob: sanitize errors, handle update failure - Move pdf_file attachment from Import to PdfImport - Document deduplication logic limitations - Fix ImportBankStatement: catch specific exceptions only - Remove unnecessary require 'set' - Remove dead json_schema method from PdfProcessor - Reduce default OpenAI timeout from 600s to 60s - Fix nil guard in text mailer template - Add require 'csv' to ImportBankStatement - Remove Gemfile pdf-reader comment * Fix RuboCop indentation in ProcessPdfJob * Refactor PDF import check to use model predicate method Replace is_a?(PdfImport) type check with requires_csv_workflow? predicate that leverages STI inheritance for cleaner controller logic. * Fix missing 'unknown' locale key and schema version mismatch - Add 'unknown: Unknown Document' to document_types locale - Fix schema version to match latest migration (2026_01_24_180211) * Document OPENAI_REQUEST_TIMEOUT env variable Added to .env.local.example and docs/hosting/ai.md * Rename ALLOWED_MIME_TYPES to ALLOWED_CSV_MIME_TYPES for clarity * Add comment explaining requires_csv_workflow? predicate * Remove redundant required_column_keys from PdfImport Base class already returns [] by default * Add ENV toggle to disable PDF processing for non-vision endpoints OPENAI_SUPPORTS_PDF_PROCESSING=false can be used for OpenAI-compatible endpoints (e.g., Ollama) that don't support vision/PDF processing. * Wire up transaction extraction for PDF bank statements - Add extracted_data JSONB column to imports - Add extract_transactions method to PdfImport - Call extraction in ProcessPdfJob for bank statements - Store transactions in extracted_data for later review * Fix ProcessPdfJob retry logic, sanitize and localize errors - Allow retries after partial success (classification ok, extraction failed) - Log sanitized error message instead of raw message to avoid data leakage - Use i18n for user-facing error messages * Add vision-capable model validation for PDF processing * Fix drag-and-drop test to use correct field name csv_file * Schema bleedover from another branch * Fix drag-drop import form field name to match controller * Add vision capability guard to process_pdf method --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: mkdev11 <jaysmth689+github@users.noreply.github.com> Co-authored-by: Juan José Mata <jjmata@jjmata.com> |