buyer: PDF book summarizer (/book) — chunk → map-reduce over suppliers

Adds an authenticated upload flow to the buyer web app: an operator
uploads a PDF, the server extracts + paragraph-aligned-chunks it
(~2.2k tokens), then runs a hierarchical map-reduce summarization by
paying marketplace suppliers per chunk — one on-chain escrow per map
call and per reduce node. One book upload fans out into dozens of real
mainnet escrows (the intended marketplace traffic) while producing a
genuine full-book summary.

Server module (buyer/src/pdf/): PDF extraction (text-only, rejects
scanned), token-aware chunker, supplier discovery/round-robin filtered
to capable models (kimi/deepseek/gpt; excludes qwen2.5:0.5b), pre-spend
cost estimate + wallet-floor guard, and a JobStore orchestrator that
reuses submitPrompt → findSubmittedEscrowRef → runAccept per call.
v1 serializes PostEscrow under a mutex (the shared tx builder can't pin
wallet inputs, so parallel escrows would double-spend); retries failed
calls on a different supplier then continues with gaps. 6 /v1/pdf-*
routes (multipart upload, estimate, confirm-gated start, SSE progress,
result, .md download) behind the existing session auth + page/chunk/
balance caps. SPA adds a 4-step BookSummarizer wizard.

Tests: chunk/estimate/supplier-pool/extract unit tests + orchestrator
(happy/gap/failover) + routes integration. Full buyer suite green
(181 tests); SPA build + typecheck clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
david
2026-06-03 11:37:49 +02:00
parent 2025ab7411
commit c552c4caa3
25 changed files with 2518 additions and 0 deletions

116
pnpm-lock.yaml generated
View File

@@ -95,6 +95,15 @@ importers:
express:
specifier: ^4.21.2
version: 4.22.1
gpt-tokenizer:
specifier: ^2.8.1
version: 2.9.0
multer:
specifier: ^1.4.5-lts.1
version: 1.4.5-lts.2
pdf-parse:
specifier: ^1.1.1
version: 1.1.4
react:
specifier: ^18.3.1
version: 18.3.1
@@ -120,6 +129,12 @@ importers:
'@types/express':
specifier: ^5.0.3
version: 5.0.6
'@types/multer':
specifier: ^1.4.11
version: 1.4.13
'@types/pdf-parse':
specifier: ^1.1.4
version: 1.1.5
'@types/react':
specifier: ^18.3.0
version: 18.3.28
@@ -1165,9 +1180,15 @@ packages:
'@types/methods@1.1.4':
resolution: {integrity: sha512-ymXWVrDiCxTBE3+RIrrP533E70eA+9qu7zdWoHuOmGujkYtzf4HQF96b8nwHLqhuf4ykX61IGRIB38CC6/sImQ==}
'@types/multer@1.4.13':
resolution: {integrity: sha512-bhhdtPw7JqCiEfC9Jimx5LqX9BDIPJEh2q/fQ4bqbBPtyEZYr3cvF22NwG0DmPZNYA0CAf2CnqDB4KIGGpJcaw==}
'@types/node@25.6.0':
resolution: {integrity: sha512-+qIYRKdNYJwY3vRCZMdJbPLJAtGjQBudzZzdzwQYkEPQd+PJGixUL5QfvCLDaULoLv+RhT3LDkwEfKaAkgSmNQ==}
'@types/pdf-parse@1.1.5':
resolution: {integrity: sha512-kBfrSXsloMnUJOKi25s3+hRmkycHfLK6A09eRGqF/N8BkQoPUmaCr+q8Cli5FnfohEz/rsv82zAiPz/LXtOGhA==}
'@types/prop-types@15.7.15':
resolution: {integrity: sha512-F6bEyamV9jKGAFBEmlQnesRPGOQqS2+Uwi0Em15xenOxHaf2hv6L8YCVn3rPdPJOiJfPiCnLIRyvwVaqMY3MIw==}
@@ -1281,6 +1302,9 @@ packages:
resolution: {integrity: sha512-KMReFUr0B4t+D+OBkjR3KYqvocp2XaSzO55UcB6mgQMd3KbcE+mWTyvVV7D/zsdEbNnV6acZUutkiHQXvTr1Rw==}
engines: {node: '>= 8'}
append-field@1.0.0:
resolution: {integrity: sha512-klpgFSWLW1ZEs8svjfb7g4qWY0YS5imI82dTg+QahUvJ8YqAY0P10Uk8tTyh9ZGuYEZEMaeJYCF5BFuX552hsw==}
arg@5.0.2:
resolution: {integrity: sha512-PYjyFOLKQ9y57JvQ6QLo8dAgNqswh8M1RMJYdQduT6xbWSgK36P/Z/v+p888pM69jMMfS8Xd8F6I1kQ/I9HUGg==}
@@ -1376,9 +1400,16 @@ packages:
engines: {node: ^6 || ^7 || ^8 || ^9 || ^10 || ^11 || ^12 || >=13.7}
hasBin: true
buffer-from@1.1.2:
resolution: {integrity: sha512-E+XQCRwSbaaiChtv6k6Dwgc+bx+Bs6vuKJHHl5kox/BaKbhiXzqQOwK4cO22yElGp2OCmjwVhT3HmxgyPGnJfQ==}
buffer@5.7.1:
resolution: {integrity: sha512-EHcyIPBQ4BSGlvjB16k5KgAJ27CIsHY/2JBmCRReo48y9rQ3MaUzWX3KVlBa4U7MyX02HdVj0K7C3WaB3ju7FQ==}
busboy@1.6.0:
resolution: {integrity: sha512-8SFQbg/0hQ9xy3UNTB0YEnsNBbWfhf7RtnzpL7TkBiTBRfrQ9Fxcnz7VJsleJpyp6rVLvXiuORqjlHi5q+PYuA==}
engines: {node: '>=10.16.0'}
bytes@3.1.2:
resolution: {integrity: sha512-/Nf7TyzTx6S3yRJObOAV7956r8cr2+Oj8AC5dt8wSP3BQAoeX58NoHyCU8P8zGkNXStjTSi6fzO6F0pBdcYbEg==}
engines: {node: '>= 0.8'}
@@ -1450,6 +1481,10 @@ packages:
component-emitter@1.3.1:
resolution: {integrity: sha512-T0+barUSQRTUQASh8bx02dl+DhF54GtIDY13Y3m9oWTklKbb3Wv974meRpeZ3lp1JpLVECWWNHC4vaG2XHXouQ==}
concat-stream@1.6.2:
resolution: {integrity: sha512-27HBghJxjiZtIk3Ycvn/4kbJk/1uZuJFfuPEns6LaEvpvG1f0hTea8lilrouyo9mVc2GWdcEZ8OLoGmSADlrCw==}
engines: {'0': node >= 0.8}
content-disposition@0.5.4:
resolution: {integrity: sha512-FveZTNuGw04cxlAiWbzi6zTAL/lhehaWbTtgluJh4/E95DqMwTmha3KZN1aAWA8cFIhHzMZUvLevkw5Rqk+tSQ==}
engines: {node: '>= 0.6'}
@@ -1779,6 +1814,9 @@ packages:
resolution: {integrity: sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==}
engines: {node: '>= 0.4'}
gpt-tokenizer@2.9.0:
resolution: {integrity: sha512-YSpexBL/k4bfliAzMrRqn3M6+it02LutVyhVpDeMKrC/O9+pCe/5s8U2hYKa2vFLD5/vHhsKc8sOn/qGqII8Kg==}
happy-dom@15.11.7:
resolution: {integrity: sha512-KyrFvnl+J9US63TEzwoiJOQzZBJY7KgBushJA8X61DMbNsH+2ONkDuLDnCnwUiPTF42tLoEmrPyoqbenVA5zrg==}
engines: {node: '>=18.0.0'}
@@ -2062,12 +2100,21 @@ packages:
mkdirp-classic@0.5.3:
resolution: {integrity: sha512-gKLcREMhtuZRwRAfqP3RFW+TK4JqApVBtOIftVgjuABpAtpxhPGaDcfvbhNvD0B8iD1oUr/txX35NjcaY6Ns/A==}
mkdirp@0.5.6:
resolution: {integrity: sha512-FP+p8RB8OWpF3YZBCrP5gtADmtXApB5AMLn+vdyA+PyxCjrCs00mjyUozssO33cwDeT3wNGdLxJ5M//YqtHAJw==}
hasBin: true
ms@2.0.0:
resolution: {integrity: sha512-Tpp60P6IUJDTuOq/5Z8cdskzJujfwqfOTkrwIwj7IRISpnkJnT6SyJ4PCPnGMoFjC9ddhal5KVIYtAt97ix05A==}
ms@2.1.3:
resolution: {integrity: sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA==}
multer@1.4.5-lts.2:
resolution: {integrity: sha512-VzGiVigcG9zUAoCNU+xShztrlr1auZOlurXynNvO9GiWD1/mTBbUljOKY+qMeazBqXgRnjzeEgJI/wyjJUHg9A==}
engines: {node: '>= 6.0.0'}
deprecated: Multer 1.x is impacted by a number of vulnerabilities, which have been patched in 2.x. You should upgrade to the latest 2.x version.
multiformats@13.4.2:
resolution: {integrity: sha512-eh6eHCrRi1+POZ3dA+Dq1C6jhP1GNtr9CRINMb67OKzqW9I5DUuZM/3jLPlzhgpGeiNUlEGEbkCYChXMCc/8DQ==}
@@ -2096,6 +2143,9 @@ packages:
resolution: {integrity: sha512-6u9UwL0HlAl21+agMN3YAMXcKByMqwGx+pq+P76vii5f7hTPtKDp08/H9py6DY+cfDw7kQNTGEj/rly3IgbNQA==}
engines: {node: '>=10'}
node-ensure@0.0.0:
resolution: {integrity: sha512-DRI60hzo2oKN1ma0ckc6nQWlHU69RH6xN0sjQTjMpChPfTYvKZdcQFfdYK2RWbJcKyUizSIy/l8OTGxMAM1QDw==}
node-fetch@2.7.0:
resolution: {integrity: sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A==}
engines: {node: 4.x || >=6.0.0}
@@ -2251,6 +2301,10 @@ packages:
resolution: {integrity: sha512-Q3CG/cYvCO1ye4QKkuH7EXxs3VC/rI1/trd+qX2+PolbaKG0H+bgcZzrTt96mMyRtejk+JMCiLUn3y29W8qmFQ==}
engines: {node: '>= 0.10'}
pdf-parse@1.1.4:
resolution: {integrity: sha512-XRIRcLgk6ZnUbsHsYXExMw+krrPE81hJ6FQPLdBNhhBefqIQKXu/WeTgNBGSwPrfU0v+UCEwn7AoAUOsVKHFvQ==}
engines: {node: '>=6.8.1'}
picocolors@1.1.1:
resolution: {integrity: sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA==}
@@ -2544,6 +2598,10 @@ packages:
std-env@3.10.0:
resolution: {integrity: sha512-5GS12FdOZNliM5mAOxFRg7Ir0pWz8MdpYm6AY6VPkGpbA7ZzmbzNcBJQ0GPvvyWgcY7QAhCgf9Uy89I03faLkg==}
streamsearch@1.1.0:
resolution: {integrity: sha512-Mcc5wHehp9aXz1ax6bZUyY5afg9u2rv5cqQI3mRrYkGC8rW2hM02jWuwjtL++LS5qinSyhj2QfLyNsuc+VsExg==}
engines: {node: '>=10.0.0'}
string-width@4.2.3:
resolution: {integrity: sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==}
engines: {node: '>=8'}
@@ -2686,6 +2744,9 @@ packages:
resolution: {integrity: sha512-nAYYwfY3qnzX30IkA6AQZjVbtK6duGontcQm1WSG1MD94YLqK0515GNApXkoxKOWMusVssAHWLh9SeaoefYFGw==}
engines: {node: '>= 0.4'}
typedarray@0.0.6:
resolution: {integrity: sha512-/aCDEGatGvZ2BIk+HmLf4ifCJFwvKFNb9/JeZPMulfgFracn9QFcAf5GO8B/mweUjSoblS5In0cWhqpfs/5PQA==}
typescript@5.9.3:
resolution: {integrity: sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw==}
engines: {node: '>=14.17'}
@@ -2857,6 +2918,10 @@ packages:
utf-8-validate:
optional: true
xtend@4.0.2:
resolution: {integrity: sha512-LKYU1iAXJXUgAXn9URjiu+MWhyUXHsvfp7mcuYm9dSUKK0/CjtrUwFAxD82/mCWbtLsGjFIad0wIsod4zrTAEQ==}
engines: {node: '>=0.4'}
yallist@3.1.1:
resolution: {integrity: sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g==}
@@ -3731,10 +3796,18 @@ snapshots:
'@types/methods@1.1.4': {}
'@types/multer@1.4.13':
dependencies:
'@types/express': 5.0.6
'@types/node@25.6.0':
dependencies:
undici-types: 7.19.2
'@types/pdf-parse@1.1.5':
dependencies:
'@types/node': 25.6.0
'@types/prop-types@15.7.15': {}
'@types/qs@6.15.0': {}
@@ -3874,6 +3947,8 @@ snapshots:
normalize-path: 3.0.0
picomatch: 2.3.2
append-field@1.0.0: {}
arg@5.0.2: {}
aria-query@5.3.0:
@@ -3978,11 +4053,17 @@ snapshots:
node-releases: 2.0.38
update-browserslist-db: 1.2.3(browserslist@4.28.2)
buffer-from@1.1.2: {}
buffer@5.7.1:
dependencies:
base64-js: 1.5.1
ieee754: 1.2.1
busboy@1.6.0:
dependencies:
streamsearch: 1.1.0
bytes@3.1.2: {}
cac@6.7.14: {}
@@ -4068,6 +4149,13 @@ snapshots:
component-emitter@1.3.1: {}
concat-stream@1.6.2:
dependencies:
buffer-from: 1.1.2
inherits: 2.0.4
readable-stream: 2.3.8
typedarray: 0.0.6
content-disposition@0.5.4:
dependencies:
safe-buffer: 5.2.1
@@ -4446,6 +4534,8 @@ snapshots:
gopd@1.2.0: {}
gpt-tokenizer@2.9.0: {}
happy-dom@15.11.7:
dependencies:
entities: 4.5.0
@@ -4692,10 +4782,24 @@ snapshots:
mkdirp-classic@0.5.3: {}
mkdirp@0.5.6:
dependencies:
minimist: 1.2.8
ms@2.0.0: {}
ms@2.1.3: {}
multer@1.4.5-lts.2:
dependencies:
append-field: 1.0.0
busboy: 1.6.0
concat-stream: 1.6.2
mkdirp: 0.5.6
object-assign: 4.1.1
type-is: 1.6.18
xtend: 4.0.2
multiformats@13.4.2: {}
multipasta@0.2.7: {}
@@ -4718,6 +4822,8 @@ snapshots:
dependencies:
semver: 7.7.4
node-ensure@0.0.0: {}
node-fetch@2.7.0:
dependencies:
whatwg-url: 5.0.0
@@ -4782,6 +4888,10 @@ snapshots:
sha.js: 2.4.12
to-buffer: 1.2.2
pdf-parse@1.1.4:
dependencies:
node-ensure: 0.0.0
picocolors@1.1.1: {}
picomatch@2.3.2: {}
@@ -5125,6 +5235,8 @@ snapshots:
std-env@3.10.0: {}
streamsearch@1.1.0: {}
string-width@4.2.3:
dependencies:
emoji-regex: 8.0.0
@@ -5311,6 +5423,8 @@ snapshots:
es-errors: 1.3.0
is-typed-array: 1.1.15
typedarray@0.0.6: {}
typescript@5.9.3: {}
uint8-varint@2.0.4:
@@ -5469,4 +5583,6 @@ snapshots:
ws@8.20.0: {}
xtend@4.0.2: {}
yallist@3.1.1: {}