1013c94eb1ad283e960114aef04c19c2806b5db7
3
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 JesseMarkowitzandClaude Opus 5
|
480414efe0 |
M7: a first-class imported knowledge library
A campaign can import local .txt and .md files as Canon, Reference or Inspiration, and the class is load-bearing rather than a label: it decides the words a passage is framed with in the prompt, the weight it carries when passages are ranked, and which budget it competes in when the context is tight. This is a separate subsystem, which is the Phase 0B decision (IMPORTED-KNOWLEDGE-DESIGN.md §73). Story Cards do not carry classification, provenance, content identity, chunking, an index or a lifecycle, and they were not promoted into something that does. Nothing here reads or writes one. The subsystem, in backend/app/knowledge/: classes the three classes, their weights, and the prompt framing chunking deterministic, heading-aware, 60-800 tokens, no overlap fts SQLite FTS5 with porter stemming; scoped and bounded in SQL importer validate, hash, store, chunk, index — in one transaction embeddings local Ollama vectors through the shared provider retrieval query construction, hybrid merge, rerank inject the budgeted cut and the rendered prompt sections Relevance admission is a separate stage from ranking, and that separation is the milestone's most expensive lesson. An independent review found the first implementation deciding relevance with a floor expressed as a share of the best candidate — which the best clears by construction — so a passage was admitted on every turn regardless of the scene. A query about tide tables and container tonnage retrieved all five sources of a fantasy campaign, narrator-only hidden Canon among them. So the pipeline is now: candidate generation -> admission -> ranking -> class weighting -> budget Admission reads raw, candidate-set-independent signals: the cosine the model returned, and how many distinct meaningful query terms a passage contains. Ranking reads normalized ones, because bm25 has no fixed range and cosine's zero is not zero. Normalization decides order among things that matched; it can never decide whether anything matched. Authority is applied after admission, so a class orders what matched and never rescues what did not. Retrieval may therefore return nothing, and on a scene unrelated to the library it does. The other decisions that each replaced an obvious wrong one: - The class multiplies relevance rather than adding to it. An additive bonus satisfies "Canon outranks Reference" and makes "do not include irrelevant Canon" impossible, because a large enough constant wins on its own. - The semantic floor is measured, not guessed: 113 production-path pairs against nomic-embed-text put targeted matches at 0.55-0.85 and off-topic pairs at 0.36-0.56, and 0.58 sits between them. Because it is a property of that model and not of cosine similarity, it is keyed to the model rather than applied to whatever is configured: an embedding model with no measured calibration in this build does not borrow the number. Semantic admission is skipped, the campaign retrieves lexically, and the reason is stated in the knowledge status and in the turn's provenance. Degrading to lexical keeps the library usable; lending the threshold to an unmeasured model is how the admitted-everything defect would return. - One lexical term is not evidence. Two distinct meaningful terms, or one that is neither a standing campaign entity nor a negligible share of the query. The stop list grew from 42 words to 261, all function words — no subject matter, because a stop list that removes subject matter stops finding "The Silver Key". - Lexical retrieval is a production path, not a fallback. It finds the proper nouns and invented terms a setting bible is made of, and the library is fully usable with no embedding model configured. Safety is structural rather than filtered. Imported text reaches the prompt whole, inside a section that says what it is, under a rule stating the authority order in words and refusing every instruction inside it. No endpoint accepts a filesystem path, so H08 has no mechanism to escape from. Nothing renders imported content as HTML, so a script tag is five visible characters and a remote image is never fetched. Import, chunking, indexing, retrieval and a turn open no socket at all; only embeddings do, through the endpoint allowlist the memory bank already uses. Provenance is the rendered text, not a foreign key: deleting a source cannot turn a historical turn's evidence into dangling ids. Schema: knowledge_sources, knowledge_chunks, knowledge_embeddings, and an FTS5 virtual table attached to knowledge_chunks as a DDL hook so it is created and dropped with the table it indexes. Migration 92. A pre-M7 database opens unchanged and needs no sources to play. Bundle: the source content and the reader's judgements about it travel; the passages, index rows and vectors are rebuilt on import, so a restored campaign is searchable immediately without a reindex step. One runtime dependency: python-multipart, Starlette's multipart parser. It is what makes the upload surface possible, and the upload surface is why no pathname is ever accepted. The test doubles were the reason the defect shipped, so they were corrected too. The retrieval stub scored unrelated text at 0.06-0.20 where the real model scores it at 0.43-0.44, and its docstring said it had deliberately removed the constant component that "would put a similarity floor under every pair" — which is exactly the property real models have. The stub now has that floor, one test fails if it is ever removed, and another reproduces the superseded rule and asserts it is still fooled by the same fixture. Run against the pre-corrective implementation, the new suite fails 13 of 18. Tests: 939 passed, 14 skipped (836/7 at M6). 110 new across seven files, one of which mocks nothing between itself and Ollama and re-measures the similarity separation on every run. 43/43 checks in a real Firefox, reproduced. Docker build clean. Four other defects found by review or by the browser run were fixed here rather than carried: an unreachable relevance constant that appeared to enforce something and did not; acceptance tests using the wrong fixture files, so G07's trap was never exercised; a bidirectional override surviving into displayed filenames; and, from the implementation pass, the Insights panel showing M5's two state sections as raw keys and the source inspector refetching on every keystroke. M7 was independently reviewed, which returned PASS WITH CORRECTIVE WORK REQUIRED. Both blocking findings are closed, and closeout resolved the embedding-model calibration boundary the corrective pass had left as debt. planning/reports/M7-IMPLEMENTATION-REPORT.md carries the review, the corrective closeout and the closeout verification in sequence, none overwriting another. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017HdaXiFbscatQaLS7dJk6b |
||
|
JesseMarkowitzandClaude Opus 5
|
8652fe7cd8 |
M2 review: two regressions the green suite hid, and the reports
The post-implementation review of M2, plus the three corrections it took
to make the evidence true. Reports:
planning/reports/M2-BASELINE-REPORT.md 868 lines, the measurements
planning/reports/M2-IMPLEMENTATION-REPORT.md 758 lines, the reading of them
Verdict is PASS, accept with non-blocking debt, proceed to M3. Every M2
requirement is met and the ones that matter were tested by running the
build rather than reading it: a cloud endpoint written straight into
SQLite with sqlite3, behind the API's back, still refused at the wire;
trusted-LAN HTTPS against the real second machine with verification on;
captures showing zero packets outside loopback and the approved host.
Three defects, all found by running the shipped image.
The memory bank was dead. M2 removed Settings.api_key_plain with the API
key, and memorybank's two provider factories still read it. It failed
inside a fire-and-forget task, so no user error, no log anyone would
read, and no test — every memory test stubs those factories. All 604
tests passed with summaries and embeddings silently not happening.
The configurable model timeout never reached the turn engine. Stored,
validated, exposed in the API, rendered in the UI, and not passed to the
provider. M2's own exit criterion was half met: the constant had moved
but the setting did nothing.
And requirements.lock still pinned quickjs, psycopg and cryptography, so
the setup path DEVELOPMENT.md gives a new developer would have
reinstalled all three.
Both code defects now have the test that would have caught them: one
constructs every provider factory from a real Settings row, one drives
the turn endpoint, the chat endpoint and the summariser and asserts the
configured timeout arrives at each. That is the lesson worth keeping from
this milestone — after removing an attribute, build each consumer from a
real object; after adding a setting, prove it lands. Both failures were
in background or plumbing paths, which is exactly where a subtractive
change cannot see itself.
606 tests pass, up from 604. Lint, build and image are clean. Every
runtime result in the baseline report came from an image built after
these fixes; the reports say plainly that commit
|
||
|
JesseMarkowitzandClaude Opus 5
|
c1a73b3d77 |
M1: make the first story turn work with no Internet
Phase 0B ran the upstream application on a network with no route out and the first turn died in tiktoken, which downloads its BPE table the first time anything counts a token. The browser separately fetched three font families from Google on every page load. Neither is visible on a machine that has been online once, which is why both now have tests. The tokenizer table is vendored at backend/app/context/vendor/cl100k_base.tiktoken and backend/app/context/encoding.py builds the encoding from it directly, verifying its SHA-256 against the digest tiktoken itself pins for that URL. No code path in the tokenizer can reach the network any more — not a warm cache, not an environment variable a deployment could forget. The encoding was checked token for token against tiktoken's own. The three font families are self-hosted as variable fonts under frontend/public/fonts/ (343 KiB, Latin and Latin Extended), declared in frontend/src/styles/fonts.css, and re-vendored by frontend/tools/vendor_fonts.py. Their OFL licences ship beside them. With no remote asset left, the CSP drops both Google hosts and gains object-src, base-uri and form-action; woff2 also gets its real media type, which Python's table lacks on a slim image. A trusted-LAN Ollama turned out not to work at all over HTTPS. httpx verifies against the certifi bundle, so an endpoint whose certificate comes from a CA the user installed on their own machines — a StartOS server's Ollama, for one — was refused with CERTIFICATE_VERIFY_FAILED while curl and the browser on the same host accepted it. app/tlstrust.py builds one context that unions the platform CA store with certifi's, and all four outbound clients use it. A union rather than a swap, so an image with an empty system store cannot start failing on endpoints that worked before. Verification itself is untouched: CERT_REQUIRED, hostname checking on, and no insecure escape hatch. The storyteller listener is now loopback by explicit statement rather than by inheriting uvicorn's default: start.sh, start.ps1, and docker-compose.yml, which publishes to 127.0.0.1 rather than every interface. Reaching an Ollama on another machine is outbound and needs none of that inbound exposure. backend/requirements.lock pins the exact tested closure; requirements.txt keeps the ranges. DEVELOPMENT.md covers setup, the same-host and trusted-LAN Ollama configurations, and how to re-run the offline proof. PROVENANCE.md records the upstream commit, the MIT terms, and both vendored assets. Verified, not just compiled. On an --internal Docker network with 1.1.1.1 unreachable and no name resolving, a campaign was created and played for six turns through same-host Ollama, restarted, and resumed. A second run played ten turns through Ollama on a separate physical machine on the LAN over verified HTTPS, summaries and embeddings included, with the storyteller's default route deleted so the LAN was reachable and the Internet was not. Its capture: 893 packets to the approved host, 730 loopback, zero anywhere else, and zero DNS queries. Two induced model failures left the accepted story bit-identical. The inherited SPA was opened in a browser and a campaign read back from it. Evidence is in planning/reports/M1-BASELINE-REPORT.md, along with the findings that did not belong in this change. 648 backend tests pass, up from the inherited 632; frontend lint and build are clean; the image builds. No M2 work is included: the hosted, cloud, analytics, Postgres and scripting surfaces are untouched. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017foPNqFjAJa2Ngebf5mEfL |