mirror of
https://github.com/MBombeck/HealthLog.git
synced 2026-11-08 12:32:43 +00:00
Marc-André Bombeck
502783a3ea
Replace the scalar document_id discriminator on a coach conversation with a CoachConversationDocument join table and a sticky documentScoped flag, so a conversation can be grounded on several stored documents at once while the prompt-injection fence stays intact across the data-model change. The fence is re-established at both enforcement points, fail-closed: - Client: resolveCoachSendTarget routes any turn on a fenced conversation (or a fresh chat with staged attachments) to the new /api/insights/chat/fenced endpoint; the fenced body is strict and never carries scope, guided-question, or prefill hints. - Server: the tool route fetches with documentScoped:false AND 404s when the fetched row still carries an attachment (flag/join drift), emitting a fence_drift audit alarm. Document text now enters an LLM prompt in exactly one code path — the fenced pipeline — with no tools and no health snapshot; a module-graph test pins that the tool loop is unreachable from it. The fenced turn fences each document separately with a server-built, scrubbed header line (title and filename are untrusted text), runs a per-document egress consent check on the single picked provider, and grounds numerically over the live attachment union only. Attachments are capped at five documents and 192 KB of combined text with honest truncation. Attach and detach ride dedicated endpoints: attaching validates the document is owned, live, indexed, and within cap, then flips the conversation fenced (the one legal, privilege-reducing transition, audit-logged); detaching removes the document but never clears the flag. The document-sheet chat keeps its public wire contract and shares the same fenced pipeline over the join. Migration 0245 adds the join table and the flag, backfills every legacy single-document chat into a one-attachment fenced conversation, and drops the scalar column in the same transaction — no dual-truth window.
docs/ — internal reference + operator playbooks
The user-facing documentation lives at https://docs.healthlog.dev — that's the canonical surface for self-hosting guides, integration walkthroughs, AI-provider setup, and the doctor-report workflow.
The files in this directory are the internal operator playbooks, audit notes, and machine-readable specs that ship alongside the source:
api/— the OpenAPI 3.1 spec for the native-client subset (iOS DTO codegen target). Seeapi/README.mdfor the preview commands. Also home to the MCP-server contract:api/mcp-capabilities.md(tools, resources, prompts, write model) andapi/mcp-skills.md(building a connector / skill).ops/— backup / restore + encryption-key-rotation playbooks. These are the runbooks an operator reaches for during an incident.self-hosting/— horizontal-scaling notes (HEALTHLOG_PROCESS_TYPE=web|worker|all) and the deploy-pipeline recipe. Routine install steps stay ondocs.healthlog.dev. Includesself-hosting/mcp.md— enabling the off-by-default MCP connector and pointing Claude.ai / ChatGPT / Claude Desktop at it, andself-hosting/sso.md— OIDC SSO login: IdP setup, the identity-pinning security model,OIDC_ONLYconsequences, and the break-glass runbook.migration/— release-by-release migration notes. Read the entry for the version you're upgrading from.audit/— per-release audit summaries archived for forensic traceability.apple-store-connect-checklist.md— the iOS submission gate.doctor-report.md— PDF generator design notes.codex-protocol-spec.md— Codex / ChatGPT OAuth protocol reverse-engineering notes.ui-guidelines.md— UI / a11y house style.
If you're a self-hoster looking to spin up an instance, start at https://docs.healthlog.dev or jump to the Quick Start in the project README.