cloverleaf-larry

bryan/cloverleaf-larry

Fork 0

Commit Graph

Author	SHA1	Message	Date
Bryan Johnson	b9415f3b57	v0.3.3: PHI sanitize/desanitize + {{phi:...}} prompt preprocessing Bryan's ask: use Larry on prod data without PHI ever leaving the client box. Added: lib/hl7-sanitize.sh — tokenize PHI fields in HL7 messages lib/hl7-desanitize.sh — reverse op (local view-time unmask) Tokenization model: - Replace PHI fields with [[CATEGORY_NNNN]] tokens (MRN, NAME, DOB, ADDR, PHONE, ACCT, SSN, PROV, VISIT, etc.) - Same value → same token across messages (deterministic via local lookup table; analysis can still correlate patients). - Lookup table at $LARRY_HOME/sanitize/lookup.tsv mode 0600 — never leaves the client. - Default PHI rule set covers PID, PV1, NK1, GT1, IN1, OBR, OBX, DG1, ORC; --rules-file to extend. - --strict also tokenizes unknown Z segments wholesale. Prompt-side preprocessing in larry.sh: - {{phi:VALUE}} inline marker, auto-category lookup - {{phi:CATEGORY:VALUE}} explicit category - Replaced with the token BEFORE the user input enters conversation history. The original never reaches the API. - Local feedback "phi> {{phi:...}} → [[TOKEN]]" printed to terminal only. New REPL slash commands: /phi <value> tokenize a single value, print the token /unmask <token> show original (local terminal only, never API) /tokens show full PHI ↔ token lookup table New tools in larry.sh schema: hl7_sanitize agent can sanitize a file before reading PHI tokenize-value / detokenize-value (subcommands of hl7-sanitize.sh) Persona update (agents/larry.md): - Documented PHI mode and rules for proactive sanitize-first behavior MANUAL.md updated with the full PHI section including limitations. Brings total native tools to 29. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>	2026-05-26 10:29:20 -07:00
Bryan Johnson	6060cd28c1	v0.3.2: lesson capture (local-first learning loop) Bryan's pivot: until bjnoela.com is back online, transfer learnings via local file capture on the client + manual paste-back to home-Larry. NO credentials required on the client box. Capture flow: - lib/lessons.sh records lessons to $LARRY_HOME/lessons/<date>.md - lesson_record tool in larry.sh lets the agent record proactively - /lesson, /lessons, /export REPL commands - agents/larry.md updated: capture corrections, conventions, quirks silently when Bryan teaches them Export flow: - lessons.sh export \| bundle \| --gh-issue (uses gh CLI if available) - Bryan pastes the bundle to home-Larry on his dev machine - home-Larry commits the refinement into cloverleaf-larry/agents/ - next launch on any client pulls updated persona via self-update Brings total native tools to 28. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>	2026-05-26 10:00:37 -07:00
Bryan Johnson	e08f030df5	v0.3.0: initial release of Larry-Anywhere Portable AI agent for Cloverleaf integration work. Pure bash + curl + jq. Zero dependency on v1 wrapper scripts or v2 cloverleaf-tools.pyz. 27 native Anthropic tools: NetConfig parsing (read) nc_list_protocols, nc_list_processes, nc_protocol_block, nc_protocol_field, nc_protocol_nested, nc_protocol_summary, nc_destinations, nc_sources, nc_xlate_refs, nc_tclproc_refs NetConfig modification (journal-backed writes with rollback) nc_insert_protocol, nc_add_route, larry_rollback_list Workflows nc_find_inbound, nc_make_jump (3-thread jump pattern), nc_find (tbn/tbp/tbh/tbpr/where replacements), nc_document, nc_diff_interface, nc_regression Messages hl7_field, nc_msgs (smat is SQLite!), hl7_diff (with --ignore MSH.7) File system read_file, list_dir, grep_files, glob_files, write_file, bash_exec Validated against a 22-site real Cloverleaf test install. Five worked examples end-to-end: jump-thread generation, smat MRN search, system documentation, interface+connected diff, HL7-aware regression diff. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>	2026-05-26 09:46:20 -07:00

Author

SHA1

Message

Date

Bryan Johnson

b9415f3b57

v0.3.3: PHI sanitize/desanitize + {{phi:...}} prompt preprocessing

Bryan's ask: use Larry on prod data without PHI ever leaving the client box.

Added:
  lib/hl7-sanitize.sh       — tokenize PHI fields in HL7 messages
  lib/hl7-desanitize.sh     — reverse op (local view-time unmask)

Tokenization model:
  - Replace PHI fields with [[CATEGORY_NNNN]] tokens (MRN, NAME, DOB,
    ADDR, PHONE, ACCT, SSN, PROV, VISIT, etc.)
  - Same value → same token across messages (deterministic via local
    lookup table; analysis can still correlate patients).
  - Lookup table at $LARRY_HOME/sanitize/lookup.tsv mode 0600 — never
    leaves the client.
  - Default PHI rule set covers PID, PV1, NK1, GT1, IN1, OBR, OBX,
    DG1, ORC; --rules-file to extend.
  - --strict also tokenizes unknown Z segments wholesale.

Prompt-side preprocessing in larry.sh:
  - {{phi:VALUE}}             inline marker, auto-category lookup
  - {{phi:CATEGORY:VALUE}}    explicit category
  - Replaced with the token BEFORE the user input enters conversation
    history. The original never reaches the API.
  - Local feedback "phi> {{phi:...}} → [[TOKEN]]" printed to terminal only.

New REPL slash commands:
  /phi <value>        tokenize a single value, print the token
  /unmask <token>     show original (local terminal only, never API)
  /tokens             show full PHI ↔ token lookup table

New tools in larry.sh schema:
  hl7_sanitize        agent can sanitize a file before reading PHI
  tokenize-value / detokenize-value (subcommands of hl7-sanitize.sh)

Persona update (agents/larry.md):
  - Documented PHI mode and rules for proactive sanitize-first behavior

MANUAL.md updated with the full PHI section including limitations.

Brings total native tools to 29.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-26 10:29:20 -07:00

Bryan Johnson

6060cd28c1

v0.3.2: lesson capture (local-first learning loop)

Bryan's pivot: until bjnoela.com is back online, transfer learnings via
local file capture on the client + manual paste-back to home-Larry. NO
credentials required on the client box.

Capture flow:
  - lib/lessons.sh records lessons to $LARRY_HOME/lessons/<date>.md
  - lesson_record tool in larry.sh lets the agent record proactively
  - /lesson, /lessons, /export REPL commands
  - agents/larry.md updated: capture corrections, conventions, quirks
    silently when Bryan teaches them

Export flow:
  - lessons.sh export | bundle | --gh-issue (uses gh CLI if available)
  - Bryan pastes the bundle to home-Larry on his dev machine
  - home-Larry commits the refinement into cloverleaf-larry/agents/
  - next launch on any client pulls updated persona via self-update

Brings total native tools to 28.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-26 10:00:37 -07:00

Bryan Johnson

e08f030df5

v0.3.0: initial release of Larry-Anywhere

Portable AI agent for Cloverleaf integration work. Pure bash + curl + jq.
Zero dependency on v1 wrapper scripts or v2 cloverleaf-tools.pyz.

27 native Anthropic tools:

NetConfig parsing (read)
  nc_list_protocols, nc_list_processes, nc_protocol_block,
  nc_protocol_field, nc_protocol_nested, nc_protocol_summary,
  nc_destinations, nc_sources, nc_xlate_refs, nc_tclproc_refs

NetConfig modification (journal-backed writes with rollback)
  nc_insert_protocol, nc_add_route, larry_rollback_list

Workflows
  nc_find_inbound, nc_make_jump (3-thread jump pattern), nc_find
  (tbn/tbp/tbh/tbpr/where replacements), nc_document, nc_diff_interface,
  nc_regression

Messages
  hl7_field, nc_msgs (smat is SQLite!), hl7_diff (with --ignore MSH.7)

File system
  read_file, list_dir, grep_files, glob_files, write_file, bash_exec

Validated against a 22-site real Cloverleaf test install. Five worked
examples end-to-end: jump-thread generation, smat MRN search, system
documentation, interface+connected diff, HL7-aware regression diff.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-26 09:46:20 -07:00

3 Commits