A/B test (2026-05-05) showed DeepSeek V4-Pro is 2-3x faster and ~20x cheaper
than Sonnet for style/lexicon pattern analysis, with comparable quality.
Adds adapters/deepseek-paperclip-adapter/ package, documents adapter requirements
(env injection, run-id headers), updates CLAUDE.md with adapter integration notes,
and records lessons from ערר 1200-25 (block order for 1xxx, "להלן מתוך" pattern,
expanded factual background, bridge planning analysis, flat heading structure).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The curator's promptTemplate (stored in DB) now teaches Hermes how to
post issue_thread_interactions instead of free-text comments. Three
patterns supported, curator picks per context:
- ask_user_questions for filtering findings (multi-select)
- request_confirmation for accept/reject of a single proposal
- suggest_tasks for proposing follow-up issues
Verified end-to-end on CMP-71: curator hit a real obstacle (couldn't
read the final DOCX from its container) and chose request_confirmation
on its own to ask the user how to proceed — exactly the conversational
behavior we want.
Paperclip auto-wakes the curator with $PAPERCLIP_APPROVAL_ID when the
user responds. The new prompt has a §B branch that handles the second
wake (read response → act → close).
The UI side was already built in d099470 (mirror Paperclip interactions
in case page) — now Hermes-side agents produce interactions too, not
just claude_local agents.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The previous F2 stage in legal-ceo.md fired after the first DOCX export
— too early, since the user often iterates with עריכה-* uploads after
the first export. The true "this is dafna's chosen final" signal is the
"סמן כסופי" button in the UI, which calls api_mark_final.
This commit moves the curator wakeup from CEO's instructions to a
direct hook in api_mark_final:
- web/paperclip_client.py: add CURATOR_AGENTS dict (CMP + CMPA UUIDs)
and wake_curator_for_final() helper. Looks up main case issue,
creates a child issue assigned to the curator, tags plugin_state for
case visibility, and triggers wakeup via Paperclip API.
- web/app.py: api_mark_final now calls workflow_tools.ingest_final_version
(so case_law table finally gets populated for search_decisions) and
pc_wake_curator_for_final. Both are best-effort — failure does not
block marking final.
- legal-ceo.md: remove F2 stage, leave only the agents-table reference
noting the curator runs from api_mark_final.
- hermes-curator.md: update activation description to reflect the new
flow.
Result: curator runs only when chaim deliberately clicks "סמן כסופי",
on the actual final file, with no risk of analyzing a draft that will
later change.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds new sub-agent "מנהל ידע" (hermes_local adapter) that runs after
each successful export to analyze the final decision and suggest updates
to skills/decision/SKILL.md and lessons. Read-only on case data, write
only on a single comment per run.
- legal-ceo.md: new stage F2 after F (export). Looks up curator by name
in current company, creates async sub-issue, no waiting. Falls back to
silent skip if no curator configured.
- legal-ceo.md: agents table updated with both curator UUIDs (CMP + CMPA).
- hermes-curator.md: role instructions documenting CMP/CMPA split and
what the curator does/does not do.
Stage 1 POC. End-to-end validated on CMP-68 (case 1130-25) with two
substantive findings on style patterns. CMPA agent created with separate
~/.hermes/profiles/curator-cmpa profile (own MEMORY.md focused on
היטל השבחה / פיצויים).
Known gaps to follow up: curator does not auto-close its issue, does
not auto-persist findings to MEMORY.md, comment attribution falls back
to chaim's user (install-key) — these are tracked separately and do
not block validation.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Brings the legal-ai ↔ Paperclip integration in line with the official
Paperclip skill. Net effect: HEARTBEAT.md -47% (370→195 lines), all 14
agents on uniform runtime_config + budget + instructionsBundleMode, and
two cross-company helpers replacing manual SQL.
Highlights:
- HEARTBEAT.md refactor: project-specific only, delegates to the official
paperclipai/paperclip skill (loaded per agent). Adds heartbeat-context
fast-path (§1.7) and PAPERCLIP_WAKE_PAYLOAD_JSON shortcut (§1.5).
- Issue Thread Interactions API: legal-ceo.md now uses
ask_user_questions / request_confirmation / suggest_tasks instead of
free-text comments — gives chair structured UI with idempotency keys.
- pc.sh + paperclip_api.pc_request: every API call goes through helpers
that inject Authorization + X-Paperclip-Run-Id (audit trail).
- sync_agents_across_companies.py: master(CMP)→mirror(CMPA) sync via
Paperclip API, idempotent, with --verify and --apply modes.
- skills/new-company-setup: 11-step blueprint distilling all 11 gaps
into a single onboarding runbook for the next company.
- .taskmaster: 12 tasks covering each gap (one already closed: #29).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When Paperclip wakes the CEO and the model issues an mcp__legal-ai__*
call within ~10s of session init, Claude Code sometimes returns
"No such tool available" because the legal-ai MCP server hasn't
finished bringing up its tool catalog yet. Observed twice today on
CMPA precedent-extraction wakeups (sessions 9989fbaf and a9c61801);
the agent fell back to bash + .venv/bin/python and finished the work,
but the race needed fixing on the server side.
Three changes that close the window:
1. Lazy schema init (services/db.py + server.py)
`init_schema()` was awaited inside the FastMCP lifespan, blocking
the `initialize`/`tools/list` handshake until ~10 CREATE TABLE IF
NOT EXISTS statements ran. Under contention (two CEOs waking at
once for different companies) this stretched. Now the lifespan
returns immediately and `get_pool()` runs the schema migrations
exactly once on first DB access, guarded by an asyncio.Lock.
tools/list is answered in milliseconds regardless of DB state.
2. Lazy heavy imports
- services/embeddings.py: voyageai (~450ms) loaded only inside
_get_client()
- services/extractor.py: google.cloud.vision (~550ms) loaded only
inside _get_vision_client() and _ocr_with_google_vision()
These two were being imported at module top from
legal_mcp.tools.documents -> services.processor -> services.{
extractor,embeddings}, so the FastMCP server couldn't even start
responding until both finished. Cold start dropped from 2.7s to
1.17s end-to-end (init + tools/list response).
3. Agent-side warmup + retry guidance (.claude/agents/legal-ceo.md)
Even with a fast server, the model can still race on the very
first call. The precedent-extraction section now tells the CEO
to call workflow_status as a warmup probe and to retry after a
short sleep if it sees "No such tool available", before falling
back to the python bypass.
Also expanded the precedent-tool whitelists on the sub-agents that
delegate halacha/library work (commits 4a9a6b7 + 7ee90dc added the
tools to the MCP server but only the CEO got them in its allowed
list). Added to: legal-researcher (full extraction set), legal-analyst
(library_get/list + halacha review), legal-writer (library lookups +
halacha_review), legal-qa (library_get + halacha_review), and the two
that the CEO was already missing (halacha_review, halachot_pending).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When a precedent is uploaded to the library, the FastAPI container now
fires a Paperclip wakeup so Claude (running locally as the CEO agent)
picks up the new row and runs `precedent_process_pending` for both
metadata and halacha extraction. The user no longer has to remember to
trigger it manually.
Mechanics:
- New `wake_for_precedent_extraction()` in paperclip_client.py creates
(or reuses) a per-company "ספריית פסיקה — תור חילוץ" project, opens
a fresh issue assigned to the company CEO with the case_law_id +
citation in the description, and pings the Board API wakeup endpoint
with `triggerDetail=precedent_library_upload`.
- ingest_precedent's _run() in app.py captures the returned case_law_id
and best-effort calls the wake function (failures are logged, not
surfaced — the upload itself stays clean).
- legal-ceo.md adds the precedent_process_pending tool family and a
new "חילוץ פסיקה אוטומטי" section that tells the CEO to short-circuit
past the heartbeat scan when woken with this trigger.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a third corpus of legal authority distinct from style_corpus
(Daphna's prior decisions for voice) and case_precedents (chair-attached
quotes per case). The new corpus holds chair-uploaded court rulings and
other appeals committee decisions, with binding rules (הלכות) extracted
automatically and queued for chair approval.
Pipeline (web/app.py + services/precedent_library.py):
file → extract → chunk → Voyage embed → halacha_extractor → store +
publish progress over the existing Redis SSE channel.
Schema V7 (services/db.py): extends case_law with source_kind +
extraction status fields under a CHECK constraint pinning practice_area
to the three appeals committee domains (rishuy_uvniya, betterment_levy,
compensation_197). New precedent_chunks (vector(1024)) and halachot
tables (vector(1024) over rule_statement, IVFFlat indexes, gin on
practice_areas/subject_tags). Halachot start as pending_review; only
approved/published rows are visible to search_precedent_library.
Agents: legal-writer, legal-researcher, legal-analyst, legal-ceo,
legal-qa get search_precedent_library. legal-writer prompt explains
the three-corpus distinction and CREAC use; legal-qa now verifies that
every cited halacha resolves to an approved row in the corpus.
UI: /precedents page with four tabs — library / semantic search /
pending review (J/K nav, A/R/E shortcuts, badge count) / stats.
Reuses the existing upload-sheet progress + SSE pattern.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two latent issues surfaced today while watching the case 8174-24
end-to-end run, both worth documenting and engineering around because
they will recur on every future case.
Bug 1 — issue.released flips done→todo
After an agent successfully PATCHes its issue to "done", Paperclip's
internal issue.released action reverts the status to "todo" within
~30 seconds. This triggers a fresh wakeup of the same agent on a
task that is already complete.
Reproduced on CMPA-18 (30/04/26):
18:14:57 agent PATCH → status: done
18:15:35 Paperclip → issue.released → status: todo
18:15:54 new researcher run started
The fix at the right altitude (Paperclip itself) is outside our repo.
Mitigation in HEARTBEAT.md §3 — when an agent boots and finds the
issue in `todo` while expected outputs (file, DB rows) already exist,
it must short-circuit: post a "no change" comment, PATCH back to done,
and exit. Costs ~$0.20 per false wakeup but breaks the loop.
Bug 2 — Bash backtick trap on long comment bodies
Researcher agent built a curl pipeline like:
curl ... -d "$(python3 -c "body = '''...
📁 קובץ מחקר: `/path/to/file.md`
'''")"
The backticks around the file path (markdown convention) get
evaluated by the OUTER bash $(...) as command substitution. Bash
then tries to exec /path/to/file.md, which is not executable, and
prints "Permission denied" — a misleading error since the actual
file ownership is fine. The curl itself succeeded; only the bash
prelude noised up the log.
Fix in HEARTBEAT.md §4א: long bodies must go via Write→tempfile
then `curl -d @file`. Avoids every shell quoting edge case.
Files:
• docs/paperclip-quirks.md — new. Full writeup of both bugs plus
two prior known-quirks (CEO auto-block in_progress, INSERT vs
API for wakeups). Each section: what happens, empirical evidence
from logs, impact, workaround, status.
• .claude/agents/HEARTBEAT.md — added the self-recovery section to
§3 and the temp-file pattern to §4א. The temp-file pattern is the
canonical answer for any agent posting markdown comments —
applies to all 7 agents in this skill set.
• CLAUDE.md — referenced the new doc from the docs index.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two structural gaps in legal-researcher's "שלב 5: דיווח" surfaced while
auditing the case 8174-24 run:
1. **No DB linkage.** The skill told the researcher to post a comment
summarizing precedents but never to call mcp__legal-ai__precedent_attach.
The MCP tool itself wasn't even in the tools frontmatter — so even
a researcher that wanted to write to case_precedents physically
couldn't. Result: 0 rows in case_precedents after a successful
research run, even with 8 precedents identified and verified in
the comment text. The writer then has to grep free-text instead
of querying a structured table.
2. **No persisted file.** Research output existed only as a Paperclip
comment. The writer/QA can't `Read` it from disk; they have to go
through Paperclip API to fetch comment bodies. Compare to the
analyst, which is required to write `analysis-and-research.md`.
Fix:
• Added precedent_attach, precedent_list, precedent_search_library
to the tools frontmatter.
• Rewrote step 5 with explicit ordering: save to disk → attach
verified precedents to DB → update status → email → post comment.
• Documented the precedent_attach call signature inline (case_number,
citation, quote, section_id) so the agent doesn't have to reverse-
engineer it. Includes guidance on which precedents to attach
(verified with quote) vs which to leave for external verification.
Effect: future research runs will populate case_precedents and
data/cases/{N}/documents/research/precedent-research.md, both of which
the writer needs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The retry loop bug we fixed in legal-analyst yesterday existed in every
single sub-agent skill. They all post a comment + wake the CEO + exit,
leaving their own issue in `in_progress`. Paperclip's "in_progress with
no live execution" watchdog then re-wakes them, repeating until something
external transitions the issue. Watched it happen on CMPA-17 (researcher)
today — 4 iterations + manual SIGTERM + manual PATCH.
Same fix applied to all 5 remaining agents:
• legal-researcher.md
• legal-writer.md
• legal-qa.md
• legal-exporter.md
• legal-proofreader.md (file was incomplete — also added the missing
שלב 5: דיווח and wake-CEO sections to bring it to parity with the
other agents)
Each gets a "סגור את ה-issue של עצמך — חובה!" section with two PATCH
templates: one for `done` after a successful run, one for `blocked` if
checks fail or output is incomplete. The section sits before the
wake-CEO block, with an explicit reference to the CMPA-17 incident so
the rule has a concrete anchor.
Result: every agent now has the same close-issue contract. No more
zombie in_progress issues, no more 4× wakeup loops.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two structural bugs surfaced while monitoring the fresh end-to-end
run on case 8174-24:
1. **No appraiser_facts extraction.** legal-analyst.md's "what to
extract" table didn't mention doc_type='appraisal' at all, and
`extract_appraiser_facts` wasn't in its tools frontmatter. The
CEO compounded this by writing in CMPA-16's body that all 3
appraisals were "reference materials, do not extract" — which
is correct for `extract_claims` but wrong for the appraisal-
specific extractor. Result: 0 appraiser_facts in DB after a
full run, even though the user had carefully tagged each
appraisal's `appraiser_side` (committee/appellant) precisely
so detect_conflicts could compare them.
2. **Issue stays in_progress, Paperclip retries forever.** Step 7
("שמירה ודיווח") instructed the analyst to update the *case*
status, post a comment, send email, and wake the CEO — but
never to PATCH the issue itself to `done`. Paperclip's
"in_progress with no live execution" watchdog then re-woke the
analyst, which posted "I'm done" again, which re-triggered
another wakeup. We saw three iterations on CMPA-16 before the
issue finally transitioned. The PATCH pattern was already
documented in HEARTBEAT.md §4ב — the analyst skill just never
referenced it.
Changes:
• legal-analyst.md
- Added mcp__legal-ai__extract_appraiser_facts to tools list.
- Rewrote the "what to extract" table to use doc_type as the
key column and added an `appraisal` row + a callout explaining
why it goes through a different extractor.
- Added explicit step 5 "חלץ עובדות שמאי" with the call.
- Step 7 now PATCHes the issue to `done` (or `blocked` on
failure) before waking the CEO. Refers to the actual incident
so the rule has a concrete anchor.
- Cleaned up the chunking guidance — phase 1 of claude_session
already handles big docs automatically; no need to manually
split.
• legal-ceo.md (analyst issue template section)
- Replaced the generic "list of docs not to extract from" with a
per-doc_type action table that explicitly says
`appraisal → extract_appraiser_facts (NOT extract_claims)`.
- Added an explicit guard: "for every appraisal in the case,
verify the issue body says to run extract_appraiser_facts —
otherwise the writer gets a numbers-free block ז".
- Added the close-the-issue-with-PATCH instruction so the CEO
knows to write that into every analyst issue.
These edits don't affect the run currently in flight (the CEO's
prompt was already cached and the analyst already ran). They take
effect on the next analyst invocation.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Until now only legal-writer referenced the voice corpus. Without these
references the qa agent can't validate writer output, the researcher
chooses precedents outside Daphna's canon, and the analyst's claims
classification doesn't match block-zayin rules.
- legal-qa: adds 8th check "voice_compliance" — block ז structure,
block י voice (אכן/אולם, "אנחנו" verbs, no numbered lists), correct
precedent from canon, acceptance template match.
- legal-researcher: must check daphna-precedent-network.md before
proposing any precedent; cross-reference with Daphna's own past
decisions via search_decisions.
- legal-analyst: reads block-zayin-claims.md — its output is the
writer's input for block ז.
- legal-ceo: lists all 6 voice docs and which agent reads each.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three new voice docs based on deep reading of 1033-25 (full-acceptance) and
7 representative cases for block-zayin (claims summary):
- daphna-acceptance-architecture.md: 5 distinct templates for case acceptance
(A: internal flaw + voiding; B: remand to committee; C: corrections in
request; D: substantive 8xxx; E: appraiser remand). Fixes the wrong
reference in architecture-by-outcome that treated full-acceptance as a
variation of partial-acceptance.
- daphna-block-zayin-claims.md: rules for claims summary block — order by
procedural role, neutrality, sub-headings per party, anti-patterns
(numbered lists, evaluation words, premature conclusion).
- daphna-decision-tree.md: operational tool that unifies all 5 voice docs
into a short analytical process. Starts with the decisive question:
"what is the winning evidence?". Decision trees for architecture
selection, opening mode, citation choice, length by weight.
Updates legal-writer.md to read decision-tree first, then the 5 voice docs,
plus block-zayin.md before block ז.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
After reading all 23 1xxx decisions from style_corpus DB (in addition to
the 10 training files and 1130-25/1194-25 deep reads), synthesized two
new operational documents:
docs/daphna-precedent-network.md
- Maps each legal issue to the specific precedent Daphna cites
- 9 threshold issues (standing, השפר, סעיף 152, קנייני, פגמי פרסום,
פסילה, עבירות בנייה) with her preferred quotes for each
- 8 substantive issues (תכנון נקודתי vs כולל, חיקוק תכנית, סטייה ניכרת,
62א, חניה, תמ"א 38, תכניות ישנות, שימוש חורג)
- Lists ~30 external precedents she cites consistently + ~15 personal
precedents (her own canon — 1110/20 בעלז, 1112/22 שקופה, 1181/22 אדלר,
1130-25, etc.)
- Distinguishes precedents she cites vs. those she does NOT cite
docs/daphna-architecture-by-outcome.md
- 7 distinct block-yod architectures keyed to outcome type:
1. Pure rejection (short, 555-2000 words)
2. Rejection after complex analysis (2500-4500)
3. Threshold dismissal + merits "ועל מנת לא לצאת בחסר" (mode F)
4. Three or more distinct issues (sub-headings)
5. Partial acceptance (full funnel architecture)
6. Joined appeals
7. Remand follow-up
- Decision tree for the agent (4 questions → architecture choice)
- Internal proportions table (opening 5-10%, doctrine 15-25%, etc.)
- Costs matrix with 6 scenarios
Updated docs/daphna-voice-fingerprint.md with section 6 (additions from
23-file corpus read): 2 new opening modes (F: threshold+merits, G:
remand follow-up), nuanced sub-heading rule, self-citation of full
analytical blocks, 10 new "we" verbs, 11 traditional phrases with
sources, expanded costs matrix, transparency about petition outcomes,
warning that 1015-24 is dissent (not Daphna's voice).
Updated .claude/agents/legal-writer.md to require reading all 4 voice
docs before block-yod (the "voice quartet"), with explicit decision
tree integration.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
After analyzing all 24 building_permit decisions in style_corpus DB
(not just the 2 local files), refined two anti-patterns:
1. Sub-headings: actually permitted when block-yod handles 3+ distinct
legal issues (e.g., 1079-24 had "הבקשות לפסילה" / "מעמד המבקשת
וזכות עמידה" / "עותרים ציבוריים"). The earlier rule of "no
sub-headings except academic cases" was too strict — based only on
small local sample.
2. Paragraph numbering: discovered it's an evolutionary pattern, not
a static rule. Pre-2025 decisions had sequential paragraph numbers
(1, 2, 3 throughout); recent decisions (1126-25, 1128-25, 1130-25,
1194-25) abandoned it for narrative flow. The agent should NOT add
paragraph numbers — the new style.
The (1)...(2)...(3)... in-paragraph enumeration ban remains absolute —
0/33 final decisions used it. Distinction now made explicit:
in-paragraph enumeration ≠ paragraph-level numbering (former always
forbidden; latter is evolutionary).
Updated:
- docs/daphna-voice-fingerprint.md — corpus stats, refined anti-patterns
- .claude/agents/legal-writer.md — checklist with new distinctions
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Synthesized two voice documents from corpus reading:
- docs/voice-1130-25.md: deep read of case 1130-25 block-yod (5000 words),
extracting the 9-movement funnel architecture, 8 reasoning templates,
10 'we' verbs with their distinct functions, the 'akhen...ulam' pattern,
pacing/silence principles, and the deliberative meta-narrative.
- docs/daphna-voice-fingerprint.md: cross-corpus synthesis of 10 finals
(1 planning + 9 appraisal levy). Identifies 10 invariants, 5 opening
modes mapped to outcome certainty, mandatory ברמ 3644/13 preamble for
shamai cases, copy-paste templates, and 7 anti-patterns to avoid.
Updated .claude/agents/legal-writer.md:
- Added voice docs as MUST-READ before block-yod (was missing the deep
voice layer; only had surface style_guide patterns)
- Replaced the ' (1)...(2)...(3)...' enumeration template with the 5 opening
modes (the enumeration was a known anti-pattern Daphna always removes)
- Added the 'we' verbs catalog with explicit functions
- Made 'אכן...אולם' pattern mandatory for issues with substantial
counter-arguments (was vaguely 'אמנם...אולם')
- Added mandatory ברמ 3644/13 preamble for 8xxx shamai cases
- Added self-citation triple-mode (refer/defer/distinguish) — Daphna's
emerging practice of building personal jurisprudence
- Added 8-item anti-patterns checklist for post-write review
- Replaced block-yod-alef section with proper 4-paragraph closing
template (process narrative → outcome → costs → date)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Paperclip auto-blocks any in_progress issue without a live execution path
within ~1 minute of the run finishing. When the CEO ends a run with an
@chaim question pending, the main case issue was staying in_progress and
getting auto-blocked, flooding the case timeline with "automatically
retried continuation" system comments (7 occurrences on 2026-04-16).
Add an explicit status protocol to the CEO instructions:
- in_review at the end of any run that leaves a pending @chaim question
- in_progress when resuming from user_commented (also at start of comment routing)
- done only after final export
Applied at all three @chaim waiting points (stages B/C) and at the top
of comment routing.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Fixes critical bug in 1033-25: user-uploaded עריכה-*.docx files were
orphaned on disk while exports kept rebuilding from stale DB blocks.
New architecture:
- User-uploaded DOCX becomes the source of truth (cases.active_draft_path)
- System edits via XML surgery with real Word <w:ins>/<w:del> revisions
- User can Accept/Reject each change from within Word
Components:
- docx_reviser.py: XML surgery for Track Changes (15 tests)
- docx_retrofit.py: retroactive bookmark injection with Hebrew marker
detection + heading heuristic (9 tests)
- docx_exporter.py: emits bookmarks around each of the 12 blocks
- 3 new MCP tools: apply_user_edit, list_bookmarks, revise_draft
- 4 new/updated endpoints: upload (auto-registers active draft),
/exports/revise, /exports/bookmarks, /exports/{filename}/retrofit,
/active-draft
- DB migration: cases.active_draft_path column
- UI: correct banner using real v-numbers, "מקור האמת" badge,
detailed upload toast with bookmarks_added/missing_blocks
- agents: legal-exporter (3 export modes), legal-ceo (stage G for
revision handling), legal-writer (revision mode)
Multi-tenancy:
- Works for both CMP (1xxx cases) and CMPA (8xxx/9xxx cases)
- New revise-draft skill added to both companies
- deploy-track-changes.sh syncs skills CMP ↔ CMPA
- retrofit_case.py: one-off retrofit of existing files
Tests: 34 passing (15 reviser + 9 retrofit + 4 exporter bookmarks + 6 e2e)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- legal-analyst: opus 4.6 → opus 4.7
- legal-proofreader: opus 4.6 → opus 4.7
- legal-writer: sonnet 4.6 → opus 4.7 (complex block writing benefits from stronger model)
- block_writer MODEL_MAP: updated opus ID to 4.7
Opus 4.7 brings: high-res images (2576px), better file-based memory,
improved DOCX generation, and task budgets for agentic loops.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New issues created by the CEO via curl were missing plugin_state records,
causing them to be invisible in the legal-ai UI. Added iron rule: after every
POST to create an issue, INSERT into plugin_state with the case number.
Also fixed 8070-25 CMPA issues directly in DB (3 records added).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- CEO agent now sends email via notify.py when awaiting human response
- CEO creates child issues (parentId) instead of flat disconnected issues
- Fix notify.py email address to chaim+paperclip@marcus-law.co.il
- Move Paperclip UI assets (RTL CSS + Hebrew JS) into repo under scripts/
- Add deploy.sh script to push assets to live Paperclip instance
- Fix comment box positioning: newest comment on top, input below it
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The CEO was ignoring the focused wake reason and doing a full heartbeat
scan of all cases/issues before getting to the actual comment. Added
step 0: check $PAPERCLIP_WAKE_REASON first — if user_commented, skip
directly to comment handling. Don't scan other cases.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
CEO was missing get_chair_directions, record_chair_feedback,
list_chair_feedback, and search_case_documents. Without these tools
it couldn't read or update chair directions when processing draft
annotations.
Now the CEO will:
1. Read existing chair_directions via MCP tool
2. Record each draft annotation as chair_feedback
3. Update analysis-and-research.md
4. Post summary for user review before routing to writer
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When the user writes editing instructions inside a draft DOCX, the CEO
must not just forward them as a checklist. Instead:
1. Read analysis-and-research.md + existing chair_directions
2. Translate draft annotations into methodological structure (syllogism)
3. Update chair_directions with the new analysis
4. Post summary to user and WAIT for approval
5. Only after approval → create issue for writer
This gives the user a chance to verify the CEO understood correctly
before the writer starts working.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Even when the user asks to edit specific paragraphs in an existing
draft, the CEO must first analyze through the methodology: identify
which legal issue the edit serves, build syllogistic structure,
reference specific source documents, and state the review standard.
Without this, the writer gets a technical checklist instead of
methodological guidance.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Agent JWT cannot wake other agents directly (returns "Agent can only
invoke itself"). The correct pattern: create an issue + assign to the
target agent → Paperclip triggers wakeup automatically.
Also documented all correct API routes in HEARTBEAT.md:
- POST /api/issues/{id}/comments (not /issues/)
- POST /api/companies/{company-id}/issues (not /api/issues)
- PATCH /api/issues/{id}
- POST /api/agents/{id}/wakeup (self only, with payload.issueId)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The CEO was sending empty issues like "הועבר לכתיבה" without any
methodological content. The writer needs: syllogistic structure per
issue, source document references, claim handling table, chair
directions, style guidelines, and draft file path when available.
Added "תבנית issue לכותב ההחלטה" with all 5 required sections.
Updated comment routing to read drafts word-by-word and use the template.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The agents used /api/agents/{id}/wake (404) with a fallback of INSERT
INTO agent_wakeup_requests. The DB insert creates only the wakeup
record without a heartbeat_run, so the Paperclip dispatcher never
processes it — agents get stuck in queued forever.
Fix:
- All agents: /wake → /wakeup (correct Paperclip API endpoint)
- Remove all DB INSERT fallbacks, replace with warning
- Document the rule in CLAUDE.md: always API, never DB insert
- Save to memory for future conversations
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When a user comments on a Paperclip issue, the built-in automation wakes
the assigned agent directly, bypassing the CEO. This meant user instructions
(like "read the uploaded draft and route to the right agent") were ignored.
Changes:
- Plugin: add issue.comment.created event handler that wakes the CEO agent
with the comment context (plugin-legal-ai, separate repo)
- HEARTBEAT: add steps 2b (read recent user comments) and 2c (check
attachments) before agents start working
- CEO agent: add comment-routing section — read, check attachments, route
- Writer agent: add step 0 — check for uploaded DOCX drafts before writing
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Install git in Docker image and wrap all subprocess git calls in
try/except so a missing or failing git binary never kills an upload
that already succeeded.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
After Dafna fills her positions in the analysis document, the analyst
now runs a second pass to: verify cited case law against corpus and
case documents, deepen factual findings based on the chosen direction,
close open questions, and strengthen CREAC preparation.
Pipeline flow updated: direction_approved → analyst pass 2 →
analysis_enriched → CEO creates writer issue → ready_for_writing.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The status map was using informal descriptions ("מסמכים הוגהו")
instead of actual DB values. Now each row shows:
- The exact status string in cases.status
- Which agent sets it
- What the CEO should do next
New statuses added: proofread, analyst_verified, research_complete,
qa_passed, qa_failed, exported. Removed ambiguous conditions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Every agent now has explicit instructions in its own definition file,
not just in HEARTBEAT.md. An agent following only its own step-by-step
instructions will do the right thing on any new case.
All 6 non-CEO agents: explicit wakeup CEO block in completion step
(curl API + psql fallback, with agent name customized)
legal-ceo.md: issue template for analyst with 5 mandatory items
(document mapping table, no-extract list, split large docs,
wakeup CEO, blocked if failed)
legal-writer.md: explicit Read of decision-methodology.md as step 1
(before case_get, not just "read before starting")
legal-qa.md: methodology_compliance severity → critical
(was warning — decisions without syllogisms/steel-man now blocked)
legal-proofreader.md: added case_update tool + status='proofread'
(was missing entirely — CEO couldn't know proofreading was done)
legal-researcher.md: added case_update + mail notification
(was missing — CEO couldn't know research was done)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Documents >15K chars must be split by chapter/section and extracted
in parts. If extract_claims times out, retry with chunks or extract
manually. This prevents the Matmon document issue (108K chars, 4x timeout).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Test run on case 1130-25 revealed critical gaps. This commit fixes:
HEARTBEAT.md (#1, #11):
- Agents MUST wake CEO after completing any task (wakeup request)
- New "blocked" status option — agents cannot mark "done" if something failed
- Fallback: direct DB insert if API wake doesn't work
legal-analyst.md (#2):
- New step 6: completeness checks BEFORE finishing
- Verify all appeal/response documents extracted successfully
- Verify all extracted documents produced claims
- Verify classification is correct (no claims from committee)
- If any check fails → status = "blocked", not "done"
legal-ceo.md (#3, #6, #7, #12, #13, #14, #15):
- Step A rewritten with 3 sub-checks:
A1: extraction completeness (no missing documents)
A2: negative checks (wrong classification, abnormal counts, missing parties)
A3: methodology compliance (syllogisms, CREAC prep, steel-man, etc.)
- Any failure blocks progress to step B
legal-qa.md (#6 reinforcement):
- New step 2b: negative checks on the written decision
- Missing issues, bare quotes, empty formulas, mixed findings/conclusions
Also:
- Synced all agent files to /home/chaim/legal-ai/ (Paperclip reads from there)
- Synced methodology + lessons + corpus docs
- Fixed claim classification in DB: 20 committee/applicant claims → response (#5)
Remaining gaps (3):
- #4: Paperclip cache may need restart to pick up new definitions
- #7: Matmon document retry (25K words, 0 claims extracted)
- #9: 53 appellant claims may need synthesis (high but not blocking)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
"בית ספר להחלטות" Phase 2 — the system now has formal analytical
methodology for building quasi-judicial decisions, separate from
Dafna's writing style (SKILL.md) and content checklists.
What was done:
- Downloaded 5 authoritative sources (~341K words): FJC Judicial
Writing Manual (1991+2020), Garner Legal Writing in Plain English,
Posner How Judges Think, Scalia/Garner Making Your Case
- Extracted principles from all sources into intermediate docs
- Synthesized into docs/decision-methodology.md (3,400 words,
12 sections, 10 guiding principles)
- Integrated methodology into block-yod prompt via {methodology_guidance}
- Restructured legal-writer agent workflow to follow analytical stages
- Made "answer all claims" flexible (bundle/skip via chair_directions)
- Added methodology compliance check (#7) to legal-qa agent
- Updated all knowledge files (CLAUDE.md, SKILL.md, lessons, corpus)
Three-layer architecture:
1. Methodology (decision-methodology.md) — universal, how to think
2. Content checklists (lessons.py) — specific per appeal subtype
3. Style (SKILL.md) — Dafna's personal writing patterns
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Closes the loop so דפנה's positions (written inline in the UI and
saved to analysis-and-research.md) automatically become binding
direction for the legal-writer agent — no manual copy-paste,
no bypass.
Backend:
- research_md.extract_chair_directions(path) returns a compact dict
with status (missing/empty/partial/complete), filled_count,
empty_count, and a reduced list of threshold_claims + issues each
with {id, number, title, direction}. Designed to be directly usable
as direction_doc by the writer.
- New MCP tool: drafting.get_chair_directions(case_number) wraps the
helper, resolves the case research file path via config.find_case_dir,
returns formatted JSON.
- Registered in server.py as mcp__legal-ai__get_chair_directions.
legal-writer agent update:
- Adds get_chair_directions to the tools list.
- New mandatory "שלב 1ב" before any block writing: call
get_chair_directions, branch on status.
- missing → halt, report "legal-analyst לא רץ עדיין"
- empty → halt, instruct Dafna to fill positions via the UI URL
- partial → halt unless user confirms; write only filled sections
- complete → proceed
- New "שלב 1ג" constructs an internal direction_doc from the
received chair rulings before writing block י.
- Block י section expanded with 5 binding rules:
1. Open each discussion with Dafna's ruling as the thesis
2. Frame the reasoning in her style (use get_style_guide phrases)
3. Match her tone (decisive vs nuanced)
4. Must NOT contradict her position — if she disagreed with your
own inclination, her position rules
5. Use legal_questions from the analysis file as the analytical
structure (principle question first, concrete application second)
- New bullet section for block יא: summarize each chair ruling
briefly, state final outcome, close with the signed date formula.
Verified all four status paths (missing/empty/partial/complete) via
local test. Now Dafna's workflow is fully end-to-end: she reads the
analyst report in the UI, fills "עמדת ועדת הערר" in each card, hits
blur to auto-save, then triggers legal-writer — which picks up her
positions as direction without any file shuffle.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add "עמדת ועדת הערר" placeholder to legal-analyst agent template
for each legal issue, to be filled by the chair as guidance for the
writing agent
- Fix green checkmark not showing for proofread documents (treat
'proofread' status same as 'completed')
- Show time alongside date in local files listing
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add delete_document_chunks for reprocessing, save extracted text to disk
- Expand case directory structure (original/extracted/proofread/backup)
- Update classifier patterns (תגובה, הודעת עמדה)
- Fix proofreader agent paths for new directory layout
- Update HEARTBEAT to notify on every task completion
- Improve bidi_table with LRE/PDF directional embedding
- Add Paperclip project verification and auto-close setup issue
- Add auto-sync-cases.sh for Gitea synchronization
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Remove cases/new|in-progress|completed subdivision (status managed in DB)
- Rename documents/original → documents/originals (consistent plural)
- Move exports from global data/exports/ into cases/{num}/exports/
- Add documents/research/ for case law and analysis files
- Update all agents, scripts, config, web API endpoints, and DB paths
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New: scripts/notify.py — sends via SMTP (notify@marcus-law.co.il → paperclip+chaim@marcus-law.co.il)
Updated: HEARTBEAT.md — agents must send email when waiting for human decision
Triggers: outcome choice, direction approval, QA failures, review ready.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
All agent output — comments, status, errors, summaries, thinking — must be in Hebrew.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Two issues that caused QA agent to fail:
1. save_block_content saved to DB only — now also rebuilds drafts/decision.md
2. legal-writer.md now has explicit mandatory step: case_update(status="drafted")
Without these, workflow_status reports has_draft=false and QA can't run.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
brainstorm_directions tool uses claude -p subprocess which times out
when called from inside a claude session (agent). CEO should think
about directions directly — it already has all the context.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
CEO now follows a step-by-step interactive flow:
A. Check status and what's been done
B. Summarize case + ask Chaim for outcome (1/2/3)
C. Read response, run brainstorm, present directions
D. Read direction choice, approve, launch writer agent
E. Monitor writing progress
F. QA and export
All interaction happens through Paperclip comments.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Manages the decision writing pipeline:
- Creates issues and assigns to specialist agents
- Tracks status across all active cases
- Reports to human (Chaim) when approvals needed
- Never writes or analyzes directly — delegates
All 4 specialist agents now report to CEO.
Hierarchy: עוזר משפטי → מנתח/חוקר/כותב/בודק
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
