release api/v1.1.0

Co-Authored-By: Claude <noreply@anthropic.com>
fix(webber-api): clear mypy, and the dead code it was covering for
2026-08-11 16:30:09 +02:00 · 2026-08-11 16:27:51 +02:00 · 2026-08-11 15:05:02 +02:00 · 2026-08-09 18:57:22 +02:00 · 2026-08-09 15:56:20 +02:00 · 2026-08-09 15:10:32 +02:00
77 changed files with 1565 additions and 653 deletions
@@ -0,0 +1,67 @@
 {
  "env": {
    "PQL_VAULT": "/mnt/media/Projects/webber"
  },
  "permissions": {
    "allow": [
      "Bash(pql)",
      "Bash(pql *)",
      "Bash(/home/jpmschweitzer/.local/bin/pql:*)",
      "Bash(git status:*)",
      "Bash(git log:*)",
      "Bash(git diff:*)",
      "Bash(git branch:*)",
      "Bash(.venv/bin/python -m pytest:*)",
      "Bash(.venv/bin/pytest:*)",
      "Bash(pytest:*)",
      "Bash(ruff *)",
      "Bash(mypy *)",
      "Bash(docker logs webber:*)",
      "Bash(curl -s http://localhost:8086/*)",
      "Bash(curl -s http://localhost:8095/*)"
    ],
    "deny": [
      "Bash(/mnt/media/Projects/cladmin/ops/bin/toj)",
      "Bash(/mnt/media/Projects/cladmin/ops/bin/toj:*)",
      "Bash(chmod -R 777 *)",
      "Bash(chmod 777 *)",
      "Bash(dd if=*)",
      "Bash(find * -delete*)",
      "Bash(find * -exec*)",
      "Bash(git * add --all*)",
      "Bash(git * add -A*)",
      "Bash(git * add .)",
      "Bash(git * branch -D *)",
      "Bash(git * checkout -- *)",
      "Bash(git * clean -fd*)",
      "Bash(git * clean -fdx*)",
      "Bash(git * commit --no-verify*)",
      "Bash(git * merge --no-ff*)",
      "Bash(git * push --force*)",
      "Bash(git * push -f*)",
      "Bash(git * reset --hard*)",
      "Bash(git * restore .*)",
      "Bash(git add --all*)",
      "Bash(git add -A*)",
      "Bash(git add .)",
      "Bash(git branch -D *)",
      "Bash(git checkout -- *)",
      "Bash(git clean -fd*)",
      "Bash(git clean -fdx*)",
      "Bash(git commit --no-verify*)",
      "Bash(git merge --no-ff*)",
      "Bash(git push --force*)",
      "Bash(git push -f*)",
      "Bash(git reset --hard*)",
      "Bash(git restore .*)",
      "Bash(mkfs*)",
      "Bash(rm -rf $HOME*)",
      "Bash(rm -rf /*)",
      "Bash(rm -rf ~*)",
      "Bash(su *)",
      "Bash(sudo *)",
      "Bash(toj)",
      "Bash(toj:*)"
    ]
  }
 }
@@ -0,0 +1 @@
 .pql/changelog/*.sql merge=union
@@ -0,0 +1,13 @@
 #!/usr/bin/env bash
 # Trigger only. The checks live in the Makefile, where they can be read, run by
 # hand (`make pre-push`), and changed under review.
 #
 # This file is identical in every repo in this workspace, deliberately: the call
 # surface is the same everywhere even though what each gate runs is not, so
 # nobody has to read a repo to find out how to check it (D-27).
 #
 # Enable per clone with:  git config core.hooksPath .githooks
 # Never bypass with --no-verify. Suppress a specific finding deliberately
 # instead, with a reason — see `make pre-push`.
 set -euo pipefail
 exec make -C "$(git rev-parse --show-toplevel)" pre-push
@@ -75,3 +75,16 @@ webber-sandbox/.current_template
 # Ruff cache
 .ruff_cache/
 # Claude Code user-specific settings
 .claude/settings.local.json
 .pql/*
 !.pql/changelog/
 # pql shims planted by `pql init` into the dir core.hooksPath points at.
 # Per-clone: each embeds the absolute path of the pql binary that planted it.
 # Only .githooks/pre-push is shared.
 .githooks/pre-commit
 .githooks/post-merge
 .githooks/post-checkout
 .githooks/post-rewrite
@@ -0,0 +1,11 @@
 -- Changelog format marker, written by pql. Comments only: this file
 -- is never executed — Import descends into the per-table directories
 -- and does not read the changelog root.
 --
 -- A changelog carrying no marker is format 1, the shape that existed
 -- before formats were versioned. An older format is migrated forward
 -- by `pql plan upgrade` (and automatically from the post-merge hook);
 -- a newer one is refused rather than replayed under rules this binary
 -- does not know. See D-28 and docs/versions.md.
 -- pql:changelog_format: 2.0.0
 -- pql:written_by: 2.2.0
@@ -0,0 +1,139 @@
 -- Auto-generated by pql init. CREATE TABLE statements
 -- for the planning schema; per-table dir keeps the changelog
 -- self-describing per D-15. CREATE TABLE IF NOT EXISTS is
 -- idempotent so running schema files from each directory in
 -- replay order is harmless.
 --
 -- Importer parses the markers below to detect schema drift
 -- between the producing pql version and the local one — a
 -- bumped canonical_version means projection rules changed
 -- and replay must refuse rather than silently corrupt state.
 -- pql:created_by: 2.2.0
 -- pql:canonical_version: 2
 CREATE TABLE IF NOT EXISTS decisions (
    id                TEXT PRIMARY KEY,
    type              TEXT NOT NULL CHECK(type IN ('confirmed','question','rejected')),
    domain            TEXT NOT NULL,
    title             TEXT NOT NULL,
    status            TEXT NOT NULL DEFAULT 'active'
                          CHECK(status IN ('active','superseded','resolved','open')),
    date              TEXT,
    file_path         TEXT NOT NULL,
    synced_at         TEXT NOT NULL DEFAULT (datetime('now')),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS decision_refs (
    source_id         TEXT NOT NULL REFERENCES decisions(id) ON DELETE CASCADE,
    target_id         TEXT NOT NULL REFERENCES decisions(id) ON DELETE CASCADE,
    ref_type          TEXT NOT NULL
                          CHECK(ref_type IN ('supersedes','references','resolves','depends_on','amends')),
    note              TEXT,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (source_id, target_id, ref_type)
 );
 -- Identity split (D-26): a ticket's stable, collision-proof identity is its
 -- record_id (a locally-generated ULID, planning.NewRecordID); the friendly
 -- T-NNN label lives in ticket_idmap and may be reconciled. Every structural
 -- reference (parent, deps, history, labels) targets record_id, so a label
 -- clash never corrupts the graph — only ticket_idmap needs a relabel.
 CREATE TABLE IF NOT EXISTS tickets (
    record_id         TEXT PRIMARY KEY,
    type              TEXT NOT NULL CHECK(type IN ('initiative','epic','story','task','bug')),
    parent_record_id  TEXT REFERENCES tickets(record_id),
    title             TEXT NOT NULL,
    description       TEXT,
    -- No CHECK enumeration: the ticket status vocabulary is per-vault
    -- configurable (ticket_statuses in .pql/config.yaml). Validation lives
    -- in Go (planning.StatusSet), so adding/renaming statuses needs no
    -- schema change. The DEFAULT is a harmless fallback — CreateTicket
    -- always inserts the configured default explicitly.
    status            TEXT NOT NULL DEFAULT 'backlog',
    priority          TEXT DEFAULT 'medium'
                          CHECK(priority IN ('critical','high','medium','low')),
    assigned_to       TEXT,
    team              TEXT,
    decision_ref      TEXT REFERENCES decisions(id),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 -- ticket_idmap maps a record_id to its current friendly label (T-NNN).
 -- ticket_id is intentionally NOT globally unique: two uncoordinated clones
 -- can mint the same label, which surfaces as a duplicate-label collision
 -- (detected at replay) and is fixed with "pql ticket relabel".
 CREATE TABLE IF NOT EXISTS ticket_idmap (
    record_id         TEXT PRIMARY KEY REFERENCES tickets(record_id),
    ticket_id         TEXT NOT NULL,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS ticket_deps (
    blocker_record_id TEXT NOT NULL REFERENCES tickets(record_id),
    blocked_record_id TEXT NOT NULL REFERENCES tickets(record_id),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (blocker_record_id, blocked_record_id)
 );
 CREATE TABLE IF NOT EXISTS ticket_history (
    ticket_record_id  TEXT NOT NULL REFERENCES tickets(record_id),
    field             TEXT NOT NULL,
    old_value         TEXT,
    new_value         TEXT,
    changed_by        TEXT,
    changed_at        TEXT NOT NULL DEFAULT (datetime('now')),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT UNIQUE,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS ticket_labels (
    ticket_record_id  TEXT NOT NULL REFERENCES tickets(record_id),
    label             TEXT NOT NULL,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (ticket_record_id, label)
 );
 CREATE TABLE IF NOT EXISTS meta (
    key        TEXT PRIMARY KEY,
    value      TEXT NOT NULL,
    updated_at TEXT NOT NULL DEFAULT (datetime('now'))
 );
 CREATE INDEX IF NOT EXISTS idx_tickets_status        ON tickets(status);
 CREATE INDEX IF NOT EXISTS idx_tickets_team          ON tickets(team);
 CREATE INDEX IF NOT EXISTS idx_tickets_decision_ref  ON tickets(decision_ref);
 CREATE INDEX IF NOT EXISTS idx_tickets_assigned      ON tickets(assigned_to);
 CREATE INDEX IF NOT EXISTS idx_tickets_parent        ON tickets(parent_record_id);
 CREATE INDEX IF NOT EXISTS idx_ticket_idmap_label    ON ticket_idmap(ticket_id);
 CREATE INDEX IF NOT EXISTS idx_decisions_domain      ON decisions(domain);
 CREATE INDEX IF NOT EXISTS idx_decisions_type        ON decisions(type);
 CREATE INDEX IF NOT EXISTS idx_decision_refs_target  ON decision_refs(target_id);
@@ -0,0 +1,139 @@
 -- Auto-generated by pql init. CREATE TABLE statements
 -- for the planning schema; per-table dir keeps the changelog
 -- self-describing per D-15. CREATE TABLE IF NOT EXISTS is
 -- idempotent so running schema files from each directory in
 -- replay order is harmless.
 --
 -- Importer parses the markers below to detect schema drift
 -- between the producing pql version and the local one — a
 -- bumped canonical_version means projection rules changed
 -- and replay must refuse rather than silently corrupt state.
 -- pql:created_by: 2.2.0
 -- pql:canonical_version: 2
 CREATE TABLE IF NOT EXISTS decisions (
    id                TEXT PRIMARY KEY,
    type              TEXT NOT NULL CHECK(type IN ('confirmed','question','rejected')),
    domain            TEXT NOT NULL,
    title             TEXT NOT NULL,
    status            TEXT NOT NULL DEFAULT 'active'
                          CHECK(status IN ('active','superseded','resolved','open')),
    date              TEXT,
    file_path         TEXT NOT NULL,
    synced_at         TEXT NOT NULL DEFAULT (datetime('now')),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS decision_refs (
    source_id         TEXT NOT NULL REFERENCES decisions(id) ON DELETE CASCADE,
    target_id         TEXT NOT NULL REFERENCES decisions(id) ON DELETE CASCADE,
    ref_type          TEXT NOT NULL
                          CHECK(ref_type IN ('supersedes','references','resolves','depends_on','amends')),
    note              TEXT,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (source_id, target_id, ref_type)
 );
 -- Identity split (D-26): a ticket's stable, collision-proof identity is its
 -- record_id (a locally-generated ULID, planning.NewRecordID); the friendly
 -- T-NNN label lives in ticket_idmap and may be reconciled. Every structural
 -- reference (parent, deps, history, labels) targets record_id, so a label
 -- clash never corrupts the graph — only ticket_idmap needs a relabel.
 CREATE TABLE IF NOT EXISTS tickets (
    record_id         TEXT PRIMARY KEY,
    type              TEXT NOT NULL CHECK(type IN ('initiative','epic','story','task','bug')),
    parent_record_id  TEXT REFERENCES tickets(record_id),
    title             TEXT NOT NULL,
    description       TEXT,
    -- No CHECK enumeration: the ticket status vocabulary is per-vault
    -- configurable (ticket_statuses in .pql/config.yaml). Validation lives
    -- in Go (planning.StatusSet), so adding/renaming statuses needs no
    -- schema change. The DEFAULT is a harmless fallback — CreateTicket
    -- always inserts the configured default explicitly.
    status            TEXT NOT NULL DEFAULT 'backlog',
    priority          TEXT DEFAULT 'medium'
                          CHECK(priority IN ('critical','high','medium','low')),
    assigned_to       TEXT,
    team              TEXT,
    decision_ref      TEXT REFERENCES decisions(id),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 -- ticket_idmap maps a record_id to its current friendly label (T-NNN).
 -- ticket_id is intentionally NOT globally unique: two uncoordinated clones
 -- can mint the same label, which surfaces as a duplicate-label collision
 -- (detected at replay) and is fixed with "pql ticket relabel".
 CREATE TABLE IF NOT EXISTS ticket_idmap (
    record_id         TEXT PRIMARY KEY REFERENCES tickets(record_id),
    ticket_id         TEXT NOT NULL,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS ticket_deps (
    blocker_record_id TEXT NOT NULL REFERENCES tickets(record_id),
    blocked_record_id TEXT NOT NULL REFERENCES tickets(record_id),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (blocker_record_id, blocked_record_id)
 );
 CREATE TABLE IF NOT EXISTS ticket_history (
    ticket_record_id  TEXT NOT NULL REFERENCES tickets(record_id),
    field             TEXT NOT NULL,
    old_value         TEXT,
    new_value         TEXT,
    changed_by        TEXT,
    changed_at        TEXT NOT NULL DEFAULT (datetime('now')),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT UNIQUE,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS ticket_labels (
    ticket_record_id  TEXT NOT NULL REFERENCES tickets(record_id),
    label             TEXT NOT NULL,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (ticket_record_id, label)
 );
 CREATE TABLE IF NOT EXISTS meta (
    key        TEXT PRIMARY KEY,
    value      TEXT NOT NULL,
    updated_at TEXT NOT NULL DEFAULT (datetime('now'))
 );
 CREATE INDEX IF NOT EXISTS idx_tickets_status        ON tickets(status);
 CREATE INDEX IF NOT EXISTS idx_tickets_team          ON tickets(team);
 CREATE INDEX IF NOT EXISTS idx_tickets_decision_ref  ON tickets(decision_ref);
 CREATE INDEX IF NOT EXISTS idx_tickets_assigned      ON tickets(assigned_to);
 CREATE INDEX IF NOT EXISTS idx_tickets_parent        ON tickets(parent_record_id);
 CREATE INDEX IF NOT EXISTS idx_ticket_idmap_label    ON ticket_idmap(ticket_id);
 CREATE INDEX IF NOT EXISTS idx_decisions_domain      ON decisions(domain);
 CREATE INDEX IF NOT EXISTS idx_decisions_type        ON decisions(type);
 CREATE INDEX IF NOT EXISTS idx_decision_refs_target  ON decision_refs(target_id);
@@ -0,0 +1,139 @@
 -- Auto-generated by pql init. CREATE TABLE statements
 -- for the planning schema; per-table dir keeps the changelog
 -- self-describing per D-15. CREATE TABLE IF NOT EXISTS is
 -- idempotent so running schema files from each directory in
 -- replay order is harmless.
 --
 -- Importer parses the markers below to detect schema drift
 -- between the producing pql version and the local one — a
 -- bumped canonical_version means projection rules changed
 -- and replay must refuse rather than silently corrupt state.
 -- pql:created_by: 2.2.0
 -- pql:canonical_version: 2
 CREATE TABLE IF NOT EXISTS decisions (
    id                TEXT PRIMARY KEY,
    type              TEXT NOT NULL CHECK(type IN ('confirmed','question','rejected')),
    domain            TEXT NOT NULL,
    title             TEXT NOT NULL,
    status            TEXT NOT NULL DEFAULT 'active'
                          CHECK(status IN ('active','superseded','resolved','open')),
    date              TEXT,
    file_path         TEXT NOT NULL,
    synced_at         TEXT NOT NULL DEFAULT (datetime('now')),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS decision_refs (
    source_id         TEXT NOT NULL REFERENCES decisions(id) ON DELETE CASCADE,
    target_id         TEXT NOT NULL REFERENCES decisions(id) ON DELETE CASCADE,
    ref_type          TEXT NOT NULL
                          CHECK(ref_type IN ('supersedes','references','resolves','depends_on','amends')),
    note              TEXT,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (source_id, target_id, ref_type)
 );
 -- Identity split (D-26): a ticket's stable, collision-proof identity is its
 -- record_id (a locally-generated ULID, planning.NewRecordID); the friendly
 -- T-NNN label lives in ticket_idmap and may be reconciled. Every structural
 -- reference (parent, deps, history, labels) targets record_id, so a label
 -- clash never corrupts the graph — only ticket_idmap needs a relabel.
 CREATE TABLE IF NOT EXISTS tickets (
    record_id         TEXT PRIMARY KEY,
    type              TEXT NOT NULL CHECK(type IN ('initiative','epic','story','task','bug')),
    parent_record_id  TEXT REFERENCES tickets(record_id),
    title             TEXT NOT NULL,
    description       TEXT,
    -- No CHECK enumeration: the ticket status vocabulary is per-vault
    -- configurable (ticket_statuses in .pql/config.yaml). Validation lives
    -- in Go (planning.StatusSet), so adding/renaming statuses needs no
    -- schema change. The DEFAULT is a harmless fallback — CreateTicket
    -- always inserts the configured default explicitly.
    status            TEXT NOT NULL DEFAULT 'backlog',
    priority          TEXT DEFAULT 'medium'
                          CHECK(priority IN ('critical','high','medium','low')),
    assigned_to       TEXT,
    team              TEXT,
    decision_ref      TEXT REFERENCES decisions(id),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 -- ticket_idmap maps a record_id to its current friendly label (T-NNN).
 -- ticket_id is intentionally NOT globally unique: two uncoordinated clones
 -- can mint the same label, which surfaces as a duplicate-label collision
 -- (detected at replay) and is fixed with "pql ticket relabel".
 CREATE TABLE IF NOT EXISTS ticket_idmap (
    record_id         TEXT PRIMARY KEY REFERENCES tickets(record_id),
    ticket_id         TEXT NOT NULL,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS ticket_deps (
    blocker_record_id TEXT NOT NULL REFERENCES tickets(record_id),
    blocked_record_id TEXT NOT NULL REFERENCES tickets(record_id),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (blocker_record_id, blocked_record_id)
 );
 CREATE TABLE IF NOT EXISTS ticket_history (
    ticket_record_id  TEXT NOT NULL REFERENCES tickets(record_id),
    field             TEXT NOT NULL,
    old_value         TEXT,
    new_value         TEXT,
    changed_by        TEXT,
    changed_at        TEXT NOT NULL DEFAULT (datetime('now')),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT UNIQUE,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS ticket_labels (
    ticket_record_id  TEXT NOT NULL REFERENCES tickets(record_id),
    label             TEXT NOT NULL,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (ticket_record_id, label)
 );
 CREATE TABLE IF NOT EXISTS meta (
    key        TEXT PRIMARY KEY,
    value      TEXT NOT NULL,
    updated_at TEXT NOT NULL DEFAULT (datetime('now'))
 );
 CREATE INDEX IF NOT EXISTS idx_tickets_status        ON tickets(status);
 CREATE INDEX IF NOT EXISTS idx_tickets_team          ON tickets(team);
 CREATE INDEX IF NOT EXISTS idx_tickets_decision_ref  ON tickets(decision_ref);
 CREATE INDEX IF NOT EXISTS idx_tickets_assigned      ON tickets(assigned_to);
 CREATE INDEX IF NOT EXISTS idx_tickets_parent        ON tickets(parent_record_id);
 CREATE INDEX IF NOT EXISTS idx_ticket_idmap_label    ON ticket_idmap(ticket_id);
 CREATE INDEX IF NOT EXISTS idx_decisions_domain      ON decisions(domain);
 CREATE INDEX IF NOT EXISTS idx_decisions_type        ON decisions(type);
 CREATE INDEX IF NOT EXISTS idx_decision_refs_target  ON decision_refs(target_id);
@@ -0,0 +1,139 @@
 -- Auto-generated by pql init. CREATE TABLE statements
 -- for the planning schema; per-table dir keeps the changelog
 -- self-describing per D-15. CREATE TABLE IF NOT EXISTS is
 -- idempotent so running schema files from each directory in
 -- replay order is harmless.
 --
 -- Importer parses the markers below to detect schema drift
 -- between the producing pql version and the local one — a
 -- bumped canonical_version means projection rules changed
 -- and replay must refuse rather than silently corrupt state.
 -- pql:created_by: 2.2.0
 -- pql:canonical_version: 2
 CREATE TABLE IF NOT EXISTS decisions (
    id                TEXT PRIMARY KEY,
    type              TEXT NOT NULL CHECK(type IN ('confirmed','question','rejected')),
    domain            TEXT NOT NULL,
    title             TEXT NOT NULL,
    status            TEXT NOT NULL DEFAULT 'active'
                          CHECK(status IN ('active','superseded','resolved','open')),
    date              TEXT,
    file_path         TEXT NOT NULL,
    synced_at         TEXT NOT NULL DEFAULT (datetime('now')),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS decision_refs (
    source_id         TEXT NOT NULL REFERENCES decisions(id) ON DELETE CASCADE,
    target_id         TEXT NOT NULL REFERENCES decisions(id) ON DELETE CASCADE,
    ref_type          TEXT NOT NULL
                          CHECK(ref_type IN ('supersedes','references','resolves','depends_on','amends')),
    note              TEXT,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (source_id, target_id, ref_type)
 );
 -- Identity split (D-26): a ticket's stable, collision-proof identity is its
 -- record_id (a locally-generated ULID, planning.NewRecordID); the friendly
 -- T-NNN label lives in ticket_idmap and may be reconciled. Every structural
 -- reference (parent, deps, history, labels) targets record_id, so a label
 -- clash never corrupts the graph — only ticket_idmap needs a relabel.
 CREATE TABLE IF NOT EXISTS tickets (
    record_id         TEXT PRIMARY KEY,
    type              TEXT NOT NULL CHECK(type IN ('initiative','epic','story','task','bug')),
    parent_record_id  TEXT REFERENCES tickets(record_id),
    title             TEXT NOT NULL,
    description       TEXT,
    -- No CHECK enumeration: the ticket status vocabulary is per-vault
    -- configurable (ticket_statuses in .pql/config.yaml). Validation lives
    -- in Go (planning.StatusSet), so adding/renaming statuses needs no
    -- schema change. The DEFAULT is a harmless fallback — CreateTicket
    -- always inserts the configured default explicitly.
    status            TEXT NOT NULL DEFAULT 'backlog',
    priority          TEXT DEFAULT 'medium'
                          CHECK(priority IN ('critical','high','medium','low')),
    assigned_to       TEXT,
    team              TEXT,
    decision_ref      TEXT REFERENCES decisions(id),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 -- ticket_idmap maps a record_id to its current friendly label (T-NNN).
 -- ticket_id is intentionally NOT globally unique: two uncoordinated clones
 -- can mint the same label, which surfaces as a duplicate-label collision
 -- (detected at replay) and is fixed with "pql ticket relabel".
 CREATE TABLE IF NOT EXISTS ticket_idmap (
    record_id         TEXT PRIMARY KEY REFERENCES tickets(record_id),
    ticket_id         TEXT NOT NULL,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS ticket_deps (
    blocker_record_id TEXT NOT NULL REFERENCES tickets(record_id),
    blocked_record_id TEXT NOT NULL REFERENCES tickets(record_id),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (blocker_record_id, blocked_record_id)
 );
 CREATE TABLE IF NOT EXISTS ticket_history (
    ticket_record_id  TEXT NOT NULL REFERENCES tickets(record_id),
    field             TEXT NOT NULL,
    old_value         TEXT,
    new_value         TEXT,
    changed_by        TEXT,
    changed_at        TEXT NOT NULL DEFAULT (datetime('now')),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT UNIQUE,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS ticket_labels (
    ticket_record_id  TEXT NOT NULL REFERENCES tickets(record_id),
    label             TEXT NOT NULL,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (ticket_record_id, label)
 );
 CREATE TABLE IF NOT EXISTS meta (
    key        TEXT PRIMARY KEY,
    value      TEXT NOT NULL,
    updated_at TEXT NOT NULL DEFAULT (datetime('now'))
 );
 CREATE INDEX IF NOT EXISTS idx_tickets_status        ON tickets(status);
 CREATE INDEX IF NOT EXISTS idx_tickets_team          ON tickets(team);
 CREATE INDEX IF NOT EXISTS idx_tickets_decision_ref  ON tickets(decision_ref);
 CREATE INDEX IF NOT EXISTS idx_tickets_assigned      ON tickets(assigned_to);
 CREATE INDEX IF NOT EXISTS idx_tickets_parent        ON tickets(parent_record_id);
 CREATE INDEX IF NOT EXISTS idx_ticket_idmap_label    ON ticket_idmap(ticket_id);
 CREATE INDEX IF NOT EXISTS idx_decisions_domain      ON decisions(domain);
 CREATE INDEX IF NOT EXISTS idx_decisions_type        ON decisions(type);
 CREATE INDEX IF NOT EXISTS idx_decision_refs_target  ON decision_refs(target_id);
@@ -0,0 +1,139 @@
 -- Auto-generated by pql init. CREATE TABLE statements
 -- for the planning schema; per-table dir keeps the changelog
 -- self-describing per D-15. CREATE TABLE IF NOT EXISTS is
 -- idempotent so running schema files from each directory in
 -- replay order is harmless.
 --
 -- Importer parses the markers below to detect schema drift
 -- between the producing pql version and the local one — a
 -- bumped canonical_version means projection rules changed
 -- and replay must refuse rather than silently corrupt state.
 -- pql:created_by: 2.2.0
 -- pql:canonical_version: 2
 CREATE TABLE IF NOT EXISTS decisions (
    id                TEXT PRIMARY KEY,
    type              TEXT NOT NULL CHECK(type IN ('confirmed','question','rejected')),
    domain            TEXT NOT NULL,
    title             TEXT NOT NULL,
    status            TEXT NOT NULL DEFAULT 'active'
                          CHECK(status IN ('active','superseded','resolved','open')),
    date              TEXT,
    file_path         TEXT NOT NULL,
    synced_at         TEXT NOT NULL DEFAULT (datetime('now')),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS decision_refs (
    source_id         TEXT NOT NULL REFERENCES decisions(id) ON DELETE CASCADE,
    target_id         TEXT NOT NULL REFERENCES decisions(id) ON DELETE CASCADE,
    ref_type          TEXT NOT NULL
                          CHECK(ref_type IN ('supersedes','references','resolves','depends_on','amends')),
    note              TEXT,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (source_id, target_id, ref_type)
 );
 -- Identity split (D-26): a ticket's stable, collision-proof identity is its
 -- record_id (a locally-generated ULID, planning.NewRecordID); the friendly
 -- T-NNN label lives in ticket_idmap and may be reconciled. Every structural
 -- reference (parent, deps, history, labels) targets record_id, so a label
 -- clash never corrupts the graph — only ticket_idmap needs a relabel.
 CREATE TABLE IF NOT EXISTS tickets (
    record_id         TEXT PRIMARY KEY,
    type              TEXT NOT NULL CHECK(type IN ('initiative','epic','story','task','bug')),
    parent_record_id  TEXT REFERENCES tickets(record_id),
    title             TEXT NOT NULL,
    description       TEXT,
    -- No CHECK enumeration: the ticket status vocabulary is per-vault
    -- configurable (ticket_statuses in .pql/config.yaml). Validation lives
    -- in Go (planning.StatusSet), so adding/renaming statuses needs no
    -- schema change. The DEFAULT is a harmless fallback — CreateTicket
    -- always inserts the configured default explicitly.
    status            TEXT NOT NULL DEFAULT 'backlog',
    priority          TEXT DEFAULT 'medium'
                          CHECK(priority IN ('critical','high','medium','low')),
    assigned_to       TEXT,
    team              TEXT,
    decision_ref      TEXT REFERENCES decisions(id),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 -- ticket_idmap maps a record_id to its current friendly label (T-NNN).
 -- ticket_id is intentionally NOT globally unique: two uncoordinated clones
 -- can mint the same label, which surfaces as a duplicate-label collision
 -- (detected at replay) and is fixed with "pql ticket relabel".
 CREATE TABLE IF NOT EXISTS ticket_idmap (
    record_id         TEXT PRIMARY KEY REFERENCES tickets(record_id),
    ticket_id         TEXT NOT NULL,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS ticket_deps (
    blocker_record_id TEXT NOT NULL REFERENCES tickets(record_id),
    blocked_record_id TEXT NOT NULL REFERENCES tickets(record_id),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (blocker_record_id, blocked_record_id)
 );
 CREATE TABLE IF NOT EXISTS ticket_history (
    ticket_record_id  TEXT NOT NULL REFERENCES tickets(record_id),
    field             TEXT NOT NULL,
    old_value         TEXT,
    new_value         TEXT,
    changed_by        TEXT,
    changed_at        TEXT NOT NULL DEFAULT (datetime('now')),
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT UNIQUE,
    canonical_version INTEGER
 );
 CREATE TABLE IF NOT EXISTS ticket_labels (
    ticket_record_id  TEXT NOT NULL REFERENCES tickets(record_id),
    label             TEXT NOT NULL,
    created_at        TEXT NOT NULL DEFAULT (datetime('now')),
    updated_at        TEXT NOT NULL DEFAULT (datetime('now')),
    deleted_at        TEXT,
    hash              TEXT,
    canonical_version INTEGER,
    PRIMARY KEY (ticket_record_id, label)
 );
 CREATE TABLE IF NOT EXISTS meta (
    key        TEXT PRIMARY KEY,
    value      TEXT NOT NULL,
    updated_at TEXT NOT NULL DEFAULT (datetime('now'))
 );
 CREATE INDEX IF NOT EXISTS idx_tickets_status        ON tickets(status);
 CREATE INDEX IF NOT EXISTS idx_tickets_team          ON tickets(team);
 CREATE INDEX IF NOT EXISTS idx_tickets_decision_ref  ON tickets(decision_ref);
 CREATE INDEX IF NOT EXISTS idx_tickets_assigned      ON tickets(assigned_to);
 CREATE INDEX IF NOT EXISTS idx_tickets_parent        ON tickets(parent_record_id);
 CREATE INDEX IF NOT EXISTS idx_ticket_idmap_label    ON ticket_idmap(ticket_id);
 CREATE INDEX IF NOT EXISTS idx_decisions_domain      ON decisions(domain);
 CREATE INDEX IF NOT EXISTS idx_decisions_type        ON decisions(type);
 CREATE INDEX IF NOT EXISTS idx_decision_refs_target  ON decision_refs(target_id);
@@ -1,289 +0,0 @@
 # Webber Monorepo - Agent Instructions
 > **Start every session by reading this file.**
 > This file contains everything you need to work with this codebase efficiently.
 ## Quick Reference
 | Action | Command |
 |--------|---------|
 | Start API server | `cd webber-api && ./wakeup.sh` |
 | View API logs | `tail -f webber-api/logs/server.log` |
 | Run API tests | `cd webber-api && .venv/bin/python -m pytest tests/ -v` |
 | Check CLI status | `cd webber-cli && .venv/bin/webber-cli status` |
 | Load sandbox | `./sandbox.sh load calculator-cli` |
 | Explore sandbox | `cd webber-cli && .venv/bin/webber-cli explore "query" -d ../webber-sandbox` |
 ---
 ## Repository Structure
 ```
 webber/
 ├── webber-api/          # FastAPI backend server
 │   ├── src/             # API source code
 │   ├── tests/           # API tests (pytest)
 │   ├── docs/            # Architecture docs, COVERAGE.md
 │   ├── logs/            # Runtime logs (server.log)
 │   ├── .venv/           # API virtual environment
 │   ├── wakeup.sh        # Dev server startup script
 │   └── AGENTS.md        # API-specific development guide
 │
 ├── webber-cli/          # CLI client
 │   ├── webber_cli/      # Python package (underscore!)
 │   ├── .venv/           # CLI virtual environment
 │   └── README.md        # CLI usage guide
 │
 ├── webber-sandbox/      # Active test project (contents swappable)
 │   ├── src/             # Current project source
 │   ├── tests/           # Current project tests
 │   ├── .venv/           # Sandbox virtual environment
 │   └── TASKS.md         # Tasks for Webber to complete
 │
 ├── sandbox-templates/   # Template storage
 │   ├── calculator-cli/  # Simple CLI with intentional bugs
 │   └── empty/           # Blank starter project
 │
 ├── sandbox.sh           # Sandbox management script
 └── AGENTS.md            # THIS FILE
 ```
 ---
 ## Development Workflow
 ### 1. Start the API Server
 ```bash
 cd webber-api
 ./wakeup.sh
 ```
 - **Port:** 8095 (dev), 8086 (production Docker)
 - **Logs:** `webber-api/logs/server.log`
 - **Health check:** `curl http://localhost:8095/health`
 - **API docs:** http://localhost:8095/docs
 To stop: `Ctrl+C` or `pkill -f "uvicorn src.main:app"`
 ### 2. Run Tests
 ```bash
 # API tests (39 tests)
 cd webber-api
 .venv/bin/python -m pytest tests/ -v
 # With coverage
 .venv/bin/python -m pytest tests/ --cov=src
 # Single test file
 .venv/bin/python -m pytest tests/test_tools.py -v
 ```
 ### 3. Use the CLI
 ```bash
 cd webber-cli
 # Check API connection
 .venv/bin/webber-cli status
 # Interactive chat (default mode - full capabilities)
 .venv/bin/webber-cli chat -d ../webber-sandbox
 # Read-only mode (safe exploration and planning)
 .venv/bin/webber-cli chat --mode plan -d ../webber-sandbox
 # Auto-accept mode (no approval prompts - use with caution)
 .venv/bin/webber-cli chat --mode auto_accept -d ../webber-sandbox
 # List previous sessions
 .venv/bin/webber-cli sessions
 # Resume a previous session
 .venv/bin/webber-cli chat --resume <session-id>
 ```
 **CLI Features:**
 - **Tab completion** for commands and file paths
 - **Command history** persisted to `~/.webber_history`
 - **Session persistence** - conversations saved and resumable
 - **Config file** - persistent settings via `~/.webber/config.toml`
 - **Runtime mode switching** via `mode plan|default|auto_accept`
 - **Directory navigation** via `cd <path>`
 **Configuration:**
 ```bash
 # Show current config
 .venv/bin/webber-cli config
 # Initialize config file with defaults
 .venv/bin/webber-cli config --init
 ```
 **Note:** The API server must be running for CLI commands to work.
 ---
 ## Sandbox Management
 The sandbox is a swappable test project for functional testing.
 ### Available Templates
 | Template | Description |
 |----------|-------------|
 | `calculator-cli` | Python CLI with intentional bugs (div-by-zero, missing tests) |
 | `empty` | Blank starter project |
 ### Commands
 ```bash
 # List available templates
 ./sandbox.sh list
 # Load a template (clears sandbox, preserves .venv)
 ./sandbox.sh load calculator-cli
 # Reset to last loaded template
 ./sandbox.sh reset
 # Save current sandbox as new template
 ./sandbox.sh save my-template
 # Check current status
 ./sandbox.sh status
 ```
 ### After Loading a Template
 ```bash
 cd webber-sandbox
 source .venv/bin/activate  # Create .venv first if missing
 pip install -r requirements.txt
 # Read the tasks
 cat TASKS.md
 # Run the project's tests
 pytest tests/ -v
 ```
 ---
 ## Testing Webber's Capabilities
 ### Scenario: Find bugs in calculator-cli
 ```bash
 # 1. Load the template
 ./sandbox.sh load calculator-cli
 # 2. Have Webber explore it (plan mode = read-only)
 cd webber-cli
 .venv/bin/webber-cli chat --mode plan -d ../webber-sandbox
 # Then ask: "find all bugs in the code"
 # 3. Check TASKS.md for expected bugs
 cat ../webber-sandbox/TASKS.md
 ```
 ### Known bugs in calculator-cli:
 - Division by zero not handled (`operations.py:divide`)
 - Invalid operation causes KeyError (`main.py:get_operation`)
 - Power function broken for fractional exponents
 - Missing tests for divide and power functions
 ---
 ## Key Files for Debugging
 | File | Purpose |
 |------|---------|
 | `webber-api/logs/server.log` | API server logs |
 | `webber-api/src/domains/agents/explore/prompts.py` | Explore agent system prompts |
 | `webber-api/src/domains/agents/explore/agent.py` | Explore agent implementation |
 | `webber-api/src/ollama/provider.py` | Ollama integration (sanitizes content:null) |
 | `webber-api/docs/COVERAGE.md` | Feature coverage and known issues |
 ---
 ## Versioning & Releases
 Uses prefixed tags:
 - `api/vX.Y.Z` → Triggers API Docker build
 - `cli/vX.Y.Z` → Triggers CLI build (future)
 ### MANDATORY Release Procedure
 **NEVER push a tag before updating version files.** Follow this exact order:
 ```bash
 # For API releases:
 # 1. Update version in webber-api/pyproject.toml
 # 2. Update webber-api/CHANGELOG.md with release notes
 # 3. Commit the version bump
 git add -A && git commit -m "chore: release api vX.Y.Z"
 # 4. Create the tag (AFTER the commit)
 git tag api/vX.Y.Z
 # 5. Push everything together
 git push origin main --tags
 # For CLI releases:
 # 1. Update version in webber-cli/pyproject.toml
 # 2. Update webber-cli/CHANGELOG.md with release notes
 # 3. Commit the version bump
 git add -A && git commit -m "chore: release cli vX.Y.Z"
 # 4. Create the tag (AFTER the commit)
 git tag cli/vX.Y.Z
 # 5. Push everything together
 git push origin main --tags
 ```
 **Why this matters:** Pushing a tag before the version commit requires deleting and recreating the tag, which can trigger CI/CD pipelines prematurely and cause deployment issues.
 ---
 ## Troubleshooting
 ### API server won't start
 ```bash
 # Check if port is in use
 lsof -i :8095
 # Kill stuck process
 pkill -f "uvicorn src.main:app"
 ```
 ### CLI can't connect
 ```bash
 # Check API is running
 curl http://localhost:8095/health
 # Check CLI config
 echo $WEBBER_API_URL  # Should be http://localhost:8095
 ```
 ### Ollama errors
 ```bash
 # Check Ollama is running
 curl http://192.168.86.149:11434/api/tags
 # Check model is available
 curl http://192.168.86.149:11434/api/tags | grep mistral-nemo
 ```
 ### Tests failing
 ```bash
 # Run with verbose output
 cd webber-api
 .venv/bin/python -m pytest tests/ -v --tb=short
 ```
 ---
 ## Known Limitations
 1. **Model hallucination** - Mistral Nemo sometimes makes up file contents instead of using tool results
 See `webber-api/docs/COVERAGE.md` for full feature coverage status.
@@ -0,0 +1,189 @@
 # CLAUDE.md — webber
 Local-LLM multi-agent development assistant — "similar to Claude Code but running locally"
 (`webber-api/docs/architecture.md`), backed by Ollama via PydanticAI. Logical monorepo, single
 `.git`, three subprojects: `webber-api/` (FastAPI server, deployed), `webber-cli/` (Typer CLI
 client), `webber-sandbox/` (swappable test project used by `sandbox.sh`, not shipped).
 ## Ports
 | | Port | How |
 |---|---|---|
 | Local dev | **8095** | `cd webber-api && ./wakeup.sh`, uvicorn `--reload`, logs to `webber-api/logs/server.log` |
 | Production | **8086** | container `webber`, confirmed running (`docker ps`) on `docker-dataplane` |
 `wakeup.sh` refuses to start if 8095 is already bound — it does not silently pick another
 port. Testing `localhost:8086` on the dev box hits the *container*, not your reload server.
 ## Live contract
 `http://localhost:8086/openapi.json` — 10 paths, `version: 1.0.1` (verified 2026-08-09,
 matches `webber-api/pyproject.toml` and the live `/health` response). Human docs at
 `http://localhost:8086/docs`. Query the live spec rather than inferring routes from source —
 `src/domains/router.py` currently has two routers commented out (see Architecture), so a
 source read alone will overcount if you don't check whether an include is live.
 ```
 /, /health, /agents/, /agents/run, /agents/stream, /agents/{agent_type},
 /conversations/, /conversations/{conversation_id},
 /conversations/{conversation_id}/messages, /conversations/{conversation_id}/save
 ```
 ## Architecture
 Domain-first layout under `webber-api/src/domains/<name>/`. `src/main.py` includes exactly one
 router, `src.domains.router.root_router`, which composes the domain routers. A full directory
 map lives in `webber-api/docs/architecture.md` — read that before adding a domain rather than
 duplicating it here.
 **How liveness below was established:** `docker exec webber python3 -c "import src.main; import
 sys; print(sorted(m for m in sys.modules if m.startswith('src.')))"` — i.e. importing the real
 app inside the running container and reading `sys.modules`, not grepping `main.py`. Re-run that
 command to re-check; a grep of imports will miss function-body imports, and this repo has one
 that matters.
 - **Wired at startup, serving routes:** `src.domains.health`, `src.domains.agents` (router +
  `explore`/`plan`/`task` agent packages), `src.domains.conversations`, `src.shared.*`,
  `src.ollama`, `src.db` (imported both by `conversations/router.py` at module scope and by
  `main.py`'s lifespan shutdown handler).
 - **Present in source, explicitly disabled:** `src/domains/router.py` has
  `# from src.domains.auth.router import router as auth_router` and the equivalent for
  `tools_router` — both commented out with the include calls also commented out. `src/domains/auth/`
  is just an empty `__init__.py`. This one *is* dead — the disabling is visible in the same file,
  not a matter of tracing an indirect import.
 - **The trap: `src/domains/tools/` is not in `sys.modules` right after `import src.main`, but it
  is not dead.** `src/domains/agents/{explore,plan,task}/agent.py` each have a method
  (e.g. `PlanAgent._register_tools`) that does `from src.domains.agents.plan.tools import
  register_plan_tools` **inside the function body**, called every time that agent is
  constructed — i.e. on every `/agents/run` or `/agents/stream` request for that agent type.
  That nested module then imports the real tool classes from `src.domains.tools.file`,
  `.search`, `.shell` at module scope. A static snapshot taken before any request is served
  will not show `src.domains.tools` loaded; that is a timing artifact, not evidence it is
  unused. Don't delete `src/domains/tools/` on the strength of a `sys.modules` check alone —
  confirm by hitting `/agents/run` and re-checking, or by tracing the call graph from each
  agent's `_register_tools`.
 - **`src/cli/`** is the implementation behind `webber-cli`'s `pyproject.toml` script entry —
  it is a separate Typer app, not imported by the API (`src.main`) at all. Its liveness is
  "is the CLI installed and invoked", not "is it wired into the API process".
 Group new work by domain, not file type — `webber-api/docs/fastapi-best-practices.md` is the
 house reference (mirrors the convention used across the other in-house FastAPI services here).
 ## Database
 SQLite by default (`database_url = "sqlite+aiosqlite:///./webber.db"` in
 `src/shared/config.py`), not Postgres — confirmed by reading `src/shared/config.py` and
 `src/db/database.py` (the latter's docstring says the pattern is ported from core-api, but
 the backend differs). Models under `webber-api/src/domains/<name>/models.py` import `Base`
 from `src/db/models.py`. No Alembic here (unlike core-api) — did not find a migrations
 directory; unverified whether schema changes have any managed migration path at all. Check
 before assuming one exists.
 ## Working here
 **Test locally first.** `cd webber-api && ./wakeup.sh` auto-reloads on code changes (not on
 `requirements.txt` changes — restart after adding a dependency). Deploy only once a feature
 is complete and tested.
 ```bash
 cd webber-api
 .venv/bin/python -m pytest tests/           # all tests
 .venv/bin/python -m pytest tests/ -v --cov  # verbose + coverage
 .venv/bin/python -m pytest tests/test_tools.py -v   # single file
 ```
 `webber-api/pyproject.toml` declares `[tool.ruff]` and `[tool.mypy]` — unlike core-api, this
 repo does have ruff/mypy config; whether either runs in CI is a separate question (see CI below
 — it does not).
 Copy `webber-api/.env.example` to `webber-api/.env`. Notable defaults: `OLLAMA_URL` points at
 `192.168.86.149:11434` (the host's Ollama, not a container), `OLLAMA_AGENT_MODEL=gemma4:e2b`,
 optional Tatlock integration via `TATLOCK_API_URL`/`INTERNAL_API_KEY`, optional SearXNG via
 `SEARXNG_URL` for the `web_search` tool.
 ### Sandbox
 `webber-sandbox/` is a disposable project used to exercise the agents end-to-end, managed by
 `./sandbox.sh {list,load,reset,save,status}` from the repo root. `sandbox-templates/` holds the
 reusable templates (`calculator-cli` has intentionally-seeded bugs for testing Explore/Task).
 This directory is fixture material, not shipped code — do not treat bugs in it as real bugs.
 ### CLI
 `webber-cli/` is a Typer client (`webber-cli status|chat|explore|sessions|config`) with tab
 completion, session persistence (`~/.webber_history`, `~/.webber/config.toml`), and three chat
 modes (`plan` read-only, `default`, `auto_accept`). It talks to the API over HTTP — it does not
 share a process with `webber-api`. Run it from its own venv: `cd webber-cli && .venv/bin/webber-cli status`.
 ## CI
 `.gitea/workflows/build-api.yml` triggers only on `api/vX.Y.Z` tags: creates a Gitea release,
 builds/pushes `git.schweitz.net/jpmschweitzer/webber-api`, then pings Watchtower.
 `build-cli.yml` triggers on `cli/vX.Y.Z` tags but is a placeholder — it only echoes a TODO, it
 does not build or publish anything. **No test or lint gate runs in CI for either package** —
 pytest and ruff only run locally or on request. Verify tests pass before tagging.
 ## Work tracking
 Work lives in **pql**, not a markdown TODO or `docs/COVERAGE.md`. **This repo's vault is
 standalone** — its tickets and its internal decisions live here in `.pql/` and `governance/`,
 and travel with a clone, because `.pql/changelog/` is committed and replayed by the git hooks
 (workspace D-15). The databases are gitignored and rebuildable with `pql plan rebuild`.
 `pql` is **not** on the non-interactive `PATH` — invoke it as
 `/home/jpmschweitzer/.local/bin/pql`. From inside this repo no `--vault` is needed: pql anchors
 at the nearest `.git/` ancestor, which is this repo.
 ```bash
 /home/jpmschweitzer/.local/bin/pql ticket list        # this repo's open work
 /home/jpmschweitzer/.local/bin/pql plan whatsnext     # next unblocked item, with context
 /home/jpmschweitzer/.local/bin/pql decisions list     # this repo's own decisions
 ```
 Stack-level decisions that constrain this service live in the **workspace** vault and need the
 flag:
 ```bash
 /home/jpmschweitzer/.local/bin/pql --vault /mnt/media/Projects decisions list --domain webber
 ```
 Note `ticket new --decision D-N` resolves ids within **one** vault, so a ticket here cannot link
 to a workspace decision. Cite the id in the ticket body instead.
 Do not add a TODO section to a markdown file.
 ## Git
 - **History is linear — no merge commits.** Work on `main`, or a short-lived branch that is
  fast-forwarded and deleted. (This repo's `AGENTS.md` previously mandated `feature/...` or
  `fix/...` branches for every change and forbade committing to `main` directly — that rule was
  retired workspace-wide on 2026-08-08 and does not apply here anymore.)
 - **Conventional Commits**: `feat:`, `fix:`, `refactor:`, `docs:`, `chore:`.
 - **Atomic commits** — one logical change each.
 - **Stage explicitly. Never `git add -A`** — denied by policy; it sweeps in whatever else is
  dirty, including secrets.
 - Each package versions independently via prefixed tags (`api/vX.Y.Z`, `cli/vX.Y.Z`) and its
  own `CHANGELOG.md` (`webber-api/CHANGELOG.md`, `webber-cli/CHANGELOG.md`); the root
  `CHANGELOG.md` is just an index pointing at both.
 ## Releasing (API)
 Ask whether a deploy is wanted first — it is not automatic.
 1. Bump the version in `webber-api/pyproject.toml`.
 2. Move `[Unreleased]` entries into a dated version section in `webber-api/CHANGELOG.md`.
 3. Stage the changed files by name, commit, tag `api/vX.Y.Z`, `git push origin main --tags`.
 4. Gitea CI (`build-api.yml`) builds and pushes the image on the tag; Watchtower deploys it.
 5. Verify: `curl http://192.168.86.149:8086/health`.
 CLI releases (`cli/vX.Y.Z`) currently only log a TODO in CI — there is no build/publish step
 to trigger yet.
 ## Known issues (carried over, unverified beyond what's stated)
 - **Model hallucination**: the Explore agent's model can hallucinate file contents instead of
  using actual tool results, per `webber-api/AGENTS.md` — a mitigation (stronger model or
  response validation) was suggested there but not confirmed implemented.
 - **Ollama `content: null` workaround**: `src/ollama/provider.py` (confirmed present, loaded at
  startup per the `sys.modules` check above) sanitizes `content: null` to `content: ""` for
  assistant messages with tool calls, working around an Ollama API limitation.
@@ -0,0 +1,62 @@
 # webber — the repo's command surface (D-27).
 #
 # Multi-component, so this lives at the root and reaches down rather than
 # sitting inside webber-api/. The code, tests and tooling config are all in
 # webber-api/; sandbox-templates/ and sandbox.sh are the other half of the repo
 # and have no build of their own. Keeping one Makefile means `make test` means
 # the same thing wherever you are standing (D-27).
 #
 # Paths resolve here (D-10): `python3` is 3.8 on this host, and a bare `pytest`
 # or `ruff` resolves only in a login shell.
 API    := $(CURDIR)/webber-api
 VENV   := $(API)/.venv
 PYTHON ?= python3.12
 .DEFAULT_GOAL := help
 .PHONY: help
 help: ## Show this help
 	@grep -hE '^[a-z][a-z0-9_-]*:.*?## ' $(MAKEFILE_LIST) \
 	  | awk 'BEGIN{FS=":.*?## "}{printf "  \033[36m%-14s\033[0m %s\n", $$1, $$2}'
 .PHONY: setup
 setup: ## Create the webber-api venv and install dev dependencies
 	cd $(API) && $(PYTHON) -m venv .venv && .venv/bin/pip install -e ".[dev]"
 .PHONY: test
 test: ## Run the webber-api test suite
 	@test -x $(VENV)/bin/python || { echo "FAIL — no venv; run: make setup"; exit 69; }
 	cd $(API) && .venv/bin/python -m pytest tests/
 .PHONY: lint
 lint: ## ruff check over webber-api
 	@test -x $(VENV)/bin/ruff || { echo "FAIL — ruff not installed; run: make setup"; exit 69; }
 	cd $(API) && .venv/bin/ruff check .
 .PHONY: typecheck
 typecheck: ## mypy over webber-api
 	@test -x $(VENV)/bin/mypy || { echo "FAIL — mypy not installed; run: make setup"; exit 69; }
 	cd $(API) && .venv/bin/mypy .
 # git hands a hook a non-login shell, which never sees ~/.local/bin — where
 # gitleaks lands. Without this the scan reports "not installed" on every push,
 # which is a check that fails open (D-24).
 export PATH := $(HOME)/.local/bin:/usr/local/bin:$(PATH)
 .PHONY: secrets
 secrets: ## Scan the commits about to be pushed for credentials
 	@ci/secrets.sh
 # The call surface is identical in every repo; what it runs is not.
 #
 # `secrets` runs first, deliberately: it is the only failure here that cannot be
 # undone by fixing it afterwards. A failed lint costs another commit; a pushed
 # credential is cached and indexed whether or not it is later deleted.
 #
 # Some of these fail today, and are left wired anyway. The state was measured
 # once and written down in T-56 rather than being worked around here — a gate
 # quietly narrowed to what already passes is a gate that reports success for
 # doing nothing, which is the failure this workspace keeps rediscovering.
 .PHONY: pre-push
 pre-push: secrets lint typecheck test ## Everything the pre-push hook runs
@@ -107,13 +107,13 @@ This project uses prefixed tags for independent release cycles:
 ## Requirements
 - Python 3.12+
- Ollama running with `mistral-nemo:latest` model
+- Ollama running with `gemma4:e2b` model
 - Docker (for production deployment)
 - SearXNG (optional, for web search)
 ## Documentation
- `webber-api/AGENTS.md` - API development guidelines
+- `CLAUDE.md` - Agent development guidelines (repo-wide)
 - `webber-api/docs/COVERAGE.md` - Feature coverage and roadmap
 - `webber-api/docs/architecture.md` - System architecture
 - `webber-cli/README.md` - CLI usage guide
@@ -0,0 +1,50 @@
 #!/usr/bin/env bash
 # Secret scan over the commits about to be pushed.
 #
 # Lives here rather than inside .githooks/pre-push so it can be read, run by
 # hand (`make secrets`), and changed under review. A hook is a trigger; it is
 # not a home for logic. Identical in every repo in this workspace (D-27).
 set -euo pipefail
 cd "$(git rev-parse --show-toplevel)"
 # A non-login shell — which is what git gives a hook — skips /etc/profile.d
 # and never sees ~/.local/bin, where the gitleaks release tarball lands.
 # Without this the scan reports "not installed" on every push.
 [ -d "$HOME/.local/bin" ] && PATH="$HOME/.local/bin:$PATH"
 if ! command -v gitleaks >/dev/null 2>&1; then
  echo "FAIL secrets — gitleaks not installed, so this check would be a no-op pretending to pass." >&2
  echo "     https://github.com/gitleaks/gitleaks/releases → ~/.local/bin/gitleaks" >&2
  exit 1
 fi
 # Scan the outgoing range, not full history. History here carries findings
 # that are settled — test fixtures and vendored third-party code — and a gate
 # that fails on something unfixable gets bypassed within a week. What matters
 # is what is about to leave this machine.
 if upstream=$(git rev-parse --abbrev-ref --symbolic-full-name '@{u}' 2>/dev/null); then
  range="$upstream..HEAD"
 elif git rev-parse --verify --quiet origin/main >/dev/null; then
  range="origin/main..HEAD"
 else
  range=""
 fi
 if [ -z "$range" ]; then
  gitleaks dir . --redact --no-banner --exit-code 1 || {
    echo "FAIL secrets — gitleaks found a credential in the working tree." >&2; exit 1; }
  exit 0
 fi
 [ -n "$(git log --oneline "$range" 2>/dev/null)" ] || exit 0
 gitleaks git . --log-opts="$range" --redact --no-banner --exit-code 1 >/dev/null 2>&1 || {
  echo "FAIL secrets — gitleaks found a credential in the commits being pushed." >&2
  echo "     inspect (values redacted):  gitleaks git . --log-opts=\"$range\" --redact" >&2
  echo "     then remove and rotate it, or suppress deliberately:" >&2
  echo "       inline  '# gitleaks:allow  <reason>'" >&2
  echo "       or add the fingerprint to .gitleaksignore WITH a reason" >&2
  exit 1
 }
 echo "  ok   secrets"
@@ -0,0 +1,54 @@
 # Decisions, Questions, Rejected
 This directory holds structured planning records that pql parses
 into pql.db. Each record is a `### [DQR]-N: Title` heading inside
 a markdown file. Files live in three per-type subdirectories:
 - `decisions/<domain>.md` — confirmed design decisions
 - `questions/<domain>.md` — open questions that may resolve into
  decisions or rejected proposals
 - `rejected/<domain>.md` — rejected proposals (kept for the audit
  trail)
 The parser infers domain from the filename stem and record type
 from the parent subdirectory.
 D-records that propose implementation work link to `initiative`-type
 tickets via `decision_ref`. Run `pql decisions show <id>
 --with-tickets` to inspect implementation status.
 ## Recommended domains
 Start with this canonical set; create files as records land in
 each domain:
 - **architecture** — structural commitments (storage, layering,
  languages, libraries)
 - **process** — team workflow (commits, branches, releases, reviews)
 - **design** — user-facing surface (UX, UI, public APIs)
 - **coding-conventions** — team-internal code shape (style, lint,
  file layout)
 - **testing** — quality strategy (coverage, layers, gates)
 You might also want, project-permitting:
 - `accessibility` — if you ship user-facing software
 - `security` — if you handle user data or network surfaces
 - `licensing` — if you release open-source or commercial
 - `documentation` — if user-docs are non-trivial
 - `deployment` — if shipping is non-trivial
 - `performance` — if you have perf budgets / SLOs
 <!-- pql:records (auto-generated; do not edit manually) -->
 ## Decisions
 - _(none)_
 ## Open questions
 - _(none)_
 ## Rejected
 - _(none)_
@@ -14,7 +14,7 @@ CORS_ORIGINS=["http://localhost:3000","http://localhost:8080"]
 # LLM - Ollama (tower-of-joy)
 OLLAMA_URL=http://192.168.86.149:11434
-OLLAMA_AGENT_MODEL=mistral-nemo-large:latest
+OLLAMA_AGENT_MODEL=gemma4:e2b
 OLLAMA_EMBED_MODEL=nomic-embed-text:latest
 # Auth - Tatlock integration (optional)
@@ -1,128 +0,0 @@
 # AGENTS.md
 > **Start every session by reading this file.**
 > This file outlines the operational protocols, coding standards, and architectural decisions for this FastAPI project.
 ## 1. Agent Operational Protocols
 ### 🧠 Work Patterns (Plan-Act-Reflect)
 * **Plan:** Before writing code, briefly outline your plan. Identify which files you will touch and what the side effects might be.
 * **Act:** Execute the changes in small, atomic steps.
 * **Reflect:** After coding, verify your work. Did you break existing tests? Did you add new tests?
 ### 🛡️ Git Discipline
 * **ALWAYS add the relevant tests for the added code** Make sure to keep the test coverage up as we go, and run tests before commiting.
 * **NEVER commit to `main` or `master` directly.** Always create a feature branch: `feature/your-feature-name` or `fix/issue-description`.
 * **Commit Messages:** Use the [Conventional Commits](https://www.conventionalcommits.org/) format.
    * `feat: add user login endpoint`
    * `fix: resolve database connection timeout`
    * `refactor: split monolith dependency file`
 * **Atomic Commits:** Keep commits small. One logical change = one commit.
 ### 📝 Changelog Maintenance
 * **Update `CHANGELOG.md`** with every user-facing change.
 * Format: `## [Unreleased] - YYYY-MM-DD` followed by `### Added`, `### Changed`, or `### Fixed`.
 ### 🚀 Release Flow
 When changes are ready for deployment:
 1. **Ask user if deploy cycle is desired **
 2. **Update version** in `pyproject.toml`:
   - Bug fixes: bump patch version (1.8.3 → 1.8.4)
   - New features: bump minor version (1.8.4 → 1.9.0)
 3. **Update CHANGELOG.md**:
   - Move items from `[Unreleased]` to new version section
   - Add release date: `## [1.8.4] - 2025-12-16`
 4. **Commit and tag**:
   ```bash
   git add -A
   git commit -m "fix: description of changes"
   git tag v1.8.4
   git push origin main --tags
   ```
 5. **CI/CD triggers automatically**:
   - Gitea CI builds Docker image on new version tag (starts with "v")
   - Watchtower pulls and deploys to production
   - Verify deployment: `curl http://192.168.86.149:8086/health`
 ---
 ### 🧪 Local Development Setup
 * **Always test locally first** before committing and deploying. The build-deploy loop is slow.
 * **Only deploy** when a phase or feature is complete and tested locally
 * **Environment**: Copy `.env.example` to `.env` and configure for your local setup
 #### ⚠️ CRITICAL: Starting the Local Server
 **ALWAYS use `./wakeup.sh` to start the local server. NEVER use raw uvicorn commands.**
 ```bash
 ./wakeup.sh
 ```
 The wakeup script provides:
 - **Port conflict detection** - Warns if port 8086 is already in use
 - **Virtual environment activation** - Ensures correct Python environment
 - **Centralized logging** - All logs written to `logs/server.log` for easy tailing
 - **Auto-reload** - Code changes picked up automatically (except requirements.txt changes)
 - **Consistent configuration** - Same startup every time
 To monitor logs in another terminal:
 ```bash
 tail -f logs/server.log
 ```
 To stop the server: Press `Ctrl+C`
 To kill a stuck server:
 ```bash
 pkill -f "uvicorn src.main:app"
 # or
 kill $(lsof -t -i:8086)
 ```
 #### Testing
 **Test REST endpoints** against `http://localhost:8086`:
 ```bash
 curl http://localhost:8086/health
 curl http://localhost:8086/
 curl http://localhost:8086/docs   # Swagger UI
 ```
 **Running tests**: Always use the venv explicitly to avoid environment mismatches:
 ```bash
 .venv/bin/python -m pytest tests/           # All tests
 .venv/bin/python -m pytest tests/ -v        # Verbose output
 .venv/bin/python -m pytest tests/ --cov     # With coverage
 ```
 ---
 ## 1.5 Known Issues & Future Improvements
 ### Explore Agent
 - **Model Hallucination**: Mistral Nemo sometimes hallucinates file contents instead of using actual tool results. Consider using a more capable model (codestral, qwen2.5-coder) or adding response validation.
 - **Ollama Provider**: We use a custom `WebberOllamaProvider` (ported from tatlock) that sanitizes `content: null` to `content: ""` for assistant messages with tool calls. This works around an Ollama API limitation.
 - **Gitignore Support**: ✅ Fixed - The filesystem tools now honor `.gitignore` patterns and default ignores (`.venv/`, `__pycache__/`, `node_modules/`, etc.).
 ---
 ## 2. FastAPI Architecture & Best Practices
 *Reference: [FastAPI Best Practices](https://github.com/zhanymkanov/fastapi-best-practices)*
 ### 📂 Project Structure (Directory-based, NOT File-type based)
 Do **not** group files by type (e.g., one huge `routers` folder). Group by **domain/module** inside a `src/` directory.
 **Correct Structure:**
 ```text
 to be determined
@@ -7,6 +7,22 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 ## [1.1.0] - 2026-08-11
 ### Added
 - `webber version` command. It was implemented and imported but never registered, so the
  subcommand did not exist; the fuller output includes the resolved Ollama URL and model.
 ### Fixed
 - The Ollama `content: null` sanitiser raised `AttributeError` on first use. It looked up the
  parent client's chat getter via `.fget`, and openai now exposes `chat` as a
  `cached_property`. Any agent request would have failed before reaching the model.
 ### Changed
 - Default `OLLAMA_AGENT_MODEL` is now `gemma4:e2b` instead of `mistral-nemo-large:latest`, so a deployment without an explicit override no longer exhausts shared GPU memory
 - `BaseAgent` is generic over its context type and `run_stream` is typed as
  `AsyncIterator[str | StreamEvent]`, matching what callers already receive.
 ## [1.0.1] - 2026-07-19
 ### Changed
@@ -13,7 +13,7 @@ Webber is a FastAPI-based agent orchestration service that provides:
 **Port:** 8086
 **Runtime:** Python 3.12, FastAPI, Uvicorn
 **Agent Framework:** PydanticAI
-**Default LLM:** Ollama with mistral-nemo-large:latest
+**Default LLM:** Ollama with gemma4:e2b
 ---
@@ -205,7 +205,7 @@ All settings via environment variables or `.env`:
 | HOST | 0.0.0.0 | Server host |
 | PORT | 8086 | Server port |
 | OLLAMA_URL | http://192.168.86.149:11434 | Ollama API URL |
-| OLLAMA_AGENT_MODEL | mistral-nemo-large:latest | Agent reasoning model |
+| OLLAMA_AGENT_MODEL | gemma4:e2b | Agent reasoning model |
 | OLLAMA_EMBED_MODEL | nomic-embed-text:latest | Embedding model |
 | TATLOCK_API_URL | http://tatlock:8000 | Tatlock auth service |
 | SEARXNG_URL | http://searxng:8080 | SearXNG web search instance |
@@ -359,7 +359,7 @@ Gitea Actions workflow:
 Deployed in Portainer `agents` stack alongside Tatlock:
 - Network: `docker-dataplane`
- Registry: `git.schweitz.internal/jpmschweitzer/webber`
+- Registry: `git.schweitz.net/jpmschweitzer/webber`
 - Auto-update: Watchtower with label `com.centurylinklabs.watchtower.enable=true`
 ---
@@ -1,6 +1,6 @@
 [project]
 name = "webber-api"
-version = "1.0.1"
+version = "1.1.0"
 description = "Webber API - Multi-Agent AI Development Server"
 authors = [
    {name = "jpmschweitzer"}
@@ -15,6 +15,9 @@ pip-audit~=2.9.0
 # Type checking
 mypy~=1.19.1
 # Stubs for aiofiles, which ships none. Without them mypy reports
 # import-untyped on every module that reads or writes a file.
 types-aiofiles~=25.1
 # Linting and formatting
 ruff~=0.9.4
@@ -6,9 +6,9 @@ from pathlib import Path
 import typer
 from src.cli.session.loop import AgenticLoop
 from src.cli.theme import get_theme
 from src.cli.ui.console import get_console
 from src.cli.session.loop import AgenticLoop
 from src.shared.logging import setup_logging
 console = get_console()
@@ -53,11 +53,17 @@ def main(
 # Import and register commands
-from src.cli.commands import chat, explore, version  # noqa: E402, F401
+from src.cli.commands import chat, explore, version  # noqa: E402
 # Register subcommands
 app.command(name="chat")(chat.chat_command)
 app.command(name="explore")(explore.explore_command)
 # version was imported and never registered, so `webber version` did not exist.
 # The --version flag above is the terse form; show_version prints the panel with
 # the resolved Ollama URL, model and debug state, which is the one worth having
 # when something is misconfigured. The F401 suppression on the import was what
 # kept the omission quiet.
 app.command(name="version")(version.show_version)
 if __name__ == "__main__":
@@ -4,4 +4,4 @@ Session management for CLI.
 from src.cli.session.context import SessionState
 from src.cli.session.loop import AgenticLoop
-__all__ = ["SessionState", "AgenticLoop"]
+__all__ = ["AgenticLoop", "SessionState"]
@@ -1,14 +1,13 @@
 """
 Agentic conversation loop for interactive CLI.
 """
 from typing import Any
 from rich.console import Console
 from src.cli.session.context import SessionState
 from src.cli.ui.display import format_response
 from src.domains.agents.base import BaseAgent
-from src.shared.logging import logged, trace_span, get_logger
+from src.shared.logging import get_logger, logged, trace_span
 logger = get_logger(__name__)
@@ -4,7 +4,7 @@ CLI theme configuration.
 Centralized color and style definitions for the Webber CLI.
 All color choices should be defined here for easy customization.
 """
-from dataclasses import dataclass
+from dataclasses import dataclass, field
@dataclass(frozen=True)
@@ -36,7 +36,7 @@ class ThemeColors:
 class ThemeConfig:
    """Complete theme configuration."""
-    colors: ThemeColors = ThemeColors()
+    colors: ThemeColors = field(default_factory=ThemeColors)
    # Spinner style for loading indicators
    spinner: str = "dots"
@@ -2,6 +2,6 @@
 CLI UI components.
 """
 from src.cli.ui.console import get_console
-from src.cli.ui.display import format_response, format_code
+from src.cli.ui.display import format_code, format_response
-__all__ = ["get_console", "format_response", "format_code"]
+__all__ = ["format_code", "format_response", "get_console"]
@@ -8,7 +8,6 @@ from rich.syntax import Syntax
 from rich.text import Text
 from src.cli.theme import get_theme
 from src.cli.ui.console import get_console
 def format_response(text: str) -> Markdown | Text:
@@ -7,8 +7,8 @@ from src.db.database import Database, get_database, get_session
 from src.db.models import Base
 __all__ = [
    "Base",
    "Database",
    "get_database",
    "get_session",
    "Base",
 ]
@@ -4,34 +4,34 @@ Agent implementations.
 All agents inherit from BaseAgent and are registered in the global registry.
 """
 from src.domains.agents.base import (
    BaseAgent,
    AgentContext,
    AgentProtocol,
-    register_agent,
+    BaseAgent,
    get_agent,
    list_agents,
    get_registry,
    list_agents,
    register_agent,
 )
 from src.domains.agents.explore import (
    ExploreAgentImpl,
    ExploreContext,
    explore_agent,
    explore,
    explore_agent,
 )
 __all__ = [
    # Base classes
    "BaseAgent",
    "AgentContext",
    "AgentProtocol",
-    # Registry functions
+    # Base classes
-    "register_agent",
+    "BaseAgent",
    "get_agent",
    "list_agents",
    "get_registry",
    # Explore agent
    "ExploreAgentImpl",
    "ExploreContext",
    "explore_agent",
    "explore",
    "explore_agent",
    "get_agent",
    "get_registry",
    "list_agents",
    # Registry functions
    "register_agent",
 ]
@@ -6,10 +6,11 @@ All agents are built on PydanticAI and registered in a central registry.
 from abc import ABC, abstractmethod
 from collections.abc import AsyncIterator
 from dataclasses import dataclass, field
-from typing import Any, Protocol, runtime_checkable
+from typing import Any, Generic, Protocol, TypeVar, runtime_checkable
 from pydantic_ai import Agent
 from src.domains.agents.schemas import StreamEvent
 from src.shared.logging import get_logger
 logger = get_logger(__name__)
@@ -27,6 +28,15 @@ class AgentContext:
    timeout_seconds: int = 120
 # Every agent narrows the context its tools receive — ExploreContext,
 # PlanContext, TaskContext. Without this parameter BaseAgent could only say
 # `Agent`, which is `Agent[Any, Any]`, and pydantic_ai then types every
 # `.run()` result as Any. That is where 35 of this package's mypy errors came
 # from: functions declared `-> str` returning Any, each looking like a local
 # annotation slip rather than one missing type parameter in the base class.
 CtxT = TypeVar("CtxT", bound=AgentContext)
@runtime_checkable
 class AgentProtocol(Protocol):
    """Protocol that all agents must implement."""
@@ -60,7 +70,7 @@ class AgentProtocol(Protocol):
        ...
-class BaseAgent(ABC):
+class BaseAgent(ABC, Generic[CtxT]):
    """
    Abstract base class for agent implementations.
@@ -71,7 +81,8 @@ class BaseAgent(ABC):
            name = "explore"
            description = "Fast codebase exploration"
-            def _create_agent(self) -> Agent:
+            class ExploreAgent(BaseAgent[ExploreContext]):
                def _create_agent(self) -> Agent[ExploreContext, str]:
                    # Create and configure PydanticAI agent
                    ...
@@ -92,15 +103,21 @@ class BaseAgent(ABC):
        """Human-readable description."""
        pass
    # Declared on the base rather than only in each subclass's __init__. The
    # base reached it through hasattr, so mypy could not determine its type at
    # all; the guard existed because nothing guaranteed the attribute existed.
    # Declaring it here makes the None check sufficient.
    _agent: "Agent[CtxT, str] | None" = None
    @property
-    def agent(self) -> Agent:
+    def agent(self) -> "Agent[CtxT, str]":
        """Lazy-loaded PydanticAI agent."""
-        if not hasattr(self, '_agent') or self._agent is None:
+        if self._agent is None:
            self._agent = self._create_agent()
        return self._agent
    @abstractmethod
-    def _create_agent(self) -> Agent:
+    def _create_agent(self) -> "Agent[CtxT, str]":
        """
        Create and configure the PydanticAI agent.
@@ -115,7 +132,7 @@ class BaseAgent(ABC):
    async def run_stream(
        self, prompt: str, **kwargs: Any
-    ) -> AsyncIterator[str]:
+    ) -> AsyncIterator[str | StreamEvent]:
        """
        Execute the agent with streaming output.
@@ -4,13 +4,13 @@ Explore Agent - Fast codebase exploration.
 from src.domains.agents.explore.agent import (
    ExploreAgentImpl,
    ExploreContext,
    explore_agent,
    explore,
    explore_agent,
 )
 __all__ = [
    "ExploreAgentImpl",
    "ExploreContext",
    "explore_agent",
    "explore",
    "explore_agent",
 ]
@@ -12,11 +12,11 @@ from typing import Any
 from pydantic_ai import Agent
 from pydantic_ai.models.openai import OpenAIModel
-from src.domains.agents.base import BaseAgent, AgentContext, register_agent
+from src.domains.agents.base import AgentContext, BaseAgent, register_agent
 from src.domains.agents.explore.prompts import EXPLORE_SYSTEM_PROMPT
 from src.ollama.provider import get_ollama_provider
 from src.shared.config import get_settings
-from src.shared.logging import logged, get_logger, trace_span
+from src.shared.logging import get_logger, logged, trace_span
 logger = get_logger(__name__)
@@ -31,7 +31,7 @@ class ExploreContext(AgentContext):
    pass
-class ExploreAgentImpl(BaseAgent):
+class ExploreAgentImpl(BaseAgent[ExploreContext]):
    """
    Fast codebase exploration agent.
@@ -44,7 +44,7 @@ class ExploreAgentImpl(BaseAgent):
    def __init__(self):
        """Initialize the explore agent."""
-        self._agent: Agent[ExploreContext, str] | None = None
+        self._agent = None
        self._settings = get_settings()
    def _create_agent(self) -> Agent[ExploreContext, str]:
@@ -5,10 +5,10 @@ Registers our tool implementations with the PydanticAI agent.
 """
 from pydantic_ai import Agent, RunContext
-from src.domains.agents.base import AgentContext
+from src.domains.agents.explore.agent import ExploreContext
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.file.glob import GlobFilesTool
 from src.domains.tools.file.edit import EditFileTool
 from src.domains.tools.file.glob import GlobFilesTool
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.file.write import WriteFileTool
 from src.domains.tools.search.grep import GrepContentTool
 from src.domains.tools.search.web import WebSearchTool
@@ -16,7 +16,7 @@ from src.domains.tools.shell.bash import BashReadOnlyTool
 from src.domains.tools.shell.bash_full import BashTool
-def register_explore_tools(agent: Agent[AgentContext, str]) -> None:
+def register_explore_tools(agent: Agent[ExploreContext, str]) -> None:
    """
    Register all exploration tools with the agent.
@@ -25,7 +25,7 @@ def register_explore_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def read_file(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[ExploreContext],
        file_path: str,
        offset: int = 0,
        limit: int = 2000
@@ -52,7 +52,7 @@ def register_explore_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def glob_files(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[ExploreContext],
        pattern: str,
        path: str | None = None,
        limit: int = 100
@@ -85,7 +85,7 @@ def register_explore_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def grep_content(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[ExploreContext],
        pattern: str,
        path: str | None = None,
        file_glob: str | None = None,
@@ -125,7 +125,7 @@ def register_explore_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def bash_readonly(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[ExploreContext],
        command: str,
        cwd: str | None = None,
        timeout: int = 30
@@ -170,7 +170,7 @@ def register_explore_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def edit_file(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[ExploreContext],
        file_path: str,
        old_string: str,
        new_string: str,
@@ -204,7 +204,7 @@ def register_explore_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def write_file(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[ExploreContext],
        file_path: str,
        content: str
    ) -> str:
@@ -231,7 +231,7 @@ def register_explore_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def bash(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[ExploreContext],
        command: str,
        cwd: str | None = None,
        timeout: int = 60
@@ -277,7 +277,7 @@ def register_explore_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def web_search(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[ExploreContext],
        query: str,
        num_results: int = 5,
        categories: str | None = None
@@ -16,15 +16,15 @@ Usage:
 from src.domains.agents.plan.agent import (
    PlanAgentImpl,
    PlanContext,
    plan_agent,
    plan,
    plan_agent,
    plan_stream,
 )
 __all__ = [
    "PlanAgentImpl",
    "PlanContext",
    "plan_agent",
    "plan",
    "plan_agent",
    "plan_stream",
 ]
@@ -12,11 +12,11 @@ from typing import Any
 from pydantic_ai import Agent
 from pydantic_ai.models.openai import OpenAIModel
-from src.domains.agents.base import BaseAgent, AgentContext, register_agent
+from src.domains.agents.base import AgentContext, BaseAgent, register_agent
 from src.domains.agents.plan.prompts import PLAN_SYSTEM_PROMPT
 from src.ollama.provider import get_ollama_provider
 from src.shared.config import get_settings
-from src.shared.logging import logged, get_logger, trace_span
+from src.shared.logging import get_logger, logged, trace_span
 logger = get_logger(__name__)
@@ -32,7 +32,7 @@ class PlanContext(AgentContext):
    pass
-class PlanAgentImpl(BaseAgent):
+class PlanAgentImpl(BaseAgent[PlanContext]):
    """
    Software architect agent for implementation planning.
@@ -47,7 +47,7 @@ class PlanAgentImpl(BaseAgent):
    def __init__(self):
        """Initialize the plan agent."""
-        self._agent: Agent[PlanContext, str] | None = None
+        self._agent = None
        self._settings = get_settings()
    def _create_agent(self) -> Agent[PlanContext, str]:
@@ -6,14 +6,14 @@ It cannot modify files - only explore and analyze.
 """
 from pydantic_ai import Agent, RunContext
-from src.domains.agents.base import AgentContext
+from src.domains.agents.plan.agent import PlanContext
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.file.glob import GlobFilesTool
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.search.grep import GrepContentTool
 from src.domains.tools.shell.bash import BashReadOnlyTool
-def register_plan_tools(agent: Agent[AgentContext, str]) -> None:
+def register_plan_tools(agent: Agent[PlanContext, str]) -> None:
    """
    Register read-only exploration tools with the Plan agent.
@@ -28,7 +28,7 @@ def register_plan_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def read_file(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[PlanContext],
        file_path: str,
        offset: int = 0,
        limit: int = 2000
@@ -55,7 +55,7 @@ def register_plan_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def glob_files(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[PlanContext],
        pattern: str,
        path: str | None = None,
        limit: int = 100
@@ -88,7 +88,7 @@ def register_plan_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def grep_content(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[PlanContext],
        pattern: str,
        path: str | None = None,
        file_glob: str | None = None,
@@ -128,7 +128,7 @@ def register_plan_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def bash_readonly(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[PlanContext],
        command: str,
        cwd: str | None = None,
        timeout: int = 30
@@ -10,23 +10,24 @@ Streaming uses structured events instead of raw text to avoid
 garbled output during tool execution.
 """
 import json
 from fastapi import APIRouter, HTTPException
 from fastapi.responses import StreamingResponse
 from src.domains.agents.base import get_agent, list_agents
 # Import agents to ensure they're registered
-import src.domains.agents.explore  # noqa: F401
+import src.domains.agents.explore
-import src.domains.agents.plan  # noqa: F401
+import src.domains.agents.plan
 import src.domains.agents.task  # noqa: F401
 from src.domains.agents.base import get_agent, list_agents
 from src.domains.agents.schemas import (
    AgentRunRequest,
    AgentRunResponse,
    AgentInfo,
    AgentListResponse,
    AgentRunRequest,
    AgentRunResponse,
    PermissionMode,
    StreamEvent,
 )
 from src.shared.logging import get_logger, logged
 def _get_mode(mode_value: str | PermissionMode) -> PermissionMode:
@@ -34,7 +35,6 @@ def _get_mode(mode_value: str | PermissionMode) -> PermissionMode:
    if isinstance(mode_value, PermissionMode):
        return mode_value
    return PermissionMode(mode_value)
 from src.shared.logging import logged, get_logger
 logger = get_logger(__name__)
@@ -70,7 +70,13 @@ class ApprovalRuleSet(BaseSchema):
    First matching rule determines the action.
    If no rules match, falls back to default action.
    """
-    rules: list[ApprovalRule] = []
+    # Suppression justified: this is a pydantic model, not a plain class. Pydantic
    # deep-copies field defaults per instance — verified: two ApprovalRuleSet()
    # instances have `rules` lists that are not the same object, and appending
    # to one leaves the other empty. RUF012's suggested fix, annotating this
    # ClassVar, would remove the field from the model altogether. Ruff cannot
    # see the pydantic base because BaseSchema is a local subclass of BaseModel.
    rules: list[ApprovalRule] = []  # noqa: RUF012
    default_action: ApprovalAction = ApprovalAction.ask  # Default when no rules match
@@ -19,15 +19,15 @@ Usage:
 from src.domains.agents.task.agent import (
    TaskAgentImpl,
    TaskContext,
    task_agent,
    task,
    task_agent,
    task_stream,
 )
 __all__ = [
    "TaskAgentImpl",
    "TaskContext",
    "task_agent",
    "task",
    "task_agent",
    "task_stream",
 ]
@@ -8,6 +8,7 @@ Full orchestrator agent that can:
 - Stream structured events instead of raw text
 """
 import asyncio
 import contextlib
 import os
 from collections.abc import AsyncIterator
 from dataclasses import dataclass, field
@@ -16,12 +17,12 @@ from typing import Any
 from pydantic_ai import Agent
 from pydantic_ai.models.openai import OpenAIModel
-from src.domains.agents.base import BaseAgent, AgentContext, register_agent
+from src.domains.agents.base import AgentContext, BaseAgent, register_agent
 from src.domains.agents.schemas import PermissionMode, StreamEvent, StreamEventType
-from src.domains.agents.task.prompts import TASK_SYSTEM_PROMPT, TASK_PLAN_MODE_PROMPT
+from src.domains.agents.task.prompts import TASK_PLAN_MODE_PROMPT, TASK_SYSTEM_PROMPT
 from src.ollama.provider import get_ollama_provider
 from src.shared.config import get_settings
-from src.shared.logging import logged, get_logger, trace_span
+from src.shared.logging import get_logger, logged, trace_span
 logger = get_logger(__name__)
@@ -61,7 +62,7 @@ def _summarize_result(result: str, max_len: int = 80) -> str:
    return result
-class TaskAgentImpl(BaseAgent):
+class TaskAgentImpl(BaseAgent[TaskContext]):
    """
    Full orchestrator agent for autonomous task execution.
@@ -127,8 +128,8 @@ class TaskAgentImpl(BaseAgent):
    def _register_tools(self, agent: Agent[TaskContext, str], mode: PermissionMode) -> None:
        """Register tools with the agent based on permission mode."""
        from src.domains.agents.task.tools_streaming import (
            register_task_tools_streaming,
            register_readonly_tools_streaming,
            register_task_tools_streaming,
        )
        if mode == PermissionMode.plan:
@@ -293,8 +294,16 @@ User request: {prompt}"""
                        message=f"Retrying (attempt {retries + 1})..."
                    )
-                # Run agent in background task so we can yield events
+                # Run agent in background task so we can yield events.
-                async def run_agent() -> str:
+                #
                # full_prompt and ctx are bound as defaults rather than closed
                # over. Today the closure is safe either way — the task is
                # awaited below before `continue` reaches the next iteration, so
                # neither name can be rebound while it is pending. Binding them
                # keeps that true if the await ever moves, which is the failure
                # B023 is warning about and the kind that surfaces as one agent
                # silently running another's prompt.
                async def run_agent(full_prompt: str = full_prompt, ctx: TaskContext = ctx) -> str:
                    try:
                        result = await agent.run(full_prompt, deps=ctx)
                        return result.output
@@ -314,7 +323,7 @@ User request: {prompt}"""
                                timeout=0.1
                            )
                            yield event
-                        except asyncio.TimeoutError:
+                        except TimeoutError:
                            # No events, check if agent is done
                            continue
@@ -346,10 +355,8 @@ User request: {prompt}"""
                    # Cancel agent if still running
                    if not agent_task.done():
                        agent_task.cancel()
-                        try:
+                        with contextlib.suppress(asyncio.CancelledError):
                            await agent_task
                        except asyncio.CancelledError:
                            pass
                    return
            # Yield response in chunks for streaming feel
@@ -7,10 +7,10 @@ The Task agent has access to tools based on permission mode:
 """
 from pydantic_ai import Agent, RunContext
-from src.domains.agents.base import AgentContext
+from src.domains.agents.task.agent import TaskContext
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.file.glob import GlobFilesTool
 from src.domains.tools.file.edit import EditFileTool
 from src.domains.tools.file.glob import GlobFilesTool
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.file.write import WriteFileTool
 from src.domains.tools.search.grep import GrepContentTool
 from src.domains.tools.search.web import WebSearchTool
@@ -18,11 +18,11 @@ from src.domains.tools.shell.bash import BashReadOnlyTool
 from src.domains.tools.shell.bash_full import BashTool
-def _register_read_file(agent: Agent[AgentContext, str]) -> None:
+def _register_read_file(agent: Agent[TaskContext, str]) -> None:
    """Register read_file tool."""
    @agent.tool
    async def read_file(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[TaskContext],
        file_path: str,
        offset: int = 0,
        limit: int = 2000
@@ -48,11 +48,11 @@ def _register_read_file(agent: Agent[AgentContext, str]) -> None:
        return result.to_string()
-def _register_glob_files(agent: Agent[AgentContext, str]) -> None:
+def _register_glob_files(agent: Agent[TaskContext, str]) -> None:
    """Register glob_files tool."""
    @agent.tool
    async def glob_files(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[TaskContext],
        pattern: str,
        path: str | None = None,
        limit: int = 100
@@ -82,11 +82,11 @@ def _register_glob_files(agent: Agent[AgentContext, str]) -> None:
        return result.to_string()
-def _register_grep_content(agent: Agent[AgentContext, str]) -> None:
+def _register_grep_content(agent: Agent[TaskContext, str]) -> None:
    """Register grep_content tool."""
    @agent.tool
    async def grep_content(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[TaskContext],
        pattern: str,
        path: str | None = None,
        file_glob: str | None = None,
@@ -118,11 +118,11 @@ def _register_grep_content(agent: Agent[AgentContext, str]) -> None:
        return result.to_string()
-def _register_bash_readonly(agent: Agent[AgentContext, str]) -> None:
+def _register_bash_readonly(agent: Agent[TaskContext, str]) -> None:
    """Register bash_readonly tool."""
    @agent.tool
    async def bash_readonly(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[TaskContext],
        command: str,
        cwd: str | None = None,
        timeout: int = 30
@@ -156,11 +156,11 @@ def _register_bash_readonly(agent: Agent[AgentContext, str]) -> None:
        return result.to_string()
-def _register_spawn_agent(agent: Agent[AgentContext, str], readonly_only: bool = False) -> None:
+def _register_spawn_agent(agent: Agent[TaskContext, str], readonly_only: bool = False) -> None:
    """Register spawn_agent tool."""
    @agent.tool
    async def spawn_agent(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[TaskContext],
        agent_type: str,
        prompt: str,
        working_dir: str | None = None
@@ -212,7 +212,7 @@ def _register_spawn_agent(agent: Agent[AgentContext, str], readonly_only: bool =
            return f"Sub-agent error: {e}"
-def register_readonly_tools(agent: Agent[AgentContext, str]) -> None:
+def register_readonly_tools(agent: Agent[TaskContext, str]) -> None:
    """
    Register read-only tools with the agent.
@@ -227,7 +227,7 @@ def register_readonly_tools(agent: Agent[AgentContext, str]) -> None:
    _register_spawn_agent(agent, readonly_only=True)
-def register_task_tools(agent: Agent[AgentContext, str]) -> None:
+def register_task_tools(agent: Agent[TaskContext, str]) -> None:
    """
    Register all tools with the Task agent.
@@ -247,7 +247,7 @@ def register_task_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def edit_file(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[TaskContext],
        file_path: str,
        old_string: str,
        new_string: str,
@@ -281,7 +281,7 @@ def register_task_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def write_file(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[TaskContext],
        file_path: str,
        content: str
    ) -> str:
@@ -308,7 +308,7 @@ def register_task_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def bash(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[TaskContext],
        command: str,
        cwd: str | None = None,
        timeout: int = 60
@@ -350,7 +350,7 @@ def register_task_tools(agent: Agent[AgentContext, str]) -> None:
    @agent.tool
    async def web_search(
-        ctx: RunContext[AgentContext],
+        ctx: RunContext[TaskContext],
        query: str,
        num_results: int = 5,
        categories: str | None = None
@@ -9,9 +9,9 @@ from pydantic_ai import Agent, RunContext
 from src.domains.agents.base import AgentContext
 from src.domains.agents.schemas import StreamEvent, StreamEventType
 from src.domains.agents.task.agent import TaskContext
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.file.glob import GlobFilesTool
 from src.domains.tools.file.edit import EditFileTool
 from src.domains.tools.file.glob import GlobFilesTool
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.file.write import WriteFileTool
 from src.domains.tools.search.grep import GrepContentTool
 from src.domains.tools.search.web import WebSearchTool
@@ -11,6 +11,6 @@ from src.domains.conversations.service import ConversationService
 __all__ = [
    "Conversation",
    "Message",
    "ConversationService",
    "Message",
 ]
@@ -20,7 +20,7 @@ from src.domains.conversations.schemas import (
 )
 from src.domains.conversations.service import ConversationService
 from src.shared.auth import require_auth
-from src.shared.logging import logged, get_logger
+from src.shared.logging import get_logger, logged
 logger = get_logger(__name__)
@@ -170,7 +170,7 @@ async def add_message(
        logger.exception(f"Agent response failed: {e}")
        raise HTTPException(
            status_code=500,
-            detail=f"Agent error: {str(e)}"
+            detail=f"Agent error: {e!s}"
        )
    # Add assistant message
@@ -6,7 +6,6 @@ from uuid import UUID
 from pydantic import BaseModel, Field
 # === Request Schemas ===
 class CreateConversationRequest(BaseModel):
@@ -5,7 +5,7 @@ Handles CRUD operations, context building, and summarization triggers.
 """
 from uuid import UUID
-from sqlalchemy import select, func
+from sqlalchemy import func, select
 from sqlalchemy.ext.asyncio import AsyncSession
 from sqlalchemy.orm import selectinload
@@ -6,9 +6,9 @@ main.py only includes this root_router.
 """
 from fastapi import APIRouter
 from src.domains.health.router import router as health_router
 from src.domains.agents.router import router as agents_router
 from src.domains.conversations.router import router as conversations_router
 from src.domains.health.router import router as health_router
 # from src.domains.auth.router import router as auth_router
 # from src.domains.tools.router import router as tools_router
@@ -4,19 +4,19 @@ Tool implementations for agent use.
 All tools inherit from BaseTool and return ToolResult.
 """
 from src.domains.tools.base import BaseTool, ToolResult
-from src.domains.tools.file import ReadFileTool, GlobFilesTool, EditFileTool, WriteFileTool
+from src.domains.tools.file import EditFileTool, GlobFilesTool, ReadFileTool, WriteFileTool
 from src.domains.tools.search import GrepContentTool, WebSearchTool
 from src.domains.tools.shell import BashReadOnlyTool, BashTool
 __all__ = [
    "BaseTool",
    "ToolResult",
    "ReadFileTool",
    "GlobFilesTool",
    "EditFileTool",
    "WriteFileTool",
    "GrepContentTool",
    "WebSearchTool",
    "BashReadOnlyTool",
    "BashTool",
    "EditFileTool",
    "GlobFilesTool",
    "GrepContentTool",
    "ReadFileTool",
    "ToolResult",
    "WebSearchTool",
    "WriteFileTool",
 ]
@@ -32,10 +32,7 @@ class ToolResult:
        if not self.success:
            return f"ERROR: {self.error}"
-        if isinstance(self.data, str):
+        content = self.data if isinstance(self.data, str) else str(self.data)
            content = self.data
        else:
            content = str(self.data)
        if len(content) > max_length:
            self.truncated = True
@@ -90,6 +87,21 @@ class BaseTool(ABC):
        """
        Execute the tool with given arguments.
        Note on the `# type: ignore[override]` each implementation carries.
        Every tool narrows this to its own named parameters — read_file takes
        file_path/offset/limit, bash takes command/timeout — which mypy reports
        as an LSP violation, and strictly it is: a caller holding a BaseTool
        could call .execute(anything=1) and no implementation would accept it.
        Nothing does. Checked: no reference anywhere in this package is typed as
        BaseTool, and every call site constructs the concrete tool and passes its
        specific arguments. What this abstract method buys is the runtime
        guarantee that a tool without an execute cannot be instantiated, and that
        is worth keeping.
        The suppressions are per-site rather than a disable_error_code for the
        whole package, so a future override that IS unsound still gets caught.
        Returns:
            ToolResult with success status and data or error
        """
@@ -1,9 +1,9 @@
 """
 File operation tools.
 """
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.file.glob import GlobFilesTool
 from src.domains.tools.file.edit import EditFileTool
 from src.domains.tools.file.glob import GlobFilesTool
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.file.write import WriteFileTool
-__all__ = ["ReadFileTool", "GlobFilesTool", "EditFileTool", "WriteFileTool"]
+__all__ = ["EditFileTool", "GlobFilesTool", "ReadFileTool", "WriteFileTool"]
@@ -2,11 +2,12 @@
 File editing tool with find-and-replace functionality.
 """
 import difflib
 import aiofiles
 from pathlib import Path
 import aiofiles
 from src.domains.tools.base import BaseTool, ToolResult
-from src.shared.logging import logged, get_logger
+from src.shared.logging import get_logger, logged
 logger = get_logger(__name__)
@@ -95,7 +96,7 @@ Examples:
        return "".join(diff)
    @logged()
-    async def execute(
+    async def execute(  # type: ignore[override]  # see BaseTool.execute
        self,
        file_path: str,
        old_string: str,
@@ -147,15 +148,15 @@ Examples:
        try:
            # Read file content
-            async with aiofiles.open(path, 'r', encoding='utf-8', errors='replace') as f:
+            async with aiofiles.open(path, encoding='utf-8', errors='replace') as f:
                content = await f.read()
            # Check if old_string exists
            count = content.count(old_string)
            if count == 0:
                return self._error(
-                    f"old_string not found in file. "
+                    "old_string not found in file. "
-                    f"Make sure to match exact whitespace and indentation."
+                    "Make sure to match exact whitespace and indentation."
                )
            # Check uniqueness if replace_all is False
@@ -6,7 +6,7 @@ from pathlib import Path
 from src.domains.tools.base import BaseTool, ToolResult
 from src.domains.tools.gitignore import filter_gitignored
-from src.shared.logging import logged, get_logger
+from src.shared.logging import get_logger, logged
 logger = get_logger(__name__)
@@ -63,7 +63,7 @@ IMPORTANT:
        self.honor_gitignore = honor_gitignore
    @logged()
-    async def execute(
+    async def execute(  # type: ignore[override]  # see BaseTool.execute
        self,
        pattern: str,
        path: str | None = None,
@@ -1,11 +1,12 @@
 """
 File reading tool with line number formatting and sandboxing.
 """
 import aiofiles
 from pathlib import Path
 import aiofiles
 from src.domains.tools.base import BaseTool, ToolResult
-from src.shared.logging import logged, get_logger
+from src.shared.logging import get_logger, logged
 logger = get_logger(__name__)
@@ -55,7 +56,7 @@ IMPORTANT:
        self.max_line_length = max_line_length
    @logged()
-    async def execute(
+    async def execute(  # type: ignore[override]  # see BaseTool.execute
        self,
        file_path: str,
        offset: int = 0,
@@ -87,7 +88,7 @@ IMPORTANT:
            return self._error(f"Not a file: {file_path}")
        try:
-            async with aiofiles.open(path, 'r', encoding='utf-8', errors='replace') as f:
+            async with aiofiles.open(path, encoding='utf-8', errors='replace') as f:
                content = await f.read()
            lines = content.splitlines()
@@ -1,11 +1,12 @@
 """
 File writing tool for creating and overwriting files.
 """
 import aiofiles
 from pathlib import Path
 import aiofiles
 from src.domains.tools.base import BaseTool, ToolResult
-from src.shared.logging import logged, get_logger
+from src.shared.logging import get_logger, logged
 logger = get_logger(__name__)
@@ -57,7 +58,7 @@ Examples:
        self.max_content_size = max_content_size
    @logged()
-    async def execute(
+    async def execute(  # type: ignore[override]  # see BaseTool.execute
        self,
        file_path: str,
        content: str
@@ -90,10 +90,7 @@ class GitignoreFilter:
        # Make path relative to root for matching
        try:
-            if path.is_absolute():
+            rel_path = path.resolve().relative_to(self.root_dir) if path.is_absolute() else path
                rel_path = path.resolve().relative_to(self.root_dir)
            else:
                rel_path = path
        except ValueError:
            # Path is not under root_dir, don't filter
            return False
@@ -7,7 +7,7 @@ from typing import Literal
 from src.domains.tools.base import BaseTool, ToolResult
 from src.domains.tools.gitignore import filter_gitignored
-from src.shared.logging import logged, get_logger
+from src.shared.logging import get_logger, logged
 logger = get_logger(__name__)
@@ -70,7 +70,7 @@ IMPORTANT:
        self.honor_gitignore = honor_gitignore
    @logged()
-    async def execute(
+    async def execute(  # type: ignore[override]  # see BaseTool.execute
        self,
        pattern: str,
        path: str | None = None,
@@ -3,12 +3,13 @@ Web search tool using SearXNG.
 """
 from dataclasses import dataclass
 from datetime import datetime
 from typing import Any
 import httpx
 from src.domains.tools.base import BaseTool, ToolResult
 from src.shared.config import get_settings
-from src.shared.logging import logged, get_logger
+from src.shared.logging import get_logger, logged
 from src.shared.retry import retry_async
 logger = get_logger(__name__)
@@ -91,10 +92,13 @@ IMPORTANT:
                params=params,
            )
            response.raise_for_status()
-            return response.json()
+            # httpx types .json() as Any. Naming the shape here keeps the Any from
        # travelling into every caller of this method.
        payload: dict[Any, Any] = response.json()
        return payload
    @logged()
-    async def execute(
+    async def execute(  # type: ignore[override]  # see BaseTool.execute
        self,
        query: str,
        num_results: int = 5,
@@ -8,7 +8,7 @@ import shlex
 from pathlib import Path
 from src.domains.tools.base import BaseTool, ToolResult
-from src.shared.logging import logged, get_logger
+from src.shared.logging import get_logger, logged
 logger = get_logger(__name__)
@@ -115,7 +115,7 @@ Examples:
        self.max_output_size = max_output_size
    @logged()
-    async def execute(
+    async def execute(  # type: ignore[override]  # see BaseTool.execute
        self,
        command: str,
        cwd: str | None = None,
@@ -190,7 +190,7 @@ Examples:
                exit_code=proc.returncode
            )
-        except asyncio.TimeoutError:
+        except TimeoutError:
            return self._error(f"Command timed out after {timeout} seconds")
        except Exception as e:
            logger.exception(f"Error executing command: {command}")
@@ -8,7 +8,7 @@ import shlex
 from pathlib import Path
 from src.domains.tools.base import BaseTool, ToolResult
-from src.shared.logging import logged, get_logger
+from src.shared.logging import get_logger, logged
 logger = get_logger(__name__)
@@ -153,7 +153,7 @@ Examples:
        self.max_output_size = max_output_size
    @logged()
-    async def execute(
+    async def execute(  # type: ignore[override]  # see BaseTool.execute
        self,
        command: str,
        cwd: str | None = None,
@@ -228,7 +228,7 @@ Examples:
                exit_code=proc.returncode
            )
-        except asyncio.TimeoutError:
+        except TimeoutError:
            return self._error(f"Command timed out after {timeout} seconds")
        except Exception as e:
            logger.exception(f"Error executing command: {command}")
@@ -340,7 +340,7 @@ Examples:
        # Handle git with flags before subcommand (e.g., git -C path status)
        if git_subcommand.startswith("-"):
            # Find the actual subcommand
-            for i, token in enumerate(tokens[2:], 2):
+            for _i, token in enumerate(tokens[2:], 2):
                if not token.startswith("-"):
                    git_subcommand = token
                    break
@@ -54,17 +54,54 @@ class _SanitizedAsyncOpenAI(AsyncOpenAI):
        super().__init__(api_key="ollama", **kwargs)
    @property
-    def chat(self) -> "_SanitizedChat":
+    def chat(self) -> "_SanitizedChat":  # type: ignore[override]
-        """Return sanitized chat interface."""
+        """Return sanitized chat interface.
        Deliberately incompatible with AsyncOpenAI.chat, which is a Chat
        resource. Replacing it is the entire mechanism of this class: Ollama
        rejects assistant messages carrying content: null alongside tool_calls,
        so every completion has to pass through the sanitiser. Typing it as the
        parent's Chat would describe an object this class does not return.
        The suppression is on this member alone; the rest of the client keeps
        its inherited types.
        """
        return _SanitizedChat(self)
 def _parent_chat(client: AsyncOpenAI) -> Any:
    """Get AsyncOpenAI's own `chat`, bypassing the subclass override.
    This read the descriptor's `.fget` until 2026-08-11, which is the property
    API. openai made `chat` a functools.cached_property, whose getter is `.func`,
    so the call raised AttributeError the moment anything touched `.chat` — that
    is, on the first completion any agent tried to make. Verified broken in the
    running container on openai 2.46.0 as well as locally on 2.15.0.
    It went unnoticed because the endpoints that reach it had served no requests
    in 30 days, and because the line carried a bare `# type: ignore` that
    suppressed exactly the complaint that would have flagged it.
    Reading whichever getter the descriptor actually exposes keeps this working
    across that change and the reverse of it, and raises something legible if
    openai adopts a third shape.
    """
    descriptor = AsyncOpenAI.__dict__["chat"]
    getter = getattr(descriptor, "func", None) or getattr(descriptor, "fget", None)
    if getter is None:  # pragma: no cover - defensive
        raise TypeError(
            f"AsyncOpenAI.chat is a {type(descriptor).__name__} with neither "
            "'func' nor 'fget'; the sanitising wrapper needs updating"
        )
    return getter(client)
 class _SanitizedChat:
    """Chat interface wrapper with sanitized completions."""
    def __init__(self, client: _SanitizedAsyncOpenAI):
        self._client = client
-        self._original_chat = AsyncOpenAI.chat.fget(client)  # type: ignore
+        self._original_chat = _parent_chat(client)
    @property
    def completions(self) -> "_SanitizedCompletions":
@@ -110,8 +147,10 @@ def _sanitize_messages(messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
        msg_copy = dict(msg)
        # Fix null content in assistant messages with tool calls
-        if msg_copy.get("role") == "assistant":
+        if (
-            if msg_copy.get("content") is None and msg_copy.get("tool_calls"):
+            msg_copy.get("role") == "assistant"
            and msg_copy.get("content") is None and msg_copy.get("tool_calls")
        ):
                msg_copy["content"] = ""
                logger.debug(
                    f"Sanitized null content, tool_calls={len(msg_copy['tool_calls'])}"
@@ -64,7 +64,7 @@ class Settings(BaseSettings):
    # LLM - Ollama (always hot in VRAM on tower-of-joy)
    ollama_url: str = "http://192.168.86.149:11434"
-    ollama_agent_model: str = "mistral-nemo-large:latest"
+    ollama_agent_model: str = "gemma4:e2b"
    ollama_embed_model: str = "nomic-embed-text:latest"
    # Auth - Tatlock integration
@@ -16,6 +16,7 @@ from collections.abc import Callable
 from contextvars import ContextVar, Token
 from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Any, ParamSpec, TypeVar, cast
 from uuid import uuid4
 # === Trace Context ===
@@ -80,12 +81,21 @@ def get_logger(name: str) -> logging.Logger:
 # === Decorator ===
 # @logged wraps ~24 functions across this package. Untyped, its decorator
 # erased every one of their signatures, so mypy saw `Any` coming back from
 # annotated functions like `ToolResult.execute() -> ToolResult`. That surfaced
 # as 33 no-any-return errors scattered across the tools and agents — each
 # reading like a local annotation slip, all of them this one decorator.
 P = ParamSpec("P")
 R = TypeVar("R")
 def logged(
    logger: logging.Logger | None = None,
    slow_threshold_ms: float = 100.0,
    warn_threshold_ms: float = 500.0,
    include_args: bool = False,
-):
+) -> Callable[[Callable[P, R]], Callable[P, R]]:
    """
    Decorator for automatic function logging with temporal benchmarking.
@@ -102,7 +112,7 @@ def logged(
        @logged(slow_threshold_ms=50, warn_threshold_ms=200)
        def critical_path(): ...
    """
-    def decorator(func: Callable):
+    def decorator(func: Callable[P, R]) -> Callable[P, R]:
        nonlocal logger
        if logger is None:
            logger = logging.getLogger(func.__module__)
@@ -140,7 +150,7 @@ def logged(
                logger.debug(f"[{tid}] {func_name} completed in {duration:.2f}ms")
        @functools.wraps(func)
-        async def async_wrapper(*args, **kwargs):
+        async def async_wrapper(*args: P.args, **kwargs: P.kwargs) -> Any:
            span = _create_span()
            token = _current_span.set(span)
@@ -150,7 +160,7 @@ def logged(
                logger.debug(f"[{span.trace_id[:8]}] -> {func_name}")
            try:
-                result = await func(*args, **kwargs)
+                result = await cast(Any, func(*args, **kwargs))
                _log_completion(span)
                return result
            except Exception as e:
@@ -160,7 +170,7 @@ def logged(
                _current_span.reset(token)
        @functools.wraps(func)
-        def sync_wrapper(*args, **kwargs):
+        def sync_wrapper(*args: P.args, **kwargs: P.kwargs) -> R:
            span = _create_span()
            token = _current_span.set(span)
@@ -179,7 +189,11 @@ def logged(
            finally:
                _current_span.reset(token)
-        return async_wrapper if asyncio.iscoroutinefunction(func) else sync_wrapper
+        # The branch is chosen at decoration time; mypy cannot narrow R to a
        # coroutine on the strength of iscoroutinefunction, so the union is
        # asserted here once instead of at every call site.
        chosen = async_wrapper if asyncio.iscoroutinefunction(func) else sync_wrapper
        return cast(Callable[P, R], chosen)
    return decorator
@@ -79,7 +79,7 @@ def calculate_backoff(
        Delay in seconds
    """
    # Exponential backoff: base_delay * 2^attempt
-    delay = min(base_delay * (2 ** attempt), max_delay)
+    delay: float = min(base_delay * (2 ** attempt), max_delay)
    if jitter:
        # Add up to 25% random jitter
@@ -114,6 +114,11 @@ def with_retry(
                return response.json()
    """
    extra_exceptions = retryable_exceptions or ()
    # Bound to a named, typed tuple: mypy cannot verify that a star-unpacked
    # tuple in an `except` clause holds exception classes, and reports it as
    # "exception type must be derived from BaseException" — which reads like a
    # real defect rather than an inference limit.
    retry_on: tuple[type[Exception], ...] = (*RETRYABLE_EXCEPTIONS, *extra_exceptions)
    def decorator(func: Callable[..., Awaitable[T]]) -> Callable[..., Awaitable[T]]:
        @wraps(func)
@@ -124,7 +129,7 @@ def with_retry(
                try:
                    return await func(*args, **kwargs)
-                except (*RETRYABLE_EXCEPTIONS, *extra_exceptions) as e:
+                except retry_on as e:
                    last_exception = e
                    should_retry = True
@@ -145,7 +150,7 @@ def with_retry(
                    await asyncio.sleep(delay)
                elif not should_retry:
                    # Non-retryable HTTP error
-                    raise last_exception  # type: ignore
+                    raise last_exception
            # All retries exhausted
            logger.error(
@@ -21,7 +21,6 @@ from httpx import ASGITransport, AsyncClient
 from src.main import app
 # =============================================================================
 # Command Line Options
 # =============================================================================
@@ -4,8 +4,9 @@ Tests for agent REST API endpoints.
 Includes integration tests that verify real code paths work correctly
 without over-mocking (only LLM calls are mocked).
 """
 from unittest.mock import AsyncMock, MagicMock, patch
 import pytest
 from unittest.mock import AsyncMock, patch, MagicMock
 from src.domains.agents.schemas import PermissionMode
@@ -312,9 +313,10 @@ class TestAgentMethodSignatures:
    def test_task_agent_run_accepts_mode(self):
        """Verify TaskAgentImpl.run() accepts mode parameter."""
        from src.domains.agents.task.agent import TaskAgentImpl
        import inspect
        from src.domains.agents.task.agent import TaskAgentImpl
        sig = inspect.signature(TaskAgentImpl.run)
        params = list(sig.parameters.keys())
@@ -325,9 +327,10 @@ class TestAgentMethodSignatures:
    def test_task_agent_run_stream_accepts_mode(self):
        """Verify TaskAgentImpl.run_stream() accepts mode parameter."""
        from src.domains.agents.task.agent import TaskAgentImpl
        import inspect
        from src.domains.agents.task.agent import TaskAgentImpl
        sig = inspect.signature(TaskAgentImpl.run_stream)
        params = list(sig.parameters.keys())
@@ -337,9 +340,10 @@ class TestAgentMethodSignatures:
    def test_trace_span_signature(self):
        """Verify trace_span only accepts expected parameters."""
        from src.shared.logging import trace_span
        import inspect
        from src.shared.logging import trace_span
        sig = inspect.signature(trace_span.__init__)
        params = list(sig.parameters.keys())
@@ -3,15 +3,14 @@ Tests for conversations domain.
 Tests conversation CRUD, context building, and API endpoints.
 """
 import pytest
 from uuid import uuid4
 import pytest
 from src.domains.conversations.models import Conversation, Message
 from src.domains.conversations.schemas import (
    CreateConversationRequest,
    AddMessageRequest,
-    ConversationResponse,
+    CreateConversationRequest,
    MessageResponse,
 )
@@ -173,9 +172,10 @@ class TestConversationService:
    @pytest.mark.anyio
    async def test_context_prompt_no_history(self):
        """Test building context prompt with no history."""
        from src.domains.conversations.service import ConversationService
        from unittest.mock import MagicMock
        from src.domains.conversations.service import ConversationService
        # Create mock session
        mock_session = MagicMock()
        service = ConversationService(mock_session)
@@ -190,10 +190,11 @@ class TestConversationService:
    @pytest.mark.anyio
    async def test_context_prompt_with_history(self):
        """Test building context prompt with message history."""
        from src.domains.conversations.service import ConversationService
        from src.domains.conversations.models import Message
        from unittest.mock import MagicMock
        from src.domains.conversations.models import Message
        from src.domains.conversations.service import ConversationService
        mock_session = MagicMock()
        service = ConversationService(mock_session)
@@ -221,10 +222,11 @@ class TestConversationService:
    @pytest.mark.anyio
    async def test_context_prompt_with_summary(self):
        """Test building context prompt with summary message."""
        from src.domains.conversations.service import ConversationService
        from src.domains.conversations.models import Message
        from unittest.mock import MagicMock
        from src.domains.conversations.models import Message
        from src.domains.conversations.service import ConversationService
        mock_session = MagicMock()
        service = ConversationService(mock_session)
@@ -253,8 +255,8 @@ class TestSummarization:
    def test_format_messages_for_summary(self):
        """Test formatting messages for summarization."""
        from src.domains.conversations.summarize import format_messages_for_summary
        from src.domains.conversations.models import Message
        from src.domains.conversations.summarize import format_messages_for_summary
        messages = [
            Message(
@@ -276,8 +278,8 @@ class TestSummarization:
    def test_format_messages_with_summary(self):
        """Test formatting messages that include a summary."""
        from src.domains.conversations.summarize import format_messages_for_summary
        from src.domains.conversations.models import Message
        from src.domains.conversations.summarize import format_messages_for_summary
        messages = [
            Message(
@@ -6,8 +6,8 @@ from pathlib import Path
 import pytest
 from src.domains.tools.gitignore import GitignoreFilter, filter_gitignored
 from src.domains.tools.file.glob import GlobFilesTool
 from src.domains.tools.gitignore import GitignoreFilter, filter_gitignored
 from src.domains.tools.search.grep import GrepContentTool
@@ -0,0 +1,55 @@
 """The sanitising Ollama client must actually be reachable.
 src/ollama/provider.py exists to work around Ollama rejecting assistant
 messages that carry `content: null` alongside `tool_calls`. On 2026-08-11 it
 raised AttributeError the moment anything touched `.chat`: it fetched the
 parent's getter via `AsyncOpenAI.chat.fget`, and openai had made `chat` a
 functools.cached_property, whose getter is `.func`.
 Nothing caught it. The line carried a bare `# type: ignore`, so mypy stayed
 quiet, and the endpoints that reach this code had served no requests in 30 days,
 so no user hit it either. The mitigation was dead and everything looked fine.
 These tests exercise the path rather than the types, because the failure was a
 runtime attribute lookup that no annotation would have caught.
 """
 from openai import AsyncOpenAI
 from src.ollama.provider import _parent_chat, _SanitizedAsyncOpenAI, get_ollama_provider
 class TestSanitizedClientIsReachable:
    def test_chat_can_be_accessed(self):
        """The regression: this raised AttributeError, not a type error."""
        client = _SanitizedAsyncOpenAI(base_url="http://localhost:11434/v1")
        chat = client.chat
        assert chat is not None
        assert chat.completions is not None
    def test_provider_reaches_completions(self):
        """The full chain an agent request walks, short of the network call."""
        provider = get_ollama_provider()
        assert provider._openai_client.chat.completions is not None
    def test_parent_lookup_survives_either_descriptor_shape(self):
        """openai has used both property and cached_property for `chat`.
        Whichever it is, the parent's own getter must be found — the previous
        code hardcoded `.fget` and broke on the switch to cached_property.
        """
        descriptor = AsyncOpenAI.__dict__["chat"]
        assert hasattr(descriptor, "func") or hasattr(descriptor, "fget"), (
            "AsyncOpenAI.chat exposes neither getter; _parent_chat needs updating"
        )
        client = _SanitizedAsyncOpenAI(base_url="http://localhost:11434/v1")
        assert _parent_chat(client) is not None
    def test_parent_chat_is_not_the_override(self):
        """It must return openai's Chat, not recurse into the subclass property.
        Returning the subclass's own `chat` would be infinite recursion, and the
        sanitiser would wrap itself instead of the real completions resource.
        """
        client = _SanitizedAsyncOpenAI(base_url="http://localhost:11434/v1")
        assert type(_parent_chat(client)).__name__ != "_SanitizedChat"
@@ -6,7 +6,7 @@ Tests registration, API endpoints, and tool restrictions.
 import pytest
 from src.domains.agents.base import get_agent, list_agents
-from src.domains.agents.plan import plan_agent, PlanAgentImpl
+from src.domains.agents.plan import PlanAgentImpl, plan_agent
 class TestPlanAgentRegistration:
@@ -1,17 +1,16 @@
 """
 Tests for retry utilities.
 """
 import pytest
 from unittest.mock import AsyncMock, patch
 import httpx
 import pytest
 from src.shared.retry import (
-    with_retry,
+    calculate_backoff,
    retry_async,
    is_retryable_exception,
    is_retryable_http_status,
-    calculate_backoff,
+    retry_async,
    with_retry,
 )
@@ -6,10 +6,10 @@ from pathlib import Path
 import pytest
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.file.write import WriteFileTool
 from src.domains.tools.file.edit import EditFileTool
 from src.domains.tools.file.glob import GlobFilesTool
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.file.write import WriteFileTool
 from src.domains.tools.shell.bash_full import BashTool
@@ -275,5 +275,5 @@ class TestResourceLimits:
        assert result.success
        # Should only return 5 files
-        lines = [l for l in result.data.strip().split("\n") if l]
+        lines = [line for line in result.data.strip().split("\n") if line]
        assert len(lines) <= 5
@@ -3,11 +3,11 @@ Tests for the Task agent.
 Tests registration, API endpoints, tool access, and spawn_agent functionality.
 """
 import pytest
 from unittest.mock import AsyncMock, patch
 from src.domains.agents.base import get_agent, list_agents
-from src.domains.agents.task import task_agent, TaskAgentImpl
+from src.domains.agents.task import TaskAgentImpl, task_agent
 class TestTaskAgentRegistration:
@@ -90,39 +90,28 @@ class TestTaskAgentTools:
 class TestSpawnAgentTool:
    """Tests for spawn_agent orchestration functionality."""
    @pytest.mark.skip(
        reason="never finished — the body built a mock context and then asserted "
               "nothing, so it counted as a passing test while verifying nothing"
    )
    @pytest.mark.anyio
    async def test_spawn_explore_agent(self):
-        """Test spawning an explore agent."""
+        """Spawning an explore agent should delegate to the explore agent.
        from src.domains.agents.task.tools import register_task_tools
        from src.domains.agents.base import AgentContext
        from pydantic_ai import Agent, RunContext
        from unittest.mock import MagicMock
-        # Create a mock context
+        The scaffolding that used to sit here — a MagicMock RunContext, an
-        ctx = MagicMock(spec=RunContext)
+        AgentContext with a /tmp working dir, and a patch of
-        ctx.deps = AgentContext(
+        src.domains.agents.base.get_agent — ran and then stopped at the comment
-            working_dir="/tmp",
+        "For now, verify the explore agent would be called correctly". There was
-            allowed_paths=["/tmp"],
+        no assertion, so it passed unconditionally.
            timeout_seconds=30
        )
-        # Mock the explore agent
+        Removed rather than tidied: ruff flagged its imports as unused, and
-        with patch("src.domains.agents.base.get_agent") as mock_get_agent:
+        deleting those would have made the test look clean while leaving it
-            mock_explore = AsyncMock()
+        hollow. git history has the setup for whoever finishes this.
-            mock_explore.run = AsyncMock(return_value="Found 5 Python files")
+        """
            mock_get_agent.return_value = mock_explore
            # Import and call spawn_agent directly
            from src.domains.agents.task import tools
            # We need to test the actual tool function
            # For now, verify the explore agent would be called correctly
    @pytest.mark.anyio
    async def test_spawn_unknown_agent_returns_error(self):
        """Test that spawning unknown agent type returns error."""
        from src.domains.agents.base import AgentContext
        from unittest.mock import MagicMock
        from pydantic_ai import RunContext
        # We can't easily test the tool directly, but we can verify
        # the agent type validation logic
@@ -1,9 +1,8 @@
 """
 Tests for token counting utilities.
 """
 import pytest
-from src.shared.tokens import count_tokens, count_message_tokens, estimate_tokens
+from src.shared.tokens import count_message_tokens, count_tokens, estimate_tokens
 class TestTokenCounting:
@@ -6,8 +6,8 @@ from pathlib import Path
 import pytest
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.file.glob import GlobFilesTool
 from src.domains.tools.file.read import ReadFileTool
 from src.domains.tools.search.grep import GrepContentTool
 from src.domains.tools.shell.bash import BashReadOnlyTool
@@ -1,8 +1,9 @@
 """
 Tests for WebSearchTool.
 """
 from unittest.mock import AsyncMock, MagicMock, patch
 import pytest
 from unittest.mock import AsyncMock, patch, MagicMock
 from src.domains.tools.search.web import WebSearchTool
Author	SHA1	Message	Date
jpmschweitzerandClaude	7172927a79	release api/v1.1.0 Build and Push API / release (push) Successful in 2s Details Build and Push API / build (push) Successful in 2m17s Details Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-11 16:30:09 +02:00
jpmschweitzerandClaude	3e495daa73	fix(webber-api): clear mypy, and the dead code it was covering for 55 errors to zero. Nearly all of them traced back to two causes rather than 55. THE DECORATOR. @logged wraps ~24 functions across this package and was declared `def decorator(func: Callable):` with no ParamSpec and no return annotation, so it erased the signature of everything it touched. ToolResult.execute() is annotated `-> ToolResult`; through the decorator it came back Any, and mypy reported 33 no-any-return errors spread across the tools and agents. Each looked like a local annotation slip. All of them were one decorator. Typed with ParamSpec/TypeVar; the async branch casts at the await rather than loosening R, because loosening R would put the Any straight back into every caller. THE MISSING TYPE PARAMETER. BaseAgent was not generic, so _create_agent returned a bare Agent — Agent[Any, Any] — and pydantic_ai then typed every run() result as Any. BaseAgent is now Generic[CtxT] bound to AgentContext, _agent is declared on the base instead of reached through hasattr, and the three tool-registration functions take their agent's real context type. tools_streaming.py already did this; the other three had not been updated. Eight `execute` overrides carry a targeted ignore rather than a package-wide disable_error_code. Every tool narrows the base's **kwargs to its own named parameters, which is a real LSP violation — but nothing anywhere is typed as BaseTool, and every call site constructs the concrete tool. The abstract method earns its place by making a tool without execute impossible to instantiate. The reasoning lives in BaseTool.execute's docstring; the per-site suppressions mean an override that IS unsound still gets caught. BaseAgent.run_stream widened to AsyncIterator[str \| StreamEvent], which is what callers already receive: task streams structured events, explore and plan stream strings, and the router branches on isinstance with a comment calling the string path legacy. The annotation now says what the code does. AND THE PART THAT MATTERS MORE THAN THE TYPES. Chasing the last error found that the Ollama sanitiser has been broken. It fetched the parent's chat getter with `AsyncOpenAI.chat.fget`, and openai made `chat` a functools.cached_property, whose getter is `.func`. Touching `.chat` raised AttributeError — meaning the content: null workaround that CLAUDE.md documents as live would have failed on the first completion any agent attempted. Confirmed in the running container (openai 2.46.0) as well as locally (2.15.0). Two things hid it. The line carried a bare `# type: ignore`, which suppressed precisely the complaint that would have caught it. And /agents/run and /agents/stream have served zero requests in 30 days, so nothing exercised the path. A mitigation can rot completely while every check stays green, if no check actually runs it. The lookup now reads whichever getter the descriptor exposes and raises a legible TypeError if openai adopts a third shape. tests/test_ollama_provider.py walks the chain an agent request walks, short of the network call — mutation-checked: all four fail against the old lookup. 215 passed, 23 skipped, plus the four new. mypy clean over 90 files. Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-11 16:27:51 +02:00
jpmschweitzerandClaude	eb3467d06a	fix(webber-api): clear ruff, and two things it was pointing at 97 findings to zero. Most were mechanical — 52 unsorted import blocks, 10 unsorted __all__, assorted pyupgrade and simplify hints. Two were not, and both were visible only because the lint made me look. `webber version` did not exist. src/cli/commands/version.py defines show_version(), main.py imported it, and the registration line was never written — the CLI exposed chat and explore only. The import carried `# noqa: F401`, which is what kept the omission quiet: someone marked the symptom as intentional instead of asking why it was unused. show_version is not redundant with the --version flag; it prints the resolved Ollama URL, model and debug state, which is the form worth having when something is misconfigured. Registered, and the suppression dropped because the import is now genuinely used. test_spawn_explore_agent asserted nothing. It built a mock RunContext, patched get_agent, and stopped at the comment "For now, verify the explore agent would be called correctly". It had been counted as a passing test. An AST sweep of all 238 test functions found it was the only one, which is worth knowing — the problem was contained, not systemic. It is now skipped with a reason, so it reports as unfinished rather than as passing. Reducing it rather than deleting its imports was the point: tidying the imports would have made a hollow test look clean. Two findings were false positives, and both are recorded rather than silently worked around: B023 flagged run_agent closing over full_prompt and ctx. Traced: agent_task is awaited at line 326 before `continue` reaches the next iteration, so neither name can be rebound while the closure is pending, and the exception path cancels and awaits too. Not a bug. Bound as defaults anyway, because that stays true if the await ever moves. I had called it a live bug before tracing it, which is the mistake Rule 5 exists for. RUF012 flagged `rules: list[ApprovalRule] = []` on ApprovalRuleSet. Its suggested fix — annotate ClassVar — would remove the field from the model. ApprovalRuleSet is a pydantic model and pydantic deep-copies defaults per instance; verified by constructing two and confirming their lists are distinct objects. Suppressed with that evidence in the comment. Ruff cannot see the pydantic base because BaseSchema is a local subclass of BaseModel. Also moved a stray `from src.shared.logging import ...` that had drifted below a function definition, and merged a nested if in the ollama provider. 215 passed, 23 skipped, unchanged except for the new skip. `webber version` exercised end to end. mypy is NOT addressed here and the gate still fails on it — 55 errors in 14 files, 35 of them no-any-return from pydantic_ai's untyped returns. That was hidden behind ruff, because the gate stops at the first failing stage. Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-11 15:05:02 +02:00
jpmschweitzerandClaude	9f5e331d11	build(ci): move the pre-push gate into the Makefile The hook carried ~50 lines of gitleaks logic and a comment explaining it was self-contained because "this repo has no Makefile". It has one now, so the reason is gone and the arrangement is backwards: a hook is a trigger, and logic belongs where it can be read, run by hand, and changed under review. .githooks/pre-push is now a byte-identical shim onto `make pre-push` in every repo in the workspace. The scan itself moves to ci/secrets.sh unchanged, and `make secrets` runs it on its own. The call surface is identical everywhere; what it runs is not, and should not be — each repo gates what it actually has. That is the point of standardising the name rather than the contents: nobody has to read a repo to find out how to check it. secrets runs first, deliberately. It is the only failure here that cannot be undone by fixing it afterwards — a failed lint costs another commit, a pushed credential is cached and indexed whether or not it is later deleted. Some of these gates fail today, on lint debt that predates them, and they are left wired anyway. The board was measured once and written down in T-56 instead of being worked around here. Narrowing each gate to whatever already passes would produce a gate that reports success for doing nothing, which is the failure this workspace keeps rediscovering. Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-09 18:57:22 +02:00
jpmschweitzerandClaude	225dc74385	ci(make): reserve exit 69 for "could not run" (D-26) Environment guards now exit 69 rather than 1, so a caller can tell a suite that could not start from one that ran and failed. The first toj test sweep reported "3 repositories failed" and none of the three had executed a test — two could not find go, one had no venv. That points the reader at the tests when the fault is in the environment. Only the environment guards change. A gitleaks finding, a failed test run and a vulncheck hit still exit 1, because those did run and did fail. Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-09 15:56:20 +02:00
jpmschweitzerandClaude	80d5cc1c3e	build: add the Makefile command surface (D-27) Every repo gets one at the root: help, plus test and lint where those exist. The point is that a target name means the same thing in every repo, so an agent or a person can act without reading the repo first. Paths resolve here rather than in callers (D-10). python3 on this host is 3.8 and cannot parse these sources, and a bare pytest or ruff resolves only in a login shell — so both are named explicitly through the venv, and a missing venv fails with the command to fix it rather than a bare no-such-file. Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-09 15:10:32 +02:00
jpmschweitzerandClaude	964c071d3f	chore(claude): pin PQL_VAULT per project so cwd stops choosing the vault pql is now a bare word on PATH, which removed the long incantation that had been forcing --vault into every call by habit. Convenience lowered the cost of the wrong thing without lowering the cost of the right one: a three-word pql ticket new targets whichever vault the cwd happens to sit in, and there are nine of them with colliding id sequences. PQL_VAULT in each project settings file makes the vault a property of the session rather than of the working directory — the same lesson Rule 3 records for git -C, applied to pql. Verified the env var overrides cwd discovery, that an explicit --vault still beats the env var, and that the harness hot-reloads it without a restart. This does not make provenance visible: no output says which vault answered, so a forgotten --vault still returns a well-formed answer about the wrong dataset. That remains T-37. Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-09 13:48:59 +02:00
jpmschweitzerandClaude	0883101b17	chore(claude): deny toj in the sub-repos toj is now on the global PATH as /usr/local/bin/toj, so its scope boundary had to stop being "the absolute path is inconvenient to type" and start being a rule. Its repo and settings verbs operate on the workspace root; run from inside this repo they answer about the wrong tree. Both spellings are denied, bare and absolute, because a deny with one spelling left open is decorative. Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-09 13:42:04 +02:00
jpmschweitzerandClaude	992ff8256e	ci: gate pushes on a gitleaks scan of the outgoing commits No repo here scanned for committed credentials. The hook is self-contained rather than delegating to a Makefile, because this repo has none and a hook reaching into a sibling repo breaks the moment this one is cloned elsewhere. Scans the outgoing range rather than full history: history carries settled findings — test fixtures, vendored third-party code — and a gate that fails on something unfixable gets bypassed within a week. Setting core.hooksPath means pql init must replant its replication shims into .githooks, which is why they are gitignored here alongside the tracked pre-push. Same layout pql itself uses. Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-09 12:46:55 +02:00
jpmschweitzerandClaude	b4d5c4d9b2	docs: correct the vault policy, and qualify workspace decision ids This repo's Work tracking section still described the reversed policy -- that tickets and decisions live in the workspace vault and this repo's trees stay empty. That was overturned the same day: repo vaults are standalone and a repo's work travels with a clone, because the changelog is committed. Every other repo was corrected at the time; this one was missed because the search for the offending phrase used a fixed string and the phrase happened to wrap across a line break here. Worth noting as a search failure rather than a writing one -- five files were checked, four matched, and the fifth was reported clean. Decision ids are also qualified now. They are per-vault sequences, so a bare D-15 here will mean this repo's D-15 the moment this repo records one; pql already holds D-1 through D-31 against the workspace's D-1 through D-21, all of them unrelated. Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-09 04:17:29 +02:00
jpmschweitzerandClaude	8eec3b68d6	docs: replace both AGENTS.md files with one CLAUDE.md One agent doc per repo, and it is CLAUDE.md. This repo carried two -- one at the root and one under webber-api/ -- which is the drift problem in its purest form: two documents, one subject, and no way to know which the last reader trusted. Written fresh rather than reformatted. README.md linked to webber-api/AGENTS.md, so that pointer moves with the file rather than dangling. The architecture section states the method used to establish what is live -- import the app inside the container and read sys.modules -- and then the case where that method fails here. src/domains/tools is absent from a cold snapshot and is entirely live: each agent's _register_tools imports its tool package from inside the method body, on every /agents/run. Absence from a snapshot taken before any request is served is a timing artifact, not evidence of death, and deleting on that basis would have removed the tool layer. Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-09 03:14:50 +02:00
jpmschweitzerandClaude	401c7f4e8c	chore: adopt the workspace agent-config baseline Commits a .claude/settings.json rather than leaving permissions to per-developer local state, and initialises a pql vault for this repo's tickets and internal decisions. Every git deny rule appears in both the `git <verb>` and `git * <verb>` forms. Only the second catches `git -C <path>`, and without it the whole deny list is decorative -- it looks like a policy and stops nothing. The allow list carries pql's absolute path alongside the bare name. pql is installed to ~/.local/bin, which is on the login PATH but not the one a non-interactive shell gets, so the bare-name rules match nothing on their own and every call would prompt anyway. .gitignore now covers .claude/settings.local.json, which is machine-local and must never be shared. `pql init` contributed the .pql/* rules with an exception for the changelog, which is the replication log of record and has to be committed for tickets to travel with a clone. Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-09 03:14:24 +02:00
jpmschweitzerandClaude	9612c7af05	docs(architecture): correct agent model to gemma4:e2b Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-07 14:59:12 +02:00
jpmschweitzerandClaude	9d58df85f3	fix(config): default agent model to gemma4:e2b mistral-nemo-large holds ~9.2 GB of the 11 GB card it shares with Speaches, which starves Whisper and breaks voice transcription. gemma4:e2b holds 1.9 GB and is faster. The deployed stack already overrides this via OLLAMA_AGENT_MODEL; this aligns the default so a deployment without that override does not reintroduce the contention. Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-07 14:58:57 +02:00
jpmschweitzerandClaude	3de96fe070	docs: correct Ollama model references to gemma4:e2b The deployed agent model is gemma4:e2b; these references still named mistral-nemo, so the setup and troubleshooting steps checked for a model that is no longer expected to be present. Co-Authored-By: Claude <noreply@anthropic.com>	2026-08-07 14:51:58 +02:00
jpmschweitzerandClaude Fable 5	e2acb7de39	docs(architecture): registry is git.schweitz.net not git.schweitz.internal Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-19 17:11:08 +02:00