Adds a Window::All option to the per-agent stats page and the hive-wide
rollup, selectable as a new 'all' tab on both.
- hive-ag3nt (per-agent, time-bucketed): All ranges from MIN(started_at)
to now (fallback to now on an empty table) with an adaptive bucket
width laddered by span — hourly <=2d, daily <=90d, weekly <=2y, 30-day
beyond — so the trend series stays bounded (~<=104 buckets) at any age.
- hive-c0re (swarm rollup, not time-bucketed): All sets from=0 so the
aggregate covers every recorded turn across all agents.
- frontend: an 'all' button on both the agent stats and dashboard hive
stats window selectors (createTabStrip + fetch already pass the window
string through, so no JS change needed).
cargo check passes on both crates; FE builds clean. Fixes#1919.
Closes the #1787 loop — the sanctioned create path now that agents
can't create repos directly. Adds:
- wire: Request::CreateRepo{repo} + Response::RepoCreated{full_name,
clone_url} (hive-sh4re).
- agent_server: dispatch_shared arm + handle_create_repo — validates the
repo name, then forge::create_agent_repo (org-owned repo, agent=write
collaborator, operator-team branch protection). Returns the full name
+ clone url so the agent can git clone immediately.
- MCP: create_repo tool + CreateRepoArgs in the harness.
- a new opt-in ToolGroup::Forge (=[create_repo]) so the operator
controls which agents can spin up repos (least privilege).
Workspace clippy -D warnings, cargo test, nix fmt all green.
/api/dashboard-state reported ctx_tokens from raw ctx_usage.input_tokens,
which is only the *uncached* input. With prompt caching the bulk of the
prompt is cache-read, so input_tokens is ~0 and every SW4RM card showed
'ctx·0k'. Use ctx_usage.context_tokens() (input + cache-read + cache-creation
= the real window size) to match the agent page (ships the full ctx_usage)
and turn.rs's cache-TTL check. Doc comment updated.
Two fixes from review:
- Liveness: /api/state isn't polled while online (only during login), so
hooking refreshBashTasks to it only populated on cold load. Bash tasks
start + finish asynchronously between turns, so add a light ~4s interval
to keep the tasks pill live; the /api/state-time call now just does the
first-paint populate. Doc note corrected to match.
- Move the blocking dir scan + per-file reads in /api/bash-tasks off the
async executor via tokio::task::spawn_blocking (damocles nit).
Snapshot of the agent's in-flight bash tasks: reads the in-container
bash-tasks/ dir (the co-located hive-bash-mcp daemon writes one TaskFile
JSON per task), deserializes the canonical hive_sh4re::TaskFile, filters to
Pending/Running, and returns them running-first then oldest-first. Skips
unreadable/malformed files (and the daemon's .json.tmp scratch writes) so a
stray file can't fail the list. Snapshot-only for v1; the page polls it like
/api/loose-ends, SSE live-push is a possible follow-up.
Builds the read/surface half of the per-session first-turn-tokens metric
(the capture — sessions table + turn_stats.session_id — landed separately).
A fresh claude session's first turn pays the full static prefix (system
prompt + tools + CLAUDE.md + first wake) as uncached input, so its
input_tokens is a clean proxy for prompt / CLAUDE.md sprawl — watching it
over time surfaces creep.
- stats.rs: add `Snapshot.first_turn_ctx: Option<u64>` populated by
`read_first_turn_ctx` — the agreed per-session derive (first turn,
`ORDER BY started_at LIMIT 1`, of the most recent session that started
in the window). Inert-until-capture: `.ok()` maps both "no fresh
session yet" and "older db without the sessions table" to None, the
same decoupling as read_bash_breakdown; the field is skipped from the
JSON when None. Pre-capture rows have a NULL session_id and are excluded.
- agent stats.js: add a "first-turn ctx" summary chip, guarded on a
numeric value so it stays hidden until capture has data.
clippy + cargo fmt clean; agent bundle builds.
Clean the legacy backlog so the tracker-tag lint can become a required
gate (mara's warn-during-cleanup -> full-tree-enforcement path). Rewrite
the ~33 real `closes/see #NNN` provenance refs in doc-comments to prose
across hive-forge, hive-c0re, hive-ag3nt, hive-matrix-mcp, hive-sh4re,
and add a `lint:allow` line marker to check-issue-refs.sh for genuine
non-tracker `#<digits>` (a hash-digit heading-detection test input).
Tree is now lint-clean; tracker-tag lint ready to promote to required.
The surfacing half of the per-agent favorite-tools stat. Reads a
`bash_commands(ts INTEGER NOT NULL, head TEXT NOT NULL)` table from the
per-agent turn-stats.sqlite — one row per bash task, written by
hive-bash-mcp (the capture half, landing separately) — and rolls up the
top-10 command heads for a doughnut, mirroring the existing
tool_breakdown.
- stats.rs: new `Snapshot.bash_breakdown` + `read_bash_breakdown()`.
The read is guarded: a missing `bash_commands` table (capture hasn't
shipped / agent hasn't run a bash task) maps to an empty list, never
an error — the snapshot degrades gracefully. Unit tests cover both
the absent-table and populated cases (incl. window cutoff + ordering).
- frontend: a "favorite tools (bash)" doughnut card on the agent /stats
page, kept hidden until bash_breakdown has data so it never shows a
permanently-empty doughnut while capture is pending.
Part of #1433 (does not close it — pairs with the hive-bash-mcp capture
half). Inert until the capture lands; merge order with it is irrelevant.
First slice of #1424 (per-agent /stats enrichments):
- Backend: add per-bucket result_counts to the stats Snapshot (mirrors
model_counts), so result outcomes can be charted over time, not just
as a window total.
- Frontend: two new summary chips — cache hit-rate % (cached input vs
all input-side tokens) and avg tokens/turn — both derived from the
existing per-bucket token sums. Plus a stacked result-trend chart so
error / rate-limit / compaction spikes are visible across the window.
Hive-wide aggregate, cost estimate, and container resource load land in
follow-up PRs.
When an agent parks on a long-poll that expires with nothing to show,
nudge it to spend the idle time on other useful work instead of
immediately re-blocking on the same call.
- recv: when wait_seconds > 0 and the inbox is empty at timeout, the
'(empty)' result now carries IDLE_WAIT_HINT. Immediate peeks
(no/zero wait) are unchanged.
- bash_status: when wait_seconds > 0 and the task is still
pending/running at timeout, append BASH_IDLE_WAIT_HINT. Finished
tasks and no-wait calls are unchanged.
Both thread a 'waited' flag into the formatter so the hint only fires
on an actual wait-timeout. Unit tests cover both. Implements #1411.
The nixpkgs bump to clippy 0.1.95 / cargo 1.95.0 added + strengthened a
large batch of lints. CI denied ALL warnings (`-D warnings`) against the
`pedantic = warn` workspace lint, so the bump hard-failed `nix flake
check` workspace-wide with zero code changes — and would recur on every
future clippy bump.
Posture fix (the durable part): CI now runs
`-D warnings -A clippy::pedantic`, so the default/correctness/style lints
stay a hard gate while the "extra, opinionated" pedantic group is
advisory only (still `warn` for local `cargo clippy` via the workspace
lints table, just non-blocking in CI). `-A` rather than `-W` so the
group drop doesn't re-enable the specific pedantic lints the workspace
allows (e.g. `must_use_candidate`).
Also fixes the genuine DEFAULT/STYLE lints the bump surfaced across the
workspace (doc_lazy_continuation, collapsible_if, ptr_arg,
match_like_matches_macro, …) via `cargo clippy --fix` + manual stragglers
(`too_many_arguments` #[allow] on the host-config constructors), and
three tests that had rotted while the CI runner was offline (#1221):
- topology::top_level_agents_in_multi_root — hardcoded unsorted expected
- rebuild_queue::depends_on_evicted_dep_counts_as_resolved — needs
MAX_HISTORY_PER_KIND newer terminals to evict, not one
- coordinator::agent_paths doctest — illustrative pseudo-code, now `ignore`
Validated: clippy + formatting + cargo-test checks all pass.
