- Dockerfile: built with uv into /opt/nisse (installed, not editable),
run on python:3.12-slim with openssh-client as user nisse; stateless,
with state in a /var/lib/nisse-dev volume, config mounted at
/etc/nisse-dev/nisse-dev.yaml, secrets as environment variables, keys
mounted read-only. 202 MB. Its `test` stage adds the tests and their
tools over the installed package (UV_NO_SYNC, so `uv run` never swaps
in the source tree); the default target is the agent.
- scripts/e2e.sh --image REF runs the suite inside an image's test stage,
on its own sshd.
- CI builds both images on every PR (nothing pushed); release.yml pushes
gitea.dongar.net/dongar/nisse-dev:<tag> and :latest on a v* tag, with
the REGISTRY_TOKEN secret.
- scripts/bringup.sh builds the code under test into an image and runs it
in the systemd unit (root, $E2E mounted at its own path); `plan` prints
what it would run; the build-VM set-aside reads the projects: config.
Checked: the image refuses to start without a config, runs as uid 10001;
one e2e test passed from the test stage (2m45s, $0).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
- Questions never change state (L5, #77): a message ending in "?" to a
waiting project item starts a question run (reply and look-only tools,
an instruction to change nothing), and the item goes back to the very
wait it was in: a restatement up stays up and a go binds to it; the
agent's own question stays open.
- Explanations: a restatement gives its reasons and the main alternative;
a revision says what changed (restate(changed), sent back without it);
a milestone's summary says what was done, verified and left open.
- Progress in prose (#42): the driver's and a helper's own words for a
turn are posted, trimmed, at most once a minute per item; `details`
shows the last tool calls; a message arriving mid-run is acknowledged at
once ("Noted; ...").
- CI: the e2e job's comments and the plan no longer claim a newer push
cancels the run it supersedes (Gitea here doesn't); the concurrency
block goes.
Tests: conversation unit tests (questions in a go-ahead and an answer wait,
an unanswerable question, revisions, progress rate and trimming, details,
mid-run notes), the helper's progress, the walk asking questions in every
state with a questions_change_nothing property (routing questions the old
way fails 32 of 48 seeds), and an e2e question while a restatement is up.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
- roles.driver (unset: the planner's model) and roles.classifier (unset:
the expert's); the mapping is pinned when an item opens, and the driver
and the go-ahead reader run on the item's own (L9).
- profiles: in configuration (tools, strengths, weaknesses), used in
briefings: the driver's instructions say what its helper and expert are
good at, the helper's brief who reads its handback; never a model name.
- delegate(task) and ask_expert(question) for the driver. A helper works
on a branch off the milestone's; on a handback its work comes back as
uncommitted changes, otherwise it is discarded, so harness branches
never hold commits only the clone has. ask_expert keeps its budget.
- Triggers: failure_limit failed commands in a row (Driver's new "stuck"
outcome) or the turn cap, mid-milestone, call a helper in once per
milestone; if it fails too, the item waits on the operator. A
delegation cut off by a crash is discarded at boot.
- Evaluation capture: delegations and ask_expert as before, and the
reader's verdicts as classifier pairs.
Tests: help tests (merge-back, discard, needs a milestone, the stuck
trigger and its once-per-milestone limit, the expert and its budget,
pinning, briefings by profile, boot discarding a cut-off delegation),
config tests for roles and profiles, and the walk delegating with a
scripted helper that sometimes fails, with a delegations_settle property.
The walk found helper commits stranded on a merged PR's branch, fixed by
returning a helper's work uncommitted.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
- propose_project(name, purpose, decisions) in a conversation goes up for
a go-ahead (checked: a slug, not an existing project, no trailing
question).
- On go, the provisioning checklist (D1): a repository with a README,
protection on its default branch, the agent as a collaborator, a build
VM, a deploy key, and the project entry as YAML with <...> to fill in.
- On "done", the agent reads its configuration again and adds the new
project live (build_loop_agent(load=...); only additions), then checks
what was provided (D4, verified, not assumed): permissions and
protection as it sees them, then on a throwaway branch with an empty
commit, a branch push must succeed and a push to the default branch and
merging its own PR must be refused. The check's PR is closed and its
branch deleted. Failures are said per item; nothing starts.
- Checked: the tracking issue (the distilled decisions, carrying the new
item's ID), and the project's item, agreed and labelled `design`, whose
first milestone is ARCHITECTURE.md and the build plan. A conversation
waiting on provisioning doesn't close as idle.
- The walk replays exactly from its seed (item IDs too), and event IDs
stay unique across simulated restarts, as a server's are.
- The test config holds output to 8192 tokens, under the test key's
per-request cost cap.
Tests: new-project unit tests (checklist and its YAML parse as config, done
before the entry, what isn't set up, a checked project's record and first
PR, an existing name), protection enforced by a hook on the fake forge,
the walk proposing projects and saying done, and an e2e new project in a
repository the test operator provisions from the agent's checklist.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
- Every e2e role runs on qwen3.8-27b on the RTX 4090 (e2e_roles();
NISSE_E2E_MODEL overrides, e.g. claude-haiku-4-5). The first full run
passed 7 of 8 in 26 minutes for $0.0000; the eighth was a real finding,
fixed with the new-project PR.
- scripts/e2e.sh reports a run's spend on the test key and the day's total
against its budget: above $0 on the local model means a paid fallback.
- CI runs the suite as its own job on pull requests (not pushes to main),
on a throwaway sshd (--local), cancelling a run a newer push supersedes,
so the checks job still reports in minutes.
- The plan says so: e2e on every PR; locally only -k / --lf.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
Every live test that touches a repository gets one of its own from
e2e_support.fresh_repo, made by the test operator as an operator makes a
project's (D4, D8): seeded from tests/integration/seed/ (the sandbox's
package, without past runs' leftovers), the agent's account a collaborator
with write access, main protected (pushes only by the owner, an approval to
merge), and a deploy key generated for the run. It is deleted afterwards
(NISSE_E2E_KEEP_REPOS keeps it); scripts/e2e-cleanup.sh deletes leftovers.
- Both e2e fixtures use it; per-run base branches are gone. The merge
helper approves first, as the protection now requires.
- test_gitea_live uses it, so CI needs NISSE_OPERATOR_TOKEN and no longer
writes the sandbox deploy key (NISSE_PUSH_KEY).
- A live test of the helper: seeded, shared with the agent, protected
against it, deleted.
- nisse-test.yaml's project entry is a placeholder; pytest and ruff skip
the seed.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
- A top-level message that isn't a command is a conversation: an item in
the `general` scope (L1), threaded under the operator's message, with
`reply`, `ask_human` and `propose_work` and no workspace or execution.
`general` is reserved as a project name.
- propose_work(project, title, summary) goes up as a revision for a
go-ahead (or a plain yes). On go, under a file_issue intent (L8), the
record issue is opened in that project, assigned to the agent and
carrying the new item's ID; its item starts agreed, with the summary as
its brief. Intake skips any issue carrying an ID (D1); boot adopts a
filed issue or puts the proposal up again.
- A conversation closes after tuning.loop.general_idle_s (default a day);
a reply in its thread then starts a new conversation that continues it.
Tests: conversation unit tests (threading, filing, the marker, an unknown
project, changes, idle close and continuation, a plain yes, both crash
cases, commands at top level); the walk with conversations, proposals and
idle time, and records_have_one_item / conversations_do_no_work; an e2e
conversation that becomes filed work.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
- Config: `projects: {name: entry}` with repo, base_branch, workspace,
build_host, push credential, labels (defaults added to every issue),
secrets by ${VAR} reference with visibility (commands | harness), and
egress (recorded, not enforced). Every problem in every entry is
reported at once; an inline secret, a bad visibility, a repeated repo or
a non-slug name is an error.
- The old loop runs exactly one project (only_project) and refuses more.
- The new loop is per project: each its own clone, workspace (with its
commands-visible secrets, redacted on return), push credential and
milestones; intake polls every project's repository; items are scoped
to their project for every run, publish and PR watch. Issues are named
project#14 when there is more than one project, and a bare #14 that
matches two is asked about. Switching projects parks the one worked on
last (all others after a boot).
- A restatement that ends in a question is sent back to the driver, not
posted: the e2e driver kept asking "Is this the right interpretation?",
which a plain yes can't answer.
Tests: config entries and errors, two-project assembly, two-project loop
tests (intake, own workspaces and repos, #14 in both, do-next, label
defaults, parking across projects), the property walk over two projects
with a new own_repository_only property (an item using the first
project's repo fails 15 of 16 seeds), and the restatement check.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
- L1: `general`, the scope of conversation not (yet) about a project: an
item per thread, no repository, build VM or execution; closes after a day
idle, a later reply starting a linked item.
- L5: every conversation is an item from its first message; chit-chat is
answered, only work gets a Gitea issue.
- D1: a conversation's record issue is opened once it's work on a project.
The new-project sequence: proposal, a provisioning checklist in Matrix,
verified when the operator says done, a tracking issue carrying the
distilled decisions (not the raw chat), then the architecture PRs.
- Q: a scratch build VM for general replaces the answered question about
records for pure conversations.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
- Every milestone branch is cut from the latest default branch: the next
milestone builds on the merged previous one, and a redo after a closed PR
drops the rejected work. Uncommitted work comes along.
- While the item's PR is open, start_milestone is refused, with the PR's
state read from Gitea at that moment, not the last watch round.
- finish_milestone(final): earlier PRs say "Part of #N", the last "Closes
#N"; unsaid, it's final, as before.
- close_item with the item's PR still open waits for the merge (L2: a
closed item leaves nothing open).
- The driver's instructions cover ARCHITECTURE.md and build plans under
docs/plans/ (D2); the harness never parses a plan.
- Parking stashes uncommitted work and pushes it to <item>-parked, put back
on resume, instead of committing it onto the item's branch. The walk
found a half-done review fix parked onto a PR that had merged meanwhile,
where it was lost. Architecture D4's parking line says so.
Tests: unit tests for fresh milestone branches, the merge wait (including
a merge not yet watched), redo after a closed PR, Part of/Closes, close
waiting on an open PR, and the parked-fix regression; the walk's new
milestones_start_fresh property (fork-from-current fails 9 seeds); an e2e
two-milestone feature.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
- Commands that name their item ("go #14", "abandon #14", "stop #14")
apply to it wherever they're said; go, approve and abandon alone at top
level are asked about (L5). stop is never taken as an answer.
- A plain-language reply to a restatement is read by GoAheadReader, one
model call that agrees only on a clear yes; questions never reach it. The
agent says "taking that as a go-ahead on rev-N" first, bound to the
revision on screen at arrival (L3, L5, D1).
- Labels steer (D1): `bug` goes ahead after tuning.loop.bug_grace_s
(default 600 s) unless the operator replies; `discuss` isn't offered
restate until the operator has spoken; `bug`, `discuss` and `design` add
to the driver's instructions. A restatement asks no questions.
Tests: label and command unit tests, the property walk with labelled
issues, plain yeses, named gos and time passing (grace_only_unanswered,
discuss_talks_first), and e2e tests for a bug proceeding after its grace
period and a plain-language go-ahead.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
Several work items on the new loop (L1, D4):
- Switching parks the item on the workspace: its work is committed and its
branch pushed; resuming checks the item's branch back out. Branches of
open items are never set aside by a fresh workspace.
- Next item: the operator's "do #N next" first, otherwise the oldest.
- Issues with open Gitea dependencies are blocked until they close, checked
at intake and on every round; status shows blocked items and the line.
Tests: queue unit tests, the property walk over several issues with
dependencies and a new parked_work_safe property (it catches parking
disabled), and an end-to-end test with two issues where B depends on A.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
The priority is the smallest new loop running live, so M1.4 and M1.5 move
after M2.1. Each milestone is now checked by an automated end-to-end test
(new M1.6) against real resources, not a manual live run; manual runs are
for the new loop's first runs and phase ends.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
The push credential is either a push-only account's token, handed to git
through a credential helper that names environment variables, never
values, or a deploy key in a short-lived ssh-agent. The remote URL
follows the credential. Configured as gitea.push_user and push_token, or
gitea.push_key.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
execution.SSHHost.execute is now the only way the agent runs anything
(L13). Commands travel as a script on SSH's stdin, so the secrets handed
to a call are never on a command line, and every value handed out is
redacted from the output. Timeouts kill the remote process group, and
an unreachable host is reported as such, not as a failed command.
Workspace and GitRepo run on the build VM. The clone uses the
repository's SSH URL, so no credential is stored in it (#89); fetches
and pushes get the push key over stdin, in a short-lived ssh-agent,
and PRs are still opened from the agent's host with its API token.
The bench runs on the build host too.
Tests reach "the build VM" through a throwaway local sshd (nisse_dev
.testing); CI installs openssh-server. The live push test now pushes
with the sandbox's deploy key (NISSE_PUSH_KEY).
Fixes#89.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
SSH execution and the agent as a container image come first (Phase 1),
then the new loop as a thin end-to-end slice, widened milestone by
milestone with a live run after each. Outline, Vikunja and per-agent VMs
are gone; the vault, the infrastructure repository and the agent host
replace them. The survey and issue map are refreshed.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
Name the action classes harmless, contained and dangerous instead of
numbering them; say what escalation doesn't depend on; say when a work
item's Matrix thread starts and how threads route commands; add open
questions for the state store's engine, ops issuing credentials, and
releases.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
- abandon closes the item's open PRs
- a PR the operator closed is an answer, never reopened by a retry
- a review fix for a PR that merged meanwhile goes out as a new PR
- redoing a milestone after a closed PR gets a new branch and PR
- a record issue carries its work item's ID from creation
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
Ops work lives in one infrastructure repository for both sites, with
site labels; intake, labels and dependencies work as for nisse-dev, and
agent-to-agent requests are cross-repo issues.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
Each rule is stated once in its home section and referred to by ID
elsewhere. No decision added or removed; implementation detail moved to
Development-Plan.md section 6, keyed by architecture section. P8 folded
into P1, P5 and X1; the Appendix about the old spec dropped. Section
IDs are unchanged.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
Issues assigned to dev-agent are the intake; the agent restates its
understanding and either proceeds (bug label) or waits for a go-ahead.
Labels steer and are never required. Build plans and ARCHITECTURE.md
are working documents reviewed in PRs, not gates; scope is the issue
and its conversation. Work items can be blocked on Gitea dependencies,
each gets a Matrix thread, milestones are started and finished by
control tools, and the next milestone waits for the previous merge.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
Agents run as containers on one stable agent host that keeps their
state and secrets and never runs a command a model chose. Model-chosen
commands run on disposable tool VMs over SSH: a build VM per project
for nisse-dev, its own tool VM for nisse-ops. Secrets are a set per
agent, handed out per operation by the harness and redacted from tool
output. MCP servers stay on the agent host as the one exception.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
A model no longer reads another role's turns as its own (#78). The log
stays one record per work item; what a role is shown is projected from
it by Transcript.view() (views.py), which the planner, executor and
helper now build their context from:
- own events unchanged;
- operator messages labelled with their channel, e.g.
[operator, Matrix] or [operator, comment on PR #165];
- orchestrator facts (a new `fact` event) as [orchestrator] statements;
- the executor sees a helper's handback as [helper report], not its turns;
- a helper sees the approved plan and the executor's milestone work as
one-line narration;
- the planner sees no other role's work at all.
The orchestrator now writes facts at the points the models must know
about: work item opened, plan approved or rejected, milestone started,
finished or stopped, published (with PR number and URL) or not, review
comment answered, next milestone, task completed or abandoned.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
Development Plan M1.1, as discussed.
- Schema v4: a work_items table (id, scope, title, status, outcome,
position, data) and an agent row whose active_item points at one
(NULL: idle). Canonical events and intents carry their work item, and
events their actor. Older stores are refused with a clear message:
there was no production data, so no migration (the mechanism stays).
- The log is reached through a Transcript bound to one work item and
one actor: store.transcript(item, actor) reads only that item and
writes with both. The planner, executor, delegation and expert desk
get one per call from the orchestrator instead of holding the store,
so a component can neither read another task's events (the planner
read every earlier task's, #78) nor write without attribution.
store.all_events() is kept for readers that span items (evaluation
capture, dumps). Intents are begun through the transcript or with
work_item=, so each belongs to its item.
- The orchestrator opens a work item on 'use', closes it with its
outcome (completed or abandoned), and carries what the operator said
while idle into the new item as copies with their origin, so a task
sent before 'use' is still planned from (D1). control.py keeps its
state machine through get_state()/transition(), now over the active
work item, until M2.6 retires it.
- nisse_dev.dump shows work items and each event's item and actor.
Tests: test_work_items.py (scoping, attribution, intent ownership,
restart, outcomes, carried messages, a second task never seeing the
first); the suites updated for the per-call transcript.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
Development Plan M0.2.
- scripts/bringup.sh: start [REF] sets the previous run aside under
/root/nisse-e2e/runs/, exports the ref under test and starts the agent
as the transient systemd unit nisse-bringup, so it outlives the shell
that started it; stop (SIGTERM, clean shutdown), status, logs, and
collect (the journal log and a readable transcript).
- nisse_dev.dump (python -m nisse_dev.dump STATE_DB [--full]): a readable
dump of a state store's state, pending intents and canonical log. Opens
the store read-only, so it is safe against a live agent.
- The agent runs as root on this development VM, as it will on its own
VM. Architecture D3/D6/D7 corrected to match the operator's intent:
installing packages and toolchains on its own VM is class 2, recorded
so the environment can be rebuilt (it was class 3 with provisioning an
open question); egress names OS package mirrors. The plan's M0.2, M4.1,
M4.2 and bring-up guards follow.
Acceptance: a smoke run started, answered status in the test room,
stopped cleanly, and collect produced the log and transcript.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
Development Plan M0.1. Every section reference in code, tests, specs/,
the example config, the tuning guide, and the CLAUDE.md and README files
now cites docs/Architecture.md (P, L, D, O, X, Q) instead of the old
spec's A-H, and docs/Architecture-Build-Spec.md is deleted (git keeps
it). The plan's old-to-new table goes with it.
Mostly mechanical, with a per-site choice where one old section split:
A4 became L2 where it meant stop/abandon/the loop and L3 where it meant
approvals; A10 became L6 in the context-budget code and L7 elsewhere; B2
became D4 for outbound Gitea and publishing and D5 for review intake;
'A3 step N' became the matching step of L8's boot sequence. Comments
describing behaviour the architecture drops (planning always escalating,
thresholds tuned at an old build step) now describe the current code and
point at the Development Plan.
docs/Architecture.md gains one line the rewrite missed: intake outages
delay but never fail work (old B2), now in L5, where the poller and
Matrix code cite it.
Comments and docs only; no behaviour change.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
docs/Development-Plan.md: where the code stands against each section of
docs/Architecture.md, the environment today, how we work (plan-first per
milestone, tests, the Quint model, a bring-up run on this box ending
each phase), and seven phases of milestones from housekeeping to
nisse-ops, each marked pre-approved or needs discussion. Every open
issue is mapped to a milestone or marked superseded; an old-to-new
section table serves the reference update in M0.1.
docs/Architecture.md: status now agreed; D7 regains the browser tool
for the internal test network, left out of the rewrite by mistake.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
A full rewrite of the architecture, following the outline agreed with the
operator: a threat model of mistakes, injection and crashes rather than a
malicious model; actions classed by their effects; hard walls, a
deterministic fast path and an action classifier; a conversational loop
driven by a local model with frontier helpers; approvals as scoped
permissions with pre-approved milestones and a trust dial; context and
memory, including agent memory; documents as nisse-dev's workflow.
Added beside docs/Architecture-Build-Spec.md, which stays until this is
agreed; the Development Plan and reference updates come after. New
section letters (P, L, D, O, X, Q) avoid clashing with the old A-H
references in the code meanwhile.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
Fixes counterexamples 1-4 from specs/orchestrator.qnt: a repeated
'approve', 'approve rev-1' meant for the architecture, approving on both
channels, and 'approve' plus an afterthought all landed on the next
plan, one the operator had not seen.
- Revisions are numbered across the work item (A4 already required
monotonic tags; the code numbered per gate), so rev-N names one plan.
- Each reply is stamped on arrival with the revision that was up: in
Matrix the one whose approval request had been sent (a plain value
the transport thread reads, restored on boot), in Gitea the latest
plan comment older than the reply (board.posts).
- Gate.evaluate applies a reply that names no revision only if its stamp
is the current revision. Otherwise an approval is not applied and
feedback rejects nothing (it is still in the transcript), and the
agent says which revision is up. 'approve rev-N' binds by its number.
- Spec A4 states both rules. The model applies them; scenarios 1-4 now
expect the properties to hold, and both held over 200,000 random
traces and Apalache's exhaustive check to depth 8.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
A4 already names abandon as one of the ways out of a halt (continue,
re-plan, or abandon) and 0.2 closes a work item as completed or
abandoned, but no command did it: from a gate or a question the only way
to drop a task was to edit the state database.
- 'abandon' ends the task from any waiting state and returns to IDLE.
The move is made durable first; then the plan issue and any open
milestone PR are closed with a note (branches kept), and any
unresolved intent is aborted so boot reconciliation does not gate on
work dropped on purpose. A Gitea failure is reported, not fatal.
- Like 'status' it is a command in every state, never read as an answer
or feedback. While work runs, 'stop' comes first, as before.
- The restart / stranded question and the PR_OPEN hints mention it.
- Spec: B1 gains the abandon edge and B2 the command.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
The host-sharing item now records the operator's preference: one local
model for every local role, with agents tagging in and out of the host
as the fallback if no single model fits. A new item records vision as a
requirement (OpenSCAD renders, later video files) and what the text-only
agent needs before any vision work.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
nisse-dev and nisse-ops both send local roles to the one 24GB host,
where llama-swap keeps one model resident. Different models per agent
would reload weights on every switch. Per-key rate limits don't help.
Lists the options, simplest first, to decide after the executor
benchmark and the ops evaluation.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
All seven newer local models passed the original four tasks 20 of 20,
so the benchmark no longer told them apart. The new tasks keep plans
explicit, as the planner is told to write them, and make the work
itself harder:
- trace-bug: a wrong multi-currency total whose cause is a shared
rate helper; discounts and tax go through it too, so a fix at the
call site fails the check.
- refactor-rename: rename load_config across a ten-module package,
leaving load_config_defaults and reload_config alone.
- spec-parser: implement parse_duration from an eight-rule SPEC.md
given three examples, and write tests for every rule.
- long-milestone: eight dependent steps adding due dates to a task
tracker, from the model through storage versions to the CLI.
Self-tests prove that a call-site fix, a blind text replace and a
partial rename all fail their checks.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The report grouped runs by model, serving note and task version, so
runs made at different tuning were silently averaged together. Tuning
is now part of the key, and a tuning column shows how a row's settings
differ from today's defaults; it appears only when some row needs it.
tuning.executor.max_turns goes from 24 to 40. On the harder benchmark
tasks Haiku, the calibration ceiling, hit 24 on both refactor-rename
runs and both long-milestone runs, one of which had finished the work.
The cap guards against a model trying forever; it isn't a budget.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Two setup failures found while calibrating the new benchmark tasks,
both of which would also fail real milestones.
Devstral's chat template (Mistral) rejected any turn in which the model
wrote some text before a tool call: the OpenAI renderer made one message
per event, so the turn became a text message and a tool-call message in
a row, and llama.cpp answered 500. The renderer now folds consecutive
user or assistant messages into one, which is the OpenAI format for a
turn anyway. Checked against the live server: the captured failing
request no longer occurs, over six real runs.
LiteLLMClient gave up on any request after a fixed 120 s. A dense 27B
model writing a whole module in one turn takes longer, so the executor
escalated work that was going well. llm.request_timeout_s now sets it
for both clients, default 600.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
dongarandClaude Opus 5.5