M2.8: switch over to the new loop
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 2m16s
CI / e2e (pull_request) Successful in 10m51s

nisse-dev now runs only the conversational loop. The gated state machine
it was built alongside is gone:

- Removed control.py, planner.py, executor.py, approvals.py, gates.py
  (command_form moves to loop/reader.py), publish.py and poller.py, the
  old assembly in agent.py (its shared helpers move to loop/build.py),
  the store's state-machine view (get_state, transition), their tests,
  the old end-to-end and live planning/milestone/gate tests, and
  specs/orchestrator.qnt with its scenarios.
- Roles are driver, helper, expert and classifier; driver is required.
  loop:, roles.planner, roles.executor and tuning.executor are refused
  with what to use instead; tuning.driver takes the turn cap and failure
  limit.
- The benchmark and the capability matrix measure the driver: the
  loop's own system prompt and tools, the task's plan as the agreed
  restatement. Task plans end with finish_milestone, so earlier runs
  show as (old); stored runs' executor tuning reads as the driver's.
- A delegation on the loop records what its helper's alias resolved to
  (L9), as the old path's did.
- The dump shows a work item's revision and what it waits for.
- Behaviour the old tests covered and the loop shares stays covered:
  driver runs that fail on a model call, stop mid-turn, reset the
  failure count; go-aheads ignoring case and punctuation; a request too
  big to fit is never sent; the assembly tests, now on build_loop_agent.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
This commit is contained in:
dongarandClaude Opus 5.5 committed 2026-10-08 03:12:58 +00:00
1 parent 09232dcbdd
commit 6ae2375194
89 files changed
+951 -8592

No files matched your search

@@ -9,4 +9,4 @@ plan: |
3. Fix `total_value` so that each item contributes its unit price times its
quantity.
4. Run `python -m pytest -q` until every test passes.
5. Call finish.
5. Call finish_milestone, with final yes.
@@ -37,4 +37,4 @@ plan: |
then the same with `list --overdue`, which must print
`[!] 1 Pay rent (due 2026-10-01)`. Delete /tmp/tracker-check.json
before and after.
9. Call finish.
9. Call finish_milestone, with final yes.
@@ -9,4 +9,4 @@ plan: |
(NNN mod 25) / 100. Correct only the failing region's entry; leave every
other line as it is.
3. Run `python -m pytest -q` until every test passes.
4. Call finish.
4. Call finish_milestone, with final yes.
@@ -13,4 +13,4 @@ plan: |
using pytest's capsys fixture.
4. Run `python -m pytest -q` until every test passes, and check that
`python -m greeter --shout Bob` prints `HELLO, BOB!`.
5. Call finish.
5. Call finish_milestone, with final yes.
@@ -15,4 +15,4 @@ plan: |
are different functions and keep their names. Change no behaviour.
4. Update the tests under `tests/` to use the new name, and run
`python -m pytest -q` until every test passes.
5. Call finish.
5. Call finish_milestone, with final yes.
@@ -12,4 +12,4 @@ plan: |
invalid input for each of the eight rules.
4. Run `python -m pytest -q test_durations.py`, and fix `durations.py`
until every test passes.
5. Call finish.
5. Call finish_milestone, with final yes.
@@ -18,4 +18,4 @@ plan: |
`invoicing/currency.py` have up to six decimal places (JPY is 0.006712),
and no step may round a rate or fraction to fewer places than that.
4. Run `python -m pytest -q` until every test passes.
5. Call finish.
5. Call finish_milestone, with final yes.
@@ -10,4 +10,4 @@ plan: |
"a--b" -> "a-b"; "" -> "".
3. Create `test_slugify.py` with pytest tests covering the four examples.
4. Run `python -m pytest -q test_slugify.py`, and fix anything until it passes.
5. Call finish.
5. Call finish_milestone, with final yes.