Commit Graph
10 Commits
Author SHA1 Message Date
marc 34f1f4396e Close diwan session: TODO/DONE instead of checkbox; purge evolutionary residue from all docs
1. 'Close diwan session' now uses TODO/DONE (assign_diwan_id inserts
'** TODO Close diwan session'), matching Reports. No headline anywhere
in diwan's own docs uses a [ ]/[X] checkbox now -- only :chat: list
items do, which is correct org usage (checklist items, not headline
states) and unaffected.

2. Rewrote PROTOCOL.md/TICK.md/DO.md/DESIGN.md to read as a single
coherent design rather than a changelog of how they got here. Removed:
contrastive 'not because X, but because Y' phrasing that only makes
sense if you know the prior rule, references to old tag names/formats
that no longer exist, a Claude-Code-vs-pi rationale that belongs in
DESIGN.md (if anywhere) not the agent-facing PROTOCOL.md, and 'no
:LINK: property' (never describe a convention by naming something it
doesn't have).

3. DESIGN.md got the heaviest pass since it had drifted from reality,
not just tone: it still said 'no flake.nix yet' (there is one, in
production use via samfelag), claimed several things 'not yet
re-verified live' that have since been verified multiple times
(tick's no-op gate, triage, the tag-consistency/escalation decision,
pi against real heading content via tick), and didn't mention
'diwan remote' or the actual flake.nix packaging shape anywhere.
Rewrote the verified-live claims and Known Gaps list to match current
reality, added flake.nix to the doc map and architecture section.

Live content migrated to match: diwan-dev-notes' decorate-home heading
('Close diwan session' checkbox -> TODO).
2026-11-09 23:17:17 +01:00
marc 19e6ae3a59 Reports: TODO/DONE format instead of checkboxes, much broader reportability bar
Format: '** TODO <title>' unread, '** DONE <title>' read -- tick deletes
DONE entries at the start of its next run (previously [X]). This only
changes the Reports heading's own keyword; :chat: entries and Close
diwan session stay checkbox-based, unaffected.

Reportability: reversed last turn's narrow 'only real findings' bar.
The report is now explicitly meant to be the one place Marc checks for
everything new or needing attention -- so triage moves, new dispatches,
session closures, and inline answers are reportable again, alongside
findings/ambiguities/problems and anywhere a note was left for Marc to
read (even one the agent already marked [X] itself -- that's not the
same as Marc having seen it). Only two exclusions remain: a run where
nothing happened at all, and a bare nudge (no information yet on
whether anything came of it).

No code changes -- this is PROTOCOL.md/TICK.md/DO.md/DESIGN.md only.
Also cleaned up one stale 'did nothing' entry in diwan-dev-notes'
diwan.org that violated the rule even under the old wording.
2026-11-09 23:08:42 +01:00
marc 43215d6e0a add 'diwan remote <machine>' to open the diwan workspace on a saved herdr machine
Threads an optional machine= kwarg through herdr_json/
herdr_diwan_workspace_id (default None, fully backward compatible),
reusing the exact focus-then-attach pattern cmd_bare already uses
locally, just against --machine <label> for the scripted focus call
and --remote <machine> for the actual interactive attach.

Verified: argparse wiring, the no-herdr-on-PATH dry-run path, and that
a bogus --machine label fails fast and cleanly (not a hang) rather than
attempting a real network connection -- confirms the warning-then-exec
fallback in cmd_remote is safe. Did not test an actual real remote
attach (no SSH path to any herdr server from this sandbox).
2026-11-09 18:43:08 +01:00
marc c7859400a1 Reports: only write entries with real information; tick: actually retire closed sessions
Reports no longer get an entry for routine mechanical steps (a plain
dispatch, a session closure Marc already asked for, a nudge, a pass
with nothing to triage) -- only for actual findings/decisions/problems.
Zero new entries in a tick run is now the normal case; PROTOCOL.md's
worked example replaced with entries that carry real information
instead of 'dispatched X'/'triaged N items' noise.

TICK.md step 3: a session whose Close diwan session is checked off now
gets genuinely torn down by the tick agent -- herdr tab close on its
DIWAN_ID's tab, :session: tag stripped from the heading, DIWAN_ID
property kept as a historical record. Resolves the 'retired-session
teardown' known gap from DESIGN.md (previously only reported, never
actually closed). Not yet verified against a real live tick run.
2026-11-09 18:34:07 +01:00
marc c09f2a1a11 fix: STATE_DIR.mkdir leftover calls still said DIWAN_DIR
Three mkdir(exist_ok=True) calls (locked(), save_state(), cmd_tick())
were never updated during the DIWAN_DIR/DIWAN_NOTES_DIR rename -- they
called .mkdir() on DIWAN_DIR (the tool's own install dir, which already
exists, so this silently no-op'd) instead of STATE_DIR (the content
repo's .diwan/ bookkeeping dir, which needs creating on a repo's first
run). Masked in all my own testing because diwan-dev-notes already had
a .diwan/ directory from manual setup predating the rename; surfaced on
thingvellir against a genuinely fresh content repo with no pre-existing
.diwan/, where it crashed with FileNotFoundError on .diwan/.lock.

Reproduced the crash against a fresh git-init'd repo with no .diwan/
directory, confirmed the fix via 'nix build' + running the packaged
binary against it.
2026-11-09 16:20:34 +01:00
marc de1576af0a add flake.nix: package diwan as a proper nix derivation
Bundles PROTOCOL.md/TICK.md/DO.md alongside the diwan script under
share/diwan/, wraps python3 with DIWAN_DIR set explicitly to that
directory and git on PATH. Verified live: built with 'nix build', ran
'result/bin/diwan tick' against diwan-dev-notes, dispatched a real pi
tick agent successfully end to end.
2026-11-09 11:12:32 +01:00
marc b9d1f96563 Reports: make the entry title itself the link, drop :LINK: property
A report subheading's title is now the link to the heading it's about
(org [[target][description]] syntax, description = the short title),
instead of a separate :LINK: property in a properties drawer. Plain text
title when there's no single heading to link. Further links, if needed,
go inline in the signed body.
2026-11-09 10:56:03 +01:00
marc 18c8284349 make pi the only harness, drop Claude Code support entirely
Removed AGENT_KIND/DIWAN_HARNESS and CLAUDE_PERMISSION_MODE/
DIWAN_PERMISSION_MODE; herdr_agent_start_args now hardcodes --kind pi and
always appends PI_APPROVE_FLAG. Motivated by a real live failure: Claude
Code blocks on an interactive first-run trust dialog in any content repo
it hasn't seen before, which herdr's real-pane dispatch can't answer
(agent_not_ready after a 30s timeout). pi has no such dialog and no
per-tool-call approval gate, so it was already the better fit for
diwan's unattended model -- confirmed live against a brand-new content
repo with zero blocking.

Updated PROTOCOL.md/DESIGN.md accordingly, replacing the harness-
agnosticism framing with an explicit pi-only statement, while leaving
TICK.md/DO.md untouched since neither ever mentioned a specific harness.
2026-11-09 10:49:12 +01:00
marc d52f733f14 rename TOOL_ROOT/CONTENT_ROOT to DIWAN_DIR/DIWAN_NOTES_DIR
DIWAN_DIR: where diwan itself is installed (was TOOL_ROOT /
DIWAN_TOOL_ROOT). DIWAN_NOTES_DIR: the content repo diwan is invoked
against (was CONTENT_ROOT); now also has its own env var override, not
just git rev-parse --show-toplevel discovery, for cron/systemd use where
cwd may not be the content repo.

The content repo's own runtime-bookkeeping directory (state.json, .lock)
is renamed STATE_DIR internally to avoid colliding with the new DIWAN_DIR
name; its on-disk path is unchanged (still a .diwan/ subdirectory of the
content repo).
2026-11-09 10:40:19 +01:00
marc fc0e556b42 diwan: the tool, split out from personal notes content
Contains only the generic diwan CLI and procedure docs (diwan, PROTOCOL.md,
TICK.md, DO.md, DESIGN.md). No personal notes, no content-repo-specific
AGENTS.md -- those now live in a separate content repo (e.g. diwan-dev-notes
for testing, ~/nc/org-agenda for the real thing), discovered at runtime via
git rev-parse --show-toplevel from wherever diwan is invoked.

History reset: this repo previously doubled as both diwan's own dev copy and
a throwaway test-content repo, with 48 commits of the two tangled together.
Starting fresh now that the split is done -- still v0/prototyping.
2026-11-09 10:13:24 +01:00