gcf-aif-ext 0.31.0 → 0.34.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +30 -3
- package/commands/gcf.js +89 -38
- package/extension.json +1 -1
- package/injections/plan-context.md +3 -0
- package/lib/audit-core.js +96 -134
- package/lib/board.js +29 -13
- package/lib/commit-files.js +1 -0
- package/lib/commit-move.js +1 -0
- package/lib/config-set.js +1 -1
- package/lib/context.js +29 -16
- package/lib/d2-states.js +208 -0
- package/lib/design-parts.js +37 -7
- package/lib/domain.js +6 -1
- package/lib/gcf-paths.js +32 -4
- package/lib/git.js +26 -5
- package/lib/integrate.js +58 -1
- package/lib/main-lock.js +195 -3
- package/lib/plan-check.js +34 -12
- package/lib/play.js +24 -22
- package/lib/review.js +5 -3
- package/lib/session-mark.js +2 -1
- package/lib/systems-doc.js +60 -13
- package/lib/work-ops.js +3 -2
- package/package.json +1 -1
- package/skills/gcf-audit/SKILL.md +10 -5
- package/skills/gcf-card/SKILL.md +12 -10
- package/skills/gcf-verdict/SKILL.md +7 -5
- package/templates/agents-block.md +11 -1
- package/templates/config.yml +9 -4
|
@@ -34,11 +34,13 @@ workflow:
|
|
|
34
34
|
4. for `keep` of a design-unit item still awaiting its verdict: compress it first - the collapse copies lines verbatim, 1 line per behavior record, refusal and boundary
|
|
35
35
|
5. for that keep: strip `contract:` down to paths and entry points and cut `intent:` to the line the subsystem's purpose still lacks; leave an unplayed item as it is - its close froze the body
|
|
36
36
|
6. run `ai-factory gcf verdict <id> <verdict> --note "<answer>"`, with `--played-on <build>` per build of `play.builds` the human played on; a kill makes a removal item for code in main unless `--no-remove`
|
|
37
|
-
7.
|
|
38
|
-
8.
|
|
39
|
-
9. for
|
|
40
|
-
10.
|
|
41
|
-
11.
|
|
37
|
+
7. after each verdict - step 6, or the milestone keep of step 13 - run `ai-factory gcf audit --json`
|
|
38
|
+
8. each stale `until` entry the verdict fired - `verdict(<id>)` of the item or of each id the milestone keep prints after `→`, or `retune(<its subsystem>)` after a tune - ask the human now, while present, as steps 4-8 of the gcf-audit skill do
|
|
39
|
+
9. for a decision run `ai-factory gcf decide <id> <choice> --reason "<why>"`; `known` parks a bug and lists it in `gcf/LIVE.md` known issues
|
|
40
|
+
10. for a feature whose child died, the human picks: `close` without the child, `continue` with a replacement, or `kill` with its live children
|
|
41
|
+
11. for `keep` on an item touching 2 or more subsystems: read each updated systems doc and report a contradiction between constraints as a D1 question instead of finishing silently
|
|
42
|
+
12. report the commit hash, `git revert <hash>` undoes that one move - not the code, nor a later move or edit on the same files - and the id of any removal item the command made
|
|
43
|
+
13. a whole milestone: compress its awaiting-verdict units as in steps 4-5, then run `ai-factory gcf verdict <milestone> keep --milestone`
|
|
42
44
|
|
|
43
45
|
invocation:
|
|
44
46
|
- run after a playtest session, on a human decision, or with no arguments to print the playtest sheet
|
|
@@ -3,6 +3,8 @@ gcf_context:
|
|
|
3
3
|
- read `gcf/INDEX.md` before anything else under `gcf/`: it lists every subsystem, design unit and work item
|
|
4
4
|
- `gcf/LIVE.md` says what the game does now, and `gcf/PILLARS.md` says what it must stay
|
|
5
5
|
- `ai-factory gcf board --json` gives the whole state in one read: the phase, the items by status with plan progress, the inbox and the open questions
|
|
6
|
+
- start a session with `ai-factory gcf audit` and state its first line before anything else
|
|
7
|
+
- a stale `until` record that line names goes to the human through the gcf-audit skill: the human confirms or replaces the value
|
|
6
8
|
|
|
7
9
|
gcf_work:
|
|
8
10
|
- every piece of work is one work item `gcf/work/<id>.md`: find the item before writing code for a feature, a bug or a tech task, or create it with the gcf-card skill
|
|
@@ -19,7 +21,8 @@ gcf_work:
|
|
|
19
21
|
- an item's plan is in the plan form: blocks `context:`, `decisions:` (records `id`, `pick`, `why`), `tasks:` (`- [ ] t1 <action> (d1)`), `pillar_check:`, `verification:`, one idea a line
|
|
20
22
|
- `ai-factory gcf plan check <id>` lists the plan's form problems as `format:` lines: fix them, they never block
|
|
21
23
|
- record each improve pass of a plan with `ai-factory gcf plan pass <id> --blocking <n> --polish <m> --json`; its verdict decides: continue, converged or stalled
|
|
22
|
-
- `ai-factory gcf review row <id> --kind plan|code --pass <k> --json` names who makes review pass k, by `review.plan|code` of `gcf/config.yml`
|
|
24
|
+
- `ai-factory gcf review row <id> --kind plan|code --pass <k> --json` names who makes review pass k, by `review.plan|code` of `gcf/config.yml`, and its `fallback`: the stand-ins in order when that row cannot make the pass
|
|
25
|
+
- a pass a stand-in or you made records both: `ai-factory gcf plan pass <id> … --by <who made it> --for <the row>`
|
|
23
26
|
- a `stalled` verdict: `ai-factory gcf review stall <id> --kind plan|code --passes <counts>` blocks the card
|
|
24
27
|
- `gcf review more` and `gcf review accept` answer a stall, and they are the human's
|
|
25
28
|
- a harness run plans in one session and implements in a fresh one (`GCF_RUN_PHASE`); in your own terminal stop after planning unless the human asked for `--through`
|
|
@@ -45,6 +48,10 @@ gcf_work:
|
|
|
45
48
|
- work that cannot go on: run `ai-factory gcf block <id> --reason "<why or the question>"`
|
|
46
49
|
- in a worktree on branch `work/<id>` change no `gcf/` file but the item's `live:` and new inbox entries, commit all, then run `ai-factory gcf verify <id> --mark`: `ai-factory gcf integrate` in the main checkout merges it and records the move
|
|
47
50
|
- a design question only the human can answer becomes a D1 record in `gcf/open-questions.md`
|
|
51
|
+
- a fired assumption is never an inbox entry
|
|
52
|
+
- a fired D2 is not re-filed as a D1: the human answers its own record; a plan that needs its value blocks with `--reason "needs the human's answer to <q-NNN> (its until fired)"`
|
|
53
|
+
- an assumption with no record, a fired inline `until` annotation or a belief your work shows false, is a D1 question
|
|
54
|
+
- file it with `ai-factory gcf question add --class D1 --question "<question>" --proposed "<your answer>"`, and `--blocks <id>` for the item it holds
|
|
48
55
|
- name each thing by the term `GLOSSARY.md` defines for it
|
|
49
56
|
- a word added to an `avoid:` of `GLOSSARY.md` leaves `gcf/design/`, `gcf/systems/`, `gcf/PILLARS.md` and every item but an unplayed one in the same commit
|
|
50
57
|
- `ai-factory gcf design check` names each hit of an avoided word in design and items as M4, `npx --yes cnlp-kit check` the rest
|
|
@@ -101,6 +108,8 @@ gcf_work:
|
|
|
101
108
|
- an answer that moves into a unit's slot goes there in English
|
|
102
109
|
- do not translate keys, statuses, ids, commands, `TBD`, `answer: q-NNN`, `## Handoff`, a `quote:` (it is verbatim from the GDD) or the fixed start of a block reason (`needs permission:`, `planning does not converge`, `waits for`)
|
|
103
110
|
- a D1 record that carries the human's `answer:` goes into the slot of each unit it blocks, with `answer: q-NNN`, and then leaves `gcf/open-questions.md`
|
|
111
|
+
- a D2 record's `answer:` from the human overrules its `assumed:`: write it into each slot that cites `assumed: q-NNN`, cite `answer: q-NNN` there, then remove the record
|
|
112
|
+
- an unplayed item's body is frozen: its `assumed: q-NNN` stays, and the answered record stays while an unplayed item cites it; it leaves after that item's verdict
|
|
104
113
|
- a pillar changes only on the human's word; its short `name:` is what the human knows it by, and its id comes from the name
|
|
105
114
|
- a new name saved with `design save` renames the id in every file that cites it
|
|
106
115
|
- `ai-factory gcf pillar retire <id> --reason "<why>"` takes a pillar out
|
|
@@ -120,6 +129,7 @@ gcf_work:
|
|
|
120
129
|
- in the project chat propose a new item by its title, never an id
|
|
121
130
|
- in the project chat propose a verdict only after the human said in the talk that they played the item and how it felt, its note in the human's words; leave the `remove` of a kill, a no or a wontfix to the rule unless the human says otherwise
|
|
122
131
|
- a move refused for hand edits under `gcf/` ends its error with `gcf-refusal: {"code":"dirty","paths":[…]}`: `ai-factory gcf edits diff --path <path>` shows them; `gcf edits commit` and `gcf edits discard` are the human's moves, never the agent's
|
|
132
|
+
- while a main run works a card, your move is still refused for that run's `gcf/` edits and does not wait; the human's move waits behind the run: propose the move to the human, or make it again after the card's commit
|
|
123
133
|
- `item amend` refused for a live run ends with `gcf-refusal: {"code":"running"}`, and refused for a card changed since its preview with `gcf-refusal: {"code":"stale"}`
|
|
124
134
|
- a move the commit gate refuses ends its error with `gcf-refusal: {"code":"gate","problems":[…]}`: git holds no commit of it; fix what it names, then make the move again
|
|
125
135
|
- `ai-factory gcf changes [--worktree <id>]` lists what is uncommitted in the checkout or an item's worktree, `gcf changes diff --path <path>` shows one text file's diff
|
package/templates/config.yml
CHANGED
|
@@ -27,16 +27,21 @@ auto_compact_pct: 0
|
|
|
27
27
|
# The review passes of a plan and of the code before its commit (Operator-Tasks-Plan t2): row k
|
|
28
28
|
# makes pass k (agent claude or codex; a Claude model alias, a Codex family or slug; an effort);
|
|
29
29
|
# the next pass goes only while the last found something blocking; the rows over, the card
|
|
30
|
-
# blocks for you. An empty list: no review.
|
|
30
|
+
# blocks for you. An empty list: no review. A row that cannot make its pass (no Codex, its limit,
|
|
31
|
+
# a failure) gives way to a model of its size: Codex medium to Fable medium then Opus high, Codex
|
|
32
|
+
# high and Fable medium to Opus high. Uncomment to change, or set it in Settings
|
|
31
33
|
# (ai-factory gcf config set review.plan --value "claude:opus:high, codex:astra:medium"):
|
|
32
34
|
# review:
|
|
33
35
|
# plan:
|
|
34
|
-
# - {agent: claude, model: opus, effort: high}
|
|
35
|
-
# - {agent: claude, model: opus, effort: high}
|
|
36
36
|
# - {agent: codex, model: astra, effort: medium}
|
|
37
|
+
# - {agent: claude, model: fable, effort: medium}
|
|
38
|
+
# - {agent: claude, model: fable, effort: medium}
|
|
37
39
|
# code:
|
|
40
|
+
# - {agent: codex, model: sol, effort: high}
|
|
38
41
|
# - {agent: claude, model: opus, effort: high}
|
|
39
|
-
#
|
|
42
|
+
# How a run drives an item: main (one at a time in the project folder, the default) or worktree
|
|
43
|
+
# (several at once, each in its own copy). A card whose worktree copy lives stays there:
|
|
44
|
+
# run_mode: worktree
|
|
40
45
|
# Lessons (Methodology §5.2.2): at the end of each session on an item its agent says what got in
|
|
41
46
|
# its way, into the inbox. `ai-factory gcf lessons prompt <id>` prints the questions. Uncomment to
|
|
42
47
|
# turn them off, to ask what the project's template should learn, or to add questions:
|