Private
Public Access
0
0

conductor(track): intent_dsl_survey v1.2 (rename + postfix + nagent fix)

Three files changed:

1. report_v1.2.md (NEW, 1301 lines) — v1.2 of the report with:
   (a) Renamed arena { } to tape { } (better term; aligns syntax with
       the Lottes tape-drive metaphor). All 46 occurrences replaced;
       3 awkward double-tape phrases cleaned up (heading 3.6,
       table cell, glossary entry).
   (b) Mixed postfix/infix notation for math (per user heuristic):
       - Strictly postfix for math primitives with precedence:
         + - * / ^, math indexing [], reducers sum/product.
       - Infix for structural ops (no precedence concern):
         :=, function calls, control flow (for/if), field access,
         block delimiters.
       - Heuristic: 'if the operator has precedence, postfix it;
         if it doesn't, infix it.' Mixed examples like
         'result := Matrix(m.rows 1 -, m.columns 1 -)' are canonical.
   (c) nagent attribution corrected: previously said nagent is
       Jody Bruchon's; it is Mike Acton's (github.com/macton/nagent;
       per conductor/tracks/nagent_review_20260608/). Jofito stays
       correctly attributed to Jody Bruchon.
   (d) Added v1.2 changelog note at top + heuristic table at start
       of section 3.

2. report_v1.1.md — nagent attribution fix propagated (post-hoc
   correction; the original v1.1 commit had the same error in the
   glossary line 1671).

3. research/cluster_3_intent_mapping.md — nagent attribution fix
   in 2 places (header at line 188, body at line 190).

Appendix A.3 (EBNF) and A.4 (Tier 1 vocab) retain v1.1 form
pending a sync pass; noted in the v1.2 changelog at the top of
the report.
This commit is contained in:
2026-06-12 10:37:10 -04:00
parent bae30cc3a7
commit 213e499420
3 changed files with 1822 additions and 3 deletions
@@ -1668,7 +1668,7 @@ That's 4 verbs total, plus the grammar. The placeholder track can demonstrate a
**Meta-Tooling** — the external agents (Gemini CLI, OpenCode) used to build the Application. The DSL is the format these agents emit. Distinct from the Application's function-calling.
**nagent**Jody Bruchon's autonomous coding agent framework. The `nagent_tags.py` parser is the inspiration for the DSL's structured-protocol idea (but the DSL rejects the XML angle-bracket notation).
**nagent**Mike Acton's autonomous coding agent framework (`github.com/macton/nagent`; per `conductor/tracks/nagent_review_20260608/`). The `nagent_tags.py` parser is the inspiration for the DSL's structured-protocol idea (but the DSL rejects the XML angle-bracket notation).
**O'Donnell** — John O'Donnell; creator of the IMGUI/MVC paradigm (per `johno.se/book/`). The DSL inherits 4 anchor claims from his work: widgets as method invocations, reads free, IEventTarget, no scene-graph abstractions.
File diff suppressed because it is too large Load Diff
@@ -185,9 +185,9 @@ This shows jq's functional composition style: `select(...) | [digits | digit] |
---
## Entry: nagent's Tag Protocol (Jody Bruchon, 20242025)
## Entry: nagent's Tag Protocol (Mike Acton, 2024\u20132025)
**What it is.** nagent is Jody Bruchon's autonomous coding agent framework. Its §4 "visible output protocol" uses a self-closing XML-ish tag format (e.g., `<nagent-read path="src/foo.py"/>`) that the agent emits as text. A parser (`nagent_tags.py`) matches tags to handler functions (`execute_read`, etc.). The protocol is explicitly not XML — first matching close-tag wins, there is no entity escaping, and the tag format is designed for human readability and LLM emit-ability rather than for machine interchange fidelity.
**What it is.** nagent is Mike Acton's autonomous coding agent framework (`github.com/macton/nagent`). Its §4 "visible output protocol" uses a self-closing XML-ish tag format (e.g., `<nagent-read path="src/foo.py"/>`) that the agent emits as text. A parser (`nagent_tags.py`) matches tags to handler functions (`execute_read`, etc.). The protocol is explicitly not XML — first matching close-tag wins, there is no entity escaping, and the tag format is designed for human readability and LLM emit-ability rather than for machine interchange fidelity.
**What we explicitly reject (and what we take):** We **take** the idea of a compact, human-readable structured protocol for tool invocation — the `<name attr="value"/>` surface syntax that external agents can emit without knowing the underlying function-call JSON schema. We **reject** the XML angle-bracket notation per the user's explicit instruction: "ignore its record formats as they problably will be less xml/json based as I don't like them." (`conductor/tracks/nagent_review_20260608/decisions.md:50` citing user signal).