● Zion Boggan
repos/TreeTrace/commits/b99f3bb
zionboggan.com ↗
Code Commits Tags

Release 0.6.0: prompt-tree graph via --graph, branded with summary mode

Bump 0.5.1 -> 0.6.0, add the 0.6.0 changelog entry, and document --graph in
the README commands and outputs sections: a branded Mermaid graph that renders
free on GitHub with no dependencies, auto-summarizing large projects.
b99f3bb   Zion Boggan committed on Jun 16, 2026 (6 days ago)
CHANGELOG.md +7 -0
@@ -2,6 +2,13 @@
Notable changes to TreeTrace. The format follows Keep a Changelog, and the project uses semantic versioning.
+## 0.6.0 - 2026-06-16
+
+### Added
+
+- Prompt-tree graph visual via `treetrace --graph`. Emits `PROMPT_TREE_GRAPH.md`, a brand-styled Mermaid flowchart that runs from the goal through the steered progression of prompts to the result, with abandoned explorations as dimmed dotted detours. The diagram renders natively and free on GitHub and any Mermaid viewer, with zero runtime dependencies. Edge labels carry an opaque backing so their text stays legible over the spine line, and node labels truncate on a word boundary so they never end mid-word.
+- Large-project summary mode for the graph. Once a tree exceeds 25 live nodes, the graph automatically collapses to a spine-only summary so the whole project still reads at a glance: each abandoned branch folds into a single dim "N abandoned steps" stub, routine intermediate steps fold into "N steps" count stubs, and the goal, strategic turns, failure-flagged nodes, and result are kept. Small trees render in full. Pass `--full` or `--summary` to force a mode.
+
## 0.5.1 - 2026-06-15
### Fixed
README.md +2 -0
@@ -107,6 +107,7 @@ Failure to eval to handoff: every correction you made by hand becomes a guardrai
| `.treetrace/lessons.md` | Human-readable lessons for future work |
| `.treetrace/evals.jsonl` | Generic model-agnostic eval cases |
| `.treetrace/agent-memory.md` | Compact memory pack for Codex, Claude Code, Cursor, or another agent |
+| `PROMPT_TREE_GRAPH.md` | Branded Mermaid graph of the prompt tree from `treetrace --graph`; renders free on GitHub with no dependencies, and large projects auto-summarize |
| `treetrace --handoff` | Agent-ready continuation brief printed to stdout |
<details>
@@ -140,6 +141,7 @@ Failure to eval to handoff: every correction you made by hand becomes a guardrai
| `npx treetrace --lessons` | Write and print `.treetrace/lessons.md` |
| `npx treetrace --evals` | Write and print `.treetrace/evals.jsonl` |
| `npx treetrace --memory` | Write and print `.treetrace/agent-memory.md` |
+| `npx treetrace --graph` | Write `PROMPT_TREE_GRAPH.md`, a branded Mermaid graph that renders free on GitHub with no dependencies; large projects auto-summarize, and `--full` or `--summary` force a mode |
| `npx treetrace --security` | Print a security-focused report and write `.treetrace/hallucinations.json` |
| `npx treetrace mcp` | Start a read-only MCP server over stdio |
| `npx treetrace --titles-only` | Compact human tree, no full prompt details |
package.json +1 -1
@@ -1,6 +1,6 @@
{
"name": "treetrace",
- "version": "0.5.1",
+ "version": "0.6.0",
"description": "Capture the agent corrections you throw away as local eval data: regression tests, failure analysis, and handoff memory. No LLM judge, no uploads.",
"keywords": [
"claude-code",