Rename Project Memory to Workspace Memory

Rename all references from "Project Memory" to "Workspace Memory" to avoid
future conflation if a "project" concept is introduced later.

Changes:
- Rename read_project_memory() -> read_workspace_memory()
- Update all prompts, tool descriptions, and comments
- Update header parsing in memory.rs to use "# Workspace Memory"
- Update display detection for "=== Workspace Memory ==="
- Update documentation and analysis/memory.md

11 files changed, ~36 occurrences updated.

analysis/memory.md

@@ -1,12 +1,12 @@
-# Project Memory
+# Workspace Memory
 > Updated: 2026-01-20T10:16:13Z | Size: 18.3k chars
 
 ### Remember Tool Wiring
 - `crates/g3-core/src/tools/memory.rs` [0..5000] - `execute_remember()`, `get_memory_path()`, `merge_memory()`
 - `crates/g3-core/src/tool_definitions.rs` [11000..12000] - remember tool definition in `create_core_tools()`
 - `crates/g3-core/src/tool_dispatch.rs` [48] - dispatch case for "remember"
-- `crates/g3-core/src/prompts.rs` [4200..6500] - Project Memory section in native prompt
+- `crates/g3-core/src/prompts.rs` [4200..6500] - Workspace Memory section in native prompt
-- `crates/g3-cli/src/lib.rs` [1472..1495] - `read_project_memory()` loads memory at startup
+- `crates/g3-cli/src/lib.rs` [1472..1495] - `read_workspace_memory()` loads memory at startup
 
 ### Context Window & Compaction
 - `crates/g3-core/src/context_window.rs` [0..815] - `ContextWindow`, `reset_with_summary()`, `should_compact()`, `thin_context()`
@@ -79,7 +79,7 @@
 
 ### CLI Module Extractions
 - `crates/g3-cli/src/metrics.rs` [0..5416] - `TurnMetrics`, `format_elapsed_time()`, `generate_turn_histogram()`
-- `crates/g3-cli/src/project_files.rs` [0..5577] - `read_agents_config()`, `read_project_readme()`, `read_project_memory()`, `extract_readme_heading()`
+- `crates/g3-cli/src/project_files.rs` [0..5577] - `read_agents_config()`, `read_project_readme()`, `read_workspace_memory()`, `extract_readme_heading()`
 - `crates/g3-cli/src/coach_feedback.rs` [0..4025] - `extract_from_logs()` for coach-player loop feedback extraction
 
 ### Context Compaction
@@ -170,10 +170,10 @@ if s.chars().count() <= max_len { ... }
 ```
 
 
-### Project Memory Location
+### Workspace Memory Location
 - Memory is now stored at `analysis/memory.md` (version controlled, shared across worktrees)
 - `crates/g3-core/src/tools/memory.rs` - `get_memory_path()` returns `analysis/memory.md`
-- `crates/g3-cli/src/project_files.rs` - `read_project_memory()` reads from `analysis/memory.md`
+- `crates/g3-cli/src/project_files.rs` - `read_workspace_memory()` reads from `analysis/memory.md`
 
 ### Compact Tool Output
 - `crates/g3-cli/src/ui_writer_impl.rs` - `print_tool_compact()` handles compact display for file ops and other tools

crates/g3-cli/src/agent_mode.rs

@@ -7,7 +7,7 @@ use tracing::debug;
 use g3_core::ui_writer::UiWriter;
 use g3_core::Agent;
 
-use crate::project_files::{combine_project_content, read_agents_config, read_include_prompt, read_project_memory, read_project_readme};
+use crate::project_files::{combine_project_content, read_agents_config, read_include_prompt, read_workspace_memory, read_project_readme};
 use crate::display::{LoadedContent, print_loaded_status, print_workspace_path};
 use crate::language_prompts::{get_language_prompts_for_workspace, get_agent_language_prompts_for_workspace_with_langs};
 use crate::simple_output::SimpleOutput;
@@ -130,7 +130,7 @@ pub async fn run_agent_mode(
     // Load AGENTS.md, README, and memory - same as normal mode
     let agents_content_opt = read_agents_config(&workspace_dir);
     let readme_content_opt = read_project_readme(&workspace_dir);
-    let memory_content_opt = read_project_memory(&workspace_dir);
+    let memory_content_opt = read_workspace_memory(&workspace_dir);
 
     // Read include prompt early so we can show it in the status line
     let include_prompt = read_include_prompt(include_prompt_path.as_deref());
@@ -194,7 +194,7 @@ pub async fn run_agent_mode(
     agent.set_agent_mode(agent_name);
 
     // Auto-memory is enabled by default in agent mode (unless --no-auto-memory is set)
-    // This prompts the LLM to save discoveries to project memory after each turn
+    // This prompts the LLM to save discoveries to workspace memory after each turn
     agent.set_auto_memory(!no_auto_memory);
     
     // Enable ACD (Aggressive Context Dehydration) if requested

crates/g3-cli/src/display.rs

@@ -54,7 +54,7 @@ impl LoadedContent {
         Self {
             has_readme: content.contains("Project README"),
             has_agents: content.contains("Agent Configuration"),
-            has_memory: content.contains("=== Project Memory"),
+            has_memory: content.contains("=== Workspace Memory"),
             include_prompt_filename: if content.contains("Included Prompt") {
                 Some("prompt".to_string()) // Default name when we can't determine the actual filename
             } else {
@@ -155,7 +155,7 @@ mod tests {
 
     #[test]
     fn test_loaded_content_from_combined() {
-        let content = "Project README\nAgent Configuration\n=== Project Memory";
+        let content = "Project README\nAgent Configuration\n=== Workspace Memory";
         let loaded = LoadedContent::from_combined_content(content);
         assert!(loaded.has_readme);
         assert!(loaded.has_agents);

crates/g3-cli/src/lib.rs

@@ -38,7 +38,7 @@ use accumulative::run_accumulative_mode;
 use agent_mode::run_agent_mode;
 use autonomous::run_autonomous;
 use interactive::run_interactive;
-use project_files::{combine_project_content, read_agents_config, read_include_prompt, read_project_memory, read_project_readme};
+use project_files::{combine_project_content, read_agents_config, read_include_prompt, read_workspace_memory, read_project_readme};
 use simple_output::SimpleOutput;
 use ui_writer_impl::ConsoleUiWriter;
 use utils::{initialize_logging, load_config_with_cli_overrides, setup_workspace_directory};
@@ -108,7 +108,7 @@ pub async fn run() -> Result<()> {
     // Load project context files
     let agents_content = read_agents_config(&workspace_dir);
     let readme_content = read_project_readme(&workspace_dir);
-    let memory_content = read_project_memory(&workspace_dir);
+    let memory_content = read_workspace_memory(&workspace_dir);
     let language_content = language_prompts::get_language_prompts_for_workspace(&workspace_dir);
     let include_prompt = read_include_prompt(cli.include_prompt.as_deref());
 

crates/g3-cli/src/project_files.rs

@@ -1,6 +1,6 @@
 //! Project file reading utilities.
 //!
-//! Reads AGENTS.md, README.md, and project memory files from the workspace.
+//! Reads AGENTS.md, README.md, and workspace memory files from the workspace.
 
 use std::path::Path;
 use tracing::error;
@@ -66,9 +66,9 @@ pub fn read_project_readme(workspace_dir: &Path) -> Option<String> {
     None
 }
 
-/// Read project memory from analysis/memory.md in the workspace directory.
+/// Read workspace memory from analysis/memory.md in the workspace directory.
 /// Returns formatted content with emoji prefix and size info, or None if not found.
-pub fn read_project_memory(workspace_dir: &Path) -> Option<String> {
+pub fn read_workspace_memory(workspace_dir: &Path) -> Option<String> {
     let memory_path = workspace_dir.join("analysis").join("memory.md");
 
     if !memory_path.exists() {
@@ -79,7 +79,7 @@ pub fn read_project_memory(workspace_dir: &Path) -> Option<String> {
         Ok(content) => {
             let size = format_size(content.len());
             Some(format!(
-                "=== Project Memory (read from analysis/memory.md, {}) ===\n{}\n=== End Project Memory ===",
+                "=== Workspace Memory (read from analysis/memory.md, {}) ===\n{}\n=== End Workspace Memory ===",
                 size,
                 content
             ))

crates/g3-core/src/prompts.rs

@@ -97,9 +97,9 @@ IMPORTANT: If the user asks you to just respond with text (like \"just say hello
 
 Do not explain what you're going to do - just do it by calling the tools.
 
-# Project Memory
+# Workspace Memory
 
-Project memory is automatically loaded at startup alongside README.md and AGENTS.md. It contains an index of features -> code locations, patterns, and entry points. If you need to re-read memory from disk (e.g., after another agent updates it), use `read_file analysis/memory.md`.
+Workspace memory is automatically loaded at startup alongside README.md and AGENTS.md. It contains an index of features -> code locations, patterns, and entry points. If you need to re-read memory from disk (e.g., after another agent updates it), use `read_file analysis/memory.md`.
 
 **IMPORTANT**: After completing a task where you discovered code locations, you **MUST** call the `remember` tool to save them..
 
@@ -133,7 +133,7 @@ When to use this pattern and why.
 
 This applies whenever you use search tools like `code_search`, `rg`, `grep`, `find`, or `read_file` to locate code.
 
-Do NOT save duplicates - check the Project Memory section (loaded at startup) to see what's already known.
+Do NOT save duplicates - check the Workspace Memory section (loaded at startup) to see what's already known.
 
 ## Example
 
@@ -228,7 +228,7 @@ Short description for providers without native calling specs:
   - Example: {\"tool\": \"research\", \"args\": {\"query\": \"Best Rust HTTP client libraries for async/await\"}}
   - Use for researching APIs, SDKs, libraries, approaches, bugs, or any topic requiring web research
 
-- **remember**: Save discovered code locations to project memory
+- **remember**: Save discovered code locations to workspace memory
   - Format: {\"tool\": \"remember\", \"args\": {\"notes\": \"markdown notes\"}}
   - Example: {\"tool\": \"remember\", \"args\": {\"notes\": \"### Feature Name\\n- `file.rs` [0..100] - `function_name()`\"}}
   - Use at the END of your turn after discovering code locations via search tools
@@ -332,9 +332,9 @@ Skip TODO tools for simple single-step tasks:
 
 If you can complete it with 1-2 tool calls, skip TODO.
 
-# Project Memory
+# Workspace Memory
 
-Project memory (if available) is automatically loaded at startup. It contains feature locations and patterns discovered in previous sessions. If you need to re-read memory from disk (e.g., after another agent updates it), use `read_file analysis/memory.md`.
+Workspace memory (if available) is automatically loaded at startup. It contains feature locations and patterns discovered in previous sessions. If you need to re-read memory from disk (e.g., after another agent updates it), use `read_file analysis/memory.md`.
 
 **ALWAYS** call `remember` at the END of your turn when you discovered:
 - A feature's location (file + char range + function/struct names)
@@ -343,7 +343,7 @@ Project memory (if available) is automatically loaded at startup. It contains fe
 
 This applies whenever you use search tools like `code_search`, `rg`, `grep`, `find`, or `read_file` to locate code.
 
-Do NOT save duplicates - check the Project Memory section (loaded at startup) to see what's already known.
+Do NOT save duplicates - check the Workspace Memory section (loaded at startup) to see what's already known.
 
 # Response Guidelines
 

crates/g3-core/src/tool_definitions.rs

@@ -272,10 +272,10 @@ fn create_core_tools(exclude_research: bool) -> Vec<Tool> {
         });
     }
 
-    // Project memory tool (memory is auto-loaded at startup, only remember is needed)
+    // Workspace memory tool (memory is auto-loaded at startup, only remember is needed)
     tools.push(Tool {
         name: "remember".to_string(),
-        description: "Update the project memory with new discoveries. Call this at the END of your turn (before your summary) if you discovered something worth noting. Provide your notes in markdown format - they will be merged with existing memory.".to_string(),
+        description: "Update the workspace memory with new discoveries. Call this at the END of your turn (before your summary) if you discovered something worth noting. Provide your notes in markdown format - they will be merged with existing memory.".to_string(),
         input_schema: json!({
             "type": "object",
             "properties": {

crates/g3-core/src/tool_dispatch.rs

@@ -44,7 +44,7 @@ pub async fn dispatch_tool<W: UiWriter>(
         // Research tool
         "research" => research::execute_research(tool_call, ctx).await,
 
-        // Project memory tools
+        // Workspace memory tools
         "remember" => memory::execute_remember(tool_call, ctx).await,
 
         // ACD (Aggressive Context Dehydration) tools

crates/g3-core/src/tools/memory.rs

@@ -1,4 +1,4 @@
-//! Project memory tool: remember.
+//! Workspace memory tool: remember.
 //!
 //! These tools provide a persistent "working memory" for the project,
 //! storing feature locations, patterns, and entry points discovered
@@ -91,12 +91,12 @@ fn merge_memory(existing: &str, new_notes: &str) -> String {
     format!("{}\n\n{}", existing_body.trim(), new_trimmed)
 }
 
-/// Remove the header line (# Project Memory and > Updated: ...) from content.
+/// Remove the header line (# Workspace Memory and > Updated: ...) from content.
 fn remove_header(content: &str) -> String {
     let mut lines: Vec<&str> = content.lines().collect();
 
-    // Remove "# Project Memory" if first line
+    // Remove "# Workspace Memory" if first line
-    if !lines.is_empty() && lines[0].starts_with("# Project Memory") {
+    if !lines.is_empty() && lines[0].starts_with("# Workspace Memory") {
         lines.remove(0);
     }
 
@@ -117,7 +117,7 @@ fn remove_header(content: &str) -> String {
 fn update_header(content: &str, timestamp: &str, size: &str) -> String {
     let body = remove_header(content);
     format!(
-        "# Project Memory\n> Updated: {} | Size: {}\n\n{}",
+        "# Workspace Memory\n> Updated: {} | Size: {}\n\n{}",
         timestamp,
         size,
         body.trim()
@@ -145,20 +145,20 @@ mod tests {
 
     #[test]
     fn test_merge_memory_append() {
-        let existing = "# Project Memory\n> Updated: 2025-01-10 | Size: 1k\n\n### Feature A\n- `a.rs` [0..50]";
+        let existing = "# Workspace Memory\n> Updated: 2025-01-10 | Size: 1k\n\n### Feature A\n- `a.rs` [0..50]";
         let new_notes = "### Feature B\n- `b.rs` [0..100]";
         let result = merge_memory(existing, new_notes);
 
         assert!(result.contains("### Feature A"));
         assert!(result.contains("### Feature B"));
-        assert!(!result.contains("# Project Memory")); // Header removed for re-adding
+        assert!(!result.contains("# Workspace Memory")); // Header removed for re-adding
     }
 
     #[test]
     fn test_remove_header() {
-        let content = "# Project Memory\n> Updated: 2025-01-10 | Size: 1k\n\n### Feature\n- details";
+        let content = "# Workspace Memory\n> Updated: 2025-01-10 | Size: 1k\n\n### Feature\n- details";
         let result = remove_header(content);
-        assert!(!result.contains("# Project Memory"));
+        assert!(!result.contains("# Workspace Memory"));
         assert!(!result.contains("> Updated:"));
         assert!(result.contains("### Feature"));
     }
@@ -168,7 +168,7 @@ mod tests {
         let content = "### Feature\n- details";
         let result = update_header(content, "2025-01-10T12:00:00Z", "500 chars");
 
-        assert!(result.starts_with("# Project Memory"));
+        assert!(result.starts_with("# Workspace Memory"));
         assert!(result.contains("> Updated: 2025-01-10T12:00:00Z | Size: 500 chars"));
         assert!(result.contains("### Feature"));
     }

crates/g3-core/src/tools/mod.rs

@@ -8,7 +8,7 @@
 //! - `webdriver` - Browser automation via WebDriver
 //! - `misc` - Other tools (screenshots, code search, etc.)
 //! - `research` - Web research via scout agent
-//! - `memory` - Project memory (read_memory, remember)
+//! - `memory` - Workspace memory (remember)
 //! - `acd` - Aggressive Context Dehydration (rehydrate)
 
 pub mod executor;

docs/tools.md

@@ -292,7 +292,7 @@ Perform web-based research on a topic.
 
 ### remember
 
-Save discoveries to project memory.
+Save discoveries to workspace memory.
 
 **Parameters**:
 - `notes` (string, required): Markdown-formatted notes to add to memory