branch: externals/ellama
commit 33a884e53e2f1c7b497245f6a0bea4eedd26d95b
Author: Sergey Kostyaev <[email protected]>
Commit: Sergey Kostyaev <[email protected]>
Add documentation for missing ellama custom variables
Added inline documentation for previously undocumented configuration
variables:
- Show chain of intermediate steps during reasoning
- Blueprint directory and file handling
- Command map and key bindings
- Completion provider for code completion tasks
- Eval loop settings (max steps, keep workspaces, loop detection)
- Markdown to org conversion settings (pandoc arguments and executable path)
- Agent prompt templates for continue and planning operations
- Balanced edit mode configuration
- DLP settings for detecting and redacting environment secrets
- Read-before-write for tool operations
- Shell command default timeout
- Transient system show limit for transient menus
---
README.org | 47 ++++++++++++++++++++++
ellama.info | 132 ++++++++++++++++++++++++++++++++++++++++++------------------
2 files changed, 140 insertions(+), 39 deletions(-)
diff --git a/README.org b/README.org
index 686903646d..2bafa00c19 100644
--- a/README.org
+++ b/README.org
@@ -398,6 +398,53 @@ generated text string.
- ~ellama-image-context-default-scope~: Default scope for image context added
interactively. Use ~ephemeral~ for one request only, or ~persistent~ to keep
image context until it is removed or reset.
+- ~ellama-always-show-chain-steps~: Show chain of intermediate steps during
+ reasoning.
+- ~ellama-blueprints~: Directory or list of directories for blueprint storage.
+- ~ellama-command-map~: Keymap for ellama commands.
+- ~ellama-completion-provider~: LLM provider for code completion tasks.
+- ~ellama-eval-default-max-steps~: Default maximum number of steps in eval
loop.
+- ~ellama-eval-keep-workspaces~: Whether to keep workspaces after eval
+ completion.
+- ~ellama-eval-loop-detection-enabled~: Enable detection of infinite loops in
+ eval loops.
+- ~ellama-eval-loop-detection-max-traces~: Maximum number of traces for loop
+ detection.
+- ~ellama-eval-loop-detection-repeated-threshold~: Threshold for repeated
+ elements to trigger loop detection.
+- ~ellama-eval-timeout-seconds~: Timeout in seconds for eval operations.
+- ~ellama-markdown-to-org-converter~: Method for markdown to org conversion.
+- ~ellama-pandoc-markdown-to-org-args~: Arguments for pandoc markdown-to-org
+ conversion.
+- ~ellama-pandoc-program~: Path to pandoc executable for markdown-to-org
+ conversion.
+- ~ellama-tools-agent-continue-prompt~: Prompt template for agent continue
+ operation.
+- ~ellama-tools-agent-planning-prompt~: Prompt template for agent planning.
+- ~ellama-tools-balanced-edit-enabled~: Enable balanced edit mode for tools.
+- ~ellama-tools-balanced-edit-modes~: Major modes eligible for balanced edit
+ mode.
+- ~ellama-tools-dlp-env-secret-entropy-threshold~: Entropy threshold for
+ detecting environment secrets.
+- ~ellama-tools-dlp-env-secret-heuristic-stages~: Stages in env secret
heuristic
+ detection.
+- ~ellama-tools-dlp-env-secret-max-length~: Maximum length for environment
+ secret detection.
+- ~ellama-tools-dlp-env-secret-min-length~: Minimum length for environment
+ secret detection.
+- ~ellama-tools-dlp-env-secret-min-score~: Minimum score for environment secret
+ heuristic.
+- ~ellama-tools-dlp-message-prefix~: Prefix for DLP messages in logs.
+- ~ellama-tools-dlp-redaction-placeholder-format~: Format template for DLP
+ redaction placeholders.
+- ~ellama-tools-irreversible-high-confidence-block-rules~: Rules for blocking
+ high-confidence irreversible actions.
+- ~ellama-tools-read-before-write-enabled~: Enable read-before-write for tool
+ operations.
+- ~ellama-tools-shell-command-default-timeout~: Default timeout for shell
+ command execution.
+- ~ellama-transient-system-show-limit~: Maximum number of system elements to
+ show in transient.
- ~ellama-session-remove-reasoning~: Remove internal reasoning from the session
after ellama provide an answer. This can improve long-term communication with
reasoning models. Enabled by default.
diff --git a/ellama.info b/ellama.info
index 79873f7f71..37c78db3c7 100644
--- a/ellama.info
+++ b/ellama.info
@@ -545,6 +545,60 @@ argument generated text string.
• ‘ellama-image-context-default-scope’: Default scope for image
context added interactively. Use ‘ephemeral’ for one request only,
or ‘persistent’ to keep image context until it is removed or reset.
+ • ‘ellama-always-show-chain-steps’: Show chain of intermediate steps
+ during reasoning.
+ • ‘ellama-blueprints’: Directory or list of directories for blueprint
+ storage.
+ • ‘ellama-command-map’: Keymap for ellama commands.
+ • ‘ellama-completion-provider’: LLM provider for code completion
+ tasks.
+ • ‘ellama-eval-default-max-steps’: Default maximum number of steps in
+ eval loop.
+ • ‘ellama-eval-keep-workspaces’: Whether to keep workspaces after
+ eval completion.
+ • ‘ellama-eval-loop-detection-enabled’: Enable detection of infinite
+ loops in eval loops.
+ • ‘ellama-eval-loop-detection-max-traces’: Maximum number of traces
+ for loop detection.
+ • ‘ellama-eval-loop-detection-repeated-threshold’: Threshold for
+ repeated elements to trigger loop detection.
+ • ‘ellama-eval-timeout-seconds’: Timeout in seconds for eval
+ operations.
+ • ‘ellama-markdown-to-org-converter’: Method for markdown to org
+ conversion.
+ • ‘ellama-pandoc-markdown-to-org-args’: Arguments for pandoc
+ markdown-to-org conversion.
+ • ‘ellama-pandoc-program’: Path to pandoc executable for
+ markdown-to-org conversion.
+ • ‘ellama-tools-agent-continue-prompt’: Prompt template for agent
+ continue operation.
+ • ‘ellama-tools-agent-planning-prompt’: Prompt template for agent
+ planning.
+ • ‘ellama-tools-balanced-edit-enabled’: Enable balanced edit mode for
+ tools.
+ • ‘ellama-tools-balanced-edit-modes’: Major modes eligible for
+ balanced edit mode.
+ • ‘ellama-tools-dlp-env-secret-entropy-threshold’: Entropy threshold
+ for detecting environment secrets.
+ • ‘ellama-tools-dlp-env-secret-heuristic-stages’: Stages in env
+ secret heuristic detection.
+ • ‘ellama-tools-dlp-env-secret-max-length’: Maximum length for
+ environment secret detection.
+ • ‘ellama-tools-dlp-env-secret-min-length’: Minimum length for
+ environment secret detection.
+ • ‘ellama-tools-dlp-env-secret-min-score’: Minimum score for
+ environment secret heuristic.
+ • ‘ellama-tools-dlp-message-prefix’: Prefix for DLP messages in logs.
+ • ‘ellama-tools-dlp-redaction-placeholder-format’: Format template
+ for DLP redaction placeholders.
+ • ‘ellama-tools-irreversible-high-confidence-block-rules’: Rules for
+ blocking high-confidence irreversible actions.
+ • ‘ellama-tools-read-before-write-enabled’: Enable read-before-write
+ for tool operations.
+ • ‘ellama-tools-shell-command-default-timeout’: Default timeout for
+ shell command execution.
+ • ‘ellama-transient-system-show-limit’: Maximum number of system
+ elements to show in transient.
• ‘ellama-session-remove-reasoning’: Remove internal reasoning from
the session after ellama provide an answer. This can improve
long-term communication with reasoning models. Enabled by default.
@@ -2594,45 +2648,45 @@ Node: Installation3973
Node: Commands8987
Node: Keymap17925
Node: Configuration20812
-Node: Session Provider Keys34578
-Node: Session Compaction36439
-Node: Image Input38733
-Node: Task Tool Subagents40878
-Node: Plan-and-Act Agent Loop44052
-Node: Edit Tool Shell Hooks46633
-Node: DLP for Tool Input/Output48926
-Node: SRT Filesystem Policy for Tools64925
-Node: Context Management70594
-Node: Transient Menus for Context Management71662
-Node: Managing the Context73341
-Node: Considerations74116
-Node: Minor modes74709
-Node: ellama-context-header-line-mode76697
-Node: ellama-context-header-line-global-mode77522
-Node: ellama-context-mode-line-mode78242
-Node: ellama-context-mode-line-global-mode79090
-Node: Ellama Session Header Line Mode79794
-Node: Enabling and Disabling80363
-Node: Customization80810
-Node: Ellama Session Mode Line Mode81098
-Node: Enabling and Disabling (1)81683
-Node: Customization (1)82130
-Node: Using Blueprints82424
-Node: Key Components of Ellama Blueprints83064
-Node: Creating and Managing Blueprints83671
-Node: Blueprints files84649
-Node: Variable Management85070
-Node: Keymap and Mode85523
-Node: Transient Menus86459
-Node: Running Blueprints programmatically87005
-Node: MCP Integration87592
-Node: Agent Skills88827
-Node: Directory Structure89190
-Node: Creating a Skill90217
-Node: How it works90592
-Node: Acknowledgments90983
-Node: Contributions91694
-Node: GNU Free Documentation License92368
+Node: Session Provider Keys37385
+Node: Session Compaction39246
+Node: Image Input41540
+Node: Task Tool Subagents43685
+Node: Plan-and-Act Agent Loop46859
+Node: Edit Tool Shell Hooks49440
+Node: DLP for Tool Input/Output51733
+Node: SRT Filesystem Policy for Tools67732
+Node: Context Management73401
+Node: Transient Menus for Context Management74469
+Node: Managing the Context76148
+Node: Considerations76923
+Node: Minor modes77516
+Node: ellama-context-header-line-mode79504
+Node: ellama-context-header-line-global-mode80329
+Node: ellama-context-mode-line-mode81049
+Node: ellama-context-mode-line-global-mode81897
+Node: Ellama Session Header Line Mode82601
+Node: Enabling and Disabling83170
+Node: Customization83617
+Node: Ellama Session Mode Line Mode83905
+Node: Enabling and Disabling (1)84490
+Node: Customization (1)84937
+Node: Using Blueprints85231
+Node: Key Components of Ellama Blueprints85871
+Node: Creating and Managing Blueprints86478
+Node: Blueprints files87456
+Node: Variable Management87877
+Node: Keymap and Mode88330
+Node: Transient Menus89266
+Node: Running Blueprints programmatically89812
+Node: MCP Integration90399
+Node: Agent Skills91634
+Node: Directory Structure91997
+Node: Creating a Skill93024
+Node: How it works93399
+Node: Acknowledgments93790
+Node: Contributions94501
+Node: GNU Free Documentation License95175
End Tag Table
